From: Yen Chi Hsuan Date: Sat, 9 Jul 2016 06:29:53 +0000 (+0800) Subject: Merge pull request #9288 from reyyed/issue#9063fix X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=5b6a74856babce30e9e72701259f790322281d3a;hp=ccff2c404d7ea9f5b21ede8ae57bb79feec7eb94;p=youtube-dl Merge pull request #9288 from reyyed/issue#9063fix [ffmpeg] Fix embedding subtitles (#9063) --- diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 35f8e6863..a1b5b0baa 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.04.19*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.04.19** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.07.09.1*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.07.09.1** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -35,7 +35,7 @@ $ youtube-dl -v [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2016.04.19 +[debug] youtube-dl version 2016.07.09.1 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md new file mode 100644 index 000000000..f24bb4b09 --- /dev/null +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -0,0 +1,22 @@ +## Please follow the guide below + +- You will be asked some questions, please read them **carefully** and answer honestly +- Put an `x` into all the boxes [ ] relevant to your *pull request* (like that [x]) +- Use *Preview* tab to see how your *pull request* will actually look like + +--- + +### Before submitting a *pull request* make sure you have: +- [ ] At least skimmed through [adding new extractor tutorial](https://github.com/rg3/youtube-dl#adding-support-for-a-new-site) and [youtube-dl coding conventions](https://github.com/rg3/youtube-dl#youtube-dl-coding-conventions) sections +- [ ] [Searched](https://github.com/rg3/youtube-dl/search?q=is%3Apr&type=Issues) the bugtracker for similar pull requests + +### What is the purpose of your *pull request*? +- [ ] Bug fix +- [ ] New extractor +- [ ] New feature + +--- + +### Description of your *pull request* and other information + +Explanation of your *pull request* in arbitrary form goes here. Please make sure the description explains the purpose and effect of your *pull request* and is worded well enough to be understood. Provide as much context and examples as possible. diff --git a/.gitignore b/.gitignore index 72c10425d..a802c75a1 100644 --- a/.gitignore +++ b/.gitignore @@ -28,10 +28,16 @@ updates_key.pem *.mp4 *.m4a *.m4v +*.mp3 *.part *.swp test/testdata +test/local_parameters.json .tox youtube-dl.zsh + +# IntelliJ related files .idea -.idea/* +*.iml + +tmp/ diff --git a/.travis.yml b/.travis.yml index cc21fae8f..136c339f0 100644 --- a/.travis.yml +++ b/.travis.yml @@ -7,11 +7,13 @@ python: - "3.4" - "3.5" sudo: false +install: + - bash ./devscripts/install_srelay.sh + - export PATH=$PATH:$(pwd)/tmp/srelay-0.4.8b6 script: nosetests test --verbose notifications: email: - filippo.valsorda@gmail.com - - phihag@phihag.de - yasoob.khld@gmail.com # irc: # channels: diff --git a/AUTHORS b/AUTHORS index 07cade723..f74b30d07 100644 --- a/AUTHORS +++ b/AUTHORS @@ -168,3 +168,12 @@ José Joaquín Atria ViÅ¥as Strádal Kagami Hiiragi Philip Huppert +blahgeek +Kevin Deldycke +inondle +Tomáš Čech +Déstin Reed +Roman Tsiupa +Artur Krysiak +Jakub Adam Wieczorek +Aleksandar Topuzović diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index c83b8655a..fbf0ab7e8 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -97,9 +97,17 @@ If you want to add support for a new site, first of all **make sure** this site After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`): 1. [Fork this repository](https://github.com/rg3/youtube-dl/fork) -2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git` -3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor` +2. Check out the source code with: + + git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git + +3. Start a new git branch with + + cd youtube-dl + git checkout -b yourextractor + 4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`: + ```python # coding: utf-8 from __future__ import unicode_literals @@ -142,17 +150,149 @@ After you have ensured this site is distributing it's content legally, you can f ``` 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. -7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want. -8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`. -9. Check the code with [flake8](https://pypi.python.org/pypi/flake8). -10. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this: +7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want. +8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](http://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. +9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this: $ git add youtube_dl/extractor/extractors.py $ git add youtube_dl/extractor/yourextractor.py $ git commit -m '[yourextractor] Add new extractor' $ git push origin yourextractor -11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. +10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. In any case, thank you very much for your contributions! +## youtube-dl coding conventions + +This section introduces a guide lines for writing idiomatic, robust and future-proof extractor code. + +Extractors are very fragile by nature since they depend on the layout of the source data provided by 3rd party media hoster out of your control and this layout tend to change. As an extractor implementer your task is not only to write code that will extract media links and metadata correctly but also to minimize code dependency on source's layout changes and even to make the code foresee potential future changes and be ready for that. This is important because it will allow extractor not to break on minor layout changes thus keeping old youtube-dl versions working. Even though this breakage issue is easily fixed by emitting a new version of youtube-dl with fix incorporated all the previous version become broken in all repositories and distros' packages that may not be so prompt in fetching the update from us. Needless to say some may never receive an update at all that is possible for non rolling release distros. + +### Mandatory and optional metafields + +For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in *info dict* are considered mandatory for successful extraction process by youtube-dl: + + - `id` (media identifier) + - `title` (media title) + - `url` (media download URL) or `formats` + +In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` to be mandatory. Thus aforementioned metafields are the critical data the extraction does not make any sense without and if any of them fail to be extracted then extractor is considered completely broken. + +[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. + +#### Example + +Say you have some source dictionary `meta` that you've fetched as JSON with HTTP request and it has a key `summary`: + +```python +meta = self._download_json(url, video_id) +``` + +Assume at this point `meta`'s layout is: + +```python +{ + ... + "summary": "some fancy summary text", + ... +} +``` + +Assume you want to extract `summary` and put into resulting info dict as `description`. Since `description` is optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like: + +```python +description = meta.get('summary') # correct +``` + +and not like: + +```python +description = meta['summary'] # incorrect +``` + +The latter will break extraction process with `KeyError` if `summary` disappears from `meta` at some time later but with former approach extraction will just go ahead with `description` set to `None` that is perfectly fine (remember `None` is equivalent for absence of data). + +Similarly, you should pass `fatal=False` when extracting optional data from a webpage with `_search_regex`, `_html_search_regex` or similar methods, for instance: + +```python +description = self._search_regex( + r']+id="title"[^>]*>([^<]+)<', + webpage, 'description', fatal=False) +``` + +With `fatal` set to `False` if `_search_regex` fails to extract `description` it will emit a warning and continue extraction. + +You can also pass `default=`, for example: + +```python +description = self._search_regex( + r']+id="title"[^>]*>([^<]+)<', + webpage, 'description', default=None) +``` + +On failure this code will silently continue the extraction with `description` set to `None`. That is useful for metafields that are known to may or may not be present. + +### Provide fallbacks + +When extracting metadata try to provide several scenarios for that. For example if `title` is present in several places/sources try extracting from at least some of them. This would make it more future-proof in case some of the sources became unavailable. + +#### Example + +Say `meta` from previous example has a `title` and you are about to extract it. Since `title` is mandatory meta field you should end up with something like: + +```python +title = meta['title'] +``` + +If `title` disappeares from `meta` in future due to some changes on hoster's side the extraction would fail since `title` is mandatory. That's expected. + +Assume that you have some another source you can extract `title` from, for example `og:title` HTML meta of a `webpage`. In this case you can provide a fallback scenario: + +```python +title = meta.get('title') or self._og_search_title(webpage) +``` + +This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`. + +### Make regular expressions flexible + +When using regular expressions try to write them fuzzy and flexible. + +#### Example + +Say you need to extract `title` from the following HTML code: + +```html +some fancy title +``` + +The code for that task should look similar to: + +```python +title = self._search_regex( + r']+class="title"[^>]*>([^<]+)', webpage, 'title') +``` + +Or even better: + +```python +title = self._search_regex( + r']+class=(["\'])title\1[^>]*>(?P[^<]+)', + webpage, 'title', group='title') +``` + +Note how you tolerate potential changes in `style` attribute's value or switch from using double quotes to single for `class` attribute: + +The code definitely should not look like: + +```python +title = self._search_regex( + r'<span style="position: absolute; left: 910px; width: 90px; float: right; z-index: 9999;" class="title">(.*?)</span>', + webpage, 'title', group='title') +``` + +### Use safe conversion functions + +Wrap all extracted numeric data into safe functions from `utils`: `int_or_none`, `float_or_none`. Use them for string to number conversions as well. + diff --git a/Makefile b/Makefile index 06cffcb71..6ee4ba4eb 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites clean: - rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe + rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe find . -name "*.pyc" -delete find . -name "*.class" -delete @@ -37,7 +37,7 @@ test: ot: offlinetest offlinetest: codetest - $(PYTHON) -m nose --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py + $(PYTHON) -m nose --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py --exclude test_socks.py tar: youtube-dl.tar.gz @@ -69,7 +69,7 @@ README.txt: README.md pandoc -f markdown -t plain README.md -o README.txt youtube-dl.1: README.md - $(PYTHON) devscripts/prepare_manpage.py >youtube-dl.1.temp.md + $(PYTHON) devscripts/prepare_manpage.py youtube-dl.1.temp.md pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1 rm -f youtube-dl.1.temp.md diff --git a/README.md b/README.md index cd18edd87..44332ea9a 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,7 @@ youtube-dl - download videos from youtube.com or other video platforms To install it right away for all UNIX users (Linux, OS X, etc.), type: - sudo curl https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl + sudo curl -L https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl sudo chmod a+rx /usr/local/bin/youtube-dl If you do not have curl, you can alternatively use a recent wget: @@ -25,20 +25,26 @@ If you do not have curl, you can alternatively use a recent wget: sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl sudo chmod a+rx /usr/local/bin/youtube-dl -Windows users can [download a .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in their home directory or any other location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29). +Windows users can [download an .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in any location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29) except for `%SYSTEMROOT%\System32` (e.g. **do not** put in `C:\Windows\System32`). -OS X users can install **youtube-dl** with [Homebrew](http://brew.sh/). +You can also use pip: + + sudo pip install --upgrade youtube-dl + +This command will update youtube-dl if you have already installed it. See the [pypi page](https://pypi.python.org/pypi/youtube_dl) for more information. + +OS X users can install youtube-dl with [Homebrew](http://brew.sh/): brew install youtube-dl -You can also use pip: +Or with [MacPorts](https://www.macports.org/): - sudo pip install youtube-dl + sudo port install youtube-dl Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html). # DESCRIPTION -**youtube-dl** is a small command-line program to download videos from +**youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on Mac OS X. It is released to the public domain, @@ -73,8 +79,8 @@ which means you can modify it, redistribute it or use it however you like. repairs broken URLs, but emits an error if this is not possible instead of searching. --ignore-config Do not read configuration files. When given - in the global configuration file /etc - /youtube-dl.conf: Do not read the user + in the global configuration file + /etc/youtube-dl.conf: Do not read the user configuration in ~/.config/youtube- dl/config (%APPDATA%/youtube-dl/config.txt on Windows) @@ -85,9 +91,11 @@ which means you can modify it, redistribute it or use it however you like. --no-color Do not emit color codes in output ## Network Options: - --proxy URL Use the specified HTTP/HTTPS proxy. Pass in - an empty string (--proxy "") for direct - connection + --proxy URL Use the specified HTTP/HTTPS/SOCKS proxy. + To enable experimental SOCKS proxy, specify + a proper scheme. For example + socks5://127.0.0.1:1080/. Pass in an empty + string (--proxy "") for direct connection --socket-timeout SECONDS Time to wait before giving up, in seconds --source-address IP Client-side IP address to bind to (experimental) @@ -95,9 +103,9 @@ which means you can modify it, redistribute it or use it however you like. (experimental) -6, --force-ipv6 Make all connections via IPv6 (experimental) - --cn-verification-proxy URL Use this proxy to verify the IP address for - some Chinese sites. The default proxy - specified by --proxy (or none, if the + --geo-verification-proxy URL Use this proxy to verify the IP address for + some geo-restricted sites. The default + proxy specified by --proxy (or none, if the options is not present) is used for the actual downloading. (experimental) @@ -160,7 +168,7 @@ which means you can modify it, redistribute it or use it however you like. (experimental) ## Download Options: - -r, --rate-limit LIMIT Maximum download rate in bytes per second + -r, --limit-rate RATE Maximum download rate in bytes per second (e.g. 50K or 4.2M) -R, --retries RETRIES Number of retries (default is 10), or "infinite". @@ -176,7 +184,9 @@ which means you can modify it, redistribute it or use it however you like. --xattr-set-filesize Set file xattribute ytdl.filesize with expected filesize (experimental) --hls-prefer-native Use the native HLS downloader instead of - ffmpeg (experimental) + ffmpeg + --hls-prefer-ffmpeg Use ffmpeg instead of the native HLS + downloader --hls-use-mpegts Use the mpegts container for HLS videos, allowing to play the video while downloading (some players may not be able @@ -245,18 +255,19 @@ which means you can modify it, redistribute it or use it however you like. --write-info-json Write video metadata to a .info.json file --write-annotations Write video annotations to a .annotations.xml file - --load-info FILE JSON file containing the video information + --load-info-json FILE JSON file containing the video information (created with the "--write-info-json" option) --cookies FILE File to read cookies from and dump cookie jar in --cache-dir DIR Location in the filesystem where youtube-dl can store some downloaded information - permanently. By default $XDG_CACHE_HOME - /youtube-dl or ~/.cache/youtube-dl . At the - moment, only YouTube player files (for - videos with obfuscated signatures) are - cached, but that may change. + permanently. By default + $XDG_CACHE_HOME/youtube-dl or + ~/.cache/youtube-dl . At the moment, only + YouTube player files (for videos with + obfuscated signatures) are cached, but that + may change. --no-cache-dir Disable filesystem caching --rm-cache-dir Delete all filesystem cache files @@ -413,7 +424,7 @@ which means you can modify it, redistribute it or use it however you like. # CONFIGURATION -You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. +You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux and OS X, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. Note that by default configuration file may not exist so you may need to create it yourself. For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime, use a proxy and save all videos under `Movies` directory in your home directory: ``` @@ -421,6 +432,7 @@ For example, with the following configuration file youtube-dl will always extrac --no-mtime --proxy 127.0.0.1:3128 -o ~/Movies/%(title)s.%(ext)s +# Lines starting with # are comments ``` Note that options in configuration file are just the same options aka switches used in regular command line calls thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`. @@ -429,7 +441,7 @@ You can use `--ignore-config` if you want to disable the configuration file for ### Authentication with `.netrc` file -You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a`.netrc` file in your `$HOME` and restrict permissions to read/write by you only: +You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a `.netrc` file in your `$HOME` and restrict permissions to read/write by you only: ``` touch $HOME/.netrc chmod a-rwx,u+rw $HOME/.netrc @@ -463,7 +475,7 @@ The basic usage is not to set any template arguments when downloading a single f - `display_id`: An alternative identifier for the video - `uploader`: Full name of the video uploader - `license`: License name the video is licensed under - - `creator`: The main artist who created the video + - `creator`: The creator of the video - `release_date`: The date (YYYYMMDD) when the video was released - `timestamp`: UNIX timestamp of the moment the video became available - `upload_date`: Video upload date (YYYYMMDD) @@ -500,6 +512,9 @@ The basic usage is not to set any template arguments when downloading a single f - `autonumber`: Five-digit number that will be increased with each download, starting at zero - `playlist`: Name or id of the playlist that contains the video - `playlist_index`: Index of the video in the playlist padded with leading zeros according to the total length of the playlist + - `playlist_id`: Playlist identifier + - `playlist_title`: Playlist title + Available for the video that belongs to some logical chapter or section: - `chapter`: Name or title of the chapter the video belongs to @@ -515,6 +530,18 @@ Available for the video that is an episode of some series or programme: - `episode_number`: Number of the video episode within a season - `episode_id`: Id of the video episode +Available for the media that is a track or a part of a music album: + - `track`: Title of the track + - `track_number`: Number of the track within an album or a disc + - `track_id`: Id of the track + - `artist`: Artist(s) of the track + - `genre`: Genre(s) of the track + - `album`: Title of the album the track belongs to + - `album_type`: Type of the album + - `album_artist`: List of all artists appeared on the album + - `disc_number`: Number of the disc or other physical medium the track belongs to + - `release_year`: Year (YYYY) when the album was released + Each aforementioned sequence when referenced in output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by particular extractor, such sequences will be replaced with `NA`. For example for `-o %(title)s-%(id)s.%(ext)s` and mp4 video with title `youtube-dl test video` and id `BaW_jenozKcj` this will result in a `youtube-dl test video-BaW_jenozKcj.mp4` file created in the current directory. @@ -527,6 +554,10 @@ The current default template is `%(title)s-%(id)s.%(ext)s`. In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title: +#### Output template and Windows batch files + +If you are using output template inside a Windows batch file then you must escape plain percent characters (`%`) by doubling, so that `-o "%(title)s-%(id)s.%(ext)s"` should become `-o "%%(title)s-%%(id)s.%%(ext)s"`. However you should not touch `%`'s that are not plain characters, e.g. environment variables for expansion should stay intact: `-o "C:\%HOMEPATH%\Desktop\%%(title)s.%%(ext)s"`. + #### Output template examples Note on Windows you may need to use double quotes instead of single. @@ -677,12 +708,20 @@ hash -r Again, from then on you'll be able to update with `sudo youtube-dl -U`. +### youtube-dl is extremely slow to start on Windows + +Add a file exclusion for `youtube-dl.exe` in Windows Defender settings. + ### I'm getting an error `Unable to extract OpenGraph title` on YouTube playlists YouTube changed their playlist format in March 2014 and later on, so you'll need at least youtube-dl 2014.07.25 to download all YouTube videos. If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to [report bugs](https://bugs.launchpad.net/ubuntu/+source/youtube-dl/+filebug) to the [Ubuntu packaging guys](mailto:ubuntu-motu@lists.ubuntu.com?subject=outdated%20version%20of%20youtube-dl) - all they have to do is update the package to a somewhat recent version. See above for a way to update. +### I'm getting an error when trying to use output template: `error: using output template conflicts with using title, video ID or auto number` + +Make sure you are not using `-o` with any of these options `-t`, `--title`, `--id`, `-A` or `--auto-number` set in command line or in a configuration file. Remove the latter if any. + ### Do I always have to pass `-citw`? By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, the only option out of `-citw` that is regularly useful is `-i`. @@ -703,7 +742,7 @@ Videos or video formats streamed via RTMP protocol can only be downloaded when [ ### I have downloaded a video but how can I play it? -Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/). +Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/). ### I extracted a video URL with `-g`, but it does not play on another machine / in my webbrowser. @@ -760,9 +799,9 @@ means you're using an outdated version of Python. Please update to Python 2.6 or Since June 2012 ([#342](https://github.com/rg3/youtube-dl/issues/342)) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`. -### The exe throws a *Runtime error from Visual C++* +### The exe throws an error due to missing `MSVCR100.dll` -To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29). +To run the exe you need to install first the [Microsoft Visual C++ 2010 Redistributable Package (x86)](https://www.microsoft.com/en-US/download/details.aspx?id=5555). ### On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files? @@ -817,6 +856,12 @@ It is *not* possible to detect whether a URL is supported or not. That's because If you want to find out whether a given URL is supported, simply call youtube-dl with it. If you get no videos back, chances are the URL is either not referring to a video or unsupported. You can find out which by examining the output (if you run youtube-dl on the console) or catching an `UnsupportedError` exception if you run it from a Python program. +# Why do I need to go through that much red tape when filing bugs? + +Before we had the issue template, despite our extensive [bug reporting instructions](#bugs), about 80% of the issue reports we got were useless, for instance because people used ancient versions hundreds of releases old, because of simple syntactic errors (not in youtube-dl but in general shell usage), because the problem was alrady reported multiple times before, because people did not actually read an error message, even if it said "please install ffmpeg", because people did not mention the URL they were trying to download and many more simple, easy-to-avoid problems, many of whom were totally unrelated to youtube-dl. + +youtube-dl is an open-source project manned by too few volunteers, so we'd rather spend time fixing bugs where we are certain none of those simple problems apply, and where we can be reasonably confident to be able to reproduce the issue without asking the reporter repeatedly. As such, the output of `youtube-dl -v YOUR_URL_HERE` is really all that's required to file an issue. The issue template also guides you through some basic steps you can do, such as checking that your version of youtube-dl is current. + # DEVELOPER INSTRUCTIONS Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution. @@ -846,9 +891,17 @@ If you want to add support for a new site, first of all **make sure** this site After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`): 1. [Fork this repository](https://github.com/rg3/youtube-dl/fork) -2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git` -3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor` +2. Check out the source code with: + + git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git + +3. Start a new git branch with + + cd youtube-dl + git checkout -b yourextractor + 4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`: + ```python # coding: utf-8 from __future__ import unicode_literals @@ -891,20 +944,152 @@ After you have ensured this site is distributing it's content legally, you can f ``` 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. -7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want. -8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`. -9. Check the code with [flake8](https://pypi.python.org/pypi/flake8). -10. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this: +7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want. +8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](http://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. +9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this: $ git add youtube_dl/extractor/extractors.py $ git add youtube_dl/extractor/yourextractor.py $ git commit -m '[yourextractor] Add new extractor' $ git push origin yourextractor -11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. +10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. In any case, thank you very much for your contributions! +## youtube-dl coding conventions + +This section introduces a guide lines for writing idiomatic, robust and future-proof extractor code. + +Extractors are very fragile by nature since they depend on the layout of the source data provided by 3rd party media hoster out of your control and this layout tend to change. As an extractor implementer your task is not only to write code that will extract media links and metadata correctly but also to minimize code dependency on source's layout changes and even to make the code foresee potential future changes and be ready for that. This is important because it will allow extractor not to break on minor layout changes thus keeping old youtube-dl versions working. Even though this breakage issue is easily fixed by emitting a new version of youtube-dl with fix incorporated all the previous version become broken in all repositories and distros' packages that may not be so prompt in fetching the update from us. Needless to say some may never receive an update at all that is possible for non rolling release distros. + +### Mandatory and optional metafields + +For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in *info dict* are considered mandatory for successful extraction process by youtube-dl: + + - `id` (media identifier) + - `title` (media title) + - `url` (media download URL) or `formats` + +In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` to be mandatory. Thus aforementioned metafields are the critical data the extraction does not make any sense without and if any of them fail to be extracted then extractor is considered completely broken. + +[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. + +#### Example + +Say you have some source dictionary `meta` that you've fetched as JSON with HTTP request and it has a key `summary`: + +```python +meta = self._download_json(url, video_id) +``` + +Assume at this point `meta`'s layout is: + +```python +{ + ... + "summary": "some fancy summary text", + ... +} +``` + +Assume you want to extract `summary` and put into resulting info dict as `description`. Since `description` is optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like: + +```python +description = meta.get('summary') # correct +``` + +and not like: + +```python +description = meta['summary'] # incorrect +``` + +The latter will break extraction process with `KeyError` if `summary` disappears from `meta` at some time later but with former approach extraction will just go ahead with `description` set to `None` that is perfectly fine (remember `None` is equivalent for absence of data). + +Similarly, you should pass `fatal=False` when extracting optional data from a webpage with `_search_regex`, `_html_search_regex` or similar methods, for instance: + +```python +description = self._search_regex( + r'<span[^>]+id="title"[^>]*>([^<]+)<', + webpage, 'description', fatal=False) +``` + +With `fatal` set to `False` if `_search_regex` fails to extract `description` it will emit a warning and continue extraction. + +You can also pass `default=<some fallback value>`, for example: + +```python +description = self._search_regex( + r'<span[^>]+id="title"[^>]*>([^<]+)<', + webpage, 'description', default=None) +``` + +On failure this code will silently continue the extraction with `description` set to `None`. That is useful for metafields that are known to may or may not be present. + +### Provide fallbacks + +When extracting metadata try to provide several scenarios for that. For example if `title` is present in several places/sources try extracting from at least some of them. This would make it more future-proof in case some of the sources became unavailable. + +#### Example + +Say `meta` from previous example has a `title` and you are about to extract it. Since `title` is mandatory meta field you should end up with something like: + +```python +title = meta['title'] +``` + +If `title` disappeares from `meta` in future due to some changes on hoster's side the extraction would fail since `title` is mandatory. That's expected. + +Assume that you have some another source you can extract `title` from, for example `og:title` HTML meta of a `webpage`. In this case you can provide a fallback scenario: + +```python +title = meta.get('title') or self._og_search_title(webpage) +``` + +This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`. + +### Make regular expressions flexible + +When using regular expressions try to write them fuzzy and flexible. + +#### Example + +Say you need to extract `title` from the following HTML code: + +```html +<span style="position: absolute; left: 910px; width: 90px; float: right; z-index: 9999;" class="title">some fancy title</span> +``` + +The code for that task should look similar to: + +```python +title = self._search_regex( + r'<span[^>]+class="title"[^>]*>([^<]+)', webpage, 'title') +``` + +Or even better: + +```python +title = self._search_regex( + r'<span[^>]+class=(["\'])title\1[^>]*>(?P<title>[^<]+)', + webpage, 'title', group='title') +``` + +Note how you tolerate potential changes in `style` attribute's value or switch from using double quotes to single for `class` attribute: + +The code definitely should not look like: + +```python +title = self._search_regex( + r'<span style="position: absolute; left: 910px; width: 90px; float: right; z-index: 9999;" class="title">(.*?)</span>', + webpage, 'title', group='title') +``` + +### Use safe conversion functions + +Wrap all extracted numeric data into safe functions from `utils`: `int_or_none`, `float_or_none`. Use them for string to number conversions as well. + # EMBEDDING YOUTUBE-DL youtube-dl makes the best effort to be a good command-line program, and thus should be callable from any programming language. If you encounter any problems parsing its output, feel free to [create a report](https://github.com/rg3/youtube-dl/issues/new). @@ -920,7 +1105,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl: ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) ``` -Most likely, you'll want to use various options. For a list of what can be done, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L121-L269). For a start, if you want to intercept youtube-dl's output, set a `logger` object. +Most likely, you'll want to use various options. For a list of options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L128-L278). For a start, if you want to intercept youtube-dl's output, set a `logger` object. Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file: diff --git a/devscripts/buildserver.py b/devscripts/buildserver.py index 7c2f49f8b..fc99c3213 100644 --- a/devscripts/buildserver.py +++ b/devscripts/buildserver.py @@ -1,17 +1,38 @@ #!/usr/bin/python3 -from http.server import HTTPServer, BaseHTTPRequestHandler -from socketserver import ThreadingMixIn import argparse import ctypes import functools +import shutil +import subprocess import sys +import tempfile import threading import traceback import os.path +sys.path.insert(0, os.path.dirname(os.path.dirname((os.path.abspath(__file__))))) +from youtube_dl.compat import ( + compat_input, + compat_http_server, + compat_str, + compat_urlparse, +) + +# These are not used outside of buildserver.py thus not in compat.py + +try: + import winreg as compat_winreg +except ImportError: # Python 2 + import _winreg as compat_winreg -class BuildHTTPServer(ThreadingMixIn, HTTPServer): +try: + import socketserver as compat_socketserver +except ImportError: # Python 2 + import SocketServer as compat_socketserver + + +class BuildHTTPServer(compat_socketserver.ThreadingMixIn, compat_http_server.HTTPServer): allow_reuse_address = True @@ -191,7 +212,7 @@ def main(args=None): action='store_const', dest='action', const='service', help='Run as a Windows service') parser.add_argument('-b', '--bind', metavar='<host:port>', - action='store', default='localhost:8142', + action='store', default='0.0.0.0:8142', help='Bind to host:port (default %default)') options = parser.parse_args(args=args) @@ -216,7 +237,7 @@ def main(args=None): srv = BuildHTTPServer((host, port), BuildHTTPRequestHandler) thr = threading.Thread(target=srv.serve_forever) thr.start() - input('Press ENTER to shut down') + compat_input('Press ENTER to shut down') srv.shutdown() thr.join() @@ -231,8 +252,6 @@ def rmtree(path): os.remove(fname) os.rmdir(path) -#============================================================================== - class BuildError(Exception): def __init__(self, output, code=500): @@ -249,15 +268,25 @@ class HTTPError(BuildError): class PythonBuilder(object): def __init__(self, **kwargs): - pythonVersion = kwargs.pop('python', '2.7') - try: - key = _winreg.OpenKey(_winreg.HKEY_LOCAL_MACHINE, r'SOFTWARE\Python\PythonCore\%s\InstallPath' % pythonVersion) + python_version = kwargs.pop('python', '3.4') + python_path = None + for node in ('Wow6432Node\\', ''): try: - self.pythonPath, _ = _winreg.QueryValueEx(key, '') - finally: - _winreg.CloseKey(key) - except Exception: - raise BuildError('No such Python version: %s' % pythonVersion) + key = compat_winreg.OpenKey( + compat_winreg.HKEY_LOCAL_MACHINE, + r'SOFTWARE\%sPython\PythonCore\%s\InstallPath' % (node, python_version)) + try: + python_path, _ = compat_winreg.QueryValueEx(key, '') + finally: + compat_winreg.CloseKey(key) + break + except Exception: + pass + + if not python_path: + raise BuildError('No such Python version: %s' % python_version) + + self.pythonPath = python_path super(PythonBuilder, self).__init__(**kwargs) @@ -305,8 +334,10 @@ class YoutubeDLBuilder(object): def build(self): try: - subprocess.check_output([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'], - cwd=self.buildPath) + proc = subprocess.Popen([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'], stdin=subprocess.PIPE, cwd=self.buildPath) + proc.wait() + #subprocess.check_output([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'], + # cwd=self.buildPath) except subprocess.CalledProcessError as e: raise BuildError(e.output) @@ -369,12 +400,12 @@ class Builder(PythonBuilder, GITBuilder, YoutubeDLBuilder, DownloadBuilder, Clea pass -class BuildHTTPRequestHandler(BaseHTTPRequestHandler): +class BuildHTTPRequestHandler(compat_http_server.BaseHTTPRequestHandler): actionDict = {'build': Builder, 'download': Builder} # They're the same, no more caching. def do_GET(self): - path = urlparse.urlparse(self.path) - paramDict = dict([(key, value[0]) for key, value in urlparse.parse_qs(path.query).items()]) + path = compat_urlparse.urlparse(self.path) + paramDict = dict([(key, value[0]) for key, value in compat_urlparse.parse_qs(path.query).items()]) action, _, path = path.path.strip('/').partition('/') if path: path = path.split('/') @@ -388,7 +419,7 @@ class BuildHTTPRequestHandler(BaseHTTPRequestHandler): builder.close() except BuildError as e: self.send_response(e.code) - msg = unicode(e).encode('UTF-8') + msg = compat_str(e).encode('UTF-8') self.send_header('Content-Type', 'text/plain; charset=UTF-8') self.send_header('Content-Length', len(msg)) self.end_headers() @@ -400,7 +431,5 @@ class BuildHTTPRequestHandler(BaseHTTPRequestHandler): else: self.send_response(500, 'Malformed URL') -#============================================================================== - if __name__ == '__main__': main() diff --git a/devscripts/create-github-release.py b/devscripts/create-github-release.py new file mode 100644 index 000000000..3b8021e74 --- /dev/null +++ b/devscripts/create-github-release.py @@ -0,0 +1,111 @@ +#!/usr/bin/env python +from __future__ import unicode_literals + +import base64 +import json +import mimetypes +import netrc +import optparse +import os +import sys + +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +from youtube_dl.compat import ( + compat_basestring, + compat_input, + compat_getpass, + compat_print, + compat_urllib_request, +) +from youtube_dl.utils import ( + make_HTTPS_handler, + sanitized_Request, +) + + +class GitHubReleaser(object): + _API_URL = 'https://api.github.com/repos/rg3/youtube-dl/releases' + _UPLOADS_URL = 'https://uploads.github.com/repos/rg3/youtube-dl/releases/%s/assets?name=%s' + _NETRC_MACHINE = 'github.com' + + def __init__(self, debuglevel=0): + self._init_github_account() + https_handler = make_HTTPS_handler({}, debuglevel=debuglevel) + self._opener = compat_urllib_request.build_opener(https_handler) + + def _init_github_account(self): + try: + info = netrc.netrc().authenticators(self._NETRC_MACHINE) + if info is not None: + self._username = info[0] + self._password = info[2] + compat_print('Using GitHub credentials found in .netrc...') + return + else: + compat_print('No GitHub credentials found in .netrc') + except (IOError, netrc.NetrcParseError): + compat_print('Unable to parse .netrc') + self._username = compat_input( + 'Type your GitHub username or email address and press [Return]: ') + self._password = compat_getpass( + 'Type your GitHub password and press [Return]: ') + + def _call(self, req): + if isinstance(req, compat_basestring): + req = sanitized_Request(req) + # Authorizing manually since GitHub does not response with 401 with + # WWW-Authenticate header set (see + # https://developer.github.com/v3/#basic-authentication) + b64 = base64.b64encode( + ('%s:%s' % (self._username, self._password)).encode('utf-8')).decode('ascii') + req.add_header('Authorization', 'Basic %s' % b64) + response = self._opener.open(req).read().decode('utf-8') + return json.loads(response) + + def list_releases(self): + return self._call(self._API_URL) + + def create_release(self, tag_name, name=None, body='', draft=False, prerelease=False): + data = { + 'tag_name': tag_name, + 'target_commitish': 'master', + 'name': name, + 'body': body, + 'draft': draft, + 'prerelease': prerelease, + } + req = sanitized_Request(self._API_URL, json.dumps(data).encode('utf-8')) + return self._call(req) + + def create_asset(self, release_id, asset): + asset_name = os.path.basename(asset) + url = self._UPLOADS_URL % (release_id, asset_name) + # Our files are small enough to be loaded directly into memory. + data = open(asset, 'rb').read() + req = sanitized_Request(url, data) + mime_type, _ = mimetypes.guess_type(asset_name) + req.add_header('Content-Type', mime_type or 'application/octet-stream') + return self._call(req) + + +def main(): + parser = optparse.OptionParser(usage='%prog VERSION BUILDPATH') + options, args = parser.parse_args() + if len(args) != 2: + parser.error('Expected a version and a build directory') + + version, build_path = args + + releaser = GitHubReleaser() + + new_release = releaser.create_release(version, name='youtube-dl %s' % version) + release_id = new_release['id'] + + for asset in os.listdir(build_path): + compat_print('Uploading %s...' % asset) + releaser.create_asset(release_id, os.path.join(build_path, asset)) + + +if __name__ == '__main__': + main() diff --git a/devscripts/install_srelay.sh b/devscripts/install_srelay.sh new file mode 100755 index 000000000..33ce8a3f7 --- /dev/null +++ b/devscripts/install_srelay.sh @@ -0,0 +1,8 @@ +#!/bin/bash + +mkdir -p tmp && cd tmp +wget -N http://downloads.sourceforge.net/project/socks-relay/socks-relay/srelay-0.4.8/srelay-0.4.8b6.tar.gz +tar zxvf srelay-0.4.8b6.tar.gz +cd srelay-0.4.8b6 +./configure +make diff --git a/devscripts/make_lazy_extractors.py b/devscripts/make_lazy_extractors.py index b5a8b9190..9a79c2bc5 100644 --- a/devscripts/make_lazy_extractors.py +++ b/devscripts/make_lazy_extractors.py @@ -14,15 +14,17 @@ if os.path.exists(lazy_extractors_filename): os.remove(lazy_extractors_filename) from youtube_dl.extractor import _ALL_CLASSES -from youtube_dl.extractor.common import InfoExtractor +from youtube_dl.extractor.common import InfoExtractor, SearchInfoExtractor with open('devscripts/lazy_load_template.py', 'rt') as f: module_template = f.read() -module_contents = [module_template + '\n' + getsource(InfoExtractor.suitable)] +module_contents = [ + module_template + '\n' + getsource(InfoExtractor.suitable) + '\n', + 'class LazyLoadSearchExtractor(LazyLoadExtractor):\n pass\n'] ie_template = ''' -class {name}(LazyLoadExtractor): +class {name}({bases}): _VALID_URL = {valid_url!r} _module = '{module}' ''' @@ -34,10 +36,20 @@ make_valid_template = ''' ''' +def get_base_name(base): + if base is InfoExtractor: + return 'LazyLoadExtractor' + elif base is SearchInfoExtractor: + return 'LazyLoadSearchExtractor' + else: + return base.__name__ + + def build_lazy_ie(ie, name): valid_url = getattr(ie, '_VALID_URL', None) s = ie_template.format( name=name, + bases=', '.join(map(get_base_name, ie.__bases__)), valid_url=valid_url, module=ie.__module__) if ie.suitable.__func__ is not InfoExtractor.suitable.__func__: @@ -47,12 +59,35 @@ def build_lazy_ie(ie, name): s += make_valid_template.format(valid_url=ie._make_valid_url()) return s +# find the correct sorting and add the required base classes so that sublcasses +# can be correctly created +classes = _ALL_CLASSES[:-1] +ordered_cls = [] +while classes: + for c in classes[:]: + bases = set(c.__bases__) - set((object, InfoExtractor, SearchInfoExtractor)) + stop = False + for b in bases: + if b not in classes and b not in ordered_cls: + if b.__name__ == 'GenericIE': + exit() + classes.insert(0, b) + stop = True + if stop: + break + if all(b in ordered_cls for b in bases): + ordered_cls.append(c) + classes.remove(c) + break +ordered_cls.append(_ALL_CLASSES[-1]) + names = [] -for ie in list(sorted(_ALL_CLASSES[:-1], key=lambda cls: cls.ie_key())) + _ALL_CLASSES[-1:]: - name = ie.ie_key() + 'IE' +for ie in ordered_cls: + name = ie.__name__ src = build_lazy_ie(ie, name) module_contents.append(src) - names.append(name) + if ie in _ALL_CLASSES: + names.append(name) module_contents.append( '_ALL_CLASSES = [{0}]'.format(', '.join(names))) diff --git a/devscripts/prepare_manpage.py b/devscripts/prepare_manpage.py index 776e6556e..e3f6339b5 100644 --- a/devscripts/prepare_manpage.py +++ b/devscripts/prepare_manpage.py @@ -1,13 +1,46 @@ from __future__ import unicode_literals import io +import optparse import os.path -import sys import re ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) README_FILE = os.path.join(ROOT_DIR, 'README.md') +PREFIX = '''%YOUTUBE-DL(1) + +# NAME + +youtube\-dl \- download videos from youtube.com or other video platforms + +# SYNOPSIS + +**youtube-dl** \[OPTIONS\] URL [URL...] + +''' + + +def main(): + parser = optparse.OptionParser(usage='%prog OUTFILE.md') + options, args = parser.parse_args() + if len(args) != 1: + parser.error('Expected an output filename') + + outfile, = args + + with io.open(README_FILE, encoding='utf-8') as f: + readme = f.read() + + readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme) + readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme) + readme = PREFIX + readme + + readme = filter_options(readme) + + with io.open(outfile, 'w', encoding='utf-8') as outf: + outf.write(readme) + def filter_options(readme): ret = '' @@ -37,27 +70,5 @@ def filter_options(readme): return ret -with io.open(README_FILE, encoding='utf-8') as f: - readme = f.read() - -PREFIX = '''%YOUTUBE-DL(1) - -# NAME - -youtube\-dl \- download videos from youtube.com or other video platforms - -# SYNOPSIS - -**youtube-dl** \[OPTIONS\] URL [URL...] - -''' -readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme) -readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme) -readme = PREFIX + readme - -readme = filter_options(readme) - -if sys.version_info < (3, 0): - print(readme.encode('utf-8')) -else: - print(readme) +if __name__ == '__main__': + main() diff --git a/devscripts/release.sh b/devscripts/release.sh index 8dea55dbb..f8d466ba8 100755 --- a/devscripts/release.sh +++ b/devscripts/release.sh @@ -6,7 +6,7 @@ # * the git config user.signingkey is properly set # You will need -# pip install coverage nose rsa +# pip install coverage nose rsa wheel # TODO # release notes @@ -15,10 +15,33 @@ set -e skip_tests=true -if [ "$1" = '--run-tests' ]; then - skip_tests=false - shift -fi +gpg_sign_commits="" +buildserver='localhost:8142' + +while true +do +case "$1" in + --run-tests) + skip_tests=false + shift + ;; + --gpg-sign-commits|-S) + gpg_sign_commits="-S" + shift + ;; + --buildserver) + buildserver="$2" + shift 2 + ;; + --*) + echo "ERROR: unknown option $1" + exit 1 + ;; + *) + break + ;; +esac +done if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi version="$1" @@ -33,6 +56,9 @@ if [ ! -z "`git status --porcelain | grep -v CHANGELOG`" ]; then echo 'ERROR: th useless_files=$(find youtube_dl -type f -not -name '*.py') if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $useless_files"; exit 1; fi if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi +if ! type pandoc >/dev/null 2>/dev/null; then echo 'ERROR: pandoc is missing'; exit 1; fi +if ! python3 -c 'import rsa' 2>/dev/null; then echo 'ERROR: python3-rsa is missing'; exit 1; fi +if ! python3 -c 'import wheel' 2>/dev/null; then echo 'ERROR: wheel is missing'; exit 1; fi /bin/echo -e "\n### First of all, testing..." make clean @@ -48,7 +74,7 @@ sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py /bin/echo -e "\n### Committing documentation, templates and youtube_dl/version.py..." make README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md supportedsites git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md docs/supportedsites.md youtube_dl/version.py -git commit -m "release $version" +git commit $gpg_sign_commits -m "release $version" /bin/echo -e "\n### Now tagging, signing and pushing..." git tag -s -m "Release $version" "$version" @@ -64,7 +90,7 @@ git push origin "$version" REV=$(git rev-parse HEAD) make youtube-dl youtube-dl.tar.gz read -p "VM running? (y/n) " -n 1 -wget "http://localhost:8142/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe +wget "http://$buildserver/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe mkdir -p "build/$version" mv youtube-dl youtube-dl.exe "build/$version" mv youtube-dl.tar.gz "build/$version/youtube-dl-$version.tar.gz" @@ -74,15 +100,16 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz" (cd build/$version/ && sha256sum $RELEASE_FILES > SHA2-256SUMS) (cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS) -/bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..." +/bin/echo -e "\n### Signing and uploading the new binaries to GitHub..." for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done -scp -r "build/$version" ytdl@yt-dl.org:html/tmp/ -ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/" + +ROOT=$(pwd) +python devscripts/create-github-release.py $version "$ROOT/build/$version" + ssh ytdl@yt-dl.org "sh html/update_latest.sh $version" /bin/echo -e "\n### Now switching to gh-pages..." git clone --branch gh-pages --single-branch . build/gh-pages -ROOT=$(pwd) ( set -e ORIGIN_URL=$(git config --get remote.origin.url) @@ -94,7 +121,7 @@ ROOT=$(pwd) "$ROOT/devscripts/gh-pages/update-copyright.py" "$ROOT/devscripts/gh-pages/update-sites.py" git add *.html *.html.in update - git commit -m "release $version" + git commit $gpg_sign_commits -m "release $version" git push "$ROOT" gh-pages git push "$ORIGIN_URL" gh-pages ) diff --git a/devscripts/show-downloads-statistics.py b/devscripts/show-downloads-statistics.py new file mode 100644 index 000000000..b591d3fc9 --- /dev/null +++ b/devscripts/show-downloads-statistics.py @@ -0,0 +1,41 @@ +#!/usr/bin/env python +from __future__ import unicode_literals + +import json +import os +import re +import sys + +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +from youtube_dl.compat import ( + compat_print, + compat_urllib_request, +) +from youtube_dl.utils import format_bytes + + +def format_size(bytes): + return '%s (%d bytes)' % (format_bytes(bytes), bytes) + + +total_bytes = 0 + +releases = json.loads(compat_urllib_request.urlopen( + 'https://api.github.com/repos/rg3/youtube-dl/releases').read().decode('utf-8')) + +for release in releases: + compat_print(release['name']) + for asset in release['assets']: + asset_name = asset['name'] + total_bytes += asset['download_count'] * asset['size'] + if all(not re.match(p, asset_name) for p in ( + r'^youtube-dl$', + r'^youtube-dl-\d{4}\.\d{2}\.\d{2}(?:\.\d+)?\.tar\.gz$', + r'^youtube-dl\.exe$')): + continue + compat_print( + ' %s size: %s downloads: %d' + % (asset_name, format_size(asset['size']), asset['download_count'])) + +compat_print('total downloads traffic: %s' % format_size(total_bytes)) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index e12a7d182..d2a2ef0c4 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -6,6 +6,7 @@ - **22tracks:genre** - **22tracks:track** - **24video** + - **3qsdn**: 3Q SDN - **3sat** - **4tube** - **56.com** @@ -15,6 +16,8 @@ - **9gag** - **abc.net.au** - **Abc7News** + - **abcnews** + - **abcnews:video** - **AcademicEarth:Course** - **acast** - **acast:channel** @@ -25,6 +28,7 @@ - **AdobeTVVideo** - **AdultSwim** - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network + - **AfreecaTV**: afreecatv.com - **Aftonbladet** - **AirMozilla** - **AlJazeera** @@ -40,7 +44,6 @@ - **appletrailers:section** - **archive.org**: archive.org videos - **ARD** - - **ARD:mediathek**: Saarländischer Rundfunk - **ARD:mediathek** - **arte.tv** - **arte.tv:+7** @@ -52,6 +55,7 @@ - **arte.tv:future** - **arte.tv:info** - **arte.tv:magazine** + - **arte.tv:playlist** - **AtresPlayer** - **ATTTechChannel** - **AudiMedia** @@ -69,6 +73,8 @@ - **bbc**: BBC - **bbc.co.uk**: BBC iPlayer - **bbc.co.uk:article**: BBC articles + - **bbc.co.uk:iplayer:playlist** + - **bbc.co.uk:playlist** - **BeatportPro** - **Beeg** - **BehindKink** @@ -77,6 +83,7 @@ - **Bild**: Bild.de - **BiliBili** - **BioBioChileTV** + - **BIQLE** - **BleacherReport** - **BleacherReportCMS** - **blinkx** @@ -98,10 +105,13 @@ - **canalc2.tv** - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv - **Canvas** + - **CarambaTV** + - **CarambaTVPage** - **CBC** - **CBCPlayer** - **CBS** - **CBSInteractive** + - **CBSLocal** - **CBSNews**: CBS News - **CBSNewsLiveVideo**: CBS News Live Videos - **CBSSports** @@ -113,11 +123,11 @@ - **chirbit** - **chirbit:profile** - **Cinchcast** - - **Cinemassacre** - **Clipfish** - **cliphunter** - **ClipRs** - **Clipsyndicate** + - **CloserToTruth** - **cloudtime**: CloudTime - **Cloudy** - **Clubic** @@ -127,12 +137,12 @@ - **CNN** - **CNNArticle** - **CNNBlogs** - - **CollegeHumor** - **CollegeRama** - **ComCarCoff** - **ComedyCentral** - **ComedyCentralShows**: The Daily Show / The Colbert Report - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED + - **Coub** - **Cracked** - **Crackle** - **Criterion** @@ -142,9 +152,12 @@ - **CSNNE** - **CSpan**: C-SPAN - **CtsNews**: 華視新聞 + - **CTV** + - **CTVNews** - **culturebox.francetvinfo.fr** - **CultureUnplugged** - **CWTV** + - **DailyMail** - **dailymotion** - **dailymotion:playlist** - **dailymotion:user** @@ -163,6 +176,7 @@ - **defense.gouv.fr** - **democracynow** - **DHM**: Filmarchiv - Deutsches Historisches Museum + - **DigitallySpeaking** - **Digiteka** - **Discovery** - **Dotsub** @@ -174,7 +188,6 @@ - **Dropbox** - **DrTuber** - **DRTV** - - **Dump** - **Dumpert** - **dvtv**: http://video.aktualne.cz/ - **dw** @@ -201,6 +214,7 @@ - **exfm**: ex.fm - **ExpoTV** - **ExtremeTube** + - **EyedoTV** - **facebook** - **faz.net** - **fc2** @@ -210,8 +224,10 @@ - **Firstpost** - **FiveTV** - **Flickr** + - **Flipagram** - **Folketinget**: Folketinget (ft.dk; Danish parliament) - **FootyRoom** + - **Formula1** - **FOX** - **Foxgay** - **FoxNews**: Fox News and Fox Business Video @@ -227,6 +243,7 @@ - **FreeVideo** - **Funimation** - **FunnyOrDie** + - **Fusion** - **GameInformer** - **Gamekings** - **GameOne** @@ -234,7 +251,6 @@ - **Gamersyde** - **GameSpot** - **GameStar** - - **Gametrailers** - **Gazeta** - **GDCVault** - **generic**: Generic downloader that works on some sites @@ -245,6 +261,7 @@ - **Globo** - **GloboArticle** - **GodTube** + - **GodTV** - **GoldenMoustache** - **Golem** - **GoogleDrive** @@ -259,6 +276,7 @@ - **Helsinki**: helsinki.fi - **HentaiStigma** - **HistoricFilms** + - **history:topic**: History.com Topic - **hitbox** - **hitbox:live** - **HornBunny** @@ -266,6 +284,8 @@ - **HotStar** - **Howcast** - **HowStuffWorks** + - **HRTi** + - **HRTiPlaylist** - **HuffPost**: Huffington Post - **Hypem** - **Iconosquare** @@ -293,6 +313,7 @@ - **jpopsuki.tv** - **JWPlatform** - **Kaltura** + - **Kamcord** - **KanalPlay**: Kanal 5/9/11 Play - **Kankan** - **Karaoketv** @@ -312,23 +333,27 @@ - **kuwo:mv**: 酷我音乐 - MV - **kuwo:singer**: 酷我音乐 - 歌手 - **kuwo:song**: 酷我音乐 - - **la7.tv** + - **la7.it** - **Laola1Tv** - **Le**: 乐视网 + - **Learnr** - **Lecture2Go** - **Lemonde** - **LePlaylist** - **LetvCloud**: 乐视云 - **Libsyn** + - **life**: Life.ru - **life:embed** - - **lifenews**: LIFE | NEWS - **limelight** - **limelight:channel** - **limelight:channel_list** + - **LiTV** - **LiveLeak** - **livestream** - **livestream:original** - **LnkGo** + - **loc**: Library of Congress + - **LocalNews8** - **LoveHomePorn** - **lrt.lt** - **lynda**: lynda.com videos @@ -338,13 +363,14 @@ - **mailru**: Видео@Mail.Ru - **MakersChannel** - **MakerTV** - - **Malemotion** - **MatchTV** - **MDR**: MDR.DE and KiKA - **media.ccc.de** + - **META** - **metacafe** - **Metacritic** - **Mgoon** + - **MGTV**: 芒果TV - **Minhateca** - **MinistryGrid** - **Minoto** @@ -367,15 +393,17 @@ - **MovieFap** - **Moviezine** - **MPORA** - - **MSNBC** + - **MSN** - **MTV** - **mtv.de** - **mtviggy.com** - **mtvservices:embedded** - **MuenchenTV**: münchen.tv - **MusicPlayOn** - - **muzu.tv** + - **mva**: Microsoft Virtual Academy videos + - **mva:course**: Microsoft Virtual Academy courses - **Mwave** + - **MwaveMeetGreet** - **MySpace** - **MySpace:album** - **MySpass** @@ -413,10 +441,13 @@ - **nfl.com** - **nhl.com** - **nhl.com:news**: NHL news - - **nhl.com:videocenter**: NHL videocenter category + - **nhl.com:videocenter** + - **nhl.com:videocenter:category**: NHL videocenter category - **nick.com** + - **nick.de** - **niconico**: ニコニコ動画 - **NiconicoPlaylist** + - **NineCNineMedia** - **njoy**: N-JOY - **njoy:embed** - **Noco** @@ -447,6 +478,8 @@ - **Odnoklassniki** - **OktoberfestTV** - **on.aol.com** + - **onet.tv** + - **onet.tv:channel** - **OnionStudios** - **Ooyala** - **OoyalaExternal** @@ -461,13 +494,14 @@ - **Patreon** - **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC) - **pcmag** - - **Periscope**: Periscope + - **People** + - **periscope**: Periscope + - **periscope:user**: Periscope user videos - **PhilharmonieDeParis**: Philharmonie de Paris - **phoenix.de** - **Photobucket** - **Pinkbike** - **Pladform** - - **PlanetaPlay** - **play.fm** - **played.to** - **PlaysTV** @@ -479,8 +513,9 @@ - **plus.google**: Google Plus - **pluzz.francetv.fr** - **podomatic** + - **PolskieRadio** - **PornHd** - - **PornHub** + - **PornHub**: PornHub and Thumbzilla - **PornHubPlaylist** - **PornHubUserVideos** - **Pornotube** @@ -497,10 +532,12 @@ - **qqmusic:playlist**: QQ音乐 - 歌单 - **qqmusic:singer**: QQ音乐 - 歌手 - **qqmusic:toplist**: QQ音乐 - 排行榜 - - **QuickVid** - **R7** + - **R7Article** - **radio.de** - **radiobremen** + - **radiocanada** + - **RadioCanadaAudioVideo** - **radiofrance** - **RadioJavan** - **Rai** @@ -510,10 +547,13 @@ - **RedTube** - **RegioTV** - **Restudy** + - **Reuters** - **ReverbNation** - - **Revision3** + - **revision** + - **revision3:embed** - **RICE** - **RingTV** + - **RockstarGames** - **RottenTomatoes** - **Roxwel** - **RTBF** @@ -550,24 +590,25 @@ - **ScreencastOMatic** - **ScreenJunkies** - **ScreenwaveMedia** + - **Seeker** - **SenateISVP** + - **SendtoNews** - **ServingSys** - **Sexu** - - **SexyKarma**: Sexy Karma and Watch Indian Porn - **Shahid** - **Shared**: shared.sx and vivo.sx - **ShareSix** - **Sina** + - **SixPlay** + - **skynewsarabia:article** - **skynewsarabia:video** - - **skynewsarabia:video** + - **SkySports** - **Slideshare** - **Slutload** - **smotri**: Smotri.com - **smotri:broadcast**: Smotri.com broadcasts - **smotri:community**: Smotri.com community videos - **smotri:user**: Smotri.com user videos - - **SnagFilms** - - **SnagFilmsEmbed** - **Snotr** - **Sohu** - **soundcloud** @@ -593,6 +634,7 @@ - **SportBoxEmbed** - **SportDeutschland** - **Sportschau** + - **sr:mediathek**: Saarländischer Rundfunk - **SRGSSR** - **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites - **SSA** @@ -609,6 +651,7 @@ - **Syfy** - **SztvHu** - **Tagesschau** + - **tagesschau:player** - **Tapely** - **Tass** - **TDSLifeway** @@ -626,6 +669,7 @@ - **Telegraaf** - **TeleMB** - **TeleTask** + - **Telewebion** - **TF1** - **TheIntercept** - **ThePlatform** @@ -672,12 +716,12 @@ - **TVCArticle** - **tvigle**: Интернет-телевидение Tvigle.ru - **tvland.com** - - **tvp.pl** - - **tvp.pl:Series** + - **tvp**: Telewizja Polska + - **tvp:series** - **TVPlay**: TV3Play and related services - **Tweakers** - - **twitch:bookmarks** - **twitch:chapter** + - **twitch:clips** - **twitch:past_broadcasts** - **twitch:profile** - **twitch:stream** @@ -691,10 +735,12 @@ - **UDNEmbed**: 聯合影音 - **Unistra** - **Urort**: NRK P3 Urørt + - **URPlay** - **USAToday** - **ustream** - **ustream:channel** - - **Ustudio** + - **ustudio** + - **ustudio:embed** - **Varzesh3** - **Vbox7** - **VeeHD** @@ -702,10 +748,12 @@ - **Vessel** - **Vesti**: Вести.Ru - **Vevo** + - **VevoPlaylist** - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet - **vh1.com** - **Vice** - **ViceShow** + - **Vidbit** - **Viddler** - **video.google:search**: Google Video search - **video.mit.edu** @@ -718,12 +766,15 @@ - **VideoPremium** - **VideoTt**: video.tt - Your True Tube (Currently broken) - **videoweed**: VideoWeed + - **Vidio** - **vidme** - **vidme:user** - **vidme:user:likes** - **Vidzi** - **vier** - **vier:videos** + - **ViewLift** + - **ViewLiftEmbed** - **Viewster** - **Viidea** - **viki** @@ -751,16 +802,15 @@ - **VRT** - **vube**: Vube.com - **VuClip** - - **vulture.com** - **Walla** - - **WashingtonPost** + - **washingtonpost** + - **washingtonpost:article** - **wat.tv** + - **WatchIndianPorn**: Watch Indian Porn - **WDR** - **wdr:mobile** - - **WDRMaus**: Sendung mit der Maus - **WebOfStories** - **WebOfStoriesPlaylist** - - **Weibo** - **WeiqiTV**: WQTV - **wholecloud**: WholeCloud - **Wimp** @@ -768,12 +818,17 @@ - **WNL** - **WorldStarHipHop** - **wrzuta.pl** + - **wrzuta.pl:playlist** - **WSJ**: Wall Street Journal - **XBef** - **XboxClips** - - **XFileShare**: XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me + - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE - **XHamster** - **XHamsterEmbed** + - **xiami:album**: 虾米音乐 - 专辑 + - **xiami:artist**: 虾米音乐 - 歌手 + - **xiami:collection**: 虾米音乐 - 精选集 + - **xiami:song**: 虾米音乐 - **XMinus** - **XNXX** - **Xstream** @@ -792,6 +847,7 @@ - **Ynet** - **YouJizz** - **youku**: 优酷 + - **youku:show** - **YouPorn** - **YourUpload** - **youtube**: YouTube.com @@ -805,6 +861,7 @@ - **youtube:search**: YouTube.com searches - **youtube:search:date**: YouTube.com searches, newest videos first - **youtube:search_url**: YouTube.com search URLs + - **youtube:shared** - **youtube:show**: YouTube.com (multi-season) shows - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication) - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword) diff --git a/setup.py b/setup.py index 9444d403d..508b27f37 100644 --- a/setup.py +++ b/setup.py @@ -21,25 +21,37 @@ try: import py2exe except ImportError: if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe': - print("Cannot import py2exe", file=sys.stderr) + print('Cannot import py2exe', file=sys.stderr) exit(1) py2exe_options = { - "bundle_files": 1, - "compressed": 1, - "optimize": 2, - "dist_dir": '.', - "dll_excludes": ['w9xpopen.exe', 'crypt32.dll'], + 'bundle_files': 1, + 'compressed': 1, + 'optimize': 2, + 'dist_dir': '.', + 'dll_excludes': ['w9xpopen.exe', 'crypt32.dll'], } +# Get the version from youtube_dl/version.py without importing the package +exec(compile(open('youtube_dl/version.py').read(), + 'youtube_dl/version.py', 'exec')) + +DESCRIPTION = 'YouTube video downloader' +LONG_DESCRIPTION = 'Command-line program to download videos from YouTube.com and other video sites' + py2exe_console = [{ - "script": "./youtube_dl/__main__.py", - "dest_base": "youtube-dl", + 'script': './youtube_dl/__main__.py', + 'dest_base': 'youtube-dl', + 'version': __version__, + 'description': DESCRIPTION, + 'comments': LONG_DESCRIPTION, + 'product_name': 'youtube-dl', + 'product_version': __version__, }] py2exe_params = { 'console': py2exe_console, - 'options': {"py2exe": py2exe_options}, + 'options': {'py2exe': py2exe_options}, 'zipfile': None } @@ -72,7 +84,7 @@ else: params['scripts'] = ['bin/youtube-dl'] class build_lazy_extractors(Command): - description = "Build the extractor lazy loading module" + description = 'Build the extractor lazy loading module' user_options = [] def initialize_options(self): @@ -87,16 +99,11 @@ class build_lazy_extractors(Command): dry_run=self.dry_run, ) -# Get the version from youtube_dl/version.py without importing the package -exec(compile(open('youtube_dl/version.py').read(), - 'youtube_dl/version.py', 'exec')) - setup( name='youtube_dl', version=__version__, - description='YouTube video downloader', - long_description='Small command-line program to download videos from' - ' YouTube.com and other video sites.', + description=DESCRIPTION, + long_description=LONG_DESCRIPTION, url='https://github.com/rg3/youtube-dl', author='Ricardo Garcia', author_email='ytdl@yt-dl.org', @@ -112,16 +119,17 @@ setup( # test_requires = ['nosetest'], classifiers=[ - "Topic :: Multimedia :: Video", - "Development Status :: 5 - Production/Stable", - "Environment :: Console", - "License :: Public Domain", - "Programming Language :: Python :: 2.6", - "Programming Language :: Python :: 2.7", - "Programming Language :: Python :: 3", - "Programming Language :: Python :: 3.2", - "Programming Language :: Python :: 3.3", - "Programming Language :: Python :: 3.4", + 'Topic :: Multimedia :: Video', + 'Development Status :: 5 - Production/Stable', + 'Environment :: Console', + 'License :: Public Domain', + 'Programming Language :: Python :: 2.6', + 'Programming Language :: Python :: 2.7', + 'Programming Language :: Python :: 3', + 'Programming Language :: Python :: 3.2', + 'Programming Language :: Python :: 3.3', + 'Programming Language :: Python :: 3.4', + 'Programming Language :: Python :: 3.5', ], cmdclass={'build_lazy_extractors': build_lazy_extractors}, diff --git a/test/helper.py b/test/helper.py index b8e22c5cb..dfee217a9 100644 --- a/test/helper.py +++ b/test/helper.py @@ -24,8 +24,13 @@ from youtube_dl.utils import ( def get_params(override=None): PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json") + LOCAL_PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), + "local_parameters.json") with io.open(PARAMETERS_FILE, encoding='utf-8') as pf: parameters = json.load(pf) + if os.path.exists(LOCAL_PARAMETERS_FILE): + with io.open(LOCAL_PARAMETERS_FILE, encoding='utf-8') as pf: + parameters.update(json.load(pf)) if override: parameters.update(override) return parameters diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index 6404ac89f..88e8ff904 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -11,7 +11,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from test.helper import FakeYDL from youtube_dl.extractor.common import InfoExtractor from youtube_dl.extractor import YoutubeIE, get_info_extractor -from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError +from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError class TestIE(InfoExtractor): @@ -66,6 +66,11 @@ class TestInfoExtractor(unittest.TestCase): self.assertEqual(ie._html_search_meta('d', html), '4') self.assertEqual(ie._html_search_meta('e', html), '5') self.assertEqual(ie._html_search_meta('f', html), '6') + self.assertEqual(ie._html_search_meta(('a', 'b', 'c'), html), '1') + self.assertEqual(ie._html_search_meta(('c', 'b', 'a'), html), '3') + self.assertEqual(ie._html_search_meta(('z', 'x', 'c'), html), '3') + self.assertRaises(RegexNotFoundError, ie._html_search_meta, 'z', html, None, fatal=True) + self.assertRaises(RegexNotFoundError, ie._html_search_meta, ('z', 'x'), html, None, fatal=True) def test_download_json(self): uri = encode_data_uri(b'{"foo": "blah"}', 'application/json') diff --git a/test/test_all_urls.py b/test/test_all_urls.py index f5af184e6..1f6079c29 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -6,6 +6,7 @@ from __future__ import unicode_literals import os import sys import unittest +import collections sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) @@ -130,6 +131,15 @@ class TestAllURLsMatching(unittest.TestCase): 'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html', ['Yahoo']) + def test_no_duplicated_ie_names(self): + name_accu = collections.defaultdict(list) + for ie in self.ies: + name_accu[ie.IE_NAME.lower()].append(type(ie).__name__) + for (ie_name, ie_list) in name_accu.items(): + self.assertEqual( + len(ie_list), 1, + 'Multiple extractors with the same IE_NAME "%s" (%s)' % (ie_name, ', '.join(ie_list))) + if __name__ == '__main__': unittest.main() diff --git a/test/test_compat.py b/test/test_compat.py index 618668210..b57424948 100644 --- a/test/test_compat.py +++ b/test/test_compat.py @@ -10,13 +10,14 @@ import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from youtube_dl.utils import get_filesystem_encoding from youtube_dl.compat import ( compat_getenv, + compat_setenv, compat_etree_fromstring, compat_expanduser, compat_shlex_split, compat_str, + compat_struct_unpack, compat_urllib_parse_unquote, compat_urllib_parse_unquote_plus, compat_urllib_parse_urlencode, @@ -26,19 +27,22 @@ from youtube_dl.compat import ( class TestCompat(unittest.TestCase): def test_compat_getenv(self): test_str = 'тест' - os.environ['YOUTUBE-DL-TEST'] = ( - test_str if sys.version_info >= (3, 0) - else test_str.encode(get_filesystem_encoding())) + compat_setenv('YOUTUBE-DL-TEST', test_str) self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str) + def test_compat_setenv(self): + test_var = 'YOUTUBE-DL-TEST' + test_str = 'тест' + compat_setenv(test_var, test_str) + compat_getenv(test_var) + self.assertEqual(compat_getenv(test_var), test_str) + def test_compat_expanduser(self): old_home = os.environ.get('HOME') test_str = 'C:\Documents and Settings\тест\Application Data' - os.environ['HOME'] = ( - test_str if sys.version_info >= (3, 0) - else test_str.encode(get_filesystem_encoding())) + compat_setenv('HOME', test_str) self.assertEqual(compat_expanduser('~'), test_str) - os.environ['HOME'] = old_home + compat_setenv('HOME', old_home or '') def test_all_present(self): import youtube_dl.compat @@ -83,6 +87,8 @@ class TestCompat(unittest.TestCase): def test_compat_shlex_split(self): self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two']) + self.assertEqual(compat_shlex_split('-option "one\ntwo" \n -flag'), ['-option', 'one\ntwo', '-flag']) + self.assertEqual(compat_shlex_split('-val 中文'), ['-val', '中文']) def test_compat_etree_fromstring(self): xml = ''' @@ -99,5 +105,15 @@ class TestCompat(unittest.TestCase): self.assertTrue(isinstance(doc.find('chinese').text, compat_str)) self.assertTrue(isinstance(doc.find('foo/bar').text, compat_str)) + def test_compat_etree_fromstring_doctype(self): + xml = '''<?xml version="1.0"?> +<!DOCTYPE smil PUBLIC "-//W3C//DTD SMIL 2.0//EN" "http://www.w3.org/2001/SMIL20/SMIL20.dtd"> +<smil xmlns="http://www.w3.org/2001/SMIL20/Language"></smil>''' + compat_etree_fromstring(xml) + + def test_struct_unpack(self): + self.assertEqual(compat_struct_unpack('!B', b'\x00'), (0,)) + + if __name__ == '__main__': unittest.main() diff --git a/test/test_http.py b/test/test_http.py index 15e0ad369..fdc68ccb4 100644 --- a/test/test_http.py +++ b/test/test_http.py @@ -16,6 +16,15 @@ import threading TEST_DIR = os.path.dirname(os.path.abspath(__file__)) +def http_server_port(httpd): + if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket): + # In Jython SSLSocket is not a subclass of socket.socket + sock = httpd.socket.sock + else: + sock = httpd.socket + return sock.getsockname()[1] + + class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler): def log_message(self, format, *args): pass @@ -31,6 +40,22 @@ class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler): self.send_header('Content-Type', 'video/mp4') self.end_headers() self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]') + elif self.path == '/302': + if sys.version_info[0] == 3: + # XXX: Python 3 http server does not allow non-ASCII header values + self.send_response(404) + self.end_headers() + return + + new_url = 'http://localhost:%d/中文.html' % http_server_port(self.server) + self.send_response(302) + self.send_header(b'Location', new_url.encode('utf-8')) + self.end_headers() + elif self.path == '/%E4%B8%AD%E6%96%87.html': + self.send_response(200) + self.send_header('Content-Type', 'text/html; charset=utf-8') + self.end_headers() + self.wfile.write(b'<html><video src="/vid.mp4" /></html>') else: assert False @@ -47,18 +72,32 @@ class FakeLogger(object): class TestHTTP(unittest.TestCase): + def setUp(self): + self.httpd = compat_http_server.HTTPServer( + ('localhost', 0), HTTPTestRequestHandler) + self.port = http_server_port(self.httpd) + self.server_thread = threading.Thread(target=self.httpd.serve_forever) + self.server_thread.daemon = True + self.server_thread.start() + + def test_unicode_path_redirection(self): + # XXX: Python 3 http server does not allow non-ASCII header values + if sys.version_info[0] == 3: + return + + ydl = YoutubeDL({'logger': FakeLogger()}) + r = ydl.extract_info('http://localhost:%d/302' % self.port) + self.assertEqual(r['url'], 'http://localhost:%d/vid.mp4' % self.port) + + +class TestHTTPS(unittest.TestCase): def setUp(self): certfn = os.path.join(TEST_DIR, 'testcert.pem') self.httpd = compat_http_server.HTTPServer( ('localhost', 0), HTTPTestRequestHandler) self.httpd.socket = ssl.wrap_socket( self.httpd.socket, certfile=certfn, server_side=True) - if os.name == 'java': - # In Jython SSLSocket is not a subclass of socket.socket - sock = self.httpd.socket.sock - else: - sock = self.httpd.socket - self.port = sock.getsockname()[1] + self.port = http_server_port(self.httpd) self.server_thread = threading.Thread(target=self.httpd.serve_forever) self.server_thread.daemon = True self.server_thread.start() @@ -94,32 +133,32 @@ class TestProxy(unittest.TestCase): def setUp(self): self.proxy = compat_http_server.HTTPServer( ('localhost', 0), _build_proxy_handler('normal')) - self.port = self.proxy.socket.getsockname()[1] + self.port = http_server_port(self.proxy) self.proxy_thread = threading.Thread(target=self.proxy.serve_forever) self.proxy_thread.daemon = True self.proxy_thread.start() - self.cn_proxy = compat_http_server.HTTPServer( - ('localhost', 0), _build_proxy_handler('cn')) - self.cn_port = self.cn_proxy.socket.getsockname()[1] - self.cn_proxy_thread = threading.Thread(target=self.cn_proxy.serve_forever) - self.cn_proxy_thread.daemon = True - self.cn_proxy_thread.start() + self.geo_proxy = compat_http_server.HTTPServer( + ('localhost', 0), _build_proxy_handler('geo')) + self.geo_port = http_server_port(self.geo_proxy) + self.geo_proxy_thread = threading.Thread(target=self.geo_proxy.serve_forever) + self.geo_proxy_thread.daemon = True + self.geo_proxy_thread.start() def test_proxy(self): - cn_proxy = 'localhost:{0}'.format(self.cn_port) + geo_proxy = 'localhost:{0}'.format(self.geo_port) ydl = YoutubeDL({ 'proxy': 'localhost:{0}'.format(self.port), - 'cn_verification_proxy': cn_proxy, + 'geo_verification_proxy': geo_proxy, }) url = 'http://foo.com/bar' response = ydl.urlopen(url).read().decode('utf-8') self.assertEqual(response, 'normal: {0}'.format(url)) req = compat_urllib_request.Request(url) - req.add_header('Ytdl-request-proxy', cn_proxy) + req.add_header('Ytdl-request-proxy', geo_proxy) response = ydl.urlopen(req).read().decode('utf-8') - self.assertEqual(response, 'cn: {0}'.format(url)) + self.assertEqual(response, 'geo: {0}'.format(url)) def test_proxy_with_idn(self): ydl = YoutubeDL({ diff --git a/test/test_socks.py b/test/test_socks.py new file mode 100644 index 000000000..1e68eb0da --- /dev/null +++ b/test/test_socks.py @@ -0,0 +1,118 @@ +#!/usr/bin/env python +# coding: utf-8 +from __future__ import unicode_literals + +# Allow direct execution +import os +import sys +import unittest +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +import random +import subprocess + +from test.helper import ( + FakeYDL, + get_params, +) +from youtube_dl.compat import ( + compat_str, + compat_urllib_request, +) + + +class TestMultipleSocks(unittest.TestCase): + @staticmethod + def _check_params(attrs): + params = get_params() + for attr in attrs: + if attr not in params: + print('Missing %s. Skipping.' % attr) + return + return params + + def test_proxy_http(self): + params = self._check_params(['primary_proxy', 'primary_server_ip']) + if params is None: + return + ydl = FakeYDL({ + 'proxy': params['primary_proxy'] + }) + self.assertEqual( + ydl.urlopen('http://yt-dl.org/ip').read().decode('utf-8'), + params['primary_server_ip']) + + def test_proxy_https(self): + params = self._check_params(['primary_proxy', 'primary_server_ip']) + if params is None: + return + ydl = FakeYDL({ + 'proxy': params['primary_proxy'] + }) + self.assertEqual( + ydl.urlopen('https://yt-dl.org/ip').read().decode('utf-8'), + params['primary_server_ip']) + + def test_secondary_proxy_http(self): + params = self._check_params(['secondary_proxy', 'secondary_server_ip']) + if params is None: + return + ydl = FakeYDL() + req = compat_urllib_request.Request('http://yt-dl.org/ip') + req.add_header('Ytdl-request-proxy', params['secondary_proxy']) + self.assertEqual( + ydl.urlopen(req).read().decode('utf-8'), + params['secondary_server_ip']) + + def test_secondary_proxy_https(self): + params = self._check_params(['secondary_proxy', 'secondary_server_ip']) + if params is None: + return + ydl = FakeYDL() + req = compat_urllib_request.Request('https://yt-dl.org/ip') + req.add_header('Ytdl-request-proxy', params['secondary_proxy']) + self.assertEqual( + ydl.urlopen(req).read().decode('utf-8'), + params['secondary_server_ip']) + + +class TestSocks(unittest.TestCase): + _SKIP_SOCKS_TEST = True + + def setUp(self): + if self._SKIP_SOCKS_TEST: + return + + self.port = random.randint(20000, 30000) + self.server_process = subprocess.Popen([ + 'srelay', '-f', '-i', '127.0.0.1:%d' % self.port], + stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) + + def tearDown(self): + if self._SKIP_SOCKS_TEST: + return + + self.server_process.terminate() + self.server_process.communicate() + + def _get_ip(self, protocol): + if self._SKIP_SOCKS_TEST: + return '127.0.0.1' + + ydl = FakeYDL({ + 'proxy': '%s://127.0.0.1:%d' % (protocol, self.port), + }) + return ydl.urlopen('http://yt-dl.org/ip').read().decode('utf-8') + + def test_socks4(self): + self.assertTrue(isinstance(self._get_ip('socks4'), compat_str)) + + def test_socks4a(self): + self.assertTrue(isinstance(self._get_ip('socks4a'), compat_str)) + + def test_socks5(self): + self.assertTrue(isinstance(self._get_ip('socks5'), compat_str)) + + +if __name__ == '__main__': + unittest.main() diff --git a/test/test_utils.py b/test/test_utils.py index e16a6761b..afd273a65 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -33,6 +33,7 @@ from youtube_dl.utils import ( ExtractorError, find_xpath_attr, fix_xml_ampersands, + get_element_by_class, InAdvancePagedList, intlist_to_bytes, is_html, @@ -50,20 +51,23 @@ from youtube_dl.utils import ( sanitize_path, prepend_extension, replace_extension, + remove_start, + remove_end, remove_quotes, shell_quote, smuggle_url, str_to_int, strip_jsonp, - struct_unpack, timeconvert, unescapeHTML, unified_strdate, + unified_timestamp, unsmuggle_url, uppercase_escape, lowercase_escape, url_basename, urlencode_postdata, + urshift, update_url_query, version_tuple, xpath_with_ns, @@ -139,8 +143,8 @@ class TestUtil(unittest.TestCase): self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True)) self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True)) - tests = 'a\xe4b\u4e2d\u56fd\u7684c' - self.assertEqual(sanitize_filename(tests, restricted=True), 'a_b_c') + tests = 'aäb\u4e2d\u56fd\u7684c' + self.assertEqual(sanitize_filename(tests, restricted=True), 'aab_c') self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#' @@ -155,6 +159,10 @@ class TestUtil(unittest.TestCase): self.assertTrue(sanitize_filename('-', restricted=True) != '') self.assertTrue(sanitize_filename(':', restricted=True) != '') + self.assertEqual(sanitize_filename( + 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True), + 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy') + def test_sanitize_ids(self): self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw') self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw') @@ -212,6 +220,16 @@ class TestUtil(unittest.TestCase): self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp') self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp') + def test_remove_start(self): + self.assertEqual(remove_start(None, 'A - '), None) + self.assertEqual(remove_start('A - B', 'A - '), 'B') + self.assertEqual(remove_start('B - A', 'A - '), 'B - A') + + def test_remove_end(self): + self.assertEqual(remove_end(None, ' - B'), None) + self.assertEqual(remove_end('A - B', ' - B'), 'A') + self.assertEqual(remove_end('B - A', ' - B'), 'B - A') + def test_remove_quotes(self): self.assertEqual(remove_quotes(None), None) self.assertEqual(remove_quotes('"'), '"') @@ -234,6 +252,8 @@ class TestUtil(unittest.TestCase): self.assertEqual(unescapeHTML('/'), '/') self.assertEqual(unescapeHTML('é'), 'é') self.assertEqual(unescapeHTML('�'), '�') + # HTML5 entities + self.assertEqual(unescapeHTML('.''), '.\'') def test_date_from_str(self): self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day')) @@ -266,8 +286,28 @@ class TestUtil(unittest.TestCase): '20150202') self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214') self.assertEqual(unified_strdate('25-09-2014'), '20140925') + self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227') self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None) + def test_unified_timestamps(self): + self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600) + self.assertEqual(unified_timestamp('8/7/2009'), 1247011200) + self.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200) + self.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598) + self.assertEqual(unified_timestamp('1968 12 10'), -33436800) + self.assertEqual(unified_timestamp('1968-12-10'), -33436800) + self.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200) + self.assertEqual( + unified_timestamp('11/26/2014 11:30:00 AM PST', day_first=False), + 1417001400) + self.assertEqual( + unified_timestamp('2/2/2015 6:47:40 PM', day_first=False), + 1422902860) + self.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900) + self.assertEqual(unified_timestamp('25-09-2014'), 1411603200) + self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200) + self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None) + def test_determine_ext(self): self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4') self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None) @@ -366,6 +406,12 @@ class TestUtil(unittest.TestCase): self.assertEqual(res_url, url) self.assertEqual(res_data, None) + smug_url = smuggle_url(url, {'a': 'b'}) + smug_smug_url = smuggle_url(smug_url, {'c': 'd'}) + res_url, res_data = unsmuggle_url(smug_smug_url) + self.assertEqual(res_url, url) + self.assertEqual(res_data, {'a': 'b', 'c': 'd'}) + def test_shell_quote(self): args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')] self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""") @@ -453,9 +499,6 @@ class TestUtil(unittest.TestCase): testPL(5, 2, (2, 99), [2, 3, 4]) testPL(5, 2, (20, 99), []) - def test_struct_unpack(self): - self.assertEqual(struct_unpack('!B', b'\x00'), (0,)) - def test_read_batch_urls(self): f = io.StringIO('''\xef\xbb\xbf foo bar\r @@ -617,6 +660,18 @@ class TestUtil(unittest.TestCase): json_code = js_to_json(inp) self.assertEqual(json.loads(json_code), json.loads(inp)) + inp = '''{ + 0:{src:'skipped', type: 'application/dash+xml'}, + 1:{src:'skipped', type: 'application/vnd.apple.mpegURL'}, + }''' + self.assertEqual(js_to_json(inp), '''{ + "0":{"src":"skipped", "type": "application/dash+xml"}, + "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"} + }''') + + inp = '''{"foo":101}''' + self.assertEqual(js_to_json(inp), '''{"foo":101}''') + def test_js_to_json_edgecases(self): on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}") self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"}) @@ -640,6 +695,27 @@ class TestUtil(unittest.TestCase): on = js_to_json('{"abc": "def",}') self.assertEqual(json.loads(on), {'abc': 'def'}) + on = js_to_json('{ 0: /* " \n */ ",]" , }') + self.assertEqual(json.loads(on), {'0': ',]'}) + + on = js_to_json(r'["<p>x<\/p>"]') + self.assertEqual(json.loads(on), ['<p>x</p>']) + + on = js_to_json(r'["\xaa"]') + self.assertEqual(json.loads(on), ['\u00aa']) + + on = js_to_json("['a\\\nb']") + self.assertEqual(json.loads(on), ['ab']) + + on = js_to_json('{0xff:0xff}') + self.assertEqual(json.loads(on), {'255': 255}) + + on = js_to_json('{077:077}') + self.assertEqual(json.loads(on), {'63': 63}) + + on = js_to_json('{42:42}') + self.assertEqual(json.loads(on), {'42': 42}) + def test_extract_attributes(self): self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'}) self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'}) @@ -912,5 +988,17 @@ The first line self.assertRaises(ValueError, encode_base_n, 0, 70) self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table) + def test_urshift(self): + self.assertEqual(urshift(3, 1), 1) + self.assertEqual(urshift(-3, 1), 2147483646) + + def test_get_element_by_class(self): + html = ''' + <span class="foo bar">nice</span> + ''' + + self.assertEqual(get_element_by_class('foo', html), 'nice') + self.assertEqual(get_element_by_class('no-such-class', html), None) + if __name__ == '__main__': unittest.main() diff --git a/tox.ini b/tox.ini index 2d7134005..9c4e4a3d1 100644 --- a/tox.ini +++ b/tox.ini @@ -9,5 +9,6 @@ passenv = HOME defaultargs = test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py + --exclude test_socks.py commands = nosetests --verbose {posargs:{[testenv]defaultargs}} # --with-coverage --cover-package=youtube_dl --cover-html # test.test_download:TestDownload.test_NowVideo diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 055433362..ba72ec6f3 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -64,6 +64,7 @@ from .utils import ( PostProcessingError, preferredencoding, prepend_extension, + register_socks_protocols, render_table, replace_extension, SameFileError, @@ -195,8 +196,8 @@ class YoutubeDL(object): prefer_insecure: Use HTTP instead of HTTPS to retrieve information. At the moment, this is only supported by YouTube. proxy: URL of the proxy server to use - cn_verification_proxy: URL of the proxy to use for IP address verification - on Chinese sites. (Experimental) + geo_verification_proxy: URL of the proxy to use for IP address verification + on geo-restricted sites. (Experimental) socket_timeout: Time to wait for unresponsive hosts, in seconds bidi_workaround: Work around buggy terminals without bidirectional text support, using fridibi @@ -303,6 +304,11 @@ class YoutubeDL(object): self.params.update(params) self.cache = Cache(self) + if self.params.get('cn_verification_proxy') is not None: + self.report_warning('--cn-verification-proxy is deprecated. Use --geo-verification-proxy instead.') + if self.params.get('geo_verification_proxy') is None: + self.params['geo_verification_proxy'] = self.params['cn_verification_proxy'] + if params.get('bidi_workaround', False): try: import pty @@ -325,7 +331,7 @@ class YoutubeDL(object): ['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs) self._output_channel = os.fdopen(master, 'rb') except OSError as ose: - if ose.errno == 2: + if ose.errno == errno.ENOENT: self.report_warning('Could not find fribidi executable, ignoring --bidi-workaround . Make sure that fribidi is an executable file in one of the directories in your $PATH.') else: raise @@ -361,6 +367,8 @@ class YoutubeDL(object): for ph in self.params.get('progress_hooks', []): self.add_progress_hook(ph) + register_socks_protocols() + def warn_if_short_id(self, argv): # short YouTube ID starting with dash? idxs = [ @@ -580,7 +588,7 @@ class YoutubeDL(object): is_id=(k == 'id')) template_dict = dict((k, sanitize(k, v)) for k, v in template_dict.items() - if v is not None) + if v is not None and not isinstance(v, (list, tuple, dict))) template_dict = collections.defaultdict(lambda: 'NA', template_dict) outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) @@ -717,6 +725,7 @@ class YoutubeDL(object): result_type = ie_result.get('_type', 'video') if result_type in ('url', 'url_transparent'): + ie_result['url'] = sanitize_url(ie_result['url']) extract_flat = self.params.get('extract_flat', False) if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) or extract_flat is True): @@ -1219,6 +1228,10 @@ class YoutubeDL(object): if 'title' not in info_dict: raise ExtractorError('Missing "title" field in extractor result') + if not isinstance(info_dict['id'], compat_str): + self.report_warning('"id" field is not a string - forcing string conversion') + info_dict['id'] = compat_str(info_dict['id']) + if 'playlist' not in info_dict: # It isn't part of a playlist info_dict['playlist'] = None @@ -1639,7 +1652,7 @@ class YoutubeDL(object): # Just a single file success = dl(filename, info_dict) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self.report_error('unable to download video data: %s' % str(err)) + self.report_error('unable to download video data: %s' % error_to_compat_str(err)) return except (OSError, IOError) as err: raise UnavailableVideoError(err) @@ -2018,6 +2031,7 @@ class YoutubeDL(object): if opts_cookiefile is None: self.cookiejar = compat_cookiejar.CookieJar() else: + opts_cookiefile = compat_expanduser(opts_cookiefile) self.cookiejar = compat_cookiejar.MozillaCookieJar( opts_cookiefile) if os.access(opts_cookiefile, os.R_OK): diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 737f6545d..2b34bf9c2 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -18,7 +18,6 @@ from .options import ( from .compat import ( compat_expanduser, compat_getpass, - compat_print, compat_shlex_split, workaround_optparse_bug9161, ) @@ -67,16 +66,16 @@ def _real_main(argv=None): # Custom HTTP headers if opts.headers is not None: for h in opts.headers: - if h.find(':', 1) < 0: + if ':' not in h: parser.error('wrong header formatting, it should be key:value, not "%s"' % h) - key, value = h.split(':', 2) + key, value = h.split(':', 1) if opts.verbose: write_string('[debug] Adding header from command line option %s:%s\n' % (key, value)) std_headers[key] = value # Dump user agent if opts.dump_user_agent: - compat_print(std_headers['User-Agent']) + write_string(std_headers['User-Agent'] + '\n', out=sys.stdout) sys.exit(0) # Batch file verification @@ -86,7 +85,9 @@ def _real_main(argv=None): if opts.batchfile == '-': batchfd = sys.stdin else: - batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore') + batchfd = io.open( + compat_expanduser(opts.batchfile), + 'r', encoding='utf-8', errors='ignore') batch_urls = read_batch_urls(batchfd) if opts.verbose: write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n') @@ -99,10 +100,10 @@ def _real_main(argv=None): if opts.list_extractors: for ie in list_extractors(opts.age_limit): - compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '')) + write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout) matchedUrls = [url for url in all_urls if ie.suitable(url)] for mu in matchedUrls: - compat_print(' ' + mu) + write_string(' ' + mu + '\n', out=sys.stdout) sys.exit(0) if opts.list_extractor_descriptions: for ie in list_extractors(opts.age_limit): @@ -115,7 +116,7 @@ def _real_main(argv=None): _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow') _COUNTS = ('', '5', '10', 'all') desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES)) - compat_print(desc) + write_string(desc + '\n', out=sys.stdout) sys.exit(0) # Conflicting, missing and erroneous options @@ -381,6 +382,8 @@ def _real_main(argv=None): 'external_downloader_args': external_downloader_args, 'postprocessor_args': postprocessor_args, 'cn_verification_proxy': opts.cn_verification_proxy, + 'geo_verification_proxy': opts.geo_verification_proxy, + } with YoutubeDL(ydl_opts) as ydl: @@ -404,7 +407,7 @@ def _real_main(argv=None): try: if opts.load_info_filename is not None: - retcode = ydl.download_with_info_file(opts.load_info_filename) + retcode = ydl.download_with_info_file(compat_expanduser(opts.load_info_filename)) else: retcode = ydl.download(all_urls) except MaxDownloadsReached: diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index 0b6c5ca7a..b8aaf5a46 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import binascii @@ -11,6 +12,7 @@ import re import shlex import shutil import socket +import struct import subprocess import sys import itertools @@ -62,6 +64,2244 @@ try: except ImportError: # Python 2 import htmlentitydefs as compat_html_entities +try: # Python >= 3.3 + compat_html_entities_html5 = compat_html_entities.html5 +except AttributeError: + # Copied from CPython 3.5.1 html/entities.py + compat_html_entities_html5 = { + 'Aacute': '\xc1', + 'aacute': '\xe1', + 'Aacute;': '\xc1', + 'aacute;': '\xe1', + 'Abreve;': '\u0102', + 'abreve;': '\u0103', + 'ac;': '\u223e', + 'acd;': '\u223f', + 'acE;': '\u223e\u0333', + 'Acirc': '\xc2', + 'acirc': '\xe2', + 'Acirc;': '\xc2', + 'acirc;': '\xe2', + 'acute': '\xb4', + 'acute;': '\xb4', + 'Acy;': '\u0410', + 'acy;': '\u0430', + 'AElig': '\xc6', + 'aelig': '\xe6', + 'AElig;': '\xc6', + 'aelig;': '\xe6', + 'af;': '\u2061', + 'Afr;': '\U0001d504', + 'afr;': '\U0001d51e', + 'Agrave': '\xc0', + 'agrave': '\xe0', + 'Agrave;': '\xc0', + 'agrave;': '\xe0', + 'alefsym;': '\u2135', + 'aleph;': '\u2135', + 'Alpha;': '\u0391', + 'alpha;': '\u03b1', + 'Amacr;': '\u0100', + 'amacr;': '\u0101', + 'amalg;': '\u2a3f', + 'AMP': '&', + 'amp': '&', + 'AMP;': '&', + 'amp;': '&', + 'And;': '\u2a53', + 'and;': '\u2227', + 'andand;': '\u2a55', + 'andd;': '\u2a5c', + 'andslope;': '\u2a58', + 'andv;': '\u2a5a', + 'ang;': '\u2220', + 'ange;': '\u29a4', + 'angle;': '\u2220', + 'angmsd;': '\u2221', + 'angmsdaa;': '\u29a8', + 'angmsdab;': '\u29a9', + 'angmsdac;': '\u29aa', + 'angmsdad;': '\u29ab', + 'angmsdae;': '\u29ac', + 'angmsdaf;': '\u29ad', + 'angmsdag;': '\u29ae', + 'angmsdah;': '\u29af', + 'angrt;': '\u221f', + 'angrtvb;': '\u22be', + 'angrtvbd;': '\u299d', + 'angsph;': '\u2222', + 'angst;': '\xc5', + 'angzarr;': '\u237c', + 'Aogon;': '\u0104', + 'aogon;': '\u0105', + 'Aopf;': '\U0001d538', + 'aopf;': '\U0001d552', + 'ap;': '\u2248', + 'apacir;': '\u2a6f', + 'apE;': '\u2a70', + 'ape;': '\u224a', + 'apid;': '\u224b', + 'apos;': "'", + 'ApplyFunction;': '\u2061', + 'approx;': '\u2248', + 'approxeq;': '\u224a', + 'Aring': '\xc5', + 'aring': '\xe5', + 'Aring;': '\xc5', + 'aring;': '\xe5', + 'Ascr;': '\U0001d49c', + 'ascr;': '\U0001d4b6', + 'Assign;': '\u2254', + 'ast;': '*', + 'asymp;': '\u2248', + 'asympeq;': '\u224d', + 'Atilde': '\xc3', + 'atilde': '\xe3', + 'Atilde;': '\xc3', + 'atilde;': '\xe3', + 'Auml': '\xc4', + 'auml': '\xe4', + 'Auml;': '\xc4', + 'auml;': '\xe4', + 'awconint;': '\u2233', + 'awint;': '\u2a11', + 'backcong;': '\u224c', + 'backepsilon;': '\u03f6', + 'backprime;': '\u2035', + 'backsim;': '\u223d', + 'backsimeq;': '\u22cd', + 'Backslash;': '\u2216', + 'Barv;': '\u2ae7', + 'barvee;': '\u22bd', + 'Barwed;': '\u2306', + 'barwed;': '\u2305', + 'barwedge;': '\u2305', + 'bbrk;': '\u23b5', + 'bbrktbrk;': '\u23b6', + 'bcong;': '\u224c', + 'Bcy;': '\u0411', + 'bcy;': '\u0431', + 'bdquo;': '\u201e', + 'becaus;': '\u2235', + 'Because;': '\u2235', + 'because;': '\u2235', + 'bemptyv;': '\u29b0', + 'bepsi;': '\u03f6', + 'bernou;': '\u212c', + 'Bernoullis;': '\u212c', + 'Beta;': '\u0392', + 'beta;': '\u03b2', + 'beth;': '\u2136', + 'between;': '\u226c', + 'Bfr;': '\U0001d505', + 'bfr;': '\U0001d51f', + 'bigcap;': '\u22c2', + 'bigcirc;': '\u25ef', + 'bigcup;': '\u22c3', + 'bigodot;': '\u2a00', + 'bigoplus;': '\u2a01', + 'bigotimes;': '\u2a02', + 'bigsqcup;': '\u2a06', + 'bigstar;': '\u2605', + 'bigtriangledown;': '\u25bd', + 'bigtriangleup;': '\u25b3', + 'biguplus;': '\u2a04', + 'bigvee;': '\u22c1', + 'bigwedge;': '\u22c0', + 'bkarow;': '\u290d', + 'blacklozenge;': '\u29eb', + 'blacksquare;': '\u25aa', + 'blacktriangle;': '\u25b4', + 'blacktriangledown;': '\u25be', + 'blacktriangleleft;': '\u25c2', + 'blacktriangleright;': '\u25b8', + 'blank;': '\u2423', + 'blk12;': '\u2592', + 'blk14;': '\u2591', + 'blk34;': '\u2593', + 'block;': '\u2588', + 'bne;': '=\u20e5', + 'bnequiv;': '\u2261\u20e5', + 'bNot;': '\u2aed', + 'bnot;': '\u2310', + 'Bopf;': '\U0001d539', + 'bopf;': '\U0001d553', + 'bot;': '\u22a5', + 'bottom;': '\u22a5', + 'bowtie;': '\u22c8', + 'boxbox;': '\u29c9', + 'boxDL;': '\u2557', + 'boxDl;': '\u2556', + 'boxdL;': '\u2555', + 'boxdl;': '\u2510', + 'boxDR;': '\u2554', + 'boxDr;': '\u2553', + 'boxdR;': '\u2552', + 'boxdr;': '\u250c', + 'boxH;': '\u2550', + 'boxh;': '\u2500', + 'boxHD;': '\u2566', + 'boxHd;': '\u2564', + 'boxhD;': '\u2565', + 'boxhd;': '\u252c', + 'boxHU;': '\u2569', + 'boxHu;': '\u2567', + 'boxhU;': '\u2568', + 'boxhu;': '\u2534', + 'boxminus;': '\u229f', + 'boxplus;': '\u229e', + 'boxtimes;': '\u22a0', + 'boxUL;': '\u255d', + 'boxUl;': '\u255c', + 'boxuL;': '\u255b', + 'boxul;': '\u2518', + 'boxUR;': '\u255a', + 'boxUr;': '\u2559', + 'boxuR;': '\u2558', + 'boxur;': '\u2514', + 'boxV;': '\u2551', + 'boxv;': '\u2502', + 'boxVH;': '\u256c', + 'boxVh;': '\u256b', + 'boxvH;': '\u256a', + 'boxvh;': '\u253c', + 'boxVL;': '\u2563', + 'boxVl;': '\u2562', + 'boxvL;': '\u2561', + 'boxvl;': '\u2524', + 'boxVR;': '\u2560', + 'boxVr;': '\u255f', + 'boxvR;': '\u255e', + 'boxvr;': '\u251c', + 'bprime;': '\u2035', + 'Breve;': '\u02d8', + 'breve;': '\u02d8', + 'brvbar': '\xa6', + 'brvbar;': '\xa6', + 'Bscr;': '\u212c', + 'bscr;': '\U0001d4b7', + 'bsemi;': '\u204f', + 'bsim;': '\u223d', + 'bsime;': '\u22cd', + 'bsol;': '\\', + 'bsolb;': '\u29c5', + 'bsolhsub;': '\u27c8', + 'bull;': '\u2022', + 'bullet;': '\u2022', + 'bump;': '\u224e', + 'bumpE;': '\u2aae', + 'bumpe;': '\u224f', + 'Bumpeq;': '\u224e', + 'bumpeq;': '\u224f', + 'Cacute;': '\u0106', + 'cacute;': '\u0107', + 'Cap;': '\u22d2', + 'cap;': '\u2229', + 'capand;': '\u2a44', + 'capbrcup;': '\u2a49', + 'capcap;': '\u2a4b', + 'capcup;': '\u2a47', + 'capdot;': '\u2a40', + 'CapitalDifferentialD;': '\u2145', + 'caps;': '\u2229\ufe00', + 'caret;': '\u2041', + 'caron;': '\u02c7', + 'Cayleys;': '\u212d', + 'ccaps;': '\u2a4d', + 'Ccaron;': '\u010c', + 'ccaron;': '\u010d', + 'Ccedil': '\xc7', + 'ccedil': '\xe7', + 'Ccedil;': '\xc7', + 'ccedil;': '\xe7', + 'Ccirc;': '\u0108', + 'ccirc;': '\u0109', + 'Cconint;': '\u2230', + 'ccups;': '\u2a4c', + 'ccupssm;': '\u2a50', + 'Cdot;': '\u010a', + 'cdot;': '\u010b', + 'cedil': '\xb8', + 'cedil;': '\xb8', + 'Cedilla;': '\xb8', + 'cemptyv;': '\u29b2', + 'cent': '\xa2', + 'cent;': '\xa2', + 'CenterDot;': '\xb7', + 'centerdot;': '\xb7', + 'Cfr;': '\u212d', + 'cfr;': '\U0001d520', + 'CHcy;': '\u0427', + 'chcy;': '\u0447', + 'check;': '\u2713', + 'checkmark;': '\u2713', + 'Chi;': '\u03a7', + 'chi;': '\u03c7', + 'cir;': '\u25cb', + 'circ;': '\u02c6', + 'circeq;': '\u2257', + 'circlearrowleft;': '\u21ba', + 'circlearrowright;': '\u21bb', + 'circledast;': '\u229b', + 'circledcirc;': '\u229a', + 'circleddash;': '\u229d', + 'CircleDot;': '\u2299', + 'circledR;': '\xae', + 'circledS;': '\u24c8', + 'CircleMinus;': '\u2296', + 'CirclePlus;': '\u2295', + 'CircleTimes;': '\u2297', + 'cirE;': '\u29c3', + 'cire;': '\u2257', + 'cirfnint;': '\u2a10', + 'cirmid;': '\u2aef', + 'cirscir;': '\u29c2', + 'ClockwiseContourIntegral;': '\u2232', + 'CloseCurlyDoubleQuote;': '\u201d', + 'CloseCurlyQuote;': '\u2019', + 'clubs;': '\u2663', + 'clubsuit;': '\u2663', + 'Colon;': '\u2237', + 'colon;': ':', + 'Colone;': '\u2a74', + 'colone;': '\u2254', + 'coloneq;': '\u2254', + 'comma;': ',', + 'commat;': '@', + 'comp;': '\u2201', + 'compfn;': '\u2218', + 'complement;': '\u2201', + 'complexes;': '\u2102', + 'cong;': '\u2245', + 'congdot;': '\u2a6d', + 'Congruent;': '\u2261', + 'Conint;': '\u222f', + 'conint;': '\u222e', + 'ContourIntegral;': '\u222e', + 'Copf;': '\u2102', + 'copf;': '\U0001d554', + 'coprod;': '\u2210', + 'Coproduct;': '\u2210', + 'COPY': '\xa9', + 'copy': '\xa9', + 'COPY;': '\xa9', + 'copy;': '\xa9', + 'copysr;': '\u2117', + 'CounterClockwiseContourIntegral;': '\u2233', + 'crarr;': '\u21b5', + 'Cross;': '\u2a2f', + 'cross;': '\u2717', + 'Cscr;': '\U0001d49e', + 'cscr;': '\U0001d4b8', + 'csub;': '\u2acf', + 'csube;': '\u2ad1', + 'csup;': '\u2ad0', + 'csupe;': '\u2ad2', + 'ctdot;': '\u22ef', + 'cudarrl;': '\u2938', + 'cudarrr;': '\u2935', + 'cuepr;': '\u22de', + 'cuesc;': '\u22df', + 'cularr;': '\u21b6', + 'cularrp;': '\u293d', + 'Cup;': '\u22d3', + 'cup;': '\u222a', + 'cupbrcap;': '\u2a48', + 'CupCap;': '\u224d', + 'cupcap;': '\u2a46', + 'cupcup;': '\u2a4a', + 'cupdot;': '\u228d', + 'cupor;': '\u2a45', + 'cups;': '\u222a\ufe00', + 'curarr;': '\u21b7', + 'curarrm;': '\u293c', + 'curlyeqprec;': '\u22de', + 'curlyeqsucc;': '\u22df', + 'curlyvee;': '\u22ce', + 'curlywedge;': '\u22cf', + 'curren': '\xa4', + 'curren;': '\xa4', + 'curvearrowleft;': '\u21b6', + 'curvearrowright;': '\u21b7', + 'cuvee;': '\u22ce', + 'cuwed;': '\u22cf', + 'cwconint;': '\u2232', + 'cwint;': '\u2231', + 'cylcty;': '\u232d', + 'Dagger;': '\u2021', + 'dagger;': '\u2020', + 'daleth;': '\u2138', + 'Darr;': '\u21a1', + 'dArr;': '\u21d3', + 'darr;': '\u2193', + 'dash;': '\u2010', + 'Dashv;': '\u2ae4', + 'dashv;': '\u22a3', + 'dbkarow;': '\u290f', + 'dblac;': '\u02dd', + 'Dcaron;': '\u010e', + 'dcaron;': '\u010f', + 'Dcy;': '\u0414', + 'dcy;': '\u0434', + 'DD;': '\u2145', + 'dd;': '\u2146', + 'ddagger;': '\u2021', + 'ddarr;': '\u21ca', + 'DDotrahd;': '\u2911', + 'ddotseq;': '\u2a77', + 'deg': '\xb0', + 'deg;': '\xb0', + 'Del;': '\u2207', + 'Delta;': '\u0394', + 'delta;': '\u03b4', + 'demptyv;': '\u29b1', + 'dfisht;': '\u297f', + 'Dfr;': '\U0001d507', + 'dfr;': '\U0001d521', + 'dHar;': '\u2965', + 'dharl;': '\u21c3', + 'dharr;': '\u21c2', + 'DiacriticalAcute;': '\xb4', + 'DiacriticalDot;': '\u02d9', + 'DiacriticalDoubleAcute;': '\u02dd', + 'DiacriticalGrave;': '`', + 'DiacriticalTilde;': '\u02dc', + 'diam;': '\u22c4', + 'Diamond;': '\u22c4', + 'diamond;': '\u22c4', + 'diamondsuit;': '\u2666', + 'diams;': '\u2666', + 'die;': '\xa8', + 'DifferentialD;': '\u2146', + 'digamma;': '\u03dd', + 'disin;': '\u22f2', + 'div;': '\xf7', + 'divide': '\xf7', + 'divide;': '\xf7', + 'divideontimes;': '\u22c7', + 'divonx;': '\u22c7', + 'DJcy;': '\u0402', + 'djcy;': '\u0452', + 'dlcorn;': '\u231e', + 'dlcrop;': '\u230d', + 'dollar;': '$', + 'Dopf;': '\U0001d53b', + 'dopf;': '\U0001d555', + 'Dot;': '\xa8', + 'dot;': '\u02d9', + 'DotDot;': '\u20dc', + 'doteq;': '\u2250', + 'doteqdot;': '\u2251', + 'DotEqual;': '\u2250', + 'dotminus;': '\u2238', + 'dotplus;': '\u2214', + 'dotsquare;': '\u22a1', + 'doublebarwedge;': '\u2306', + 'DoubleContourIntegral;': '\u222f', + 'DoubleDot;': '\xa8', + 'DoubleDownArrow;': '\u21d3', + 'DoubleLeftArrow;': '\u21d0', + 'DoubleLeftRightArrow;': '\u21d4', + 'DoubleLeftTee;': '\u2ae4', + 'DoubleLongLeftArrow;': '\u27f8', + 'DoubleLongLeftRightArrow;': '\u27fa', + 'DoubleLongRightArrow;': '\u27f9', + 'DoubleRightArrow;': '\u21d2', + 'DoubleRightTee;': '\u22a8', + 'DoubleUpArrow;': '\u21d1', + 'DoubleUpDownArrow;': '\u21d5', + 'DoubleVerticalBar;': '\u2225', + 'DownArrow;': '\u2193', + 'Downarrow;': '\u21d3', + 'downarrow;': '\u2193', + 'DownArrowBar;': '\u2913', + 'DownArrowUpArrow;': '\u21f5', + 'DownBreve;': '\u0311', + 'downdownarrows;': '\u21ca', + 'downharpoonleft;': '\u21c3', + 'downharpoonright;': '\u21c2', + 'DownLeftRightVector;': '\u2950', + 'DownLeftTeeVector;': '\u295e', + 'DownLeftVector;': '\u21bd', + 'DownLeftVectorBar;': '\u2956', + 'DownRightTeeVector;': '\u295f', + 'DownRightVector;': '\u21c1', + 'DownRightVectorBar;': '\u2957', + 'DownTee;': '\u22a4', + 'DownTeeArrow;': '\u21a7', + 'drbkarow;': '\u2910', + 'drcorn;': '\u231f', + 'drcrop;': '\u230c', + 'Dscr;': '\U0001d49f', + 'dscr;': '\U0001d4b9', + 'DScy;': '\u0405', + 'dscy;': '\u0455', + 'dsol;': '\u29f6', + 'Dstrok;': '\u0110', + 'dstrok;': '\u0111', + 'dtdot;': '\u22f1', + 'dtri;': '\u25bf', + 'dtrif;': '\u25be', + 'duarr;': '\u21f5', + 'duhar;': '\u296f', + 'dwangle;': '\u29a6', + 'DZcy;': '\u040f', + 'dzcy;': '\u045f', + 'dzigrarr;': '\u27ff', + 'Eacute': '\xc9', + 'eacute': '\xe9', + 'Eacute;': '\xc9', + 'eacute;': '\xe9', + 'easter;': '\u2a6e', + 'Ecaron;': '\u011a', + 'ecaron;': '\u011b', + 'ecir;': '\u2256', + 'Ecirc': '\xca', + 'ecirc': '\xea', + 'Ecirc;': '\xca', + 'ecirc;': '\xea', + 'ecolon;': '\u2255', + 'Ecy;': '\u042d', + 'ecy;': '\u044d', + 'eDDot;': '\u2a77', + 'Edot;': '\u0116', + 'eDot;': '\u2251', + 'edot;': '\u0117', + 'ee;': '\u2147', + 'efDot;': '\u2252', + 'Efr;': '\U0001d508', + 'efr;': '\U0001d522', + 'eg;': '\u2a9a', + 'Egrave': '\xc8', + 'egrave': '\xe8', + 'Egrave;': '\xc8', + 'egrave;': '\xe8', + 'egs;': '\u2a96', + 'egsdot;': '\u2a98', + 'el;': '\u2a99', + 'Element;': '\u2208', + 'elinters;': '\u23e7', + 'ell;': '\u2113', + 'els;': '\u2a95', + 'elsdot;': '\u2a97', + 'Emacr;': '\u0112', + 'emacr;': '\u0113', + 'empty;': '\u2205', + 'emptyset;': '\u2205', + 'EmptySmallSquare;': '\u25fb', + 'emptyv;': '\u2205', + 'EmptyVerySmallSquare;': '\u25ab', + 'emsp13;': '\u2004', + 'emsp14;': '\u2005', + 'emsp;': '\u2003', + 'ENG;': '\u014a', + 'eng;': '\u014b', + 'ensp;': '\u2002', + 'Eogon;': '\u0118', + 'eogon;': '\u0119', + 'Eopf;': '\U0001d53c', + 'eopf;': '\U0001d556', + 'epar;': '\u22d5', + 'eparsl;': '\u29e3', + 'eplus;': '\u2a71', + 'epsi;': '\u03b5', + 'Epsilon;': '\u0395', + 'epsilon;': '\u03b5', + 'epsiv;': '\u03f5', + 'eqcirc;': '\u2256', + 'eqcolon;': '\u2255', + 'eqsim;': '\u2242', + 'eqslantgtr;': '\u2a96', + 'eqslantless;': '\u2a95', + 'Equal;': '\u2a75', + 'equals;': '=', + 'EqualTilde;': '\u2242', + 'equest;': '\u225f', + 'Equilibrium;': '\u21cc', + 'equiv;': '\u2261', + 'equivDD;': '\u2a78', + 'eqvparsl;': '\u29e5', + 'erarr;': '\u2971', + 'erDot;': '\u2253', + 'Escr;': '\u2130', + 'escr;': '\u212f', + 'esdot;': '\u2250', + 'Esim;': '\u2a73', + 'esim;': '\u2242', + 'Eta;': '\u0397', + 'eta;': '\u03b7', + 'ETH': '\xd0', + 'eth': '\xf0', + 'ETH;': '\xd0', + 'eth;': '\xf0', + 'Euml': '\xcb', + 'euml': '\xeb', + 'Euml;': '\xcb', + 'euml;': '\xeb', + 'euro;': '\u20ac', + 'excl;': '!', + 'exist;': '\u2203', + 'Exists;': '\u2203', + 'expectation;': '\u2130', + 'ExponentialE;': '\u2147', + 'exponentiale;': '\u2147', + 'fallingdotseq;': '\u2252', + 'Fcy;': '\u0424', + 'fcy;': '\u0444', + 'female;': '\u2640', + 'ffilig;': '\ufb03', + 'fflig;': '\ufb00', + 'ffllig;': '\ufb04', + 'Ffr;': '\U0001d509', + 'ffr;': '\U0001d523', + 'filig;': '\ufb01', + 'FilledSmallSquare;': '\u25fc', + 'FilledVerySmallSquare;': '\u25aa', + 'fjlig;': 'fj', + 'flat;': '\u266d', + 'fllig;': '\ufb02', + 'fltns;': '\u25b1', + 'fnof;': '\u0192', + 'Fopf;': '\U0001d53d', + 'fopf;': '\U0001d557', + 'ForAll;': '\u2200', + 'forall;': '\u2200', + 'fork;': '\u22d4', + 'forkv;': '\u2ad9', + 'Fouriertrf;': '\u2131', + 'fpartint;': '\u2a0d', + 'frac12': '\xbd', + 'frac12;': '\xbd', + 'frac13;': '\u2153', + 'frac14': '\xbc', + 'frac14;': '\xbc', + 'frac15;': '\u2155', + 'frac16;': '\u2159', + 'frac18;': '\u215b', + 'frac23;': '\u2154', + 'frac25;': '\u2156', + 'frac34': '\xbe', + 'frac34;': '\xbe', + 'frac35;': '\u2157', + 'frac38;': '\u215c', + 'frac45;': '\u2158', + 'frac56;': '\u215a', + 'frac58;': '\u215d', + 'frac78;': '\u215e', + 'frasl;': '\u2044', + 'frown;': '\u2322', + 'Fscr;': '\u2131', + 'fscr;': '\U0001d4bb', + 'gacute;': '\u01f5', + 'Gamma;': '\u0393', + 'gamma;': '\u03b3', + 'Gammad;': '\u03dc', + 'gammad;': '\u03dd', + 'gap;': '\u2a86', + 'Gbreve;': '\u011e', + 'gbreve;': '\u011f', + 'Gcedil;': '\u0122', + 'Gcirc;': '\u011c', + 'gcirc;': '\u011d', + 'Gcy;': '\u0413', + 'gcy;': '\u0433', + 'Gdot;': '\u0120', + 'gdot;': '\u0121', + 'gE;': '\u2267', + 'ge;': '\u2265', + 'gEl;': '\u2a8c', + 'gel;': '\u22db', + 'geq;': '\u2265', + 'geqq;': '\u2267', + 'geqslant;': '\u2a7e', + 'ges;': '\u2a7e', + 'gescc;': '\u2aa9', + 'gesdot;': '\u2a80', + 'gesdoto;': '\u2a82', + 'gesdotol;': '\u2a84', + 'gesl;': '\u22db\ufe00', + 'gesles;': '\u2a94', + 'Gfr;': '\U0001d50a', + 'gfr;': '\U0001d524', + 'Gg;': '\u22d9', + 'gg;': '\u226b', + 'ggg;': '\u22d9', + 'gimel;': '\u2137', + 'GJcy;': '\u0403', + 'gjcy;': '\u0453', + 'gl;': '\u2277', + 'gla;': '\u2aa5', + 'glE;': '\u2a92', + 'glj;': '\u2aa4', + 'gnap;': '\u2a8a', + 'gnapprox;': '\u2a8a', + 'gnE;': '\u2269', + 'gne;': '\u2a88', + 'gneq;': '\u2a88', + 'gneqq;': '\u2269', + 'gnsim;': '\u22e7', + 'Gopf;': '\U0001d53e', + 'gopf;': '\U0001d558', + 'grave;': '`', + 'GreaterEqual;': '\u2265', + 'GreaterEqualLess;': '\u22db', + 'GreaterFullEqual;': '\u2267', + 'GreaterGreater;': '\u2aa2', + 'GreaterLess;': '\u2277', + 'GreaterSlantEqual;': '\u2a7e', + 'GreaterTilde;': '\u2273', + 'Gscr;': '\U0001d4a2', + 'gscr;': '\u210a', + 'gsim;': '\u2273', + 'gsime;': '\u2a8e', + 'gsiml;': '\u2a90', + 'GT': '>', + 'gt': '>', + 'GT;': '>', + 'Gt;': '\u226b', + 'gt;': '>', + 'gtcc;': '\u2aa7', + 'gtcir;': '\u2a7a', + 'gtdot;': '\u22d7', + 'gtlPar;': '\u2995', + 'gtquest;': '\u2a7c', + 'gtrapprox;': '\u2a86', + 'gtrarr;': '\u2978', + 'gtrdot;': '\u22d7', + 'gtreqless;': '\u22db', + 'gtreqqless;': '\u2a8c', + 'gtrless;': '\u2277', + 'gtrsim;': '\u2273', + 'gvertneqq;': '\u2269\ufe00', + 'gvnE;': '\u2269\ufe00', + 'Hacek;': '\u02c7', + 'hairsp;': '\u200a', + 'half;': '\xbd', + 'hamilt;': '\u210b', + 'HARDcy;': '\u042a', + 'hardcy;': '\u044a', + 'hArr;': '\u21d4', + 'harr;': '\u2194', + 'harrcir;': '\u2948', + 'harrw;': '\u21ad', + 'Hat;': '^', + 'hbar;': '\u210f', + 'Hcirc;': '\u0124', + 'hcirc;': '\u0125', + 'hearts;': '\u2665', + 'heartsuit;': '\u2665', + 'hellip;': '\u2026', + 'hercon;': '\u22b9', + 'Hfr;': '\u210c', + 'hfr;': '\U0001d525', + 'HilbertSpace;': '\u210b', + 'hksearow;': '\u2925', + 'hkswarow;': '\u2926', + 'hoarr;': '\u21ff', + 'homtht;': '\u223b', + 'hookleftarrow;': '\u21a9', + 'hookrightarrow;': '\u21aa', + 'Hopf;': '\u210d', + 'hopf;': '\U0001d559', + 'horbar;': '\u2015', + 'HorizontalLine;': '\u2500', + 'Hscr;': '\u210b', + 'hscr;': '\U0001d4bd', + 'hslash;': '\u210f', + 'Hstrok;': '\u0126', + 'hstrok;': '\u0127', + 'HumpDownHump;': '\u224e', + 'HumpEqual;': '\u224f', + 'hybull;': '\u2043', + 'hyphen;': '\u2010', + 'Iacute': '\xcd', + 'iacute': '\xed', + 'Iacute;': '\xcd', + 'iacute;': '\xed', + 'ic;': '\u2063', + 'Icirc': '\xce', + 'icirc': '\xee', + 'Icirc;': '\xce', + 'icirc;': '\xee', + 'Icy;': '\u0418', + 'icy;': '\u0438', + 'Idot;': '\u0130', + 'IEcy;': '\u0415', + 'iecy;': '\u0435', + 'iexcl': '\xa1', + 'iexcl;': '\xa1', + 'iff;': '\u21d4', + 'Ifr;': '\u2111', + 'ifr;': '\U0001d526', + 'Igrave': '\xcc', + 'igrave': '\xec', + 'Igrave;': '\xcc', + 'igrave;': '\xec', + 'ii;': '\u2148', + 'iiiint;': '\u2a0c', + 'iiint;': '\u222d', + 'iinfin;': '\u29dc', + 'iiota;': '\u2129', + 'IJlig;': '\u0132', + 'ijlig;': '\u0133', + 'Im;': '\u2111', + 'Imacr;': '\u012a', + 'imacr;': '\u012b', + 'image;': '\u2111', + 'ImaginaryI;': '\u2148', + 'imagline;': '\u2110', + 'imagpart;': '\u2111', + 'imath;': '\u0131', + 'imof;': '\u22b7', + 'imped;': '\u01b5', + 'Implies;': '\u21d2', + 'in;': '\u2208', + 'incare;': '\u2105', + 'infin;': '\u221e', + 'infintie;': '\u29dd', + 'inodot;': '\u0131', + 'Int;': '\u222c', + 'int;': '\u222b', + 'intcal;': '\u22ba', + 'integers;': '\u2124', + 'Integral;': '\u222b', + 'intercal;': '\u22ba', + 'Intersection;': '\u22c2', + 'intlarhk;': '\u2a17', + 'intprod;': '\u2a3c', + 'InvisibleComma;': '\u2063', + 'InvisibleTimes;': '\u2062', + 'IOcy;': '\u0401', + 'iocy;': '\u0451', + 'Iogon;': '\u012e', + 'iogon;': '\u012f', + 'Iopf;': '\U0001d540', + 'iopf;': '\U0001d55a', + 'Iota;': '\u0399', + 'iota;': '\u03b9', + 'iprod;': '\u2a3c', + 'iquest': '\xbf', + 'iquest;': '\xbf', + 'Iscr;': '\u2110', + 'iscr;': '\U0001d4be', + 'isin;': '\u2208', + 'isindot;': '\u22f5', + 'isinE;': '\u22f9', + 'isins;': '\u22f4', + 'isinsv;': '\u22f3', + 'isinv;': '\u2208', + 'it;': '\u2062', + 'Itilde;': '\u0128', + 'itilde;': '\u0129', + 'Iukcy;': '\u0406', + 'iukcy;': '\u0456', + 'Iuml': '\xcf', + 'iuml': '\xef', + 'Iuml;': '\xcf', + 'iuml;': '\xef', + 'Jcirc;': '\u0134', + 'jcirc;': '\u0135', + 'Jcy;': '\u0419', + 'jcy;': '\u0439', + 'Jfr;': '\U0001d50d', + 'jfr;': '\U0001d527', + 'jmath;': '\u0237', + 'Jopf;': '\U0001d541', + 'jopf;': '\U0001d55b', + 'Jscr;': '\U0001d4a5', + 'jscr;': '\U0001d4bf', + 'Jsercy;': '\u0408', + 'jsercy;': '\u0458', + 'Jukcy;': '\u0404', + 'jukcy;': '\u0454', + 'Kappa;': '\u039a', + 'kappa;': '\u03ba', + 'kappav;': '\u03f0', + 'Kcedil;': '\u0136', + 'kcedil;': '\u0137', + 'Kcy;': '\u041a', + 'kcy;': '\u043a', + 'Kfr;': '\U0001d50e', + 'kfr;': '\U0001d528', + 'kgreen;': '\u0138', + 'KHcy;': '\u0425', + 'khcy;': '\u0445', + 'KJcy;': '\u040c', + 'kjcy;': '\u045c', + 'Kopf;': '\U0001d542', + 'kopf;': '\U0001d55c', + 'Kscr;': '\U0001d4a6', + 'kscr;': '\U0001d4c0', + 'lAarr;': '\u21da', + 'Lacute;': '\u0139', + 'lacute;': '\u013a', + 'laemptyv;': '\u29b4', + 'lagran;': '\u2112', + 'Lambda;': '\u039b', + 'lambda;': '\u03bb', + 'Lang;': '\u27ea', + 'lang;': '\u27e8', + 'langd;': '\u2991', + 'langle;': '\u27e8', + 'lap;': '\u2a85', + 'Laplacetrf;': '\u2112', + 'laquo': '\xab', + 'laquo;': '\xab', + 'Larr;': '\u219e', + 'lArr;': '\u21d0', + 'larr;': '\u2190', + 'larrb;': '\u21e4', + 'larrbfs;': '\u291f', + 'larrfs;': '\u291d', + 'larrhk;': '\u21a9', + 'larrlp;': '\u21ab', + 'larrpl;': '\u2939', + 'larrsim;': '\u2973', + 'larrtl;': '\u21a2', + 'lat;': '\u2aab', + 'lAtail;': '\u291b', + 'latail;': '\u2919', + 'late;': '\u2aad', + 'lates;': '\u2aad\ufe00', + 'lBarr;': '\u290e', + 'lbarr;': '\u290c', + 'lbbrk;': '\u2772', + 'lbrace;': '{', + 'lbrack;': '[', + 'lbrke;': '\u298b', + 'lbrksld;': '\u298f', + 'lbrkslu;': '\u298d', + 'Lcaron;': '\u013d', + 'lcaron;': '\u013e', + 'Lcedil;': '\u013b', + 'lcedil;': '\u013c', + 'lceil;': '\u2308', + 'lcub;': '{', + 'Lcy;': '\u041b', + 'lcy;': '\u043b', + 'ldca;': '\u2936', + 'ldquo;': '\u201c', + 'ldquor;': '\u201e', + 'ldrdhar;': '\u2967', + 'ldrushar;': '\u294b', + 'ldsh;': '\u21b2', + 'lE;': '\u2266', + 'le;': '\u2264', + 'LeftAngleBracket;': '\u27e8', + 'LeftArrow;': '\u2190', + 'Leftarrow;': '\u21d0', + 'leftarrow;': '\u2190', + 'LeftArrowBar;': '\u21e4', + 'LeftArrowRightArrow;': '\u21c6', + 'leftarrowtail;': '\u21a2', + 'LeftCeiling;': '\u2308', + 'LeftDoubleBracket;': '\u27e6', + 'LeftDownTeeVector;': '\u2961', + 'LeftDownVector;': '\u21c3', + 'LeftDownVectorBar;': '\u2959', + 'LeftFloor;': '\u230a', + 'leftharpoondown;': '\u21bd', + 'leftharpoonup;': '\u21bc', + 'leftleftarrows;': '\u21c7', + 'LeftRightArrow;': '\u2194', + 'Leftrightarrow;': '\u21d4', + 'leftrightarrow;': '\u2194', + 'leftrightarrows;': '\u21c6', + 'leftrightharpoons;': '\u21cb', + 'leftrightsquigarrow;': '\u21ad', + 'LeftRightVector;': '\u294e', + 'LeftTee;': '\u22a3', + 'LeftTeeArrow;': '\u21a4', + 'LeftTeeVector;': '\u295a', + 'leftthreetimes;': '\u22cb', + 'LeftTriangle;': '\u22b2', + 'LeftTriangleBar;': '\u29cf', + 'LeftTriangleEqual;': '\u22b4', + 'LeftUpDownVector;': '\u2951', + 'LeftUpTeeVector;': '\u2960', + 'LeftUpVector;': '\u21bf', + 'LeftUpVectorBar;': '\u2958', + 'LeftVector;': '\u21bc', + 'LeftVectorBar;': '\u2952', + 'lEg;': '\u2a8b', + 'leg;': '\u22da', + 'leq;': '\u2264', + 'leqq;': '\u2266', + 'leqslant;': '\u2a7d', + 'les;': '\u2a7d', + 'lescc;': '\u2aa8', + 'lesdot;': '\u2a7f', + 'lesdoto;': '\u2a81', + 'lesdotor;': '\u2a83', + 'lesg;': '\u22da\ufe00', + 'lesges;': '\u2a93', + 'lessapprox;': '\u2a85', + 'lessdot;': '\u22d6', + 'lesseqgtr;': '\u22da', + 'lesseqqgtr;': '\u2a8b', + 'LessEqualGreater;': '\u22da', + 'LessFullEqual;': '\u2266', + 'LessGreater;': '\u2276', + 'lessgtr;': '\u2276', + 'LessLess;': '\u2aa1', + 'lesssim;': '\u2272', + 'LessSlantEqual;': '\u2a7d', + 'LessTilde;': '\u2272', + 'lfisht;': '\u297c', + 'lfloor;': '\u230a', + 'Lfr;': '\U0001d50f', + 'lfr;': '\U0001d529', + 'lg;': '\u2276', + 'lgE;': '\u2a91', + 'lHar;': '\u2962', + 'lhard;': '\u21bd', + 'lharu;': '\u21bc', + 'lharul;': '\u296a', + 'lhblk;': '\u2584', + 'LJcy;': '\u0409', + 'ljcy;': '\u0459', + 'Ll;': '\u22d8', + 'll;': '\u226a', + 'llarr;': '\u21c7', + 'llcorner;': '\u231e', + 'Lleftarrow;': '\u21da', + 'llhard;': '\u296b', + 'lltri;': '\u25fa', + 'Lmidot;': '\u013f', + 'lmidot;': '\u0140', + 'lmoust;': '\u23b0', + 'lmoustache;': '\u23b0', + 'lnap;': '\u2a89', + 'lnapprox;': '\u2a89', + 'lnE;': '\u2268', + 'lne;': '\u2a87', + 'lneq;': '\u2a87', + 'lneqq;': '\u2268', + 'lnsim;': '\u22e6', + 'loang;': '\u27ec', + 'loarr;': '\u21fd', + 'lobrk;': '\u27e6', + 'LongLeftArrow;': '\u27f5', + 'Longleftarrow;': '\u27f8', + 'longleftarrow;': '\u27f5', + 'LongLeftRightArrow;': '\u27f7', + 'Longleftrightarrow;': '\u27fa', + 'longleftrightarrow;': '\u27f7', + 'longmapsto;': '\u27fc', + 'LongRightArrow;': '\u27f6', + 'Longrightarrow;': '\u27f9', + 'longrightarrow;': '\u27f6', + 'looparrowleft;': '\u21ab', + 'looparrowright;': '\u21ac', + 'lopar;': '\u2985', + 'Lopf;': '\U0001d543', + 'lopf;': '\U0001d55d', + 'loplus;': '\u2a2d', + 'lotimes;': '\u2a34', + 'lowast;': '\u2217', + 'lowbar;': '_', + 'LowerLeftArrow;': '\u2199', + 'LowerRightArrow;': '\u2198', + 'loz;': '\u25ca', + 'lozenge;': '\u25ca', + 'lozf;': '\u29eb', + 'lpar;': '(', + 'lparlt;': '\u2993', + 'lrarr;': '\u21c6', + 'lrcorner;': '\u231f', + 'lrhar;': '\u21cb', + 'lrhard;': '\u296d', + 'lrm;': '\u200e', + 'lrtri;': '\u22bf', + 'lsaquo;': '\u2039', + 'Lscr;': '\u2112', + 'lscr;': '\U0001d4c1', + 'Lsh;': '\u21b0', + 'lsh;': '\u21b0', + 'lsim;': '\u2272', + 'lsime;': '\u2a8d', + 'lsimg;': '\u2a8f', + 'lsqb;': '[', + 'lsquo;': '\u2018', + 'lsquor;': '\u201a', + 'Lstrok;': '\u0141', + 'lstrok;': '\u0142', + 'LT': '<', + 'lt': '<', + 'LT;': '<', + 'Lt;': '\u226a', + 'lt;': '<', + 'ltcc;': '\u2aa6', + 'ltcir;': '\u2a79', + 'ltdot;': '\u22d6', + 'lthree;': '\u22cb', + 'ltimes;': '\u22c9', + 'ltlarr;': '\u2976', + 'ltquest;': '\u2a7b', + 'ltri;': '\u25c3', + 'ltrie;': '\u22b4', + 'ltrif;': '\u25c2', + 'ltrPar;': '\u2996', + 'lurdshar;': '\u294a', + 'luruhar;': '\u2966', + 'lvertneqq;': '\u2268\ufe00', + 'lvnE;': '\u2268\ufe00', + 'macr': '\xaf', + 'macr;': '\xaf', + 'male;': '\u2642', + 'malt;': '\u2720', + 'maltese;': '\u2720', + 'Map;': '\u2905', + 'map;': '\u21a6', + 'mapsto;': '\u21a6', + 'mapstodown;': '\u21a7', + 'mapstoleft;': '\u21a4', + 'mapstoup;': '\u21a5', + 'marker;': '\u25ae', + 'mcomma;': '\u2a29', + 'Mcy;': '\u041c', + 'mcy;': '\u043c', + 'mdash;': '\u2014', + 'mDDot;': '\u223a', + 'measuredangle;': '\u2221', + 'MediumSpace;': '\u205f', + 'Mellintrf;': '\u2133', + 'Mfr;': '\U0001d510', + 'mfr;': '\U0001d52a', + 'mho;': '\u2127', + 'micro': '\xb5', + 'micro;': '\xb5', + 'mid;': '\u2223', + 'midast;': '*', + 'midcir;': '\u2af0', + 'middot': '\xb7', + 'middot;': '\xb7', + 'minus;': '\u2212', + 'minusb;': '\u229f', + 'minusd;': '\u2238', + 'minusdu;': '\u2a2a', + 'MinusPlus;': '\u2213', + 'mlcp;': '\u2adb', + 'mldr;': '\u2026', + 'mnplus;': '\u2213', + 'models;': '\u22a7', + 'Mopf;': '\U0001d544', + 'mopf;': '\U0001d55e', + 'mp;': '\u2213', + 'Mscr;': '\u2133', + 'mscr;': '\U0001d4c2', + 'mstpos;': '\u223e', + 'Mu;': '\u039c', + 'mu;': '\u03bc', + 'multimap;': '\u22b8', + 'mumap;': '\u22b8', + 'nabla;': '\u2207', + 'Nacute;': '\u0143', + 'nacute;': '\u0144', + 'nang;': '\u2220\u20d2', + 'nap;': '\u2249', + 'napE;': '\u2a70\u0338', + 'napid;': '\u224b\u0338', + 'napos;': '\u0149', + 'napprox;': '\u2249', + 'natur;': '\u266e', + 'natural;': '\u266e', + 'naturals;': '\u2115', + 'nbsp': '\xa0', + 'nbsp;': '\xa0', + 'nbump;': '\u224e\u0338', + 'nbumpe;': '\u224f\u0338', + 'ncap;': '\u2a43', + 'Ncaron;': '\u0147', + 'ncaron;': '\u0148', + 'Ncedil;': '\u0145', + 'ncedil;': '\u0146', + 'ncong;': '\u2247', + 'ncongdot;': '\u2a6d\u0338', + 'ncup;': '\u2a42', + 'Ncy;': '\u041d', + 'ncy;': '\u043d', + 'ndash;': '\u2013', + 'ne;': '\u2260', + 'nearhk;': '\u2924', + 'neArr;': '\u21d7', + 'nearr;': '\u2197', + 'nearrow;': '\u2197', + 'nedot;': '\u2250\u0338', + 'NegativeMediumSpace;': '\u200b', + 'NegativeThickSpace;': '\u200b', + 'NegativeThinSpace;': '\u200b', + 'NegativeVeryThinSpace;': '\u200b', + 'nequiv;': '\u2262', + 'nesear;': '\u2928', + 'nesim;': '\u2242\u0338', + 'NestedGreaterGreater;': '\u226b', + 'NestedLessLess;': '\u226a', + 'NewLine;': '\n', + 'nexist;': '\u2204', + 'nexists;': '\u2204', + 'Nfr;': '\U0001d511', + 'nfr;': '\U0001d52b', + 'ngE;': '\u2267\u0338', + 'nge;': '\u2271', + 'ngeq;': '\u2271', + 'ngeqq;': '\u2267\u0338', + 'ngeqslant;': '\u2a7e\u0338', + 'nges;': '\u2a7e\u0338', + 'nGg;': '\u22d9\u0338', + 'ngsim;': '\u2275', + 'nGt;': '\u226b\u20d2', + 'ngt;': '\u226f', + 'ngtr;': '\u226f', + 'nGtv;': '\u226b\u0338', + 'nhArr;': '\u21ce', + 'nharr;': '\u21ae', + 'nhpar;': '\u2af2', + 'ni;': '\u220b', + 'nis;': '\u22fc', + 'nisd;': '\u22fa', + 'niv;': '\u220b', + 'NJcy;': '\u040a', + 'njcy;': '\u045a', + 'nlArr;': '\u21cd', + 'nlarr;': '\u219a', + 'nldr;': '\u2025', + 'nlE;': '\u2266\u0338', + 'nle;': '\u2270', + 'nLeftarrow;': '\u21cd', + 'nleftarrow;': '\u219a', + 'nLeftrightarrow;': '\u21ce', + 'nleftrightarrow;': '\u21ae', + 'nleq;': '\u2270', + 'nleqq;': '\u2266\u0338', + 'nleqslant;': '\u2a7d\u0338', + 'nles;': '\u2a7d\u0338', + 'nless;': '\u226e', + 'nLl;': '\u22d8\u0338', + 'nlsim;': '\u2274', + 'nLt;': '\u226a\u20d2', + 'nlt;': '\u226e', + 'nltri;': '\u22ea', + 'nltrie;': '\u22ec', + 'nLtv;': '\u226a\u0338', + 'nmid;': '\u2224', + 'NoBreak;': '\u2060', + 'NonBreakingSpace;': '\xa0', + 'Nopf;': '\u2115', + 'nopf;': '\U0001d55f', + 'not': '\xac', + 'Not;': '\u2aec', + 'not;': '\xac', + 'NotCongruent;': '\u2262', + 'NotCupCap;': '\u226d', + 'NotDoubleVerticalBar;': '\u2226', + 'NotElement;': '\u2209', + 'NotEqual;': '\u2260', + 'NotEqualTilde;': '\u2242\u0338', + 'NotExists;': '\u2204', + 'NotGreater;': '\u226f', + 'NotGreaterEqual;': '\u2271', + 'NotGreaterFullEqual;': '\u2267\u0338', + 'NotGreaterGreater;': '\u226b\u0338', + 'NotGreaterLess;': '\u2279', + 'NotGreaterSlantEqual;': '\u2a7e\u0338', + 'NotGreaterTilde;': '\u2275', + 'NotHumpDownHump;': '\u224e\u0338', + 'NotHumpEqual;': '\u224f\u0338', + 'notin;': '\u2209', + 'notindot;': '\u22f5\u0338', + 'notinE;': '\u22f9\u0338', + 'notinva;': '\u2209', + 'notinvb;': '\u22f7', + 'notinvc;': '\u22f6', + 'NotLeftTriangle;': '\u22ea', + 'NotLeftTriangleBar;': '\u29cf\u0338', + 'NotLeftTriangleEqual;': '\u22ec', + 'NotLess;': '\u226e', + 'NotLessEqual;': '\u2270', + 'NotLessGreater;': '\u2278', + 'NotLessLess;': '\u226a\u0338', + 'NotLessSlantEqual;': '\u2a7d\u0338', + 'NotLessTilde;': '\u2274', + 'NotNestedGreaterGreater;': '\u2aa2\u0338', + 'NotNestedLessLess;': '\u2aa1\u0338', + 'notni;': '\u220c', + 'notniva;': '\u220c', + 'notnivb;': '\u22fe', + 'notnivc;': '\u22fd', + 'NotPrecedes;': '\u2280', + 'NotPrecedesEqual;': '\u2aaf\u0338', + 'NotPrecedesSlantEqual;': '\u22e0', + 'NotReverseElement;': '\u220c', + 'NotRightTriangle;': '\u22eb', + 'NotRightTriangleBar;': '\u29d0\u0338', + 'NotRightTriangleEqual;': '\u22ed', + 'NotSquareSubset;': '\u228f\u0338', + 'NotSquareSubsetEqual;': '\u22e2', + 'NotSquareSuperset;': '\u2290\u0338', + 'NotSquareSupersetEqual;': '\u22e3', + 'NotSubset;': '\u2282\u20d2', + 'NotSubsetEqual;': '\u2288', + 'NotSucceeds;': '\u2281', + 'NotSucceedsEqual;': '\u2ab0\u0338', + 'NotSucceedsSlantEqual;': '\u22e1', + 'NotSucceedsTilde;': '\u227f\u0338', + 'NotSuperset;': '\u2283\u20d2', + 'NotSupersetEqual;': '\u2289', + 'NotTilde;': '\u2241', + 'NotTildeEqual;': '\u2244', + 'NotTildeFullEqual;': '\u2247', + 'NotTildeTilde;': '\u2249', + 'NotVerticalBar;': '\u2224', + 'npar;': '\u2226', + 'nparallel;': '\u2226', + 'nparsl;': '\u2afd\u20e5', + 'npart;': '\u2202\u0338', + 'npolint;': '\u2a14', + 'npr;': '\u2280', + 'nprcue;': '\u22e0', + 'npre;': '\u2aaf\u0338', + 'nprec;': '\u2280', + 'npreceq;': '\u2aaf\u0338', + 'nrArr;': '\u21cf', + 'nrarr;': '\u219b', + 'nrarrc;': '\u2933\u0338', + 'nrarrw;': '\u219d\u0338', + 'nRightarrow;': '\u21cf', + 'nrightarrow;': '\u219b', + 'nrtri;': '\u22eb', + 'nrtrie;': '\u22ed', + 'nsc;': '\u2281', + 'nsccue;': '\u22e1', + 'nsce;': '\u2ab0\u0338', + 'Nscr;': '\U0001d4a9', + 'nscr;': '\U0001d4c3', + 'nshortmid;': '\u2224', + 'nshortparallel;': '\u2226', + 'nsim;': '\u2241', + 'nsime;': '\u2244', + 'nsimeq;': '\u2244', + 'nsmid;': '\u2224', + 'nspar;': '\u2226', + 'nsqsube;': '\u22e2', + 'nsqsupe;': '\u22e3', + 'nsub;': '\u2284', + 'nsubE;': '\u2ac5\u0338', + 'nsube;': '\u2288', + 'nsubset;': '\u2282\u20d2', + 'nsubseteq;': '\u2288', + 'nsubseteqq;': '\u2ac5\u0338', + 'nsucc;': '\u2281', + 'nsucceq;': '\u2ab0\u0338', + 'nsup;': '\u2285', + 'nsupE;': '\u2ac6\u0338', + 'nsupe;': '\u2289', + 'nsupset;': '\u2283\u20d2', + 'nsupseteq;': '\u2289', + 'nsupseteqq;': '\u2ac6\u0338', + 'ntgl;': '\u2279', + 'Ntilde': '\xd1', + 'ntilde': '\xf1', + 'Ntilde;': '\xd1', + 'ntilde;': '\xf1', + 'ntlg;': '\u2278', + 'ntriangleleft;': '\u22ea', + 'ntrianglelefteq;': '\u22ec', + 'ntriangleright;': '\u22eb', + 'ntrianglerighteq;': '\u22ed', + 'Nu;': '\u039d', + 'nu;': '\u03bd', + 'num;': '#', + 'numero;': '\u2116', + 'numsp;': '\u2007', + 'nvap;': '\u224d\u20d2', + 'nVDash;': '\u22af', + 'nVdash;': '\u22ae', + 'nvDash;': '\u22ad', + 'nvdash;': '\u22ac', + 'nvge;': '\u2265\u20d2', + 'nvgt;': '>\u20d2', + 'nvHarr;': '\u2904', + 'nvinfin;': '\u29de', + 'nvlArr;': '\u2902', + 'nvle;': '\u2264\u20d2', + 'nvlt;': '<\u20d2', + 'nvltrie;': '\u22b4\u20d2', + 'nvrArr;': '\u2903', + 'nvrtrie;': '\u22b5\u20d2', + 'nvsim;': '\u223c\u20d2', + 'nwarhk;': '\u2923', + 'nwArr;': '\u21d6', + 'nwarr;': '\u2196', + 'nwarrow;': '\u2196', + 'nwnear;': '\u2927', + 'Oacute': '\xd3', + 'oacute': '\xf3', + 'Oacute;': '\xd3', + 'oacute;': '\xf3', + 'oast;': '\u229b', + 'ocir;': '\u229a', + 'Ocirc': '\xd4', + 'ocirc': '\xf4', + 'Ocirc;': '\xd4', + 'ocirc;': '\xf4', + 'Ocy;': '\u041e', + 'ocy;': '\u043e', + 'odash;': '\u229d', + 'Odblac;': '\u0150', + 'odblac;': '\u0151', + 'odiv;': '\u2a38', + 'odot;': '\u2299', + 'odsold;': '\u29bc', + 'OElig;': '\u0152', + 'oelig;': '\u0153', + 'ofcir;': '\u29bf', + 'Ofr;': '\U0001d512', + 'ofr;': '\U0001d52c', + 'ogon;': '\u02db', + 'Ograve': '\xd2', + 'ograve': '\xf2', + 'Ograve;': '\xd2', + 'ograve;': '\xf2', + 'ogt;': '\u29c1', + 'ohbar;': '\u29b5', + 'ohm;': '\u03a9', + 'oint;': '\u222e', + 'olarr;': '\u21ba', + 'olcir;': '\u29be', + 'olcross;': '\u29bb', + 'oline;': '\u203e', + 'olt;': '\u29c0', + 'Omacr;': '\u014c', + 'omacr;': '\u014d', + 'Omega;': '\u03a9', + 'omega;': '\u03c9', + 'Omicron;': '\u039f', + 'omicron;': '\u03bf', + 'omid;': '\u29b6', + 'ominus;': '\u2296', + 'Oopf;': '\U0001d546', + 'oopf;': '\U0001d560', + 'opar;': '\u29b7', + 'OpenCurlyDoubleQuote;': '\u201c', + 'OpenCurlyQuote;': '\u2018', + 'operp;': '\u29b9', + 'oplus;': '\u2295', + 'Or;': '\u2a54', + 'or;': '\u2228', + 'orarr;': '\u21bb', + 'ord;': '\u2a5d', + 'order;': '\u2134', + 'orderof;': '\u2134', + 'ordf': '\xaa', + 'ordf;': '\xaa', + 'ordm': '\xba', + 'ordm;': '\xba', + 'origof;': '\u22b6', + 'oror;': '\u2a56', + 'orslope;': '\u2a57', + 'orv;': '\u2a5b', + 'oS;': '\u24c8', + 'Oscr;': '\U0001d4aa', + 'oscr;': '\u2134', + 'Oslash': '\xd8', + 'oslash': '\xf8', + 'Oslash;': '\xd8', + 'oslash;': '\xf8', + 'osol;': '\u2298', + 'Otilde': '\xd5', + 'otilde': '\xf5', + 'Otilde;': '\xd5', + 'otilde;': '\xf5', + 'Otimes;': '\u2a37', + 'otimes;': '\u2297', + 'otimesas;': '\u2a36', + 'Ouml': '\xd6', + 'ouml': '\xf6', + 'Ouml;': '\xd6', + 'ouml;': '\xf6', + 'ovbar;': '\u233d', + 'OverBar;': '\u203e', + 'OverBrace;': '\u23de', + 'OverBracket;': '\u23b4', + 'OverParenthesis;': '\u23dc', + 'par;': '\u2225', + 'para': '\xb6', + 'para;': '\xb6', + 'parallel;': '\u2225', + 'parsim;': '\u2af3', + 'parsl;': '\u2afd', + 'part;': '\u2202', + 'PartialD;': '\u2202', + 'Pcy;': '\u041f', + 'pcy;': '\u043f', + 'percnt;': '%', + 'period;': '.', + 'permil;': '\u2030', + 'perp;': '\u22a5', + 'pertenk;': '\u2031', + 'Pfr;': '\U0001d513', + 'pfr;': '\U0001d52d', + 'Phi;': '\u03a6', + 'phi;': '\u03c6', + 'phiv;': '\u03d5', + 'phmmat;': '\u2133', + 'phone;': '\u260e', + 'Pi;': '\u03a0', + 'pi;': '\u03c0', + 'pitchfork;': '\u22d4', + 'piv;': '\u03d6', + 'planck;': '\u210f', + 'planckh;': '\u210e', + 'plankv;': '\u210f', + 'plus;': '+', + 'plusacir;': '\u2a23', + 'plusb;': '\u229e', + 'pluscir;': '\u2a22', + 'plusdo;': '\u2214', + 'plusdu;': '\u2a25', + 'pluse;': '\u2a72', + 'PlusMinus;': '\xb1', + 'plusmn': '\xb1', + 'plusmn;': '\xb1', + 'plussim;': '\u2a26', + 'plustwo;': '\u2a27', + 'pm;': '\xb1', + 'Poincareplane;': '\u210c', + 'pointint;': '\u2a15', + 'Popf;': '\u2119', + 'popf;': '\U0001d561', + 'pound': '\xa3', + 'pound;': '\xa3', + 'Pr;': '\u2abb', + 'pr;': '\u227a', + 'prap;': '\u2ab7', + 'prcue;': '\u227c', + 'prE;': '\u2ab3', + 'pre;': '\u2aaf', + 'prec;': '\u227a', + 'precapprox;': '\u2ab7', + 'preccurlyeq;': '\u227c', + 'Precedes;': '\u227a', + 'PrecedesEqual;': '\u2aaf', + 'PrecedesSlantEqual;': '\u227c', + 'PrecedesTilde;': '\u227e', + 'preceq;': '\u2aaf', + 'precnapprox;': '\u2ab9', + 'precneqq;': '\u2ab5', + 'precnsim;': '\u22e8', + 'precsim;': '\u227e', + 'Prime;': '\u2033', + 'prime;': '\u2032', + 'primes;': '\u2119', + 'prnap;': '\u2ab9', + 'prnE;': '\u2ab5', + 'prnsim;': '\u22e8', + 'prod;': '\u220f', + 'Product;': '\u220f', + 'profalar;': '\u232e', + 'profline;': '\u2312', + 'profsurf;': '\u2313', + 'prop;': '\u221d', + 'Proportion;': '\u2237', + 'Proportional;': '\u221d', + 'propto;': '\u221d', + 'prsim;': '\u227e', + 'prurel;': '\u22b0', + 'Pscr;': '\U0001d4ab', + 'pscr;': '\U0001d4c5', + 'Psi;': '\u03a8', + 'psi;': '\u03c8', + 'puncsp;': '\u2008', + 'Qfr;': '\U0001d514', + 'qfr;': '\U0001d52e', + 'qint;': '\u2a0c', + 'Qopf;': '\u211a', + 'qopf;': '\U0001d562', + 'qprime;': '\u2057', + 'Qscr;': '\U0001d4ac', + 'qscr;': '\U0001d4c6', + 'quaternions;': '\u210d', + 'quatint;': '\u2a16', + 'quest;': '?', + 'questeq;': '\u225f', + 'QUOT': '"', + 'quot': '"', + 'QUOT;': '"', + 'quot;': '"', + 'rAarr;': '\u21db', + 'race;': '\u223d\u0331', + 'Racute;': '\u0154', + 'racute;': '\u0155', + 'radic;': '\u221a', + 'raemptyv;': '\u29b3', + 'Rang;': '\u27eb', + 'rang;': '\u27e9', + 'rangd;': '\u2992', + 'range;': '\u29a5', + 'rangle;': '\u27e9', + 'raquo': '\xbb', + 'raquo;': '\xbb', + 'Rarr;': '\u21a0', + 'rArr;': '\u21d2', + 'rarr;': '\u2192', + 'rarrap;': '\u2975', + 'rarrb;': '\u21e5', + 'rarrbfs;': '\u2920', + 'rarrc;': '\u2933', + 'rarrfs;': '\u291e', + 'rarrhk;': '\u21aa', + 'rarrlp;': '\u21ac', + 'rarrpl;': '\u2945', + 'rarrsim;': '\u2974', + 'Rarrtl;': '\u2916', + 'rarrtl;': '\u21a3', + 'rarrw;': '\u219d', + 'rAtail;': '\u291c', + 'ratail;': '\u291a', + 'ratio;': '\u2236', + 'rationals;': '\u211a', + 'RBarr;': '\u2910', + 'rBarr;': '\u290f', + 'rbarr;': '\u290d', + 'rbbrk;': '\u2773', + 'rbrace;': '}', + 'rbrack;': ']', + 'rbrke;': '\u298c', + 'rbrksld;': '\u298e', + 'rbrkslu;': '\u2990', + 'Rcaron;': '\u0158', + 'rcaron;': '\u0159', + 'Rcedil;': '\u0156', + 'rcedil;': '\u0157', + 'rceil;': '\u2309', + 'rcub;': '}', + 'Rcy;': '\u0420', + 'rcy;': '\u0440', + 'rdca;': '\u2937', + 'rdldhar;': '\u2969', + 'rdquo;': '\u201d', + 'rdquor;': '\u201d', + 'rdsh;': '\u21b3', + 'Re;': '\u211c', + 'real;': '\u211c', + 'realine;': '\u211b', + 'realpart;': '\u211c', + 'reals;': '\u211d', + 'rect;': '\u25ad', + 'REG': '\xae', + 'reg': '\xae', + 'REG;': '\xae', + 'reg;': '\xae', + 'ReverseElement;': '\u220b', + 'ReverseEquilibrium;': '\u21cb', + 'ReverseUpEquilibrium;': '\u296f', + 'rfisht;': '\u297d', + 'rfloor;': '\u230b', + 'Rfr;': '\u211c', + 'rfr;': '\U0001d52f', + 'rHar;': '\u2964', + 'rhard;': '\u21c1', + 'rharu;': '\u21c0', + 'rharul;': '\u296c', + 'Rho;': '\u03a1', + 'rho;': '\u03c1', + 'rhov;': '\u03f1', + 'RightAngleBracket;': '\u27e9', + 'RightArrow;': '\u2192', + 'Rightarrow;': '\u21d2', + 'rightarrow;': '\u2192', + 'RightArrowBar;': '\u21e5', + 'RightArrowLeftArrow;': '\u21c4', + 'rightarrowtail;': '\u21a3', + 'RightCeiling;': '\u2309', + 'RightDoubleBracket;': '\u27e7', + 'RightDownTeeVector;': '\u295d', + 'RightDownVector;': '\u21c2', + 'RightDownVectorBar;': '\u2955', + 'RightFloor;': '\u230b', + 'rightharpoondown;': '\u21c1', + 'rightharpoonup;': '\u21c0', + 'rightleftarrows;': '\u21c4', + 'rightleftharpoons;': '\u21cc', + 'rightrightarrows;': '\u21c9', + 'rightsquigarrow;': '\u219d', + 'RightTee;': '\u22a2', + 'RightTeeArrow;': '\u21a6', + 'RightTeeVector;': '\u295b', + 'rightthreetimes;': '\u22cc', + 'RightTriangle;': '\u22b3', + 'RightTriangleBar;': '\u29d0', + 'RightTriangleEqual;': '\u22b5', + 'RightUpDownVector;': '\u294f', + 'RightUpTeeVector;': '\u295c', + 'RightUpVector;': '\u21be', + 'RightUpVectorBar;': '\u2954', + 'RightVector;': '\u21c0', + 'RightVectorBar;': '\u2953', + 'ring;': '\u02da', + 'risingdotseq;': '\u2253', + 'rlarr;': '\u21c4', + 'rlhar;': '\u21cc', + 'rlm;': '\u200f', + 'rmoust;': '\u23b1', + 'rmoustache;': '\u23b1', + 'rnmid;': '\u2aee', + 'roang;': '\u27ed', + 'roarr;': '\u21fe', + 'robrk;': '\u27e7', + 'ropar;': '\u2986', + 'Ropf;': '\u211d', + 'ropf;': '\U0001d563', + 'roplus;': '\u2a2e', + 'rotimes;': '\u2a35', + 'RoundImplies;': '\u2970', + 'rpar;': ')', + 'rpargt;': '\u2994', + 'rppolint;': '\u2a12', + 'rrarr;': '\u21c9', + 'Rrightarrow;': '\u21db', + 'rsaquo;': '\u203a', + 'Rscr;': '\u211b', + 'rscr;': '\U0001d4c7', + 'Rsh;': '\u21b1', + 'rsh;': '\u21b1', + 'rsqb;': ']', + 'rsquo;': '\u2019', + 'rsquor;': '\u2019', + 'rthree;': '\u22cc', + 'rtimes;': '\u22ca', + 'rtri;': '\u25b9', + 'rtrie;': '\u22b5', + 'rtrif;': '\u25b8', + 'rtriltri;': '\u29ce', + 'RuleDelayed;': '\u29f4', + 'ruluhar;': '\u2968', + 'rx;': '\u211e', + 'Sacute;': '\u015a', + 'sacute;': '\u015b', + 'sbquo;': '\u201a', + 'Sc;': '\u2abc', + 'sc;': '\u227b', + 'scap;': '\u2ab8', + 'Scaron;': '\u0160', + 'scaron;': '\u0161', + 'sccue;': '\u227d', + 'scE;': '\u2ab4', + 'sce;': '\u2ab0', + 'Scedil;': '\u015e', + 'scedil;': '\u015f', + 'Scirc;': '\u015c', + 'scirc;': '\u015d', + 'scnap;': '\u2aba', + 'scnE;': '\u2ab6', + 'scnsim;': '\u22e9', + 'scpolint;': '\u2a13', + 'scsim;': '\u227f', + 'Scy;': '\u0421', + 'scy;': '\u0441', + 'sdot;': '\u22c5', + 'sdotb;': '\u22a1', + 'sdote;': '\u2a66', + 'searhk;': '\u2925', + 'seArr;': '\u21d8', + 'searr;': '\u2198', + 'searrow;': '\u2198', + 'sect': '\xa7', + 'sect;': '\xa7', + 'semi;': ';', + 'seswar;': '\u2929', + 'setminus;': '\u2216', + 'setmn;': '\u2216', + 'sext;': '\u2736', + 'Sfr;': '\U0001d516', + 'sfr;': '\U0001d530', + 'sfrown;': '\u2322', + 'sharp;': '\u266f', + 'SHCHcy;': '\u0429', + 'shchcy;': '\u0449', + 'SHcy;': '\u0428', + 'shcy;': '\u0448', + 'ShortDownArrow;': '\u2193', + 'ShortLeftArrow;': '\u2190', + 'shortmid;': '\u2223', + 'shortparallel;': '\u2225', + 'ShortRightArrow;': '\u2192', + 'ShortUpArrow;': '\u2191', + 'shy': '\xad', + 'shy;': '\xad', + 'Sigma;': '\u03a3', + 'sigma;': '\u03c3', + 'sigmaf;': '\u03c2', + 'sigmav;': '\u03c2', + 'sim;': '\u223c', + 'simdot;': '\u2a6a', + 'sime;': '\u2243', + 'simeq;': '\u2243', + 'simg;': '\u2a9e', + 'simgE;': '\u2aa0', + 'siml;': '\u2a9d', + 'simlE;': '\u2a9f', + 'simne;': '\u2246', + 'simplus;': '\u2a24', + 'simrarr;': '\u2972', + 'slarr;': '\u2190', + 'SmallCircle;': '\u2218', + 'smallsetminus;': '\u2216', + 'smashp;': '\u2a33', + 'smeparsl;': '\u29e4', + 'smid;': '\u2223', + 'smile;': '\u2323', + 'smt;': '\u2aaa', + 'smte;': '\u2aac', + 'smtes;': '\u2aac\ufe00', + 'SOFTcy;': '\u042c', + 'softcy;': '\u044c', + 'sol;': '/', + 'solb;': '\u29c4', + 'solbar;': '\u233f', + 'Sopf;': '\U0001d54a', + 'sopf;': '\U0001d564', + 'spades;': '\u2660', + 'spadesuit;': '\u2660', + 'spar;': '\u2225', + 'sqcap;': '\u2293', + 'sqcaps;': '\u2293\ufe00', + 'sqcup;': '\u2294', + 'sqcups;': '\u2294\ufe00', + 'Sqrt;': '\u221a', + 'sqsub;': '\u228f', + 'sqsube;': '\u2291', + 'sqsubset;': '\u228f', + 'sqsubseteq;': '\u2291', + 'sqsup;': '\u2290', + 'sqsupe;': '\u2292', + 'sqsupset;': '\u2290', + 'sqsupseteq;': '\u2292', + 'squ;': '\u25a1', + 'Square;': '\u25a1', + 'square;': '\u25a1', + 'SquareIntersection;': '\u2293', + 'SquareSubset;': '\u228f', + 'SquareSubsetEqual;': '\u2291', + 'SquareSuperset;': '\u2290', + 'SquareSupersetEqual;': '\u2292', + 'SquareUnion;': '\u2294', + 'squarf;': '\u25aa', + 'squf;': '\u25aa', + 'srarr;': '\u2192', + 'Sscr;': '\U0001d4ae', + 'sscr;': '\U0001d4c8', + 'ssetmn;': '\u2216', + 'ssmile;': '\u2323', + 'sstarf;': '\u22c6', + 'Star;': '\u22c6', + 'star;': '\u2606', + 'starf;': '\u2605', + 'straightepsilon;': '\u03f5', + 'straightphi;': '\u03d5', + 'strns;': '\xaf', + 'Sub;': '\u22d0', + 'sub;': '\u2282', + 'subdot;': '\u2abd', + 'subE;': '\u2ac5', + 'sube;': '\u2286', + 'subedot;': '\u2ac3', + 'submult;': '\u2ac1', + 'subnE;': '\u2acb', + 'subne;': '\u228a', + 'subplus;': '\u2abf', + 'subrarr;': '\u2979', + 'Subset;': '\u22d0', + 'subset;': '\u2282', + 'subseteq;': '\u2286', + 'subseteqq;': '\u2ac5', + 'SubsetEqual;': '\u2286', + 'subsetneq;': '\u228a', + 'subsetneqq;': '\u2acb', + 'subsim;': '\u2ac7', + 'subsub;': '\u2ad5', + 'subsup;': '\u2ad3', + 'succ;': '\u227b', + 'succapprox;': '\u2ab8', + 'succcurlyeq;': '\u227d', + 'Succeeds;': '\u227b', + 'SucceedsEqual;': '\u2ab0', + 'SucceedsSlantEqual;': '\u227d', + 'SucceedsTilde;': '\u227f', + 'succeq;': '\u2ab0', + 'succnapprox;': '\u2aba', + 'succneqq;': '\u2ab6', + 'succnsim;': '\u22e9', + 'succsim;': '\u227f', + 'SuchThat;': '\u220b', + 'Sum;': '\u2211', + 'sum;': '\u2211', + 'sung;': '\u266a', + 'sup1': '\xb9', + 'sup1;': '\xb9', + 'sup2': '\xb2', + 'sup2;': '\xb2', + 'sup3': '\xb3', + 'sup3;': '\xb3', + 'Sup;': '\u22d1', + 'sup;': '\u2283', + 'supdot;': '\u2abe', + 'supdsub;': '\u2ad8', + 'supE;': '\u2ac6', + 'supe;': '\u2287', + 'supedot;': '\u2ac4', + 'Superset;': '\u2283', + 'SupersetEqual;': '\u2287', + 'suphsol;': '\u27c9', + 'suphsub;': '\u2ad7', + 'suplarr;': '\u297b', + 'supmult;': '\u2ac2', + 'supnE;': '\u2acc', + 'supne;': '\u228b', + 'supplus;': '\u2ac0', + 'Supset;': '\u22d1', + 'supset;': '\u2283', + 'supseteq;': '\u2287', + 'supseteqq;': '\u2ac6', + 'supsetneq;': '\u228b', + 'supsetneqq;': '\u2acc', + 'supsim;': '\u2ac8', + 'supsub;': '\u2ad4', + 'supsup;': '\u2ad6', + 'swarhk;': '\u2926', + 'swArr;': '\u21d9', + 'swarr;': '\u2199', + 'swarrow;': '\u2199', + 'swnwar;': '\u292a', + 'szlig': '\xdf', + 'szlig;': '\xdf', + 'Tab;': '\t', + 'target;': '\u2316', + 'Tau;': '\u03a4', + 'tau;': '\u03c4', + 'tbrk;': '\u23b4', + 'Tcaron;': '\u0164', + 'tcaron;': '\u0165', + 'Tcedil;': '\u0162', + 'tcedil;': '\u0163', + 'Tcy;': '\u0422', + 'tcy;': '\u0442', + 'tdot;': '\u20db', + 'telrec;': '\u2315', + 'Tfr;': '\U0001d517', + 'tfr;': '\U0001d531', + 'there4;': '\u2234', + 'Therefore;': '\u2234', + 'therefore;': '\u2234', + 'Theta;': '\u0398', + 'theta;': '\u03b8', + 'thetasym;': '\u03d1', + 'thetav;': '\u03d1', + 'thickapprox;': '\u2248', + 'thicksim;': '\u223c', + 'ThickSpace;': '\u205f\u200a', + 'thinsp;': '\u2009', + 'ThinSpace;': '\u2009', + 'thkap;': '\u2248', + 'thksim;': '\u223c', + 'THORN': '\xde', + 'thorn': '\xfe', + 'THORN;': '\xde', + 'thorn;': '\xfe', + 'Tilde;': '\u223c', + 'tilde;': '\u02dc', + 'TildeEqual;': '\u2243', + 'TildeFullEqual;': '\u2245', + 'TildeTilde;': '\u2248', + 'times': '\xd7', + 'times;': '\xd7', + 'timesb;': '\u22a0', + 'timesbar;': '\u2a31', + 'timesd;': '\u2a30', + 'tint;': '\u222d', + 'toea;': '\u2928', + 'top;': '\u22a4', + 'topbot;': '\u2336', + 'topcir;': '\u2af1', + 'Topf;': '\U0001d54b', + 'topf;': '\U0001d565', + 'topfork;': '\u2ada', + 'tosa;': '\u2929', + 'tprime;': '\u2034', + 'TRADE;': '\u2122', + 'trade;': '\u2122', + 'triangle;': '\u25b5', + 'triangledown;': '\u25bf', + 'triangleleft;': '\u25c3', + 'trianglelefteq;': '\u22b4', + 'triangleq;': '\u225c', + 'triangleright;': '\u25b9', + 'trianglerighteq;': '\u22b5', + 'tridot;': '\u25ec', + 'trie;': '\u225c', + 'triminus;': '\u2a3a', + 'TripleDot;': '\u20db', + 'triplus;': '\u2a39', + 'trisb;': '\u29cd', + 'tritime;': '\u2a3b', + 'trpezium;': '\u23e2', + 'Tscr;': '\U0001d4af', + 'tscr;': '\U0001d4c9', + 'TScy;': '\u0426', + 'tscy;': '\u0446', + 'TSHcy;': '\u040b', + 'tshcy;': '\u045b', + 'Tstrok;': '\u0166', + 'tstrok;': '\u0167', + 'twixt;': '\u226c', + 'twoheadleftarrow;': '\u219e', + 'twoheadrightarrow;': '\u21a0', + 'Uacute': '\xda', + 'uacute': '\xfa', + 'Uacute;': '\xda', + 'uacute;': '\xfa', + 'Uarr;': '\u219f', + 'uArr;': '\u21d1', + 'uarr;': '\u2191', + 'Uarrocir;': '\u2949', + 'Ubrcy;': '\u040e', + 'ubrcy;': '\u045e', + 'Ubreve;': '\u016c', + 'ubreve;': '\u016d', + 'Ucirc': '\xdb', + 'ucirc': '\xfb', + 'Ucirc;': '\xdb', + 'ucirc;': '\xfb', + 'Ucy;': '\u0423', + 'ucy;': '\u0443', + 'udarr;': '\u21c5', + 'Udblac;': '\u0170', + 'udblac;': '\u0171', + 'udhar;': '\u296e', + 'ufisht;': '\u297e', + 'Ufr;': '\U0001d518', + 'ufr;': '\U0001d532', + 'Ugrave': '\xd9', + 'ugrave': '\xf9', + 'Ugrave;': '\xd9', + 'ugrave;': '\xf9', + 'uHar;': '\u2963', + 'uharl;': '\u21bf', + 'uharr;': '\u21be', + 'uhblk;': '\u2580', + 'ulcorn;': '\u231c', + 'ulcorner;': '\u231c', + 'ulcrop;': '\u230f', + 'ultri;': '\u25f8', + 'Umacr;': '\u016a', + 'umacr;': '\u016b', + 'uml': '\xa8', + 'uml;': '\xa8', + 'UnderBar;': '_', + 'UnderBrace;': '\u23df', + 'UnderBracket;': '\u23b5', + 'UnderParenthesis;': '\u23dd', + 'Union;': '\u22c3', + 'UnionPlus;': '\u228e', + 'Uogon;': '\u0172', + 'uogon;': '\u0173', + 'Uopf;': '\U0001d54c', + 'uopf;': '\U0001d566', + 'UpArrow;': '\u2191', + 'Uparrow;': '\u21d1', + 'uparrow;': '\u2191', + 'UpArrowBar;': '\u2912', + 'UpArrowDownArrow;': '\u21c5', + 'UpDownArrow;': '\u2195', + 'Updownarrow;': '\u21d5', + 'updownarrow;': '\u2195', + 'UpEquilibrium;': '\u296e', + 'upharpoonleft;': '\u21bf', + 'upharpoonright;': '\u21be', + 'uplus;': '\u228e', + 'UpperLeftArrow;': '\u2196', + 'UpperRightArrow;': '\u2197', + 'Upsi;': '\u03d2', + 'upsi;': '\u03c5', + 'upsih;': '\u03d2', + 'Upsilon;': '\u03a5', + 'upsilon;': '\u03c5', + 'UpTee;': '\u22a5', + 'UpTeeArrow;': '\u21a5', + 'upuparrows;': '\u21c8', + 'urcorn;': '\u231d', + 'urcorner;': '\u231d', + 'urcrop;': '\u230e', + 'Uring;': '\u016e', + 'uring;': '\u016f', + 'urtri;': '\u25f9', + 'Uscr;': '\U0001d4b0', + 'uscr;': '\U0001d4ca', + 'utdot;': '\u22f0', + 'Utilde;': '\u0168', + 'utilde;': '\u0169', + 'utri;': '\u25b5', + 'utrif;': '\u25b4', + 'uuarr;': '\u21c8', + 'Uuml': '\xdc', + 'uuml': '\xfc', + 'Uuml;': '\xdc', + 'uuml;': '\xfc', + 'uwangle;': '\u29a7', + 'vangrt;': '\u299c', + 'varepsilon;': '\u03f5', + 'varkappa;': '\u03f0', + 'varnothing;': '\u2205', + 'varphi;': '\u03d5', + 'varpi;': '\u03d6', + 'varpropto;': '\u221d', + 'vArr;': '\u21d5', + 'varr;': '\u2195', + 'varrho;': '\u03f1', + 'varsigma;': '\u03c2', + 'varsubsetneq;': '\u228a\ufe00', + 'varsubsetneqq;': '\u2acb\ufe00', + 'varsupsetneq;': '\u228b\ufe00', + 'varsupsetneqq;': '\u2acc\ufe00', + 'vartheta;': '\u03d1', + 'vartriangleleft;': '\u22b2', + 'vartriangleright;': '\u22b3', + 'Vbar;': '\u2aeb', + 'vBar;': '\u2ae8', + 'vBarv;': '\u2ae9', + 'Vcy;': '\u0412', + 'vcy;': '\u0432', + 'VDash;': '\u22ab', + 'Vdash;': '\u22a9', + 'vDash;': '\u22a8', + 'vdash;': '\u22a2', + 'Vdashl;': '\u2ae6', + 'Vee;': '\u22c1', + 'vee;': '\u2228', + 'veebar;': '\u22bb', + 'veeeq;': '\u225a', + 'vellip;': '\u22ee', + 'Verbar;': '\u2016', + 'verbar;': '|', + 'Vert;': '\u2016', + 'vert;': '|', + 'VerticalBar;': '\u2223', + 'VerticalLine;': '|', + 'VerticalSeparator;': '\u2758', + 'VerticalTilde;': '\u2240', + 'VeryThinSpace;': '\u200a', + 'Vfr;': '\U0001d519', + 'vfr;': '\U0001d533', + 'vltri;': '\u22b2', + 'vnsub;': '\u2282\u20d2', + 'vnsup;': '\u2283\u20d2', + 'Vopf;': '\U0001d54d', + 'vopf;': '\U0001d567', + 'vprop;': '\u221d', + 'vrtri;': '\u22b3', + 'Vscr;': '\U0001d4b1', + 'vscr;': '\U0001d4cb', + 'vsubnE;': '\u2acb\ufe00', + 'vsubne;': '\u228a\ufe00', + 'vsupnE;': '\u2acc\ufe00', + 'vsupne;': '\u228b\ufe00', + 'Vvdash;': '\u22aa', + 'vzigzag;': '\u299a', + 'Wcirc;': '\u0174', + 'wcirc;': '\u0175', + 'wedbar;': '\u2a5f', + 'Wedge;': '\u22c0', + 'wedge;': '\u2227', + 'wedgeq;': '\u2259', + 'weierp;': '\u2118', + 'Wfr;': '\U0001d51a', + 'wfr;': '\U0001d534', + 'Wopf;': '\U0001d54e', + 'wopf;': '\U0001d568', + 'wp;': '\u2118', + 'wr;': '\u2240', + 'wreath;': '\u2240', + 'Wscr;': '\U0001d4b2', + 'wscr;': '\U0001d4cc', + 'xcap;': '\u22c2', + 'xcirc;': '\u25ef', + 'xcup;': '\u22c3', + 'xdtri;': '\u25bd', + 'Xfr;': '\U0001d51b', + 'xfr;': '\U0001d535', + 'xhArr;': '\u27fa', + 'xharr;': '\u27f7', + 'Xi;': '\u039e', + 'xi;': '\u03be', + 'xlArr;': '\u27f8', + 'xlarr;': '\u27f5', + 'xmap;': '\u27fc', + 'xnis;': '\u22fb', + 'xodot;': '\u2a00', + 'Xopf;': '\U0001d54f', + 'xopf;': '\U0001d569', + 'xoplus;': '\u2a01', + 'xotime;': '\u2a02', + 'xrArr;': '\u27f9', + 'xrarr;': '\u27f6', + 'Xscr;': '\U0001d4b3', + 'xscr;': '\U0001d4cd', + 'xsqcup;': '\u2a06', + 'xuplus;': '\u2a04', + 'xutri;': '\u25b3', + 'xvee;': '\u22c1', + 'xwedge;': '\u22c0', + 'Yacute': '\xdd', + 'yacute': '\xfd', + 'Yacute;': '\xdd', + 'yacute;': '\xfd', + 'YAcy;': '\u042f', + 'yacy;': '\u044f', + 'Ycirc;': '\u0176', + 'ycirc;': '\u0177', + 'Ycy;': '\u042b', + 'ycy;': '\u044b', + 'yen': '\xa5', + 'yen;': '\xa5', + 'Yfr;': '\U0001d51c', + 'yfr;': '\U0001d536', + 'YIcy;': '\u0407', + 'yicy;': '\u0457', + 'Yopf;': '\U0001d550', + 'yopf;': '\U0001d56a', + 'Yscr;': '\U0001d4b4', + 'yscr;': '\U0001d4ce', + 'YUcy;': '\u042e', + 'yucy;': '\u044e', + 'yuml': '\xff', + 'Yuml;': '\u0178', + 'yuml;': '\xff', + 'Zacute;': '\u0179', + 'zacute;': '\u017a', + 'Zcaron;': '\u017d', + 'zcaron;': '\u017e', + 'Zcy;': '\u0417', + 'zcy;': '\u0437', + 'Zdot;': '\u017b', + 'zdot;': '\u017c', + 'zeetrf;': '\u2128', + 'ZeroWidthSpace;': '\u200b', + 'Zeta;': '\u0396', + 'zeta;': '\u03b6', + 'Zfr;': '\u2128', + 'zfr;': '\U0001d537', + 'ZHcy;': '\u0416', + 'zhcy;': '\u0436', + 'zigrarr;': '\u21dd', + 'Zopf;': '\u2124', + 'zopf;': '\U0001d56b', + 'Zscr;': '\U0001d4b5', + 'zscr;': '\U0001d4cf', + 'zwj;': '\u200d', + 'zwnj;': '\u200c', + } + try: import http.client as compat_http_client except ImportError: # Python 2 @@ -82,7 +2322,6 @@ try: except ImportError: # Python 2 from HTMLParser import HTMLParser as compat_HTMLParser - try: from subprocess import DEVNULL compat_subprocess_get_DEVNULL = lambda: DEVNULL @@ -244,13 +2483,20 @@ try: except ImportError: # Python 2.6 from xml.parsers.expat import ExpatError as compat_xml_parse_error + +etree = xml.etree.ElementTree + + +class _TreeBuilder(etree.TreeBuilder): + def doctype(self, name, pubid, system): + pass + if sys.version_info[0] >= 3: - compat_etree_fromstring = xml.etree.ElementTree.fromstring + def compat_etree_fromstring(text): + return etree.XML(text, parser=etree.XMLParser(target=_TreeBuilder())) else: # python 2.x tries to encode unicode strings with ascii (see the # XMLParser._fixtext method) - etree = xml.etree.ElementTree - try: _etree_iter = etree.Element.iter except AttributeError: # Python <=2.6 @@ -264,7 +2510,7 @@ else: # 2.7 source def _XML(text, parser=None): if not parser: - parser = etree.XMLParser(target=etree.TreeBuilder()) + parser = etree.XMLParser(target=_TreeBuilder()) parser.feed(text) return parser.close() @@ -276,7 +2522,7 @@ else: return el def compat_etree_fromstring(text): - doc = _XML(text, parser=etree.XMLParser(target=etree.TreeBuilder(element_factory=_element_factory))) + doc = _XML(text, parser=etree.XMLParser(target=_TreeBuilder(element_factory=_element_factory))) for el in _etree_iter(doc): if el.text is not None and isinstance(el.text, bytes): el.text = el.text.decode('utf-8') @@ -340,24 +2586,28 @@ except ImportError: # Python 2 return parsed_result try: - from shlex import quote as shlex_quote + from shlex import quote as compat_shlex_quote except ImportError: # Python < 3.3 - def shlex_quote(s): + def compat_shlex_quote(s): if re.match(r'^[-_\w./]+$', s): return s else: return "'" + s.replace("'", "'\"'\"'") + "'" -if sys.version_info >= (2, 7, 3): +try: + args = shlex.split('中文') + assert (isinstance(args, list) and + isinstance(args[0], compat_str) and + args[0] == '中文') compat_shlex_split = shlex.split -else: +except (AssertionError, UnicodeEncodeError): # Working around shlex issue with unicode strings on some python 2 # versions (see http://bugs.python.org/issue1548891) def compat_shlex_split(s, comments=False, posix=True): if isinstance(s, compat_str): s = s.encode('utf-8') - return shlex.split(s, comments, posix) + return list(map(lambda s: s.decode('utf-8'), shlex.split(s, comments, posix))) def compat_ord(c): @@ -373,6 +2623,9 @@ compat_os_name = os._name if os.name == 'java' else os.name if sys.version_info >= (3, 0): compat_getenv = os.getenv compat_expanduser = os.path.expanduser + + def compat_setenv(key, value, env=os.environ): + env[key] = value else: # Environment variables should be decoded with filesystem encoding. # Otherwise it will fail if any non-ASCII characters present (see #3854 #3217 #2918) @@ -384,6 +2637,12 @@ else: env = env.decode(get_filesystem_encoding()) return env + def compat_setenv(key, value, env=os.environ): + def encode(v): + from .utils import get_filesystem_encoding + return v.encode(get_filesystem_encoding()) if isinstance(v, compat_str) else v + env[encode(key)] = encode(value) + # HACK: The default implementations of os.path.expanduser from cpython do not decode # environment variables with filesystem encoding. We will work around this by # providing adjusted implementations. @@ -456,18 +2715,6 @@ else: print(s) -try: - subprocess_check_output = subprocess.check_output -except AttributeError: - def subprocess_check_output(*args, **kwargs): - assert 'input' not in kwargs - p = subprocess.Popen(*args, stdout=subprocess.PIPE, **kwargs) - output, _ = p.communicate() - ret = p.poll() - if ret: - raise subprocess.CalledProcessError(ret, p.args, output=output) - return output - if sys.version_info < (3, 0) and sys.platform == 'win32': def compat_getpass(prompt, *args, **kwargs): if isinstance(prompt, compat_str): @@ -477,6 +2724,11 @@ if sys.version_info < (3, 0) and sys.platform == 'win32': else: compat_getpass = getpass.getpass +try: + compat_input = raw_input +except NameError: # Python 3 + compat_input = input + # Python < 2.6.5 require kwargs to be bytes try: def _testfunc(x): @@ -583,6 +2835,26 @@ if sys.version_info >= (3, 0): else: from tokenize import generate_tokens as compat_tokenize_tokenize + +try: + struct.pack('!I', 0) +except TypeError: + # In Python 2.6 and 2.7.x < 2.7.7, struct requires a bytes argument + # See https://bugs.python.org/issue19099 + def compat_struct_pack(spec, *args): + if isinstance(spec, compat_str): + spec = spec.encode('ascii') + return struct.pack(spec, *args) + + def compat_struct_unpack(spec, *args): + if isinstance(spec, compat_str): + spec = spec.encode('ascii') + return struct.unpack(spec, *args) +else: + compat_struct_pack = struct.pack + compat_struct_unpack = struct.unpack + + __all__ = [ 'compat_HTMLParser', 'compat_HTTPError', @@ -596,17 +2868,23 @@ __all__ = [ 'compat_getenv', 'compat_getpass', 'compat_html_entities', + 'compat_html_entities_html5', 'compat_http_client', 'compat_http_server', + 'compat_input', 'compat_itertools_count', 'compat_kwargs', 'compat_ord', 'compat_os_name', 'compat_parse_qs', 'compat_print', + 'compat_setenv', + 'compat_shlex_quote', 'compat_shlex_split', 'compat_socket_create_connection', 'compat_str', + 'compat_struct_pack', + 'compat_struct_unpack', 'compat_subprocess_get_DEVNULL', 'compat_tokenize_tokenize', 'compat_urllib_error', @@ -623,7 +2901,5 @@ __all__ = [ 'compat_urlretrieve', 'compat_xml_parse_error', 'compat_xpath', - 'shlex_quote', - 'subprocess_check_output', 'workaround_optparse_bug9161', ] diff --git a/youtube_dl/downloader/external.py b/youtube_dl/downloader/external.py index 8d642fc3e..fae245024 100644 --- a/youtube_dl/downloader/external.py +++ b/youtube_dl/downloader/external.py @@ -6,6 +6,7 @@ import sys import re from .common import FileDownloader +from ..compat import compat_setenv from ..postprocessor.ffmpeg import FFmpegPostProcessor, EXT_TO_OUT_FORMATS from ..utils import ( cli_option, @@ -84,7 +85,7 @@ class ExternalFD(FileDownloader): cmd, stderr=subprocess.PIPE) _, stderr = p.communicate() if p.returncode != 0: - self.to_stderr(stderr) + self.to_stderr(stderr.decode('utf-8', 'replace')) return p.returncode @@ -198,6 +199,19 @@ class FFmpegFD(ExternalFD): '-headers', ''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())] + env = None + proxy = self.params.get('proxy') + if proxy: + if not re.match(r'^[\da-zA-Z]+://', proxy): + proxy = 'http://%s' % proxy + # Since December 2015 ffmpeg supports -http_proxy option (see + # http://git.videolan.org/?p=ffmpeg.git;a=commit;h=b4eb1f29ebddd60c41a2eb39f5af701e38e0d3fd) + # We could switch to the following code if we are able to detect version properly + # args += ['-http_proxy', proxy] + env = os.environ.copy() + compat_setenv('HTTP_PROXY', proxy, env=env) + compat_setenv('http_proxy', proxy, env=env) + protocol = info_dict.get('protocol') if protocol == 'rtmp': @@ -224,7 +238,7 @@ class FFmpegFD(ExternalFD): args += ['-rtmp_live', 'live'] args += ['-i', url, '-c', 'copy'] - if protocol == 'm3u8': + if protocol in ('m3u8', 'm3u8_native'): if self.params.get('hls_use_mpegts', False) or tmpfilename == '-': args += ['-f', 'mpegts'] else: @@ -239,7 +253,7 @@ class FFmpegFD(ExternalFD): self._debug_cmd(args) - proc = subprocess.Popen(args, stdin=subprocess.PIPE) + proc = subprocess.Popen(args, stdin=subprocess.PIPE, env=env) try: retval = proc.wait() except KeyboardInterrupt: diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index 664d87543..80c21d40b 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -12,37 +12,49 @@ from ..compat import ( compat_urlparse, compat_urllib_error, compat_urllib_parse_urlparse, + compat_struct_pack, + compat_struct_unpack, ) from ..utils import ( encodeFilename, fix_xml_ampersands, sanitize_open, - struct_pack, - struct_unpack, xpath_text, ) +class DataTruncatedError(Exception): + pass + + class FlvReader(io.BytesIO): """ Reader for Flv files The file format is documented in https://www.adobe.com/devnet/f4v.html """ + def read_bytes(self, n): + data = self.read(n) + if len(data) < n: + raise DataTruncatedError( + 'FlvReader error: need %d bytes while only %d bytes got' % ( + n, len(data))) + return data + # Utility functions for reading numbers and strings def read_unsigned_long_long(self): - return struct_unpack('!Q', self.read(8))[0] + return compat_struct_unpack('!Q', self.read_bytes(8))[0] def read_unsigned_int(self): - return struct_unpack('!I', self.read(4))[0] + return compat_struct_unpack('!I', self.read_bytes(4))[0] def read_unsigned_char(self): - return struct_unpack('!B', self.read(1))[0] + return compat_struct_unpack('!B', self.read_bytes(1))[0] def read_string(self): res = b'' while True: - char = self.read(1) + char = self.read_bytes(1) if char == b'\x00': break res += char @@ -53,18 +65,18 @@ class FlvReader(io.BytesIO): Read a box and return the info as a tuple: (box_size, box_type, box_data) """ real_size = size = self.read_unsigned_int() - box_type = self.read(4) + box_type = self.read_bytes(4) header_end = 8 if size == 1: real_size = self.read_unsigned_long_long() header_end = 16 - return real_size, box_type, self.read(real_size - header_end) + return real_size, box_type, self.read_bytes(real_size - header_end) def read_asrt(self): # version self.read_unsigned_char() # flags - self.read(3) + self.read_bytes(3) quality_entry_count = self.read_unsigned_char() # QualityEntryCount for i in range(quality_entry_count): @@ -85,7 +97,7 @@ class FlvReader(io.BytesIO): # version self.read_unsigned_char() # flags - self.read(3) + self.read_bytes(3) # time scale self.read_unsigned_int() @@ -119,7 +131,7 @@ class FlvReader(io.BytesIO): # version self.read_unsigned_char() # flags - self.read(3) + self.read_bytes(3) self.read_unsigned_int() # BootstrapinfoVersion # Profile,Live,Update,Reserved @@ -184,6 +196,11 @@ def build_fragments_list(boot_info): first_frag_number = fragment_run_entry_table[0]['first'] fragments_counter = itertools.count(first_frag_number) for segment, fragments_count in segment_run_table['segment_run']: + # In some live HDS streams (for example Rai), `fragments_count` is + # abnormal and causing out-of-memory errors. It's OK to change the + # number of fragments for live streams as they are updated periodically + if fragments_count == 4294967295 and boot_info['live']: + fragments_count = 2 for _ in range(fragments_count): res.append((segment, next(fragments_counter))) @@ -194,11 +211,11 @@ def build_fragments_list(boot_info): def write_unsigned_int(stream, val): - stream.write(struct_pack('!I', val)) + stream.write(compat_struct_pack('!I', val)) def write_unsigned_int_24(stream, val): - stream.write(struct_pack('!I', val)[1:]) + stream.write(compat_struct_pack('!I', val)[1:]) def write_flv_header(stream): @@ -307,7 +324,7 @@ class F4mFD(FragmentFD): doc = compat_etree_fromstring(manifest) formats = [(int(f.attrib.get('bitrate', -1)), f) for f in self._get_unencrypted_media(doc)] - if requested_bitrate is None: + if requested_bitrate is None or len(formats) == 1: # get the best format formats = sorted(formats, key=lambda f: f[0]) rate, media = formats[-1] @@ -317,7 +334,11 @@ class F4mFD(FragmentFD): base_url = compat_urlparse.urljoin(man_url, media.attrib['url']) bootstrap_node = doc.find(_add_ns('bootstrapInfo')) - boot_info, bootstrap_url = self._parse_bootstrap_node(bootstrap_node, base_url) + # From Adobe F4M 3.0 spec: + # The <baseURL> element SHALL be the base URL for all relative + # (HTTP-based) URLs in the manifest. If <baseURL> is not present, said + # URLs should be relative to the location of the containing document. + boot_info, bootstrap_url = self._parse_bootstrap_node(bootstrap_node, man_url) live = boot_info['live'] metadata_node = media.find(_add_ns('metadata')) if metadata_node is not None: @@ -374,7 +395,17 @@ class F4mFD(FragmentFD): down.close() reader = FlvReader(down_data) while True: - _, box_type, box_data = reader.read_box_info() + try: + _, box_type, box_data = reader.read_box_info() + except DataTruncatedError: + if test: + # In tests, segments may be truncated, and thus + # FlvReader may not be able to parse the whole + # chunk. If so, write the segment as is + # See https://github.com/rg3/youtube-dl/issues/9214 + dest_stream.write(down_data) + break + raise if box_type == b'mdat': dest_stream.write(box_data) break diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index a01dac031..3b7bb3508 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -2,13 +2,24 @@ from __future__ import unicode_literals import os.path import re +import binascii +try: + from Crypto.Cipher import AES + can_decrypt_frag = True +except ImportError: + can_decrypt_frag = False from .fragment import FragmentFD +from .external import FFmpegFD -from ..compat import compat_urlparse +from ..compat import ( + compat_urlparse, + compat_struct_pack, +) from ..utils import ( encodeFilename, sanitize_open, + parse_m3u8_attributes, ) @@ -17,42 +28,101 @@ class HlsFD(FragmentFD): FD_NAME = 'hlsnative' + @staticmethod + def can_download(manifest): + UNSUPPORTED_FEATURES = ( + r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)', # encrypted streams [1] + r'#EXT-X-BYTERANGE', # playlists composed of byte ranges of media files [2] + + # Live streams heuristic does not always work (e.g. geo restricted to Germany + # http://hls-geo.daserste.de/i/videoportal/Film/c_620000/622873/format,716451,716457,716450,716458,716459,.mp4.csmil/index_4_av.m3u8?null=0) + # r'#EXT-X-MEDIA-SEQUENCE:(?!0$)', # live streams [3] + + # This heuristic also is not correct since segments may not be appended as well. + # Twitch vods of finished streams have EXT-X-PLAYLIST-TYPE:EVENT despite + # no segments will definitely be appended to the end of the playlist. + # r'#EXT-X-PLAYLIST-TYPE:EVENT', # media segments may be appended to the end of + # # event media playlists [4] + + # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.4 + # 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.2 + # 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.2 + # 4. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.5 + ) + check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES] + check_results.append(can_decrypt_frag or '#EXT-X-KEY:METHOD=AES-128' not in manifest) + return all(check_results) + def real_download(self, filename, info_dict): man_url = info_dict['url'] self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME) manifest = self.ydl.urlopen(man_url).read() s = manifest.decode('utf-8', 'ignore') - fragment_urls = [] + + if not self.can_download(s): + self.report_warning( + 'hlsnative has detected features it does not support, ' + 'extraction will be delegated to ffmpeg') + fd = FFmpegFD(self.ydl, self.params) + for ph in self._progress_hooks: + fd.add_progress_hook(ph) + return fd.real_download(filename, info_dict) + + total_frags = 0 for line in s.splitlines(): line = line.strip() if line and not line.startswith('#'): - segment_url = ( - line - if re.match(r'^https?://', line) - else compat_urlparse.urljoin(man_url, line)) - fragment_urls.append(segment_url) - # We only download the first fragment during the test - if self.params.get('test', False): - break + total_frags += 1 ctx = { 'filename': filename, - 'total_frags': len(fragment_urls), + 'total_frags': total_frags, } self._prepare_and_start_frag_download(ctx) + i = 0 + media_sequence = 0 + decrypt_info = {'METHOD': 'NONE'} frags_filenames = [] - for i, frag_url in enumerate(fragment_urls): - frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i) - success = ctx['dl'].download(frag_filename, {'url': frag_url}) - if not success: - return False - down, frag_sanitized = sanitize_open(frag_filename, 'rb') - ctx['dest_stream'].write(down.read()) - down.close() - frags_filenames.append(frag_sanitized) + for line in s.splitlines(): + line = line.strip() + if line: + if not line.startswith('#'): + frag_url = ( + line + if re.match(r'^https?://', line) + else compat_urlparse.urljoin(man_url, line)) + frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i) + success = ctx['dl'].download(frag_filename, {'url': frag_url}) + if not success: + return False + down, frag_sanitized = sanitize_open(frag_filename, 'rb') + frag_content = down.read() + down.close() + if decrypt_info['METHOD'] == 'AES-128': + iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence) + frag_content = AES.new( + decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content) + ctx['dest_stream'].write(frag_content) + frags_filenames.append(frag_sanitized) + # We only download the first fragment during the test + if self.params.get('test', False): + break + i += 1 + media_sequence += 1 + elif line.startswith('#EXT-X-KEY'): + decrypt_info = parse_m3u8_attributes(line[11:]) + if decrypt_info['METHOD'] == 'AES-128': + if 'IV' in decrypt_info: + decrypt_info['IV'] = binascii.unhexlify(decrypt_info['IV'][2:]) + if not re.match(r'^https?://', decrypt_info['URI']): + decrypt_info['URI'] = compat_urlparse.urljoin( + man_url, decrypt_info['URI']) + decrypt_info['KEY'] = self.ydl.urlopen(decrypt_info['URI']).read() + elif line.startswith('#EXT-X-MEDIA-SEQUENCE'): + media_sequence = int(line[22:]) self._finish_frag_download(ctx) diff --git a/youtube_dl/extractor/abcnews.py b/youtube_dl/extractor/abcnews.py new file mode 100644 index 000000000..b61a6327c --- /dev/null +++ b/youtube_dl/extractor/abcnews.py @@ -0,0 +1,135 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import calendar +import re +import time + +from .amp import AMPIE +from .common import InfoExtractor +from ..compat import compat_urlparse + + +class AbcNewsVideoIE(AMPIE): + IE_NAME = 'abcnews:video' + _VALID_URL = 'http://abcnews.go.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)' + + _TESTS = [{ + 'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932', + 'info_dict': { + 'id': '20411932', + 'ext': 'mp4', + 'display_id': 'week-exclusive-irans-foreign-minister-zarif', + 'title': '\'This Week\' Exclusive: Iran\'s Foreign Minister Zarif', + 'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.', + 'duration': 180, + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + video_id = mobj.group('id') + info_dict = self._extract_feed_info( + 'http://abcnews.go.com/video/itemfeed?id=%s' % video_id) + info_dict.update({ + 'id': video_id, + 'display_id': display_id, + }) + return info_dict + + +class AbcNewsIE(InfoExtractor): + IE_NAME = 'abcnews' + _VALID_URL = 'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)' + + _TESTS = [{ + 'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY', + 'info_dict': { + 'id': '10498713', + 'ext': 'flv', + 'display_id': 'dramatic-video-rare-death-job-america', + 'title': 'Occupational Hazards', + 'description': 'Nightline investigates the dangers that lurk at various jobs.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'upload_date': '20100428', + 'timestamp': 1272412800, + }, + 'add_ie': ['AbcNewsVideo'], + }, { + 'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818', + 'info_dict': { + 'id': '39125818', + 'ext': 'mp4', + 'display_id': 'justin-timberlake-performs-stop-feeling-eurovision-2016', + 'title': 'Justin Timberlake Drops Hints For Secret Single', + 'description': 'Lara Spencer reports the buzziest stories of the day in "GMA" Pop News.', + 'upload_date': '20160515', + 'timestamp': 1463329500, + }, + 'params': { + # m3u8 download + 'skip_download': True, + # The embedded YouTube video is blocked due to copyright issues + 'playlist_items': '1', + }, + 'add_ie': ['AbcNewsVideo'], + }, { + 'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + video_url = self._search_regex( + r'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage, 'video URL') + full_video_url = compat_urlparse.urljoin(url, video_url) + + youtube_url = self._html_search_regex( + r'<iframe[^>]+src="(https://www\.youtube\.com/embed/[^"]+)"', + webpage, 'YouTube URL', default=None) + + timestamp = None + date_str = self._html_search_regex( + r'<span[^>]+class="timestamp">([^<]+)</span>', + webpage, 'timestamp', fatal=False) + if date_str: + tz_offset = 0 + if date_str.endswith(' ET'): # Eastern Time + tz_offset = -5 + date_str = date_str[:-3] + date_formats = ['%b. %d, %Y', '%b %d, %Y, %I:%M %p'] + for date_format in date_formats: + try: + timestamp = calendar.timegm(time.strptime(date_str.strip(), date_format)) + except ValueError: + continue + if timestamp is not None: + timestamp -= tz_offset * 3600 + + entry = { + '_type': 'url_transparent', + 'ie_key': AbcNewsVideoIE.ie_key(), + 'url': full_video_url, + 'id': video_id, + 'display_id': display_id, + 'timestamp': timestamp, + } + + if youtube_url: + entries = [entry, self.url_result(youtube_url, 'Youtube')] + return self.playlist_result(entries) + + return entry diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py index 8753ee2cf..5ae16fa16 100644 --- a/youtube_dl/extractor/adobetv.py +++ b/youtube_dl/extractor/adobetv.py @@ -156,7 +156,10 @@ class AdobeTVVideoIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - video_data = self._download_json(url + '?format=json', video_id) + webpage = self._download_webpage(url, video_id) + + video_data = self._parse_json(self._search_regex( + r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id) formats = [{ 'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')), diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py index 1bbfe2641..8f53050c9 100644 --- a/youtube_dl/extractor/aenetworks.py +++ b/youtube_dl/extractor/aenetworks.py @@ -2,41 +2,33 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor +from .theplatform import ThePlatformIE from ..utils import ( smuggle_url, update_url_query, unescapeHTML, + extract_attributes, + get_element_by_attribute, ) +from ..compat import ( + compat_urlparse, +) + +class AENetworksBaseIE(ThePlatformIE): + _THEPLATFORM_KEY = 'crazyjava' + _THEPLATFORM_SECRET = 's3cr3t' -class AENetworksIE(InfoExtractor): + +class AENetworksIE(AENetworksBaseIE): IE_NAME = 'aenetworks' IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network' - _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?P<type>[^/]+)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])' - + _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)/full-movie)' _TESTS = [{ - 'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false', - 'info_dict': { - 'id': 'g12m5Gyt3fdR', - 'ext': 'mp4', - 'title': "Bet You Didn't Know: Valentine's Day", - 'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7', - 'timestamp': 1375819729, - 'upload_date': '20130806', - 'uploader': 'AENE-NEW', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - 'add_ie': ['ThePlatform'], - 'expected_warnings': ['JSON-LD'], - }, { 'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1', 'md5': '8ff93eb073449f151d6b90c0ae1ef0c7', 'info_dict': { - 'id': 'eg47EERs_JsZ', + 'id': '22253814', 'ext': 'mp4', 'title': 'Winter Is Coming', 'description': 'md5:641f424b7a19d8e24f26dea22cf59d74', @@ -46,42 +38,168 @@ class AENetworksIE(InfoExtractor): }, 'add_ie': ['ThePlatform'], }, { - 'url': 'http://www.aetv.com/shows/duck-dynasty/video/inlawful-entry', + 'url': 'http://www.history.com/shows/ancient-aliens/season-1', + 'info_dict': { + 'id': '71889446852', + }, + 'playlist_mincount': 5, + }, { + 'url': 'http://www.mylifetime.com/shows/atlanta-plastic', + 'info_dict': { + 'id': 'SERIES4317', + 'title': 'Atlanta Plastic', + }, + 'playlist_mincount': 2, + }, { + 'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1', 'only_matching': True }, { - 'url': 'http://www.fyi.tv/shows/tiny-house-nation/videos/207-sq-ft-minnesota-prairie-cottage', + 'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8', 'only_matching': True }, { - 'url': 'http://www.mylifetime.com/shows/project-runway-junior/video/season-1/episode-6/superstar-clients', + 'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6', + 'only_matching': True + }, { + 'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie', 'only_matching': True }] + _DOMAIN_TO_REQUESTOR_ID = { + 'history.com': 'HISTORY', + 'aetv.com': 'AETV', + 'mylifetime.com': 'LIFETIME', + 'fyi.tv': 'FYI', + } def _real_extract(self, url): - page_type, video_id = re.match(self._VALID_URL, url).groups() + domain, show_path, movie_display_id = re.match(self._VALID_URL, url).groups() + display_id = show_path or movie_display_id + webpage = self._download_webpage(url, display_id) + if show_path: + url_parts = show_path.split('/') + url_parts_len = len(url_parts) + if url_parts_len == 1: + entries = [] + for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage): + entries.append(self.url_result( + compat_urlparse.urljoin(url, season_url_path), 'AENetworks')) + return self.playlist_result( + entries, self._html_search_meta('aetn:SeriesId', webpage), + self._html_search_meta('aetn:SeriesTitle', webpage)) + elif url_parts_len == 2: + entries = [] + for episode_item in re.findall(r'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage): + episode_attributes = extract_attributes(episode_item) + episode_url = compat_urlparse.urljoin( + url, episode_attributes['data-canonical']) + entries.append(self.url_result( + episode_url, 'AENetworks', + episode_attributes['data-videoid'])) + return self.playlist_result( + entries, self._html_search_meta('aetn:SeasonId', webpage)) + + query = { + 'mbr': 'true', + 'assetTypes': 'medium_video_s3' + } + video_id = self._html_search_meta('aetn:VideoID', webpage) + media_url = self._search_regex( + r"media_url\s*=\s*'([^']+)'", webpage, 'video url') + theplatform_metadata = self._download_theplatform_metadata(self._search_regex( + r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id) + info = self._parse_theplatform_metadata(theplatform_metadata) + if theplatform_metadata.get('AETN$isBehindWall'): + requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain] + resource = '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>%s%s%s%s' % (requestor_id, theplatform_metadata['title'], theplatform_metadata['AETN$PPL_pplProgramId'], theplatform_metadata['ratings'][0]['rating']) + query['auth'] = self._extract_mvpd_auth( + url, video_id, requestor_id, resource) + info.update(self._search_json_ld(webpage, video_id, fatal=False)) + media_url = update_url_query(media_url, query) + media_url = self._sign_url(media_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET) + formats, subtitles = self._extract_theplatform_smil(media_url, video_id) + self._sort_formats(formats) + info.update({ + 'id': video_id, + 'formats': formats, + 'subtitles': subtitles, + }) + return info - webpage = self._download_webpage(url, video_id) - video_url_re = [ - r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id, - r"media_url\s*=\s*'([^']+)'" - ] - video_url = unescapeHTML(self._search_regex(video_url_re, webpage, 'video url')) - query = {'mbr': 'true'} - if page_type == 'shows': - query['assetTypes'] = 'medium_video_s3' - if 'switch=hds' in video_url: - query['switch'] = 'hls' +class HistoryTopicIE(AENetworksBaseIE): + IE_NAME = 'history:topic' + IE_DESC = 'History.com Topic' + _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P[^/]+)(?:/[^/]+(?:/(?P[^/?#]+))?)?' + _TESTS = [{ + 'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false', + 'info_dict': { + 'id': '40700995724', + 'ext': 'mp4', + 'title': "Bet You Didn't Know: Valentine's Day", + 'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7', + 'timestamp': 1375819729, + 'upload_date': '20130806', + 'uploader': 'AENE-NEW', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + 'add_ie': ['ThePlatform'], + }, { + 'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos', + 'info_dict': + { + 'id': 'world-war-i-history', + 'title': 'World War I History', + }, + 'playlist_mincount': 24, + }, { + 'url': 'http://www.history.com/topics/world-war-i-history/videos', + 'only_matching': True, + }, { + 'url': 'http://www.history.com/topics/world-war-i/world-war-i-history', + 'only_matching': True, + }, { + 'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/speeches', + 'only_matching': True, + }] - info = self._search_json_ld(webpage, video_id, fatal=False) - info.update({ + def theplatform_url_result(self, theplatform_url, video_id, query): + return { '_type': 'url_transparent', + 'id': video_id, 'url': smuggle_url( - update_url_query(video_url, query), + update_url_query(theplatform_url, query), { 'sig': { - 'key': 'crazyjava', - 'secret': 's3cr3t'}, + 'key': self._THEPLATFORM_KEY, + 'secret': self._THEPLATFORM_SECRET, + }, 'force_smil_url': True }), - }) - return info + 'ie_key': 'ThePlatform', + } + + def _real_extract(self, url): + topic_id, video_display_id = re.match(self._VALID_URL, url).groups() + if video_display_id: + webpage = self._download_webpage(url, video_display_id) + release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups() + release_url = unescapeHTML(release_url) + + return self.theplatform_url_result( + release_url, video_id, { + 'mbr': 'true', + 'switch': 'hls' + }) + else: + webpage = self._download_webpage(url, topic_id) + entries = [] + for episode_item in re.findall(r']*>', webpage): + video_attributes = extract_attributes(episode_item) + entries.append(self.theplatform_url_result( + video_attributes['data-release-url'], video_attributes['data-id'], { + 'mbr': 'true', + 'switch': 'hls' + })) + return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage)) diff --git a/youtube_dl/extractor/afreecatv.py b/youtube_dl/extractor/afreecatv.py new file mode 100644 index 000000000..518c61f67 --- /dev/null +++ b/youtube_dl/extractor/afreecatv.py @@ -0,0 +1,133 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse_urlparse, + compat_urlparse, +) +from ..utils import ( + ExtractorError, + int_or_none, + xpath_element, + xpath_text, +) + + +class AfreecaTVIE(InfoExtractor): + IE_DESC = 'afreecatv.com' + _VALID_URL = r'''(?x)^ + https?://(?:(live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)? + (?: + /app/(?:index|read_ucc_bbs)\.cgi| + /player/[Pp]layer\.(?:swf|html)) + \?.*?\bnTitleNo=(?P\d+)''' + _TESTS = [{ + 'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=', + 'md5': 'f72c89fe7ecc14c1b5ce506c4996046e', + 'info_dict': { + 'id': '36164052', + 'ext': 'mp4', + 'title': '데일리 에이프릴 요정들의 시상식!', + 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$', + 'uploader': 'dailyapril', + 'uploader_id': 'dailyapril', + 'upload_date': '20160503', + } + }, { + 'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867', + 'info_dict': { + 'id': '36153164', + 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'", + 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$', + 'uploader': 'dailyapril', + 'uploader_id': 'dailyapril', + }, + 'playlist_count': 2, + 'playlist': [{ + 'md5': 'd8b7c174568da61d774ef0203159bf97', + 'info_dict': { + 'id': '36153164_1', + 'ext': 'mp4', + 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'", + 'upload_date': '20160502', + }, + }, { + 'md5': '58f2ce7f6044e34439ab2d50612ab02b', + 'info_dict': { + 'id': '36153164_2', + 'ext': 'mp4', + 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'", + 'upload_date': '20160502', + }, + }], + }, { + 'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652', + 'only_matching': True, + }] + + @staticmethod + def parse_video_key(key): + video_key = {} + m = re.match(r'^(?P\d{8})_\w+_(?P\d+)$', key) + if m: + video_key['upload_date'] = m.group('upload_date') + video_key['part'] = m.group('part') + return video_key + + def _real_extract(self, url): + video_id = self._match_id(url) + parsed_url = compat_urllib_parse_urlparse(url) + info_url = compat_urlparse.urlunparse(parsed_url._replace( + netloc='afbbs.afreecatv.com:8080', + path='/api/video/get_video_info.php')) + video_xml = self._download_xml(info_url, video_id) + + if xpath_element(video_xml, './track/video/file') is None: + raise ExtractorError('Specified AfreecaTV video does not exist', + expected=True) + + title = xpath_text(video_xml, './track/title', 'title') + uploader = xpath_text(video_xml, './track/nickname', 'uploader') + uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id') + duration = int_or_none(xpath_text(video_xml, './track/duration', + 'duration')) + thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail') + + entries = [] + for i, video_file in enumerate(video_xml.findall('./track/video/file')): + video_key = self.parse_video_key(video_file.get('key', '')) + if not video_key: + continue + entries.append({ + 'id': '%s_%s' % (video_id, video_key.get('part', i + 1)), + 'title': title, + 'upload_date': video_key.get('upload_date'), + 'duration': int_or_none(video_file.get('duration')), + 'url': video_file.text, + }) + + info = { + 'id': video_id, + 'title': title, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'duration': duration, + 'thumbnail': thumbnail, + } + + if len(entries) > 1: + info['_type'] = 'multi_video' + info['entries'] = entries + elif len(entries) == 1: + info['url'] = entries[0]['url'] + info['upload_date'] = entries[0].get('upload_date') + else: + raise ExtractorError( + 'No files found for the specified AfreecaTV video, either' + ' the URL is incorrect or the video has been made private.', + expected=True) + + return info diff --git a/youtube_dl/extractor/aftonbladet.py b/youtube_dl/extractor/aftonbladet.py index d548592fe..5766b4fe8 100644 --- a/youtube_dl/extractor/aftonbladet.py +++ b/youtube_dl/extractor/aftonbladet.py @@ -24,10 +24,10 @@ class AftonbladetIE(InfoExtractor): webpage = self._download_webpage(url, video_id) # find internal video meta data - meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json' + meta_url = 'http://aftonbladet-play-metadata.cdn.drvideo.aptoma.no/video/%s.json' player_config = self._parse_json(self._html_search_regex( r'data-player-config="([^"]+)"', webpage, 'player config'), video_id) - internal_meta_id = player_config['videoId'] + internal_meta_id = player_config['aptomaVideoId'] internal_meta_url = meta_url % internal_meta_id internal_meta_json = self._download_json( internal_meta_url, video_id, 'Downloading video meta data') diff --git a/youtube_dl/extractor/amp.py b/youtube_dl/extractor/amp.py index 138fa0808..e8e40126b 100644 --- a/youtube_dl/extractor/amp.py +++ b/youtube_dl/extractor/amp.py @@ -5,6 +5,8 @@ from .common import InfoExtractor from ..utils import ( int_or_none, parse_iso8601, + mimetype2ext, + determine_ext, ) @@ -50,21 +52,25 @@ class AMPIE(InfoExtractor): if isinstance(media_content, dict): media_content = [media_content] for media_data in media_content: - media = media_data['@attributes'] - media_type = media['type'] - if media_type == 'video/f4m': + media = media_data.get('@attributes', {}) + media_url = media.get('url') + if not media_url: + continue + ext = mimetype2ext(media.get('type')) or determine_ext(media_url) + if ext == 'f4m': formats.extend(self._extract_f4m_formats( - media['url'] + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', + media_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id, f4m_id='hds', fatal=False)) - elif media_type == 'application/x-mpegURL': + elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - media['url'], video_id, 'mp4', m3u8_id='hls', fatal=False)) + media_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) else: formats.append({ - 'format_id': media_data['media-category']['@attributes']['label'], + 'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'), 'url': media['url'], 'tbr': int_or_none(media.get('bitrate')), 'filesize': int_or_none(media.get('fileSize')), + 'ext': ext, }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/animeondemand.py b/youtube_dl/extractor/animeondemand.py index 9b01e38f5..159c6ef5a 100644 --- a/youtube_dl/extractor/animeondemand.py +++ b/youtube_dl/extractor/animeondemand.py @@ -22,6 +22,7 @@ class AnimeOnDemandIE(InfoExtractor): _APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply' _NETRC_MACHINE = 'animeondemand' _TESTS = [{ + # jap, OmU 'url': 'https://www.anime-on-demand.de/anime/161', 'info_dict': { 'id': '161', @@ -30,17 +31,21 @@ class AnimeOnDemandIE(InfoExtractor): }, 'playlist_mincount': 4, }, { - # Film wording is used instead of Episode + # Film wording is used instead of Episode, ger/jap, Dub/OmU 'url': 'https://www.anime-on-demand.de/anime/39', 'only_matching': True, }, { - # Episodes without titles + # Episodes without titles, jap, OmU 'url': 'https://www.anime-on-demand.de/anime/162', 'only_matching': True, }, { # ger/jap, Dub/OmU, account required 'url': 'https://www.anime-on-demand.de/anime/169', 'only_matching': True, + }, { + # Full length film, non-series, ger/jap, Dub/OmU, account required + 'url': 'https://www.anime-on-demand.de/anime/185', + 'only_matching': True, }] def _login(self): @@ -110,35 +115,12 @@ class AnimeOnDemandIE(InfoExtractor): entries = [] - for num, episode_html in enumerate(re.findall( - r'(?s)]+class="episodebox-title".+?>Episodeninhalt<', webpage), 1): - episodebox_title = self._search_regex( - (r'class="episodebox-title"[^>]+title=(["\'])(?P.+?)\1', - r'class="episodebox-title"[^>]+>(?P<title>.+?)<'), - episode_html, 'episodebox title', default=None, group='title') - if not episodebox_title: - continue - - episode_number = int(self._search_regex( - r'(?:Episode|Film)\s*(\d+)', - episodebox_title, 'episode number', default=num)) - episode_title = self._search_regex( - r'(?:Episode|Film)\s*\d+\s*-\s*(.+)', - episodebox_title, 'episode title', default=None) - - video_id = 'episode-%d' % episode_number - - common_info = { - 'id': video_id, - 'series': anime_title, - 'episode': episode_title, - 'episode_number': episode_number, - } - + def extract_info(html, video_id, num=None): + title, description = [None] * 2 formats = [] for input_ in re.findall( - r'<input[^>]+class=["\'].*?streamstarter_html5[^>]+>', episode_html): + r'<input[^>]+class=["\'].*?streamstarter_html5[^>]+>', html): attributes = extract_attributes(input_) playlist_urls = [] for playlist_key in ('data-playlist', 'data-otherplaylist'): @@ -161,7 +143,7 @@ class AnimeOnDemandIE(InfoExtractor): format_id_list.append(lang) if kind: format_id_list.append(kind) - if not format_id_list: + if not format_id_list and num is not None: format_id_list.append(compat_str(num)) format_id = '-'.join(format_id_list) format_note = ', '.join(filter(None, (kind, lang_note))) @@ -215,28 +197,74 @@ class AnimeOnDemandIE(InfoExtractor): }) formats.extend(file_formats) - if formats: - self._sort_formats(formats) + return { + 'title': title, + 'description': description, + 'formats': formats, + } + + def extract_entries(html, video_id, common_info, num): + info = extract_info(html, video_id, num) + + if info['formats']: + self._sort_formats(info['formats']) f = common_info.copy() - f.update({ - 'title': title, - 'description': description, - 'formats': formats, - }) + f.update(info) entries.append(f) - # Extract teaser only when full episode is not available - if not formats: + # Extract teaser/trailer only when full episode is not available + if not info['formats']: m = re.search( - r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<', - episode_html) + r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>(?P<kind>Teaser|Trailer)<', + html) if m: f = common_info.copy() f.update({ - 'id': '%s-teaser' % f['id'], + 'id': '%s-%s' % (f['id'], m.group('kind').lower()), 'title': m.group('title'), 'url': compat_urlparse.urljoin(url, m.group('href')), }) entries.append(f) + def extract_episodes(html): + for num, episode_html in enumerate(re.findall( + r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', html), 1): + episodebox_title = self._search_regex( + (r'class="episodebox-title"[^>]+title=(["\'])(?P<title>.+?)\1', + r'class="episodebox-title"[^>]+>(?P<title>.+?)<'), + episode_html, 'episodebox title', default=None, group='title') + if not episodebox_title: + continue + + episode_number = int(self._search_regex( + r'(?:Episode|Film)\s*(\d+)', + episodebox_title, 'episode number', default=num)) + episode_title = self._search_regex( + r'(?:Episode|Film)\s*\d+\s*-\s*(.+)', + episodebox_title, 'episode title', default=None) + + video_id = 'episode-%d' % episode_number + + common_info = { + 'id': video_id, + 'series': anime_title, + 'episode': episode_title, + 'episode_number': episode_number, + } + + extract_entries(episode_html, video_id, common_info) + + def extract_film(html, video_id): + common_info = { + 'id': anime_id, + 'title': anime_title, + 'description': anime_description, + } + extract_entries(html, video_id, common_info) + + extract_episodes(webpage) + + if not entries: + extract_film(webpage, anime_id) + return self.playlist_result(entries, anime_id, anime_title, anime_description) diff --git a/youtube_dl/extractor/anvato.py b/youtube_dl/extractor/anvato.py new file mode 100644 index 000000000..cb29cf111 --- /dev/null +++ b/youtube_dl/extractor/anvato.py @@ -0,0 +1,224 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import base64 +import hashlib +import json +import random +import time + +from .common import InfoExtractor +from ..aes import aes_encrypt +from ..compat import compat_str +from ..utils import ( + bytes_to_intlist, + determine_ext, + intlist_to_bytes, + int_or_none, + strip_jsonp, +) + + +def md5_text(s): + if not isinstance(s, compat_str): + s = compat_str(s) + return hashlib.md5(s.encode('utf-8')).hexdigest() + + +class AnvatoIE(InfoExtractor): + # Copied from anvplayer.min.js + _ANVACK_TABLE = { + 'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ', + 'nbcu_nbcd_desktop_web_qa_1a6f01bdd0dc45a439043b694c8a031d': 'eSxJUbA2UUKBTXryyQ2d6NuM8oEqaPySvaPzfKNA', + 'nbcu_nbcd_desktop_web_acc_eb2ff240a5d4ae9a63d4c297c32716b6c523a129': '89JR3RtUGbvKuuJIiKOMK0SoarLb5MUx8v89RcbP', + 'nbcu_nbcd_watchvod_web_prod_e61107507180976724ec8e8319fe24ba5b4b60e1': 'Uc7dFt7MJ9GsBWB5T7iPvLaMSOt8BBxv4hAXk5vv', + 'nbcu_nbcd_watchvod_web_qa_42afedba88a36203db5a4c09a5ba29d045302232': 'T12oDYVFP2IaFvxkmYMy5dKxswpLHtGZa4ZAXEi7', + 'nbcu_nbcd_watchvod_web_acc_9193214448e2e636b0ffb78abacfd9c4f937c6ca': 'MmobcxUxMedUpohNWwXaOnMjlbiyTOBLL6d46ZpR', + 'nbcu_local_monitor_web_acc_f998ad54eaf26acd8ee033eb36f39a7b791c6335': 'QvfIoPYrwsjUCcASiw3AIkVtQob2LtJHfidp9iWg', + 'nbcu_cable_monitor_web_acc_a413759603e8bedfcd3c61b14767796e17834077': 'uwVPJLShvJWSs6sWEIuVem7MTF8A4IknMMzIlFto', + 'nbcu_nbcd_mcpstage_web_qa_4c43a8f6e95a88dbb40276c0630ba9f693a63a4e': 'PxVYZVwjhgd5TeoPRxL3whssb5OUPnM3zyAzq8GY', + 'nbcu_comcast_comcast_web_prod_074080762ad4ce956b26b43fb22abf153443a8c4': 'afnaRZfDyg1Z3WZHdupKfy6xrbAG2MHqe3VfuSwh', + 'nbcu_comcast_comcast_web_qa_706103bb93ead3ef70b1de12a0e95e3c4481ade0': 'DcjsVbX9b3uoPlhdriIiovgFQZVxpISZwz0cx1ZK', + 'nbcu_comcast_comcastcable_web_prod_669f04817536743563d7331c9293e59fbdbe3d07': '0RwMN2cWy10qhAhOscq3eK7aEe0wqnKt3vJ0WS4D', + 'nbcu_comcast_comcastcable_web_qa_3d9d2d66219094127f0f6b09cc3c7bb076e3e1ca': '2r8G9DEya7PCqBceKZgrn2XkXgASjwLMuaFE1Aad', + 'hearst_hearst_demo_web_stage_960726dfef3337059a01a78816e43b29ec04dfc7': 'cuZBPXTR6kSdoTCVXwk5KGA8rk3NrgGn4H6e9Dsp', + 'anvato_mcpqa_demo_web_stage_18b55e00db5a13faa8d03ae6e41f6f5bcb15b922': 'IOaaLQ8ymqVyem14QuAvE5SndQynTcH5CrLkU2Ih', + 'anvato_nextmedia_demo_web_stage_9787d56a02ff6b9f43e9a2b0920d8ca88beb5818': 'Pqu9zVzI1ApiIzbVA3VkGBEQHvdKSUuKpD6s2uaR', + 'anvato_scripps_app_web_prod_0837996dbe373629133857ae9eb72e740424d80a': 'du1ccmn7RxzgizwbWU7hyUaGodNlJn7HtXI0WgXW', + 'anvato_scripps_app_web_stage_360797e00fe2826be142155c4618cc52fce6c26c': '2PMrQ0BRoqCWl7nzphj0GouIMEh2mZYivAT0S1Su', + 'fs2go_fs2go_go_all_prod_21934911ccfafc03a075894ead2260d11e2ddd24': 'RcuHlKikW2IJw6HvVoEkqq2UsuEJlbEl11pWXs4Q', + 'fs2go_fs2go_go_web_prod_ead4b0eec7460c1a07783808db21b49cf1f2f9a7': '4K0HTT2u1zkQA2MaGaZmkLa1BthGSBdr7jllrhk5', + 'fs2go_fs2go_go_web_stage_407585454a4400355d4391691c67f361': 'ftnc37VKRJBmHfoGGi3kT05bHyeJzilEzhKJCyl3', + 'fs2go_fs2go_go_android_stage_44b714db6f8477f29afcba15a41e1d30': 'CtxpPvVpo6AbZGomYUhkKs7juHZwNml9b9J0J2gI', + 'anvato_cbslocal_app_web_prod_547f3e49241ef0e5d30c79b2efbca5d92c698f67': 'Pw0XX5KBDsyRnPS0R2JrSrXftsy8Jnz5pAjaYC8s', + 'anvato_cbslocal_app_web_stage_547a5f096594cd3e00620c6f825cad1096d28c80': '37OBUhX2uwNyKhhrNzSSNHSRPZpApC3trdqDBpuz', + 'fs2go_att_att_web_prod_1042dddd089a05438b6a08f972941176f699ffd8': 'JLcF20JwYvpv6uAGcLWIaV12jKwaL1R8us4b6Zkg', + 'fs2go_att_att_web_stage_807c5001955fc114a3331fe027ddc76e': 'gbu1oO1y0JiOFh4SUipt86P288JHpyjSqolrrT1x', + 'fs2go_fs2go_tudor_web_prod_a7dd8e5a7cdc830cae55eae6f3e9fee5ee49eb9b': 'ipcp87VCEZXPPe868j3orLqzc03oTy7DXsGkAXXH', + 'anvato_mhz_app_web_prod_b808218b30de7fdf60340cbd9831512bc1bf6d37': 'Stlm5Gs6BEhJLRTZHcNquyzxGqr23EuFmE5DCgjX', + 'fs2go_charter_charter_web_stage_c2c6e5a68375a1bf00fff213d3ff8f61a835a54c': 'Lz4hbJp1fwL6jlcz4M2PMzghM4jp4aAmybtT5dPc', + 'fs2go_charter_charter_web_prod_ebfe3b10f1af215a7321cd3d629e0b81dfa6fa8c': 'vUJsK345A1bVmyYDRhZX0lqFIgVXuqhmuyp1EtPK', + 'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b': 'GDKq1ixvX3MoBNdU5IOYmYa2DTUXYOozPjrCJnW7', + 'anvato_epfox_app_web_stage_a3c2ce60f8f83ef374a88b68ee73a950f8ab87ce': '2jz2NH4BsXMaDsoJ5qkHMbcczAfIReo2eFYuVC1C', + 'fs2go_verizon_verizon_web_stage_08e6df0354a4803f1b1f2428b5a9a382e8dbcd62': 'rKTVapNaAcmnUbGL4ZcuOoY4SE7VmZSQsblPFr7e', + 'fs2go_verizon_verizon_web_prod_f909564cb606eff1f731b5e22e0928676732c445': 'qLSUuHerM3u9eNPzaHyUK52obai5MvE4XDJfqYe1', + 'fs2go_foxcom_synd_web_stage_f7b9091f00ea25a4fdaaae77fca5b54cdc7e7043': '96VKF2vLd24fFiDfwPFpzM5llFN4TiIGAlodE0Re', + 'fs2go_foxcom_synd_web_prod_0f2cdd64d87e4ab6a1d54aada0ff7a7c8387a064': 'agiPjbXEyEZUkbuhcnmVPhe9NNVbDjCFq2xkcx51', + 'anvato_own_app_web_stage_1214ade5d28422c4dae9d03c1243aba0563c4dba': 'mzhamNac3swG4WsJAiUTacnGIODi6SWeVWk5D7ho', + 'anvato_own_app_web_prod_944e162ed927ec3e9ed13eb68ed2f1008ee7565e': '9TSxh6G2TXOLBoYm9ro3LdNjjvnXpKb8UR8KoIP9', + 'anvato_scripps_app_ftv_prod_a10a10468edd5afb16fb48171c03b956176afad1': 'COJ2i2UIPK7xZqIWswxe7FaVBOVgRkP1F6O6qGoH', + 'anvato_scripps_app_ftv_stage_77d3ad2bdb021ec37ca2e35eb09acd396a974c9a': 'Q7nnopNLe2PPfGLOTYBqxSaRpl209IhqaEuDZi1F', + 'anvato_univision_app_web_stage_551236ef07a0e17718c3995c35586b5ed8cb5031': 'D92PoLS6UitwxDRA191HUGT9OYcOjV6mPMa5wNyo', + 'anvato_univision_app_web_prod_039a5c0a6009e637ae8ac906718a79911e0e65e1': '5mVS5u4SQjtw6NGw2uhMbKEIONIiLqRKck5RwQLR', + 'nbcu_cnbc_springfield_ios_prod_670207fae43d6e9a94c351688851a2ce': 'M7fqCCIP9lW53oJbHs19OlJlpDrVyc2OL8gNeuTa', + 'nbcu_cnbc_springfieldvod_ios_prod_7a5f04b1ceceb0e9c9e2264a44aa236e08e034c2': 'Yia6QbJahW0S7K1I0drksimhZb4UFq92xLBmmMvk', + 'anvato_cox_app_web_prod_ce45cda237969f93e7130f50ee8bb6280c1484ab': 'cc0miZexpFtdoqZGvdhfXsLy7FXjRAOgb9V0f5fZ', + 'anvato_cox_app_web_stage_c23dbe016a8e9d8c7101d10172b92434f6088bf9': 'yivU3MYHd2eDZcOfmLbINVtqxyecKTOp8OjOuoGJ', + 'anvato_chnzero_app_web_stage_b1164d1352b579e792e542fddf13ee34c0eeb46b': 'A76QkXMmVH8lTCfU15xva1mZnSVcqeY4Xb22Kp7m', + 'anvato_chnzero_app_web_prod_253d358928dc08ec161eda2389d53707288a730c': 'OA5QI3ZWZZkdtUEDqh28AH8GedsF6FqzJI32596b', + 'anvato_discovery_vodpoc_web_stage_9fa7077b5e8af1f8355f65d4fb8d2e0e9d54e2b7': 'q3oT191tTQ5g3JCP67PkjLASI9s16DuWZ6fYmry3', + 'anvato_discovery_vodpoc_web_prod_688614983167a1af6cdf6d76343fda10a65223c1': 'qRvRQCTVHd0VVOHsMvvfidyWmlYVrTbjby7WqIuK', + 'nbcu_cnbc_springfieldvod_ftv_stage_826040aad1925a46ac5dfb4b3c5143e648c6a30d': 'JQaSb5a8Tz0PT4ti329DNmzDO30TnngTHmvX8Vua', + 'nbcu_cnbc_springfield_ftv_stage_826040aad1925a46ac5dfb4b3c5143e648c6a30d': 'JQaSb5a8Tz0PT4ti329DNmzDO30TnngTHmvX8Vua', + 'nbcu_nbcd_capture_web_stage_4dd9d585bfb984ebf856dee35db027b2465cc4ae': '0j1Ov4Vopyi2HpBZJYdL2m8ERJVGYh3nNpzPiO8F', + 'nbcu_nbcd_watch3_android_prod_7712ca5fcf1c22f19ec1870a9650f9c37db22dcf': '3LN2UB3rPUAMu7ZriWkHky9vpLMXYha8JbSnxBlx', + 'nbcu_nbcd_watchvod3_android_prod_0910a3a4692d57c0b5ff4316075bc5d096be45b9': 'mJagcQ2II30vUOAauOXne7ERwbf5S9nlB3IP17lQ', + 'anvato_scripps_app_atv_prod_790deda22e16e71e83df58f880cd389908a45d52': 'CB6trI1mpoDIM5o54DNTsji90NDBQPZ4z4RqBNSH', + 'nbcu_nbcd_watchv4_android_prod_ff67cef9cb409158c6f8c3533edddadd0b750507': 'j8CHQCUWjlYERj4NFRmUYOND85QNbHViH09UwuKm', + 'nbcu_nbcd_watchvodv4_android_prod_a814d781609989dea6a629d50ae4c7ad8cc8e907': 'rkVnUXxdA9rawVLUlDQtMue9Y4Q7lFEaIotcUhjt', + 'rvVKpA50qlOPLFxMjrCGf5pdkdQDm7qn': '1J7ZkY5Qz5lMLi93QOH9IveE7EYB3rLl', + 'nbcu_dtv_local_web_prod_b266cf49defe255fd4426a97e27c09e513e9f82f': 'HuLnJDqzLa4saCzYMJ79zDRSQpEduw1TzjMNQu2b', + 'nbcu_att_local_web_prod_4cef038b2d969a6b7d700a56a599040b6a619f67': 'Q0Em5VDc2KpydUrVwzWRXAwoNBulWUxCq2faK0AV', + 'nbcu_dish_local_web_prod_c56dcaf2da2e9157a4266c82a78195f1dd570f6b': 'bC1LWmRz9ayj2AlzizeJ1HuhTfIaJGsDBnZNgoRg', + 'nbcu_verizon_local_web_prod_88bebd2ce006d4ed980de8133496f9a74cb9b3e1': 'wzhDKJZpgvUSS1EQvpCQP8Q59qVzcPixqDGJefSk', + 'nbcu_charter_local_web_prod_9ad90f7fc4023643bb718f0fe0fd5beea2382a50': 'PyNbxNhEWLzy1ZvWEQelRuIQY88Eub7xbSVRMdfT', + 'nbcu_suddenlink_local_web_prod_20fb711725cac224baa1c1cb0b1c324d25e97178': '0Rph41lPXZbb3fqeXtHjjbxfSrNbtZp1Ygq7Jypa', + 'nbcu_wow_local_web_prod_652d9ce4f552d9c2e7b5b1ed37b8cb48155174ad': 'qayIBZ70w1dItm2zS42AptXnxW15mkjRrwnBjMPv', + 'nbcu_centurylink_local_web_prod_2034402b029bf3e837ad46814d9e4b1d1345ccd5': 'StePcPMkjsX51PcizLdLRMzxMEl5k2FlsMLUNV4k', + 'nbcu_atlanticbrd_local_web_prod_8d5f5ecbf7f7b2f5e6d908dd75d90ae3565f682e': 'NtYLb4TFUS0pRs3XTkyO5sbVGYjVf17bVbjaGscI', + 'nbcu_nbcd_watchvod_web_dev_08bc05699be47c4f31d5080263a8cfadc16d0f7c': 'hwxi2dgDoSWgfmVVXOYZm14uuvku4QfopstXckhr', + 'anvato_nextmedia_app_web_prod_a4fa8c7204aa65e71044b57aaf63711980cfe5a0': 'tQN1oGPYY1nM85rJYePWGcIb92TG0gSqoVpQTWOw', + 'anvato_mcp_lin_web_prod_4c36fbfd4d8d8ecae6488656e21ac6d1ac972749': 'GUXNf5ZDX2jFUpu4WT2Go4DJ5nhUCzpnwDRRUx1K', + 'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa': 'bLDYF8JqfG42b7bwKEgQiU9E2LTIAtnKzSgYpFUH', + 'anvato_mcp_fs2go_web_prod_c7b90a93e171469cdca00a931211a2f556370d0a': 'icgGoYGipQMMSEvhplZX1pwbN69srwKYWksz3xWK', + 'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336': 'fA2iQdI7RDpynqzQYIpXALVS83NTPr8LLFK4LFsu', + 'anvato_mcp_anv_web_prod_791407490f4c1ef2a4bcb21103e0cb1bcb3352b3': 'rMOUZqe9lwcGq2mNgG3EDusm6lKgsUnczoOX3mbg', + 'anvato_mcp_gray_web_prod_4c10f067c393ed8fc453d3930f8ab2b159973900': 'rMOUZqe9lwcGq2mNgG3EDusm6lKgsUnczoOX3mbg', + 'anvato_mcp_hearst_web_prod_5356c3de0fc7c90a3727b4863ca7fec3a4524a99': 'P3uXJ0fXXditBPCGkfvlnVScpPEfKmc64Zv7ZgbK', + 'anvato_mcp_cbs_web_prod_02f26581ff80e5bda7aad28226a8d369037f2cbe': 'mGPvo5ZA5SgjOFAPEPXv7AnOpFUICX8hvFQVz69n', + 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582': 'qyT6PXXLjVNCrHaRVj0ugAhalNRS7Ee9BP7LUokD', + 'nbcu_nbcd_watchvodv4_web_stage_4108362fba2d4ede21f262fea3c4162cbafd66c7': 'DhaU5lj0W2gEdcSSsnxURq8t7KIWtJfD966crVDk', + 'anvato_scripps_app_ios_prod_409c41960c60b308db43c3cc1da79cab9f1c3d93': 'WPxj5GraLTkYCyj3M7RozLqIycjrXOEcDGFMIJPn', + 'EZqvRyKBJLrgpClDPDF8I7Xpdp40Vx73': '4OxGd2dEakylntVKjKF0UK9PDPYB6A9W', + 'M2v78QkpleXm9hPp9jUXI63x5vA6BogR': 'ka6K32k7ZALmpINkjJUGUo0OE42Md1BQ', + 'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ' + } + + _AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce' + + def __init__(self, *args, **kwargs): + super(AnvatoIE, self).__init__(*args, **kwargs) + self.__server_time = None + + def _server_time(self, access_key, video_id): + if self.__server_time is not None: + return self.__server_time + + self.__server_time = int(self._download_json( + self._api_prefix(access_key) + 'server_time?anvack=' + access_key, video_id, + note='Fetching server time')['server_time']) + + return self.__server_time + + def _api_prefix(self, access_key): + return 'https://tkx2-%s.anvato.net/rest/v2/' % ('prod' if 'prod' in access_key else 'stage') + + def _get_video_json(self, access_key, video_id): + # See et() in anvplayer.min.js, which is an alias of getVideoJSON() + video_data_url = self._api_prefix(access_key) + 'mcp/video/%s?anvack=%s' % (video_id, access_key) + server_time = self._server_time(access_key, video_id) + input_data = '%d~%s~%s' % (server_time, md5_text(video_data_url), md5_text(server_time)) + + auth_secret = intlist_to_bytes(aes_encrypt( + bytes_to_intlist(input_data[:64]), bytes_to_intlist(self._AUTH_KEY))) + + video_data_url += '&X-Anvato-Adst-Auth=' + base64.b64encode(auth_secret).decode('ascii') + anvrid = md5_text(time.time() * 1000 * random.random())[:30] + payload = { + 'api': { + 'anvrid': anvrid, + 'anvstk': md5_text('%s|%s|%d|%s' % ( + access_key, anvrid, server_time, self._ANVACK_TABLE[access_key])), + 'anvts': server_time, + }, + } + + return self._download_json( + video_data_url, video_id, transform_source=strip_jsonp, + data=json.dumps(payload).encode('utf-8')) + + def _extract_anvato_videos(self, webpage, video_id): + anvplayer_data = self._parse_json(self._html_search_regex( + r'<script[^>]+data-anvp=\'([^\']+)\'', webpage, + 'Anvato player data'), video_id) + + video_id = anvplayer_data['video'] + access_key = anvplayer_data['accessKey'] + + video_data = self._get_video_json(access_key, video_id) + + formats = [] + for published_url in video_data['published_urls']: + video_url = published_url['embed_url'] + ext = determine_ext(video_url) + + if ext == 'smil': + formats.extend(self._extract_smil_formats(video_url, video_id)) + continue + + tbr = int_or_none(published_url.get('kbps')) + a_format = { + 'url': video_url, + 'format_id': ('-'.join(filter(None, ['http', published_url.get('cdn_name')]))).lower(), + 'tbr': tbr if tbr != 0 else None, + } + + if ext == 'm3u8': + # Not using _extract_m3u8_formats here as individual media + # playlists are also included in published_urls. + if tbr is None: + formats.append(self._m3u8_meta_format(video_url, ext='mp4', m3u8_id='hls')) + continue + else: + a_format.update({ + 'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])), + 'ext': 'mp4', + }) + elif ext == 'mp3': + a_format['vcodec'] = 'none' + else: + a_format.update({ + 'width': int_or_none(published_url.get('width')), + 'height': int_or_none(published_url.get('height')), + }) + formats.append(a_format) + + self._sort_formats(formats) + + subtitles = {} + for caption in video_data.get('captions', []): + a_caption = { + 'url': caption['url'], + 'ext': 'tt' if caption.get('format') == 'SMPTE-TT' else None + } + subtitles.setdefault(caption['language'], []).append(a_caption) + + return { + 'id': video_id, + 'formats': formats, + 'title': video_data.get('def_title'), + 'description': video_data.get('def_description'), + 'categories': video_data.get('categories'), + 'thumbnail': video_data.get('thumbnail'), + 'subtitles': subtitles, + } diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py index 24df8fe93..42c21bf41 100644 --- a/youtube_dl/extractor/aol.py +++ b/youtube_dl/extractor/aol.py @@ -12,7 +12,7 @@ from ..utils import ( class AolIE(InfoExtractor): IE_NAME = 'on.aol.com' - _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/.*-)(?P<id>[^/?-]+)' + _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P<id>[^/?#&]+)' _TESTS = [{ # video with 5min ID @@ -53,6 +53,12 @@ class AolIE(InfoExtractor): }, { 'url': 'http://on.aol.com/shows/park-bench-shw518173474-559a1b9be4b0c3bfad3357a7?context=SH:SHW518173474:PL4327:1460619712763', 'only_matching': True, + }, { + 'url': 'http://on.aol.com/video/519442220', + 'only_matching': True, + }, { + 'url': 'aol-video:5707d6b8e4b090497b04f706', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index be40f85b4..a6801f3d4 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -7,6 +7,8 @@ from .common import InfoExtractor from ..compat import compat_urlparse from ..utils import ( int_or_none, + parse_duration, + unified_strdate, ) @@ -16,7 +18,8 @@ class AppleTrailersIE(InfoExtractor): _TESTS = [{ 'url': 'http://trailers.apple.com/trailers/wb/manofsteel/', 'info_dict': { - 'id': 'manofsteel', + 'id': '5111', + 'title': 'Man of Steel', }, 'playlist': [ { @@ -70,6 +73,15 @@ class AppleTrailersIE(InfoExtractor): 'id': 'blackthorn', }, 'playlist_mincount': 2, + 'expected_warnings': ['Unable to download JSON metadata'], + }, { + # json data only available from http://trailers.apple.com/trailers/feeds/data/15881.json + 'url': 'http://trailers.apple.com/trailers/fox/kungfupanda3/', + 'info_dict': { + 'id': '15881', + 'title': 'Kung Fu Panda 3', + }, + 'playlist_mincount': 4, }, { 'url': 'http://trailers.apple.com/ca/metropole/autrui/', 'only_matching': True, @@ -85,6 +97,45 @@ class AppleTrailersIE(InfoExtractor): movie = mobj.group('movie') uploader_id = mobj.group('company') + webpage = self._download_webpage(url, movie) + film_id = self._search_regex(r"FilmId\s*=\s*'(\d+)'", webpage, 'film id') + film_data = self._download_json( + 'http://trailers.apple.com/trailers/feeds/data/%s.json' % film_id, + film_id, fatal=False) + + if film_data: + entries = [] + for clip in film_data.get('clips', []): + clip_title = clip['title'] + + formats = [] + for version, version_data in clip.get('versions', {}).items(): + for size, size_data in version_data.get('sizes', {}).items(): + src = size_data.get('src') + if not src: + continue + formats.append({ + 'format_id': '%s-%s' % (version, size), + 'url': re.sub(r'_(\d+p.mov)', r'_h\1', src), + 'width': int_or_none(size_data.get('width')), + 'height': int_or_none(size_data.get('height')), + 'language': version[:2], + }) + self._sort_formats(formats) + + entries.append({ + 'id': movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', clip_title).lower(), + 'formats': formats, + 'title': clip_title, + 'thumbnail': clip.get('screen') or clip.get('thumb'), + 'duration': parse_duration(clip.get('runtime') or clip.get('faded')), + 'upload_date': unified_strdate(clip.get('posted')), + 'uploader_id': uploader_id, + }) + + page_data = film_data.get('page', {}) + return self.playlist_result(entries, film_id, page_data.get('movie_title')) + playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc') def fix_html(s): diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 26446c2fe..13a06396d 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -8,12 +8,12 @@ from .generic import GenericIE from ..utils import ( determine_ext, ExtractorError, - get_element_by_attribute, qualities, int_or_none, parse_duration, unified_strdate, xpath_text, + update_url_query, ) from ..compat import compat_etree_fromstring @@ -35,6 +35,7 @@ class ARDMediathekIE(InfoExtractor): # m3u8 download 'skip_download': True, }, + 'skip': 'HTTP Error 404: Not Found', }, { 'url': 'http://www.ardmediathek.de/tv/Tatort/Tatort-Scheinwelten-H%C3%B6rfassung-Video/Das-Erste/Video?documentId=29522730&bcastId=602916', 'md5': 'f4d98b10759ac06c0072bbcd1f0b9e3e', @@ -45,6 +46,7 @@ class ARDMediathekIE(InfoExtractor): 'description': 'md5:196392e79876d0ac94c94e8cdb2875f1', 'duration': 5252, }, + 'skip': 'HTTP Error 404: Not Found', }, { # audio 'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086', @@ -56,6 +58,7 @@ class ARDMediathekIE(InfoExtractor): 'description': 'md5:f6e39f3461f0e1f54bfa48c8875c86ef', 'duration': 3240, }, + 'skip': 'HTTP Error 404: Not Found', }, { 'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht', 'only_matching': True, @@ -114,11 +117,14 @@ class ARDMediathekIE(InfoExtractor): continue if ext == 'f4m': formats.extend(self._extract_f4m_formats( - stream_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', - video_id, preference=-1, f4m_id='hds', fatal=False)) + update_url_query(stream_url, { + 'hdcore': '3.1.1', + 'plugin': 'aasp-3.1.1.69.124' + }), + video_id, f4m_id='hds', fatal=False)) elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - stream_url, video_id, 'mp4', preference=1, m3u8_id='hls', fatal=False)) + stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) else: if server and server.startswith('rtmp'): f = { @@ -232,7 +238,8 @@ class ARDIE(InfoExtractor): 'title': 'Die Story im Ersten: Mission unter falscher Flagge', 'upload_date': '20140804', 'thumbnail': 're:^https?://.*\.jpg$', - } + }, + 'skip': 'HTTP Error 404: Not Found', } def _real_extract(self, url): @@ -274,41 +281,3 @@ class ARDIE(InfoExtractor): 'upload_date': upload_date, 'thumbnail': thumbnail, } - - -class SportschauIE(ARDMediathekIE): - IE_NAME = 'Sportschau' - _VALID_URL = r'(?P<baseurl>https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video(?P<id>[^/#?]+))\.html' - _TESTS = [{ - 'url': 'http://www.sportschau.de/tourdefrance/videoseppeltkokainhatnichtsmitklassischemdopingzutun100.html', - 'info_dict': { - 'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100', - 'ext': 'mp4', - 'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun"', - 'thumbnail': 're:^https?://.*\.jpg$', - 'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - base_url = mobj.group('baseurl') - - webpage = self._download_webpage(url, video_id) - title = get_element_by_attribute('class', 'headline', webpage) - description = self._html_search_meta('description', webpage, 'description') - - info = self._extract_media_info( - base_url + '-mc_defaultQuality-h.json', webpage, video_id) - - info.update({ - 'title': title, - 'description': description, - }) - - return info diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index a9e3266dc..e0c5c1804 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -61,10 +61,7 @@ class ArteTvIE(InfoExtractor): } -class ArteTVPlus7IE(InfoExtractor): - IE_NAME = 'arte.tv:+7' - _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&+])' - +class ArteTVBaseIE(InfoExtractor): @classmethod def _extract_url_info(cls, url): mobj = re.match(cls._VALID_URL, url) @@ -78,60 +75,6 @@ class ArteTVPlus7IE(InfoExtractor): video_id = mobj.group('id') return video_id, lang - def _real_extract(self, url): - video_id, lang = self._extract_url_info(url) - webpage = self._download_webpage(url, video_id) - return self._extract_from_webpage(webpage, video_id, lang) - - def _extract_from_webpage(self, webpage, video_id, lang): - patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']') - ids = (video_id, '') - # some pages contain multiple videos (like - # http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D), - # so we first try to look for json URLs that contain the video id from - # the 'vid' parameter. - patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates] - json_url = self._html_search_regex( - patterns, webpage, 'json vp url', default=None) - if not json_url: - def find_iframe_url(webpage, default=NO_DEFAULT): - return self._html_search_regex( - r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1', - webpage, 'iframe url', group='url', default=default) - - iframe_url = find_iframe_url(webpage, None) - if not iframe_url: - embed_url = self._html_search_regex( - r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None) - if embed_url: - player = self._download_json( - embed_url, video_id, 'Downloading player page') - iframe_url = find_iframe_url(player['html']) - # en and es URLs produce react-based pages with different layout (e.g. - # http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world) - if not iframe_url: - program = self._search_regex( - r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n', - webpage, 'program', default=None) - if program: - embed_html = self._parse_json(program, video_id) - if embed_html: - iframe_url = find_iframe_url(embed_html['embed_html']) - if iframe_url: - json_url = compat_parse_qs( - compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] - if json_url: - title = self._search_regex( - r'<h3[^>]+title=(["\'])(?P<title>.+?)\1', - webpage, 'title', default=None, group='title') - return self._extract_from_json_url(json_url, video_id, lang, title=title) - # Different kind of embed URL (e.g. - # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium) - embed_url = self._search_regex( - r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', - webpage, 'embed url', group='url') - return self.url_result(embed_url) - def _extract_from_json_url(self, json_url, video_id, lang, title=None): info = self._download_json(json_url, video_id) player_info = info['videoJsonPlayer'] @@ -161,24 +104,53 @@ class ArteTVPlus7IE(InfoExtractor): 'es': 'E[ESP]', } + langcode = LANGS.get(lang, lang) + formats = [] for format_id, format_dict in player_info['VSR'].items(): f = dict(format_dict) versionCode = f.get('versionCode') - langcode = LANGS.get(lang, lang) - lang_rexs = [r'VO?%s-' % re.escape(langcode), r'VO?.-ST%s$' % re.escape(langcode)] - lang_pref = None - if versionCode: - matched_lang_rexs = [r for r in lang_rexs if re.match(r, versionCode)] - lang_pref = -10 if not matched_lang_rexs else 10 * len(matched_lang_rexs) - source_pref = 0 - if versionCode is not None: - # The original version with subtitles has lower relevance - if re.match(r'VO-ST(F|A|E)', versionCode): - source_pref -= 10 - # The version with sourds/mal subtitles has also lower relevance - elif re.match(r'VO?(F|A|E)-STM\1', versionCode): - source_pref -= 9 + l = re.escape(langcode) + + # Language preference from most to least priority + # Reference: section 5.6.3 of + # http://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-05.pdf + PREFERENCES = ( + # original version in requested language, without subtitles + r'VO{0}$'.format(l), + # original version in requested language, with partial subtitles in requested language + r'VO{0}-ST{0}$'.format(l), + # original version in requested language, with subtitles for the deaf and hard-of-hearing in requested language + r'VO{0}-STM{0}$'.format(l), + # non-original (dubbed) version in requested language, without subtitles + r'V{0}$'.format(l), + # non-original (dubbed) version in requested language, with subtitles partial subtitles in requested language + r'V{0}-ST{0}$'.format(l), + # non-original (dubbed) version in requested language, with subtitles for the deaf and hard-of-hearing in requested language + r'V{0}-STM{0}$'.format(l), + # original version in requested language, with partial subtitles in different language + r'VO{0}-ST(?!{0}).+?$'.format(l), + # original version in requested language, with subtitles for the deaf and hard-of-hearing in different language + r'VO{0}-STM(?!{0}).+?$'.format(l), + # original version in different language, with partial subtitles in requested language + r'VO(?:(?!{0}).+?)?-ST{0}$'.format(l), + # original version in different language, with subtitles for the deaf and hard-of-hearing in requested language + r'VO(?:(?!{0}).+?)?-STM{0}$'.format(l), + # original version in different language, without subtitles + r'VO(?:(?!{0}))?$'.format(l), + # original version in different language, with partial subtitles in different language + r'VO(?:(?!{0}).+?)?-ST(?!{0}).+?$'.format(l), + # original version in different language, with subtitles for the deaf and hard-of-hearing in different language + r'VO(?:(?!{0}).+?)?-STM(?!{0}).+?$'.format(l), + ) + + for pref, p in enumerate(PREFERENCES): + if re.match(p, versionCode): + lang_pref = len(PREFERENCES) - pref + break + else: + lang_pref = -1 + format = { 'format_id': format_id, 'preference': -10 if f.get('videoFormat') == 'M3U8' else None, @@ -188,7 +160,6 @@ class ArteTVPlus7IE(InfoExtractor): 'height': int_or_none(f.get('height')), 'tbr': int_or_none(f.get('bitrate')), 'quality': qfunc(f.get('quality')), - 'source_preference': source_pref, } if f.get('mediaType') == 'rtmp': @@ -207,28 +178,94 @@ class ArteTVPlus7IE(InfoExtractor): return info_dict +class ArteTVPlus7IE(ArteTVBaseIE): + IE_NAME = 'arte.tv:+7' + _VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/[^/]+/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)' + + _TESTS = [{ + 'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D', + 'only_matching': True, + }, { + 'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if ArteTVPlaylistIE.suitable(url) else super(ArteTVPlus7IE, cls).suitable(url) + + def _real_extract(self, url): + video_id, lang = self._extract_url_info(url) + webpage = self._download_webpage(url, video_id) + return self._extract_from_webpage(webpage, video_id, lang) + + def _extract_from_webpage(self, webpage, video_id, lang): + patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']') + ids = (video_id, '') + # some pages contain multiple videos (like + # http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D), + # so we first try to look for json URLs that contain the video id from + # the 'vid' parameter. + patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates] + json_url = self._html_search_regex( + patterns, webpage, 'json vp url', default=None) + if not json_url: + def find_iframe_url(webpage, default=NO_DEFAULT): + return self._html_search_regex( + r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1', + webpage, 'iframe url', group='url', default=default) + + iframe_url = find_iframe_url(webpage, None) + if not iframe_url: + embed_url = self._html_search_regex( + r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None) + if embed_url: + player = self._download_json( + embed_url, video_id, 'Downloading player page') + iframe_url = find_iframe_url(player['html']) + # en and es URLs produce react-based pages with different layout (e.g. + # http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world) + if not iframe_url: + program = self._search_regex( + r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n', + webpage, 'program', default=None) + if program: + embed_html = self._parse_json(program, video_id) + if embed_html: + iframe_url = find_iframe_url(embed_html['embed_html']) + if iframe_url: + json_url = compat_parse_qs( + compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] + if json_url: + title = self._search_regex( + r'<h3[^>]+title=(["\'])(?P<title>.+?)\1', + webpage, 'title', default=None, group='title') + return self._extract_from_json_url(json_url, video_id, lang, title=title) + # Different kind of embed URL (e.g. + # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium) + entries = [ + self.url_result(url) + for _, url in re.findall(r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', webpage)] + return self.playlist_result(entries) + + # It also uses the arte_vp_url url from the webpage to extract the information class ArteTVCreativeIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:creative' _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)' _TESTS = [{ - 'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design', + 'url': 'http://creative.arte.tv/fr/episode/osmosis-episode-1', 'info_dict': { - 'id': '72176', + 'id': '057405-001-A', 'ext': 'mp4', - 'title': 'Folge 2 - Corporate Design', - 'upload_date': '20131004', + 'title': 'OSMOSIS - N\'AYEZ PLUS PEUR D\'AIMER (1)', + 'upload_date': '20150716', }, }, { 'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion', - 'info_dict': { - 'id': '160676', - 'ext': 'mp4', - 'title': 'Monty Python live (mostly)', - 'description': 'Événement ! Quarante-cinq ans après leurs premiers succès, les légendaires Monty Python remontent sur scène.\n', - 'upload_date': '20140805', - } + 'playlist_count': 11, + 'add_ie': ['Youtube'], }, { 'url': 'http://creative.arte.tv/de/episode/agentur-amateur-4-der-erste-kunde', 'only_matching': True, @@ -239,7 +276,7 @@ class ArteTVInfoIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:info' _VALID_URL = r'https?://info\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)' - _TEST = { + _TESTS = [{ 'url': 'http://info.arte.tv/fr/service-civique-un-cache-misere', 'info_dict': { 'id': '067528-000-A', @@ -247,7 +284,7 @@ class ArteTVInfoIE(ArteTVPlus7IE): 'title': 'Service civique, un cache misère ?', 'upload_date': '20160403', }, - } + }] class ArteTVFutureIE(ArteTVPlus7IE): @@ -272,6 +309,8 @@ class ArteTVDDCIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:ddc' _VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>[^/?#&]+)' + _TESTS = [] + def _real_extract(self, url): video_id, lang = self._extract_url_info(url) if lang == 'folge': @@ -290,7 +329,7 @@ class ArteTVConcertIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:concert' _VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)' - _TEST = { + _TESTS = [{ 'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde', 'md5': '9ea035b7bd69696b67aa2ccaaa218161', 'info_dict': { @@ -300,24 +339,23 @@ class ArteTVConcertIE(ArteTVPlus7IE): 'upload_date': '20140128', 'description': 'md5:486eb08f991552ade77439fe6d82c305', }, - } + }] class ArteTVCinemaIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:cinema' _VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)' - _TEST = { - 'url': 'http://cinema.arte.tv/de/node/38291', - 'md5': '6b275511a5107c60bacbeeda368c3aa1', + _TESTS = [{ + 'url': 'http://cinema.arte.tv/fr/article/les-ailes-du-desir-de-julia-reck', + 'md5': 'a5b9dd5575a11d93daf0e3f404f45438', 'info_dict': { - 'id': '055876-000_PWA12025-D', + 'id': '062494-000-A', 'ext': 'mp4', - 'title': 'Tod auf dem Nil', - 'upload_date': '20160122', - 'description': 'md5:7f749bbb77d800ef2be11d54529b96bc', + 'title': 'Film lauréat du concours web - "Les ailes du désir" de Julia Reck', + 'upload_date': '20150807', }, - } + }] class ArteTVMagazineIE(ArteTVPlus7IE): @@ -362,9 +400,42 @@ class ArteTVEmbedIE(ArteTVPlus7IE): ) ''' + _TESTS = [] + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') lang = mobj.group('lang') json_url = mobj.group('json_url') return self._extract_from_json_url(json_url, video_id, lang) + + +class ArteTVPlaylistIE(ArteTVBaseIE): + IE_NAME = 'arte.tv:playlist' + _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/[^#]*#collection/(?P<id>PL-\d+)' + + _TESTS = [{ + 'url': 'http://www.arte.tv/guide/de/plus7/?country=DE#collection/PL-013263/ARTETV', + 'info_dict': { + 'id': 'PL-013263', + 'title': 'Areva & Uramin', + 'description': 'md5:a1dc0312ce357c262259139cfd48c9bf', + }, + 'playlist_mincount': 6, + }, { + 'url': 'http://www.arte.tv/guide/de/playlists?country=DE#collection/PL-013190/ARTETV', + 'only_matching': True, + }] + + def _real_extract(self, url): + playlist_id, lang = self._extract_url_info(url) + collection = self._download_json( + 'https://api.arte.tv/api/player/v1/collectionData/%s/%s?source=videos' + % (lang, playlist_id), playlist_id) + title = collection.get('title') + description = collection.get('shortDescription') or collection.get('teaserText') + entries = [ + self._extract_from_json_url( + video['jsonUrl'], video.get('programId') or playlist_id, lang) + for video in collection['videos'] if video.get('jsonUrl')] + return self.playlist_result(entries, playlist_id, title, description) diff --git a/youtube_dl/extractor/audiomack.py b/youtube_dl/extractor/audiomack.py index a52d26cec..f3bd4d444 100644 --- a/youtube_dl/extractor/audiomack.py +++ b/youtube_dl/extractor/audiomack.py @@ -6,6 +6,7 @@ import time from .common import InfoExtractor from .soundcloud import SoundcloudIE +from ..compat import compat_str from ..utils import ( ExtractorError, url_basename, @@ -136,7 +137,7 @@ class AudiomackAlbumIE(InfoExtractor): result[resultkey] = api_response[apikey] song_id = url_basename(api_response['url']).rpartition('.')[0] result['entries'].append({ - 'id': api_response.get('id', song_id), + 'id': compat_str(api_response.get('id', song_id)), 'uploader': api_response.get('artist'), 'title': api_response.get('title', song_id), 'url': api_response['url'], diff --git a/youtube_dl/extractor/azubu.py b/youtube_dl/extractor/azubu.py index efa624de1..a813eb429 100644 --- a/youtube_dl/extractor/azubu.py +++ b/youtube_dl/extractor/azubu.py @@ -46,6 +46,7 @@ class AzubuIE(InfoExtractor): 'uploader_id': 272749, 'view_count': int, }, + 'skip': 'Channel offline', }, ] @@ -56,22 +57,26 @@ class AzubuIE(InfoExtractor): 'http://www.azubu.tv/api/video/%s' % video_id, video_id)['data'] title = data['title'].strip() - description = data['description'] - thumbnail = data['thumbnail'] - view_count = data['view_count'] - uploader = data['user']['username'] - uploader_id = data['user']['id'] + description = data.get('description') + thumbnail = data.get('thumbnail') + view_count = data.get('view_count') + user = data.get('user', {}) + uploader = user.get('username') + uploader_id = user.get('id') stream_params = json.loads(data['stream_params']) - timestamp = float_or_none(stream_params['creationDate'], 1000) - duration = float_or_none(stream_params['length'], 1000) + timestamp = float_or_none(stream_params.get('creationDate'), 1000) + duration = float_or_none(stream_params.get('length'), 1000) renditions = stream_params.get('renditions') or [] video = stream_params.get('FLVFullLength') or stream_params.get('videoFullLength') if video: renditions.append(video) + if not renditions and not user.get('channel', {}).get('is_live', True): + raise ExtractorError('%s said: channel is offline.' % self.IE_NAME, expected=True) + formats = [{ 'url': fmt['url'], 'width': fmt['frameWidth'], diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index c1ef8051d..991ab0676 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -29,7 +29,7 @@ class BandcampIE(InfoExtractor): '_skip': 'There is a limit of 200 free downloads / month for the test song' }, { 'url': 'http://benprunty.bandcamp.com/track/lanius-battle', - 'md5': '2b68e5851514c20efdff2afc5603b8b4', + 'md5': '73d0b3171568232574e45652f8720b5c', 'info_dict': { 'id': '2650410135', 'ext': 'mp3', @@ -48,6 +48,10 @@ class BandcampIE(InfoExtractor): if m_trackinfo: json_code = m_trackinfo.group(1) data = json.loads(json_code)[0] + track_id = compat_str(data['id']) + + if not data.get('file'): + raise ExtractorError('Not streamable', video_id=track_id, expected=True) formats = [] for format_id, format_url in data['file'].items(): @@ -64,7 +68,7 @@ class BandcampIE(InfoExtractor): self._sort_formats(formats) return { - 'id': compat_str(data['id']), + 'id': track_id, 'title': data['title'], 'formats': formats, 'duration': float_or_none(data.get('duration')), diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 74c4510f9..4b3cd8c65 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -31,7 +31,7 @@ class BBCCoUkIE(InfoExtractor): music/clips[/#]| radio/player/ ) - (?P<id>%s) + (?P<id>%s)(?!/(?:episodes|broadcasts|clips)) ''' % _ID_REGEX _MEDIASELECTOR_URLS = [ @@ -192,6 +192,7 @@ class BBCCoUkIE(InfoExtractor): # rtmp download 'skip_download': True, }, + 'skip': 'Now it\'s really geo-restricted', }, { # compact player (https://github.com/rg3/youtube-dl/issues/8147) 'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player', @@ -698,7 +699,9 @@ class BBCIE(BBCCoUkIE): @classmethod def suitable(cls, url): - return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url) + EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE) + return (False if any(ie.suitable(url) for ie in EXCLUDE_IE) + else super(BBCIE, cls).suitable(url)) def _extract_from_media_meta(self, media_meta, video_id): # Direct links to media in media metadata (e.g. @@ -975,3 +978,72 @@ class BBCCoUkArticleIE(InfoExtractor): r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)] return self.playlist_result(entries, playlist_id, title, description) + + +class BBCCoUkPlaylistBaseIE(InfoExtractor): + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key()) + for video_id in re.findall( + self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)] + + title, description = self._extract_title_and_description(webpage) + + return self.playlist_result(entries, playlist_id, title, description) + + +class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE): + IE_NAME = 'bbc.co.uk:iplayer:playlist' + _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/episodes/(?P<id>%s)' % BBCCoUkIE._ID_REGEX + _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s' + _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)' + _TEST = { + 'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v', + 'info_dict': { + 'id': 'b05rcz9v', + 'title': 'The Disappearance', + 'description': 'French thriller serial about a missing teenager.', + }, + 'playlist_mincount': 6, + } + + def _extract_title_and_description(self, webpage): + title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False) + description = self._search_regex( + r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>', + webpage, 'description', fatal=False, group='value') + return title, description + + +class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE): + IE_NAME = 'bbc.co.uk:playlist' + _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>%s)/(?:episodes|broadcasts|clips)' % BBCCoUkIE._ID_REGEX + _URL_TEMPLATE = 'http://www.bbc.co.uk/programmes/%s' + _VIDEO_ID_TEMPLATE = r'data-pid=["\'](%s)' + _TESTS = [{ + 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips', + 'info_dict': { + 'id': 'b05rcz9v', + 'title': 'The Disappearance - Clips - BBC Four', + 'description': 'French thriller serial about a missing teenager.', + }, + 'playlist_mincount': 7, + }, { + 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06', + 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips', + 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/programmes/b055jkys/episodes/player', + 'only_matching': True, + }] + + def _extract_title_and_description(self, webpage): + title = self._og_search_title(webpage, fatal=False) + description = self._og_search_description(webpage) + return title, description diff --git a/youtube_dl/extractor/bet.py b/youtube_dl/extractor/bet.py index 986245bf0..bd3ee2e2e 100644 --- a/youtube_dl/extractor/bet.py +++ b/youtube_dl/extractor/bet.py @@ -1,31 +1,27 @@ from __future__ import unicode_literals -from .common import InfoExtractor -from ..compat import compat_urllib_parse_unquote -from ..utils import ( - xpath_text, - xpath_with_ns, - int_or_none, - parse_iso8601, -) +from .mtv import MTVServicesInfoExtractor +from ..utils import unified_strdate +from ..compat import compat_urllib_parse_urlencode -class BetIE(InfoExtractor): +class BetIE(MTVServicesInfoExtractor): _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html' _TESTS = [ { 'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html', 'info_dict': { - 'id': 'news/national/2014/a-conversation-with-president-obama', + 'id': '07e96bd3-8850-3051-b856-271b457f0ab8', 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism', 'ext': 'flv', 'title': 'A Conversation With President Obama', - 'description': 'md5:699d0652a350cf3e491cd15cc745b5da', + 'description': 'President Obama urges persistence in confronting racism and bias.', 'duration': 1534, - 'timestamp': 1418075340, 'upload_date': '20141208', - 'uploader': 'admin', 'thumbnail': 're:(?i)^https?://.*\.jpg$', + 'subtitles': { + 'en': 'mincount:2', + } }, 'params': { # rtmp download @@ -35,16 +31,17 @@ class BetIE(InfoExtractor): { 'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html', 'info_dict': { - 'id': 'news/national/2014/justice-for-ferguson-a-community-reacts', + 'id': '9f516bf1-7543-39c4-8076-dd441b459ba9', 'display_id': 'justice-for-ferguson-a-community-reacts', 'ext': 'flv', 'title': 'Justice for Ferguson: A Community Reacts', 'description': 'A BET News special.', 'duration': 1696, - 'timestamp': 1416942360, 'upload_date': '20141125', - 'uploader': 'admin', 'thumbnail': 're:(?i)^https?://.*\.jpg$', + 'subtitles': { + 'en': 'mincount:2', + } }, 'params': { # rtmp download @@ -53,57 +50,32 @@ class BetIE(InfoExtractor): } ] - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - - media_url = compat_urllib_parse_unquote(self._search_regex( - [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"], - webpage, 'media URL')) + _FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player" - video_id = self._search_regex( - r'/video/(.*)/_jcr_content/', media_url, 'video id') + def _get_feed_query(self, uri): + return compat_urllib_parse_urlencode({ + 'uuid': uri, + }) - mrss = self._download_xml(media_url, display_id) - - item = mrss.find('./channel/item') - - NS_MAP = { - 'dc': 'http://purl.org/dc/elements/1.1/', - 'media': 'http://search.yahoo.com/mrss/', - 'ka': 'http://kickapps.com/karss', - } + def _extract_mgid(self, webpage): + return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid') - title = xpath_text(item, './title', 'title') - description = xpath_text( - item, './description', 'description', fatal=False) - - timestamp = parse_iso8601(xpath_text( - item, xpath_with_ns('./dc:date', NS_MAP), - 'upload date', fatal=False)) - uploader = xpath_text( - item, xpath_with_ns('./dc:creator', NS_MAP), - 'uploader', fatal=False) + def _real_extract(self, url): + display_id = self._match_id(url) - media_content = item.find( - xpath_with_ns('./media:content', NS_MAP)) - duration = int_or_none(media_content.get('duration')) - smil_url = media_content.get('url') + webpage = self._download_webpage(url, display_id) + mgid = self._extract_mgid(webpage) + videos_info = self._get_videos_info(mgid) - thumbnail = media_content.find( - xpath_with_ns('./media:thumbnail', NS_MAP)).get('url') + info_dict = videos_info['entries'][0] - formats = self._extract_smil_formats(smil_url, display_id) - self._sort_formats(formats) + upload_date = unified_strdate(self._html_search_meta('date', webpage)) + description = self._html_search_meta('description', webpage) - return { - 'id': video_id, + info_dict.update({ 'display_id': display_id, - 'title': title, 'description': description, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'uploader': uploader, - 'duration': duration, - 'formats': formats, - } + 'upload_date': upload_date, + }) + + return info_dict diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 8baff2041..b17047b39 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -1,34 +1,42 @@ # coding: utf-8 from __future__ import unicode_literals +import calendar +import datetime import re from .common import InfoExtractor -from ..compat import compat_str +from ..compat import ( + compat_etree_fromstring, + compat_str, + compat_parse_qs, + compat_xml_parse_error, +) from ..utils import ( - int_or_none, - unescapeHTML, ExtractorError, + int_or_none, + float_or_none, xpath_text, ) class BiliBiliIE(InfoExtractor): - _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?' + _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)' _TESTS = [{ 'url': 'http://www.bilibili.tv/video/av1074402/', - 'md5': '2c301e4dab317596e837c3e7633e7d86', + 'md5': '5f7d29e1a2872f3df0cf76b1f87d3788', 'info_dict': { 'id': '1554319', 'ext': 'flv', 'title': '【金坷垃】金泡沫', - 'duration': 308313, + 'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923', + 'duration': 308.067, + 'timestamp': 1398012660, 'upload_date': '20140420', 'thumbnail': 're:^https?://.+\.jpg', - 'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923', - 'timestamp': 1397983878, 'uploader': '菊子桑', + 'uploader_id': '156160', }, }, { 'url': 'http://www.bilibili.com/video/av1041170/', @@ -36,75 +44,186 @@ class BiliBiliIE(InfoExtractor): 'id': '1041170', 'title': '【BD1080P】刀语【诸神&异域】', 'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~', - 'uploader': '枫叶逝去', - 'timestamp': 1396501299, }, 'playlist_count': 9, + }, { + 'url': 'http://www.bilibili.com/video/av4808130/', + 'info_dict': { + 'id': '4808130', + 'title': '【长篇】哆啦A梦443【钉铛】', + 'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929', + }, + 'playlist': [{ + 'md5': '55cdadedf3254caaa0d5d27cf20a8f9c', + 'info_dict': { + 'id': '4808130_part1', + 'ext': 'flv', + 'title': '【长篇】哆啦A梦443【钉铛】', + 'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929', + 'timestamp': 1464564180, + 'upload_date': '20160529', + 'uploader': '喜欢拉面', + 'uploader_id': '151066', + }, + }, { + 'md5': '926f9f67d0c482091872fbd8eca7ea3d', + 'info_dict': { + 'id': '4808130_part2', + 'ext': 'flv', + 'title': '【长篇】哆啦A梦443【钉铛】', + 'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929', + 'timestamp': 1464564180, + 'upload_date': '20160529', + 'uploader': '喜欢拉面', + 'uploader_id': '151066', + }, + }, { + 'md5': '4b7b225b968402d7c32348c646f1fd83', + 'info_dict': { + 'id': '4808130_part3', + 'ext': 'flv', + 'title': '【长篇】哆啦A梦443【钉铛】', + 'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929', + 'timestamp': 1464564180, + 'upload_date': '20160529', + 'uploader': '喜欢拉面', + 'uploader_id': '151066', + }, + }, { + 'md5': '7b795e214166501e9141139eea236e91', + 'info_dict': { + 'id': '4808130_part4', + 'ext': 'flv', + 'title': '【长篇】哆啦A梦443【钉铛】', + 'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929', + 'timestamp': 1464564180, + 'upload_date': '20160529', + 'uploader': '喜欢拉面', + 'uploader_id': '151066', + }, + }], + }, { + # Missing upload time + 'url': 'http://www.bilibili.com/video/av1867637/', + 'info_dict': { + 'id': '2880301', + 'ext': 'flv', + 'title': '【HDTV】【喜剧】岳父岳母真难当 （2014）【法国票房冠军】', + 'description': '一个信奉天主教的法国旧式传统资产阶级家庭中有四个女儿。三个女儿却分别找了阿拉伯、犹太、中国丈夫，老夫老妻唯独期盼剩下未嫁的小女儿能找一个信奉天主教的法国白人，结果没想到小女儿找了一位非裔黑人……【这次应该不会跳帧了】', + 'uploader': '黑夜为猫', + 'uploader_id': '610729', + }, + 'params': { + # Just to test metadata extraction + 'skip_download': True, + }, + 'expected_warnings': ['upload time'], }] + # BiliBili blocks keys from time to time. The current key is extracted from + # the Android client + # TODO: find the sign algorithm used in the flash player + _APP_KEY = '86385cdc024c0f6c' + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - page_num = mobj.group('page_num') or '1' - view_data = self._download_json( - 'http://api.bilibili.com/view?type=json&appkey=8e9fc618fbd41e28&id=%s&page=%s' % (video_id, page_num), - video_id) - if 'error' in view_data: - raise ExtractorError('%s said: %s' % (self.IE_NAME, view_data['error']), expected=True) + webpage = self._download_webpage(url, video_id) - cid = view_data['cid'] - title = unescapeHTML(view_data['title']) + params = compat_parse_qs(self._search_regex( + [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)', + r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'], + webpage, 'player parameters')) + cid = params['cid'][0] - doc = self._download_xml( - 'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid, - cid, - 'Downloading page %s/%s' % (page_num, view_data['pages']) - ) + info_xml_str = self._download_webpage( + 'http://interface.bilibili.com/v_cdn_play', + cid, query={'appkey': self._APP_KEY, 'cid': cid}, + note='Downloading video info page') + + err_msg = None + durls = None + info_xml = None + try: + info_xml = compat_etree_fromstring(info_xml_str.encode('utf-8')) + except compat_xml_parse_error: + info_json = self._parse_json(info_xml_str, video_id, fatal=False) + err_msg = (info_json or {}).get('error_text') + else: + err_msg = xpath_text(info_xml, './message') - if xpath_text(doc, './result') == 'error': - raise ExtractorError('%s said: %s' % (self.IE_NAME, xpath_text(doc, './message')), expected=True) + if info_xml is not None: + durls = info_xml.findall('./durl') + if not durls: + if err_msg: + raise ExtractorError('%s said: %s' % (self.IE_NAME, err_msg), expected=True) + else: + raise ExtractorError('No videos found!') entries = [] - for durl in doc.findall('./durl'): + for durl in durls: size = xpath_text(durl, ['./filesize', './size']) formats = [{ 'url': durl.find('./url').text, 'filesize': int_or_none(size), - 'ext': 'flv', }] - backup_urls = durl.find('./backup_url') - if backup_urls is not None: - for backup_url in backup_urls.findall('./url'): - formats.append({'url': backup_url.text}) - formats.reverse() + for backup_url in durl.findall('./backup_url/url'): + formats.append({ + 'url': backup_url.text, + # backup URLs have lower priorities + 'preference': -2 if 'hd.mp4' in backup_url.text else -3, + }) + + self._sort_formats(formats) entries.append({ 'id': '%s_part%s' % (cid, xpath_text(durl, './order')), - 'title': title, 'duration': int_or_none(xpath_text(durl, './length'), 1000), 'formats': formats, }) + title = self._html_search_regex('<h1[^>]+title="([^"]+)">', webpage, 'title') + description = self._html_search_meta('description', webpage) + datetime_str = self._html_search_regex( + r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False) + timestamp = None + if datetime_str: + timestamp = calendar.timegm(datetime.datetime.strptime(datetime_str, '%Y-%m-%dT%H:%M').timetuple()) + + # TODO 'view_count' requires deobfuscating Javascript info = { 'id': compat_str(cid), 'title': title, - 'description': view_data.get('description'), - 'thumbnail': view_data.get('pic'), - 'uploader': view_data.get('author'), - 'timestamp': int_or_none(view_data.get('created')), - 'view_count': int_or_none(view_data.get('play')), - 'duration': int_or_none(xpath_text(doc, './timelength')), + 'description': description, + 'timestamp': timestamp, + 'thumbnail': self._html_search_meta('thumbnailUrl', webpage), + 'duration': float_or_none(xpath_text(info_xml, './timelength'), scale=1000), } + uploader_mobj = re.search( + r'<a[^>]+href="https?://space\.bilibili\.com/(?P<id>\d+)"[^>]+title="(?P<name>[^"]+)"', + webpage) + if uploader_mobj: + info.update({ + 'uploader': uploader_mobj.group('name'), + 'uploader_id': uploader_mobj.group('id'), + }) + + for entry in entries: + entry.update(info) + if len(entries) == 1: - entries[0].update(info) return entries[0] else: - info.update({ + for idx, entry in enumerate(entries): + entry['id'] = '%s_part%d' % (video_id, (idx + 1)) + + return { '_type': 'multi_video', 'id': video_id, + 'title': title, + 'description': description, 'entries': entries, - }) - return info + } diff --git a/youtube_dl/extractor/biqle.py b/youtube_dl/extractor/biqle.py new file mode 100644 index 000000000..ae4579b33 --- /dev/null +++ b/youtube_dl/extractor/biqle.py @@ -0,0 +1,39 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class BIQLEIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?biqle\.(?:com|org|ru)/watch/(?P<id>-?\d+_\d+)' + _TESTS = [{ + 'url': 'http://www.biqle.ru/watch/847655_160197695', + 'md5': 'ad5f746a874ccded7b8f211aeea96637', + 'info_dict': { + 'id': '160197695', + 'ext': 'mp4', + 'title': 'Foo Fighters - The Pretender (Live at Wembley Stadium)', + 'uploader': 'Andrey Rogozin', + 'upload_date': '20110605', + } + }, { + 'url': 'https://biqle.org/watch/-44781847_168547604', + 'md5': '7f24e72af1db0edf7c1aaba513174f97', + 'info_dict': { + 'id': '168547604', + 'ext': 'mp4', + 'title': 'Ребенок в шоке от автоматической мойки', + 'uploader': 'Dmitry Kotov', + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + embed_url = self._proto_relative_url(self._search_regex( + r'<iframe.+?src="((?:http:)?//daxab\.com/[^"]+)".*?></iframe>', webpage, 'embed url')) + + return { + '_type': 'url_transparent', + 'url': embed_url, + } diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 13343bc25..bd538be50 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -17,6 +17,9 @@ class BloombergIE(InfoExtractor): 'title': 'Shah\'s Presentation on Foreign-Exchange Strategies', 'description': 'md5:a8ba0302912d03d246979735c17d2761', }, + 'params': { + 'format': 'best[format_id^=hds]', + }, }, { 'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets', 'only_matching': True, diff --git a/youtube_dl/extractor/br.py b/youtube_dl/extractor/br.py index 11cf49851..ff0aa11b1 100644 --- a/youtube_dl/extractor/br.py +++ b/youtube_dl/extractor/br.py @@ -29,7 +29,8 @@ class BRIE(InfoExtractor): 'duration': 180, 'uploader': 'Reinhard Weber', 'upload_date': '20150422', - } + }, + 'skip': '404 not found', }, { 'url': 'http://www.br.de/nachrichten/oberbayern/inhalt/muenchner-polizeipraesident-schreiber-gestorben-100.html', @@ -40,7 +41,8 @@ class BRIE(InfoExtractor): 'title': 'Manfred Schreiber ist tot', 'description': 'md5:b454d867f2a9fc524ebe88c3f5092d97', 'duration': 26, - } + }, + 'skip': '404 not found', }, { 'url': 'https://www.br-klassik.de/audio/peeping-tom-premierenkritik-dance-festival-muenchen-100.html', @@ -51,7 +53,8 @@ class BRIE(InfoExtractor): 'title': 'Kurzweilig und sehr bewegend', 'description': 'md5:0351996e3283d64adeb38ede91fac54e', 'duration': 296, - } + }, + 'skip': '404 not found', }, { 'url': 'http://www.br.de/radio/bayern1/service/team/videos/team-video-erdelt100.html', diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index f0781fc27..57ce0c174 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -90,6 +90,7 @@ class BrightcoveLegacyIE(InfoExtractor): 'description': 'md5:363109c02998fee92ec02211bd8000df', 'uploader': 'National Ballet of Canada', }, + 'skip': 'Video gone', }, { # test flv videos served by akamaihd.net @@ -108,7 +109,7 @@ class BrightcoveLegacyIE(InfoExtractor): }, }, { - # playlist test + # playlist with 'videoList' # from http://support.brightcove.com/en/video-cloud/docs/playlist-support-single-video-players 'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=3550052898001&playerKey=AQ%7E%7E%2CAAABmA9XpXk%7E%2C-Kp7jNgisre1fG5OdqpAFUTcs0lP_ZoL', 'info_dict': { @@ -117,6 +118,15 @@ class BrightcoveLegacyIE(InfoExtractor): }, 'playlist_mincount': 7, }, + { + # playlist with 'playlistTab' (https://github.com/rg3/youtube-dl/issues/9965) + 'url': 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=AQ%7E%7E,AAABXlLMdok%7E,NJ4EoMlZ4rZdx9eU1rkMVd8EaYPBBUlg', + 'info_dict': { + 'id': '1522758701001', + 'title': 'Lesson 08', + }, + 'playlist_mincount': 10, + }, ] FLV_VCODECS = { 1: 'SORENSON', @@ -298,18 +308,25 @@ class BrightcoveLegacyIE(InfoExtractor): info_url, player_key, 'Downloading playlist information') json_data = json.loads(playlist_info) - if 'videoList' not in json_data: + if 'videoList' in json_data: + playlist_info = json_data['videoList'] + playlist_dto = playlist_info['mediaCollectionDTO'] + elif 'playlistTabs' in json_data: + playlist_info = json_data['playlistTabs'] + playlist_dto = playlist_info['lineupListDTO']['playlistDTOs'][0] + else: raise ExtractorError('Empty playlist') - playlist_info = json_data['videoList'] - videos = [self._extract_video_info(video_info) for video_info in playlist_info['mediaCollectionDTO']['videoDTOs']] + + videos = [self._extract_video_info(video_info) for video_info in playlist_dto['videoDTOs']] return self.playlist_result(videos, playlist_id='%s' % playlist_info['id'], - playlist_title=playlist_info['mediaCollectionDTO']['displayName']) + playlist_title=playlist_dto['displayName']) def _extract_video_info(self, video_info): + video_id = compat_str(video_info['id']) publisher_id = video_info.get('publisherId') info = { - 'id': compat_str(video_info['id']), + 'id': video_id, 'title': video_info['displayName'].strip(), 'description': video_info.get('shortDescription'), 'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'), @@ -331,7 +348,8 @@ class BrightcoveLegacyIE(InfoExtractor): url_comp = compat_urllib_parse_urlparse(url) if url_comp.path.endswith('.m3u8'): formats.extend( - self._extract_m3u8_formats(url, info['id'], 'mp4')) + self._extract_m3u8_formats( + url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) continue elif 'akamaihd.net' in url_comp.netloc: # This type of renditions are served through @@ -365,7 +383,7 @@ class BrightcoveLegacyIE(InfoExtractor): a_format.update({ 'format_id': 'hls%s' % ('-%s' % tbr if tbr else ''), 'ext': 'mp4', - 'protocol': 'm3u8', + 'protocol': 'm3u8_native', }) formats.append(a_format) @@ -395,7 +413,7 @@ class BrightcoveLegacyIE(InfoExtractor): return ad_info if 'url' not in info and not info.get('formats'): - raise ExtractorError('Unable to extract video url for %s' % info['id']) + raise ExtractorError('Unable to extract video url for %s' % video_id) return info @@ -442,6 +460,10 @@ class BrightcoveNewIE(InfoExtractor): # non numeric ref: prefixed video id 'url': 'http://players.brightcove.net/710858724001/default_default/index.html?videoId=ref:event-stream-356', 'only_matching': True, + }, { + # unavailable video without message but with error_code + 'url': 'http://players.brightcove.net/1305187701/c832abfb-641b-44eb-9da0-2fe76786505f_default/index.html?videoId=4377407326001', + 'only_matching': True, }] @staticmethod @@ -512,8 +534,9 @@ class BrightcoveNewIE(InfoExtractor): }) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - json_data = self._parse_json(e.cause.read().decode(), video_id) - raise ExtractorError(json_data[0]['message'], expected=True) + json_data = self._parse_json(e.cause.read().decode(), video_id)[0] + raise ExtractorError( + json_data.get('message') or json_data['error_code'], expected=True) raise title = json_data['name'].strip() @@ -527,7 +550,7 @@ class BrightcoveNewIE(InfoExtractor): if not src: continue formats.extend(self._extract_m3u8_formats( - src, video_id, 'mp4', m3u8_id='hls', fatal=False)) + src, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) elif source_type == 'application/dash+xml': if not src: continue @@ -578,6 +601,13 @@ class BrightcoveNewIE(InfoExtractor): 'format_id': build_format_id('rtmp'), }) formats.append(f) + + errors = json_data.get('errors') + if not formats and errors: + error = errors[0] + raise ExtractorError( + error.get('message') or error.get('error_subcode') or error['error_code'], expected=True) + self._sort_formats(formats) subtitles = {} diff --git a/youtube_dl/extractor/buzzfeed.py b/youtube_dl/extractor/buzzfeed.py index df503ecc0..75fa92d7c 100644 --- a/youtube_dl/extractor/buzzfeed.py +++ b/youtube_dl/extractor/buzzfeed.py @@ -5,6 +5,7 @@ import json import re from .common import InfoExtractor +from .facebook import FacebookIE class BuzzFeedIE(InfoExtractor): @@ -20,11 +21,11 @@ class BuzzFeedIE(InfoExtractor): 'info_dict': { 'id': 'aVCR29aE_OQ', 'ext': 'mp4', + 'title': 'Angry Ram destroys a punching bag..', + 'description': 'md5:c59533190ef23fd4458a5e8c8c872345', 'upload_date': '20141024', 'uploader_id': 'Buddhanz1', - 'description': 'He likes to stay in shape with his heavy bag, he wont stop until its on the ground\n\nFollow Angry Ram on Facebook for regular updates -\nhttps://www.facebook.com/pages/Angry-Ram/1436897249899558?ref=hl', - 'uploader': 'Buddhanz', - 'title': 'Angry Ram destroys a punching bag', + 'uploader': 'Angry Ram', } }] }, { @@ -41,13 +42,30 @@ class BuzzFeedIE(InfoExtractor): 'info_dict': { 'id': 'mVmBL8B-In0', 'ext': 'mp4', + 'title': 're:Munchkin the Teddy Bear gets her exercise', + 'description': 'md5:28faab95cda6e361bcff06ec12fc21d8', 'upload_date': '20141124', 'uploader_id': 'CindysMunchkin', - 'description': 're:© 2014 Munchkin the', 'uploader': 're:^Munchkin the', - 'title': 're:Munchkin the Teddy Bear gets her exercise', }, }] + }, { + 'url': 'http://www.buzzfeed.com/craigsilverman/the-most-adorable-crash-landing-ever#.eq7pX0BAmK', + 'info_dict': { + 'id': 'the-most-adorable-crash-landing-ever', + 'title': 'Watch This Baby Goose Make The Most Adorable Crash Landing', + 'description': 'This gosling knows how to stick a landing.', + }, + 'playlist': [{ + 'md5': '763ca415512f91ca62e4621086900a23', + 'info_dict': { + 'id': '971793786185728', + 'ext': 'mp4', + 'title': 'We set up crash pads so that the goslings on our roof would have a safe landi...', + 'uploader': 'Calgary Outdoor Centre-University of Calgary', + }, + }], + 'add_ie': ['Facebook'], }] def _real_extract(self, url): @@ -66,6 +84,10 @@ class BuzzFeedIE(InfoExtractor): continue entries.append(self.url_result(video['url'])) + facebook_url = FacebookIE._extract_url(webpage) + if facebook_url: + entries.append(self.url_result(facebook_url)) + return { '_type': 'playlist', 'id': playlist_id, diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py index dda98059e..3aec601f8 100644 --- a/youtube_dl/extractor/byutv.py +++ b/youtube_dl/extractor/byutv.py @@ -11,6 +11,7 @@ class BYUtvIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)' _TEST = { 'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5', + 'md5': '05850eb8c749e2ee05ad5a1c34668493', 'info_dict': { 'id': 'studio-c-season-5-episode-5', 'ext': 'mp4', @@ -21,7 +22,8 @@ class BYUtvIE(InfoExtractor): }, 'params': { 'skip_download': True, - } + }, + 'add_ie': ['Ooyala'], } def _real_extract(self, url): diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index 25b2d4efe..61463f249 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -4,11 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urllib_parse_urlparse from ..utils import ( ExtractorError, HEADRequest, unified_strdate, - url_basename, qualities, int_or_none, ) @@ -16,24 +16,38 @@ from ..utils import ( class CanalplusIE(InfoExtractor): IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv' - _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))' + _VALID_URL = r'''(?x) + https?:// + (?: + (?: + (?:(?:www|m)\.)?canalplus\.fr| + (?:www\.)?piwiplus\.fr| + (?:www\.)?d8\.tv| + (?:www\.)?d17\.tv| + (?:www\.)?itele\.fr + )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?| + player\.canalplus\.fr/#/(?P<id>\d+) + ) + + ''' _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json' _SITE_ID_MAP = { - 'canalplus.fr': 'cplus', - 'piwiplus.fr': 'teletoon', - 'd8.tv': 'd8', - 'itele.fr': 'itele', + 'canalplus': 'cplus', + 'piwiplus': 'teletoon', + 'd8': 'd8', + 'd17': 'd17', + 'itele': 'itele', } _TESTS = [{ - 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092', - 'md5': '12164a6f14ff6df8bd628e8ba9b10b78', + 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814', + 'md5': '41f438a4904f7664b91b4ed0dec969dc', 'info_dict': { - 'id': '1263092', + 'id': '1192814', 'ext': 'mp4', - 'title': 'Le Zapping - 13/05/15', - 'description': 'md5:09738c0d06be4b5d06a0940edb0da73f', - 'upload_date': '20150513', + 'title': "L'Année du Zapping 2014 - L'Année du Zapping 2014", + 'description': "Toute l'année 2014 dans un Zapping exceptionnel !", + 'upload_date': '20150105', }, }, { 'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190', @@ -46,35 +60,45 @@ class CanalplusIE(InfoExtractor): }, 'skip': 'Only works from France', }, { - 'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html', + 'url': 'http://www.d8.tv/d8-docs-mags/pid5198-d8-en-quete-d-actualite.html?vid=1390231', 'info_dict': { - 'id': '966289', - 'ext': 'flv', - 'title': 'Campagne intime - Documentaire exceptionnel', - 'description': 'md5:d2643b799fb190846ae09c61e59a859f', - 'upload_date': '20131108', + 'id': '1390231', + 'ext': 'mp4', + 'title': "Vacances pas chères : prix discount ou grosses dépenses ? - En quête d'actualité", + 'description': 'md5:edb6cf1cb4a1e807b5dd089e1ac8bfc6', + 'upload_date': '20160512', + }, + 'params': { + 'skip_download': True, }, - 'skip': 'videos get deleted after a while', }, { - 'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559', - 'md5': '38b8f7934def74f0d6f3ba6c036a5f82', + 'url': 'http://www.itele.fr/chroniques/invite-bruce-toussaint/thierry-solere-nicolas-sarkozy-officialisera-sa-candidature-a-la-primaire-quand-il-le-voudra-167224', 'info_dict': { - 'id': '1213714', + 'id': '1398334', 'ext': 'mp4', - 'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45', - 'description': 'md5:8216206ec53426ea6321321f3b3c16db', - 'upload_date': '20150211', + 'title': "L'invité de Bruce Toussaint du 07/06/2016 - ", + 'description': 'md5:40ac7c9ad0feaeb6f605bad986f61324', + 'upload_date': '20160607', }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://m.canalplus.fr/?vid=1398231', + 'only_matching': True, + }, { + 'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061', + 'only_matching': True, }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.groupdict().get('id') + video_id = mobj.groupdict().get('id') or mobj.groupdict().get('vid') - site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal'] + site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]] # Beware, some subclasses do not define an id group - display_id = url_basename(mobj.group('path')) + display_id = mobj.group('display_id') or video_id if video_id is None: webpage = self._download_webpage(url, display_id) diff --git a/youtube_dl/extractor/carambatv.py b/youtube_dl/extractor/carambatv.py new file mode 100644 index 000000000..5797fb951 --- /dev/null +++ b/youtube_dl/extractor/carambatv.py @@ -0,0 +1,88 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + float_or_none, + int_or_none, + try_get, +) + + +class CarambaTVIE(InfoExtractor): + _VALID_URL = r'(?:carambatv:|https?://video1\.carambatv\.ru/v/)(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://video1.carambatv.ru/v/191910501', + 'md5': '2f4a81b7cfd5ab866ee2d7270cb34a2a', + 'info_dict': { + 'id': '191910501', + 'ext': 'mp4', + 'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 2678.31, + }, + }, { + 'url': 'carambatv:191910501', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + video = self._download_json( + 'http://video1.carambatv.ru/v/%s/videoinfo.js' % video_id, + video_id) + + title = video['title'] + + base_url = video.get('video') or 'http://video1.carambatv.ru/v/%s/' % video_id + + formats = [{ + 'url': base_url + f['fn'], + 'height': int_or_none(f.get('height')), + 'format_id': '%sp' % f['height'] if f.get('height') else None, + } for f in video['qualities'] if f.get('fn')] + self._sort_formats(formats) + + thumbnail = video.get('splash') + duration = float_or_none(try_get( + video, lambda x: x['annotations'][0]['end_time'], compat_str)) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + } + + +class CarambaTVPageIE(InfoExtractor): + _VALID_URL = r'https?://carambatv\.ru/(?:[^/]+/)+(?P<id>[^/?#&]+)' + _TEST = { + 'url': 'http://carambatv.ru/movie/bad-comedian/razborka-v-manile/', + 'md5': '', + 'info_dict': { + 'id': '191910501', + 'ext': 'mp4', + 'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 2678.31, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_url = self._og_search_property('video:iframe', webpage, default=None) + + if not video_url: + video_id = self._search_regex( + r'(?:video_id|crmb_vuid)\s*[:=]\s*["\']?(\d+)', + webpage, 'video id') + video_url = 'carambatv:%s' % video_id + + return self.url_result(video_url, CarambaTVIE.ie_key()) diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py index d8aa31038..ff663d079 100644 --- a/youtube_dl/extractor/cbc.py +++ b/youtube_dl/extractor/cbc.py @@ -4,64 +4,66 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import js_to_json +from ..utils import ( + js_to_json, + smuggle_url, +) class CBCIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?:[^/]+/)+(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?!player/)(?:[^/]+/)+(?P<id>[^/?#]+)' _TESTS = [{ # with mediaId 'url': 'http://www.cbc.ca/22minutes/videos/clips-season-23/don-cherry-play-offs', + 'md5': '97e24d09672fc4cf56256d6faa6c25bc', 'info_dict': { 'id': '2682904050', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Don Cherry – All-Stars', 'description': 'Don Cherry has a bee in his bonnet about AHL player John Scott because that guy’s got heart.', - 'timestamp': 1454475540, + 'timestamp': 1454463000, 'upload_date': '20160203', - }, - 'params': { - # rtmp download - 'skip_download': True, + 'uploader': 'CBCC-NEW', }, }, { # with clipId 'url': 'http://www.cbc.ca/archives/entry/1978-robin-williams-freestyles-on-90-minutes-live', + 'md5': '0274a90b51a9b4971fe005c63f592f12', 'info_dict': { 'id': '2487345465', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Robin Williams freestyles on 90 Minutes Live', 'description': 'Wacky American comedian Robin Williams shows off his infamous "freestyle" comedic talents while being interviewed on CBC\'s 90 Minutes Live.', - 'upload_date': '19700101', - }, - 'params': { - # rtmp download - 'skip_download': True, + 'upload_date': '19780210', + 'uploader': 'CBCC-NEW', + 'timestamp': 255977160, }, }, { # multiple iframes 'url': 'http://www.cbc.ca/natureofthings/blog/birds-eye-view-from-vancouvers-burrard-street-bridge-how-we-got-the-shot', 'playlist': [{ + 'md5': '377572d0b49c4ce0c9ad77470e0b96b4', 'info_dict': { 'id': '2680832926', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'An Eagle\'s-Eye View Off Burrard Bridge', 'description': 'Hercules the eagle flies from Vancouver\'s Burrard Bridge down to a nearby park with a mini-camera strapped to his back.', - 'upload_date': '19700101', + 'upload_date': '20160201', + 'timestamp': 1454342820, + 'uploader': 'CBCC-NEW', }, }, { + 'md5': '415a0e3f586113894174dfb31aa5bb1a', 'info_dict': { 'id': '2658915080', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Fly like an eagle!', 'description': 'Eagle equipped with a mini camera flies from the world\'s tallest tower', - 'upload_date': '19700101', + 'upload_date': '20150315', + 'timestamp': 1426443984, + 'uploader': 'CBCC-NEW', }, }], - 'params': { - # rtmp download - 'skip_download': True, - }, }] @classmethod @@ -90,24 +92,54 @@ class CBCIE(InfoExtractor): class CBCPlayerIE(InfoExtractor): _VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.cbc.ca/player/play/2683190193', + 'md5': '64d25f841ddf4ddb28a235338af32e2c', 'info_dict': { 'id': '2683190193', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Gerry Runs a Sweat Shop', 'description': 'md5:b457e1c01e8ff408d9d801c1c2cd29b0', - 'timestamp': 1455067800, + 'timestamp': 1455071400, 'upload_date': '20160210', + 'uploader': 'CBCC-NEW', }, - 'params': { - # rtmp download - 'skip_download': True, + }, { + # Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/ + 'url': 'http://www.cbc.ca/player/play/2657631896', + 'md5': 'e5e708c34ae6fca156aafe17c43e8b75', + 'info_dict': { + 'id': '2657631896', + 'ext': 'mp3', + 'title': 'CBC Montreal is organizing its first ever community hackathon!', + 'description': 'The modern technology we tend to depend on so heavily, is never without it\'s share of hiccups and headaches. Next weekend - CBC Montreal will be getting members of the public for its first Hackathon.', + 'timestamp': 1425704400, + 'upload_date': '20150307', + 'uploader': 'CBCC-NEW', }, - } + }, { + # available only when we add `formats=MPEG4,FLV,MP3` to theplatform url + 'url': 'http://www.cbc.ca/player/play/2164402062', + 'md5': '17a61eb813539abea40618d6323a7f82', + 'info_dict': { + 'id': '2164402062', + 'ext': 'flv', + 'title': 'Cancer survivor four times over', + 'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.', + 'timestamp': 1320410746, + 'upload_date': '20111104', + 'uploader': 'CBCC-NEW', + }, + }] def _real_extract(self, url): video_id = self._match_id(url) - return self.url_result( - 'http://feed.theplatform.com/f/ExhSPC/vms_5akSXx4Ng_Zn?byGuid=%s' % video_id, - 'ThePlatformFeed', video_id) + return { + '_type': 'url_transparent', + 'ie_key': 'ThePlatform', + 'url': smuggle_url( + 'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/%s?mbr=true&formats=MPEG4,FLV,MP3' % video_id, { + 'force_smil_url': True + }), + 'id': video_id, + } diff --git a/youtube_dl/extractor/cbs.py b/youtube_dl/extractor/cbs.py index 051d783a2..a23173d6f 100644 --- a/youtube_dl/extractor/cbs.py +++ b/youtube_dl/extractor/cbs.py @@ -1,15 +1,13 @@ from __future__ import unicode_literals -from .theplatform import ThePlatformIE +from .theplatform import ThePlatformFeedIE from ..utils import ( - xpath_text, - xpath_element, int_or_none, find_xpath_attr, ) -class CBSBaseIE(ThePlatformIE): +class CBSBaseIE(ThePlatformFeedIE): def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'): closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL') return { @@ -19,9 +17,22 @@ class CBSBaseIE(ThePlatformIE): }] } if closed_caption_e is not None and closed_caption_e.attrib.get('value') else [] + def _extract_video_info(self, filter_query, video_id): + return self._extract_feed_info( + 'dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id, lambda entry: { + 'series': entry.get('cbs$SeriesTitle'), + 'season_number': int_or_none(entry.get('cbs$SeasonNumber')), + 'episode': entry.get('cbs$EpisodeTitle'), + 'episode_number': int_or_none(entry.get('cbs$EpisodeNumber')), + }, { + 'StreamPack': { + 'manifest': 'm3u', + } + }) + class CBSIE(CBSBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<id>[^/]+)' + _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)' _TESTS = [{ 'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/', @@ -36,25 +47,7 @@ class CBSIE(CBSBaseIE): 'upload_date': '20131127', 'uploader': 'CBSI-NEW', }, - 'params': { - # rtmp download - 'skip_download': True, - }, - '_skip': 'Blocked outside the US', - }, { - 'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/', - 'info_dict': { - 'id': 'WWF_5KqY3PK1', - 'display_id': 'st-vincent', - 'ext': 'flv', - 'title': 'Live on Letterman - St. Vincent', - 'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.', - 'duration': 3221, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, + 'expected_warnings': ['Failed to download m3u8 information'], '_skip': 'Blocked outside the US', }, { 'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/', @@ -66,43 +59,5 @@ class CBSIE(CBSBaseIE): TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true' def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - content_id = self._search_regex( - [r"video\.settings\.content_id\s*=\s*'([^']+)';", r"cbsplayer\.contentId\s*=\s*'([^']+)';"], - webpage, 'content id') - items_data = self._download_xml( - 'http://can.cbs.com/thunder/player/videoPlayerService.php', - content_id, query={'partner': 'cbs', 'contentId': content_id}) - video_data = xpath_element(items_data, './/item') - title = xpath_text(video_data, 'videoTitle', 'title', True) - - subtitles = {} - formats = [] - for item in items_data.findall('.//item'): - pid = xpath_text(item, 'pid') - if not pid: - continue - tp_release_url = self.TP_RELEASE_URL_TEMPLATE % pid - if '.m3u8' in xpath_text(item, 'contentUrl', default=''): - tp_release_url += '&manifest=m3u' - tp_formats, tp_subtitles = self._extract_theplatform_smil( - tp_release_url, content_id, 'Downloading %s SMIL data' % pid) - formats.extend(tp_formats) - subtitles = self._merge_subtitles(subtitles, tp_subtitles) - self._sort_formats(formats) - - info = self.get_metadata('dJ5BDC/media/guid/2198311517/%s' % content_id, content_id) - info.update({ - 'id': content_id, - 'display_id': display_id, - 'title': title, - 'series': xpath_text(video_data, 'seriesTitle'), - 'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')), - 'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')), - 'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000), - 'thumbnail': xpath_text(video_data, 'previewImageURL'), - 'formats': formats, - 'subtitles': subtitles, - }) - return info + content_id = self._match_id(url) + return self._extract_video_info('byGuid=%s' % content_id, content_id) diff --git a/youtube_dl/extractor/cbsinteractive.py b/youtube_dl/extractor/cbsinteractive.py index 0011c3029..821db20b2 100644 --- a/youtube_dl/extractor/cbsinteractive.py +++ b/youtube_dl/extractor/cbsinteractive.py @@ -80,9 +80,6 @@ class CBSInteractiveIE(ThePlatformIE): media_guid_path = 'media/guid/%d/%s' % (self.MPX_ACCOUNTS[site], vdata['mpxRefId']) formats, subtitles = [], {} - if site == 'cnet': - formats, subtitles = self._extract_theplatform_smil( - self.TP_RELEASE_URL_TEMPLATE % media_guid_path, video_id) for (fkey, vid) in vdata['files'].items(): if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']: continue @@ -94,7 +91,7 @@ class CBSInteractiveIE(ThePlatformIE): subtitles = self._merge_subtitles(subtitles, tp_subtitles) self._sort_formats(formats) - info = self.get_metadata('kYEXFC/%s' % media_guid_path, video_id) + info = self._extract_theplatform_metadata('kYEXFC/%s' % media_guid_path, video_id) info.update({ 'id': video_id, 'display_id': display_id, diff --git a/youtube_dl/extractor/cbslocal.py b/youtube_dl/extractor/cbslocal.py new file mode 100644 index 000000000..74adb38a6 --- /dev/null +++ b/youtube_dl/extractor/cbslocal.py @@ -0,0 +1,84 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import calendar +import datetime + +from .anvato import AnvatoIE +from .sendtonews import SendtoNewsIE +from ..compat import compat_urlparse + + +class CBSLocalIE(AnvatoIE): + _VALID_URL = r'https?://[a-z]+\.cbslocal\.com/\d+/\d+/\d+/(?P<id>[0-9a-z-]+)' + + _TESTS = [{ + # Anvato backend + 'url': 'http://losangeles.cbslocal.com/2016/05/16/safety-advocates-say-fatal-car-seat-failures-are-public-health-crisis', + 'md5': 'f0ee3081e3843f575fccef901199b212', + 'info_dict': { + 'id': '3401037', + 'ext': 'mp4', + 'title': 'Safety Advocates Say Fatal Car Seat Failures Are \'Public Health Crisis\'', + 'description': 'Collapsing seats have been the focus of scrutiny for decades, though experts say remarkably little has been done to address the issue. Randy Paige reports.', + 'thumbnail': 're:^https?://.*', + 'timestamp': 1463440500, + 'upload_date': '20160516', + 'subtitles': { + 'en': 'mincount:5', + }, + 'categories': [ + 'Stations\\Spoken Word\\KCBSTV', + 'Syndication\\MSN', + 'Syndication\\NDN', + 'Syndication\\AOL', + 'Syndication\\Yahoo', + 'Syndication\\Tribune', + 'Syndication\\Curb.tv', + 'Content\\News' + ], + }, + }, { + # SendtoNews embed + 'url': 'http://cleveland.cbslocal.com/2016/05/16/indians-score-season-high-15-runs-in-blowout-win-over-reds-rapid-reaction/', + 'info_dict': { + 'id': 'GxfCe0Zo7D-175909-5588', + 'ext': 'mp4', + 'title': 'Recap: CLE 15, CIN 6', + 'description': '5/16/16: Indians\' bats explode for 15 runs in a win', + 'upload_date': '20160516', + 'timestamp': 1463433840, + 'duration': 49, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + sendtonews_url = SendtoNewsIE._extract_url(webpage) + if sendtonews_url: + info_dict = { + '_type': 'url_transparent', + 'url': compat_urlparse.urljoin(url, sendtonews_url), + } + else: + info_dict = self._extract_anvato_videos(webpage, display_id) + + time_str = self._html_search_regex( + r'class="entry-date">([^<]+)<', webpage, 'released date', fatal=False) + timestamp = None + if time_str: + timestamp = calendar.timegm(datetime.datetime.strptime( + time_str, '%b %d, %Y %I:%M %p').timetuple()) + + info_dict.update({ + 'display_id': display_id, + 'timestamp': timestamp, + }) + + return info_dict diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py index 79ddc20a0..387537e76 100644 --- a/youtube_dl/extractor/cbsnews.py +++ b/youtube_dl/extractor/cbsnews.py @@ -30,9 +30,12 @@ class CBSNewsIE(CBSBaseIE): { 'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/', 'info_dict': { - 'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack', + 'id': 'SNJBOYzXiWBOvaLsdzwH8fmtP1SCd91Y', 'ext': 'mp4', 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack', + 'description': 'md5:4a6983e480542d8b333a947bfc64ddc7', + 'upload_date': '19700101', + 'uploader': 'CBSI-NEW', 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 205, 'subtitles': { @@ -58,30 +61,8 @@ class CBSNewsIE(CBSBaseIE): webpage, 'video JSON info'), video_id) item = video_info['item'] if 'item' in video_info else video_info - title = item.get('articleTitle') or item.get('hed') - duration = item.get('duration') - thumbnail = item.get('mediaImage') or item.get('thumbnail') - - subtitles = {} - formats = [] - for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']: - pid = item.get('media' + format_id) - if not pid: - continue - release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true' % pid - tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid) - formats.extend(tp_formats) - subtitles = self._merge_subtitles(subtitles, tp_subtitles) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles, - } + guid = item['mpxRefId'] + return self._extract_video_info('byGuid=%s' % guid, guid) class CBSNewsLiveVideoIE(InfoExtractor): diff --git a/youtube_dl/extractor/cbssports.py b/youtube_dl/extractor/cbssports.py index 549ae32f3..78ca44b02 100644 --- a/youtube_dl/extractor/cbssports.py +++ b/youtube_dl/extractor/cbssports.py @@ -1,30 +1,28 @@ from __future__ import unicode_literals -import re +from .cbs import CBSBaseIE -from .common import InfoExtractor +class CBSSportsIE(CBSBaseIE): + _VALID_URL = r'https?://www\.cbssports\.com/video/player/[^/]+/(?P<id>\d+)' -class CBSSportsIE(InfoExtractor): - _VALID_URL = r'https?://www\.cbssports\.com/video/player/(?P<section>[^/]+)/(?P<id>[^/]+)' - - _TEST = { - 'url': 'http://www.cbssports.com/video/player/tennis/318462531970/0/us-open-flashbacks-1990s', + _TESTS = [{ + 'url': 'http://www.cbssports.com/video/player/videos/708337219968/0/ben-simmons-the-next-lebron?-not-so-fast', 'info_dict': { - 'id': '_d5_GbO8p1sT', - 'ext': 'flv', - 'title': 'US Open flashbacks: 1990s', - 'description': 'Bill Macatee relives the best moments in US Open history from the 1990s.', + 'id': '708337219968', + 'ext': 'mp4', + 'title': 'Ben Simmons the next LeBron? Not so fast', + 'description': 'md5:854294f627921baba1f4b9a990d87197', + 'timestamp': 1466293740, + 'upload_date': '20160618', + 'uploader': 'CBSI-NEW', }, - } + 'params': { + # m3u8 download + 'skip_download': True, + } + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - section = mobj.group('section') - video_id = mobj.group('id') - all_videos = self._download_json( - 'http://www.cbssports.com/data/video/player/getVideos/%s?as=json' % section, - video_id) - # The json file contains the info of all the videos in the section - video_info = next(v for v in all_videos if v['pcid'] == video_id) - return self.url_result('theplatform:%s' % video_info['pid'], 'ThePlatform') + video_id = self._match_id(url) + return self._extract_video_info('byId=%s' % video_id, video_id) diff --git a/youtube_dl/extractor/ccc.py b/youtube_dl/extractor/ccc.py index dda2c0959..8f7f09e22 100644 --- a/youtube_dl/extractor/ccc.py +++ b/youtube_dl/extractor/ccc.py @@ -1,13 +1,9 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( int_or_none, - parse_duration, - qualities, - unified_strdate, + parse_iso8601, ) @@ -19,14 +15,14 @@ class CCCIE(InfoExtractor): 'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video', 'md5': '3a1eda8f3a29515d27f5adb967d7e740', 'info_dict': { - 'id': '30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor', + 'id': '1839', 'ext': 'mp4', 'title': 'Introduction to Processor Design', - 'description': 'md5:80be298773966f66d56cb11260b879af', + 'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac', 'thumbnail': 're:^https?://.*\.jpg$', - 'view_count': int, 'upload_date': '20131228', - 'duration': 3660, + 'timestamp': 1388188800, + 'duration': 3710, } }, { 'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download', @@ -34,79 +30,48 @@ class CCCIE(InfoExtractor): }] def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - if self._downloader.params.get('prefer_free_formats'): - preference = qualities(['mp3', 'opus', 'mp4-lq', 'webm-lq', 'h264-sd', 'mp4-sd', 'webm-sd', 'mp4', 'webm', 'mp4-hd', 'h264-hd', 'webm-hd']) - else: - preference = qualities(['opus', 'mp3', 'webm-lq', 'mp4-lq', 'webm-sd', 'h264-sd', 'mp4-sd', 'webm', 'mp4', 'webm-hd', 'mp4-hd', 'h264-hd']) - - title = self._html_search_regex( - r'(?s)<h1>(.*?)</h1>', webpage, 'title') - description = self._html_search_regex( - r'(?s)<h3>About</h3>(.+?)<h3>', - webpage, 'description', fatal=False) - upload_date = unified_strdate(self._html_search_regex( - r"(?s)<span[^>]+class='[^']*fa-calendar-o'[^>]*>(.+?)</span>", - webpage, 'upload date', fatal=False)) - view_count = int_or_none(self._html_search_regex( - r"(?s)<span class='[^']*fa-eye'></span>(.*?)</li>", - webpage, 'view count', fatal=False)) - duration = parse_duration(self._html_search_regex( - r'(?s)<span[^>]+class=(["\']).*?fa-clock-o.*?\1[^>]*></span>(?P<duration>.+?)</li', - webpage, 'duration', fatal=False, group='duration')) + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + event_id = self._search_regex("data-id='(\d+)'", webpage, 'event id') + event_data = self._download_json('https://media.ccc.de/public/events/%s' % event_id, event_id) - matches = re.finditer(r'''(?xs) - <(?:span|div)\s+class='label\s+filetype'>(?P<format>[^<]*)</(?:span|div)>\s* - <(?:span|div)\s+class='label\s+filetype'>(?P<lang>[^<]*)</(?:span|div)>\s* - <a\s+download\s+href='(?P<http_url>[^']+)'>\s* - (?: - .*? - <a\s+(?:download\s+)?href='(?P<torrent_url>[^']+\.torrent)' - )?''', webpage) formats = [] - for m in matches: - format = m.group('format') - format_id = self._search_regex( - r'.*/([a-z0-9_-]+)/[^/]*$', - m.group('http_url'), 'format id', default=None) - if format_id: - format_id = m.group('lang') + '-' + format_id - vcodec = 'h264' if 'h264' in format_id else ( - 'none' if format_id in ('mp3', 'opus') else None + for recording in event_data.get('recordings', []): + recording_url = recording.get('recording_url') + if not recording_url: + continue + language = recording.get('language') + folder = recording.get('folder') + format_id = None + if language: + format_id = language + if folder: + if language: + format_id += '-' + folder + else: + format_id = folder + vcodec = 'h264' if 'h264' in folder else ( + 'none' if folder in ('mp3', 'opus') else None ) formats.append({ 'format_id': format_id, - 'format': format, - 'language': m.group('lang'), - 'url': m.group('http_url'), + 'url': recording_url, + 'width': int_or_none(recording.get('width')), + 'height': int_or_none(recording.get('height')), + 'filesize': int_or_none(recording.get('size'), invscale=1024 * 1024), + 'language': language, 'vcodec': vcodec, - 'preference': preference(format_id), }) - - if m.group('torrent_url'): - formats.append({ - 'format_id': 'torrent-%s' % (format if format_id is None else format_id), - 'format': '%s (torrent)' % format, - 'proto': 'torrent', - 'format_note': '(unsupported; will just download the .torrent file)', - 'vcodec': vcodec, - 'preference': -100 + preference(format_id), - 'url': m.group('torrent_url'), - }) self._sort_formats(formats) - thumbnail = self._html_search_regex( - r"<video.*?poster='([^']+)'", webpage, 'thumbnail', fatal=False) - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'view_count': view_count, - 'upload_date': upload_date, - 'duration': duration, + 'id': event_id, + 'display_id': display_id, + 'title': event_data['title'], + 'description': event_data.get('description'), + 'thumbnail': event_data.get('thumb_url'), + 'timestamp': parse_iso8601(event_data.get('date')), + 'duration': int_or_none(event_data.get('length')), + 'tags': event_data.get('tags'), 'formats': formats, } diff --git a/youtube_dl/extractor/cda.py b/youtube_dl/extractor/cda.py index 498d2c0d8..8af318703 100755 --- a/youtube_dl/extractor/cda.py +++ b/youtube_dl/extractor/cda.py @@ -58,7 +58,8 @@ class CDAIE(InfoExtractor): def extract_format(page, version): unpacked = decode_packed_codes(page) format_url = self._search_regex( - r"url:\\'(.+?)\\'", unpacked, '%s url' % version, fatal=False) + r"(?:file|url)\s*:\s*(\\?[\"'])(?P<url>http.+?)\1", unpacked, + '%s url' % version, fatal=False, group='url') if not format_url: return f = { @@ -75,7 +76,8 @@ class CDAIE(InfoExtractor): info_dict['formats'].append(f) if not info_dict['duration']: info_dict['duration'] = parse_duration(self._search_regex( - r"duration:\\'(.+?)\\'", unpacked, 'duration', fatal=False)) + r"duration\s*:\s*(\\?[\"'])(?P<duration>.+?)\1", + unpacked, 'duration', fatal=False, group='duration')) extract_format(webpage, 'default') diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 6652c8e42..5a58d1777 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -33,19 +33,33 @@ class CeskaTelevizeIE(InfoExtractor): 'skip_download': True, }, }, { - 'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina', + 'url': 'http://www.ceskatelevize.cz/ivysilani/10441294653-hyde-park-civilizace/215411058090502/bonus/20641-bonus-01-en', 'info_dict': { - 'id': '61924494876844374', + 'id': '61924494877028507', 'ext': 'mp4', - 'title': 'První republika: Zpěvačka z Dupárny Bobina', - 'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.', + 'title': 'Hyde Park Civilizace: Bonus 01 - En', + 'description': 'English Subtittles', 'thumbnail': 're:^https?://.*\.jpg', - 'duration': 88.4, + 'duration': 81.3, }, 'params': { # m3u8 download 'skip_download': True, }, + }, { + # live stream + 'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/', + 'info_dict': { + 'id': 402, + 'ext': 'mp4', + 'title': 're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$', + 'is_live': True, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + 'skip': 'Georestricted to Czech Republic', }, { # video with 18+ caution trailer 'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/', @@ -118,19 +132,21 @@ class CeskaTelevizeIE(InfoExtractor): req = sanitized_Request(compat_urllib_parse_unquote(playlist_url)) req.add_header('Referer', url) - playlist_title = self._og_search_title(webpage) - playlist_description = self._og_search_description(webpage) + playlist_title = self._og_search_title(webpage, default=None) + playlist_description = self._og_search_description(webpage, default=None) playlist = self._download_json(req, playlist_id)['playlist'] playlist_len = len(playlist) entries = [] for item in playlist: + is_live = item.get('type') == 'LIVE' formats = [] for format_id, stream_url in item['streamUrls'].items(): formats.extend(self._extract_m3u8_formats( stream_url, playlist_id, 'mp4', - entry_protocol='m3u8_native', fatal=False)) + entry_protocol='m3u8' if is_live else 'm3u8_native', + fatal=False)) self._sort_formats(formats) item_id = item.get('id') or item['assetId'] @@ -145,14 +161,22 @@ class CeskaTelevizeIE(InfoExtractor): if subs: subtitles = self.extract_subtitles(episode_id, subs) + if playlist_len == 1: + final_title = playlist_title or title + if is_live: + final_title = self._live_title(final_title) + else: + final_title = '%s (%s)' % (playlist_title, title) + entries.append({ 'id': item_id, - 'title': playlist_title if playlist_len == 1 else '%s (%s)' % (playlist_title, title), + 'title': final_title, 'description': playlist_description if playlist_len == 1 else None, 'thumbnail': thumbnail, 'duration': duration, 'formats': formats, 'subtitles': subtitles, + 'is_live': is_live, }) return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) diff --git a/youtube_dl/extractor/channel9.py b/youtube_dl/extractor/channel9.py index c74553dcf..34d4e6156 100644 --- a/youtube_dl/extractor/channel9.py +++ b/youtube_dl/extractor/channel9.py @@ -20,54 +20,64 @@ class Channel9IE(InfoExtractor): ''' IE_DESC = 'Channel 9' IE_NAME = 'channel9' - _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?' - - _TESTS = [ - { - 'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002', - 'md5': 'bbd75296ba47916b754e73c3a4bbdf10', - 'info_dict': { - 'id': 'Events/TechEd/Australia/2013/KOS002', - 'ext': 'mp4', - 'title': 'Developer Kick-Off Session: Stuff We Love', - 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f', - 'duration': 4576, - 'thumbnail': 're:http://.*\.jpg', - 'session_code': 'KOS002', - 'session_day': 'Day 1', - 'session_room': 'Arena 1A', - 'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen'], - }, + _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+?)(?P<rss>/RSS)?/?(?:[?#&]|$)' + + _TESTS = [{ + 'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002', + 'md5': 'bbd75296ba47916b754e73c3a4bbdf10', + 'info_dict': { + 'id': 'Events/TechEd/Australia/2013/KOS002', + 'ext': 'mp4', + 'title': 'Developer Kick-Off Session: Stuff We Love', + 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f', + 'duration': 4576, + 'thumbnail': 're:http://.*\.jpg', + 'session_code': 'KOS002', + 'session_day': 'Day 1', + 'session_room': 'Arena 1A', + 'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', + 'Mads Kristensen'], }, - { - 'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing', - 'md5': 'b43ee4529d111bc37ba7ee4f34813e68', - 'info_dict': { - 'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing', - 'ext': 'mp4', - 'title': 'Self-service BI with Power BI - nuclear testing', - 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b', - 'duration': 1540, - 'thumbnail': 're:http://.*\.jpg', - 'authors': ['Mike Wilmot'], - }, + }, { + 'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing', + 'md5': 'b43ee4529d111bc37ba7ee4f34813e68', + 'info_dict': { + 'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing', + 'ext': 'mp4', + 'title': 'Self-service BI with Power BI - nuclear testing', + 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b', + 'duration': 1540, + 'thumbnail': 're:http://.*\.jpg', + 'authors': ['Mike Wilmot'], }, - { - # low quality mp4 is best - 'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library', - 'info_dict': { - 'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library', - 'ext': 'mp4', - 'title': 'Ranges for the Standard Library', - 'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d', - 'duration': 5646, - 'thumbnail': 're:http://.*\.jpg', - }, - 'params': { - 'skip_download': True, - }, - } - ] + }, { + # low quality mp4 is best + 'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library', + 'info_dict': { + 'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library', + 'ext': 'mp4', + 'title': 'Ranges for the Standard Library', + 'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d', + 'duration': 5646, + 'thumbnail': 're:http://.*\.jpg', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://channel9.msdn.com/Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b/RSS', + 'info_dict': { + 'id': 'Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b', + 'title': 'Channel 9', + }, + 'playlist_count': 2, + }, { + 'url': 'https://channel9.msdn.com/Events/DEVintersection/DEVintersection-2016/RSS', + 'only_matching': True, + }, { + 'url': 'https://channel9.msdn.com/Events/Speakers/scott-hanselman/RSS?UrlSafeName=scott-hanselman', + 'only_matching': True, + }] _RSS_URL = 'http://channel9.msdn.com/%s/RSS' @@ -254,22 +264,30 @@ class Channel9IE(InfoExtractor): return self.playlist_result(contents) - def _extract_list(self, content_path): - rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS') + def _extract_list(self, video_id, rss_url=None): + if not rss_url: + rss_url = self._RSS_URL % video_id + rss = self._download_xml(rss_url, video_id, 'Downloading RSS') entries = [self.url_result(session_url.text, 'Channel9') for session_url in rss.findall('./channel/item/link')] title_text = rss.find('./channel/title').text - return self.playlist_result(entries, content_path, title_text) + return self.playlist_result(entries, video_id, title_text) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) content_path = mobj.group('contentpath') + rss = mobj.group('rss') + + if rss: + return self._extract_list(content_path, url) - webpage = self._download_webpage(url, content_path, 'Downloading web page') + webpage = self._download_webpage( + url, content_path, 'Downloading web page') - page_type_m = re.search(r'<meta name="WT.entryid" content="(?P<pagetype>[^:]+)[^"]+"/>', webpage) - if page_type_m is not None: - page_type = page_type_m.group('pagetype') + page_type = self._search_regex( + r'<meta[^>]+name=(["\'])WT\.entryid\1[^>]+content=(["\'])(?P<pagetype>[^:]+).+?\2', + webpage, 'page type', default=None, group='pagetype') + if page_type: if page_type == 'Entry': # Any 'item'-like page, may contain downloadable content return self._extract_entry_item(webpage, content_path) elif page_type == 'Session': # Event session page, may contain downloadable content @@ -278,6 +296,5 @@ class Channel9IE(InfoExtractor): return self._extract_list(content_path) else: raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True) - else: # Assuming list return self._extract_list(content_path) diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py deleted file mode 100644 index 042c4f2f1..000000000 --- a/youtube_dl/extractor/cinemassacre.py +++ /dev/null @@ -1,119 +0,0 @@ -# encoding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ExtractorError -from .screenwavemedia import ScreenwaveMediaIE - - -class CinemassacreIE(InfoExtractor): - _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)' - _TESTS = [ - { - 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', - 'md5': 'fde81fbafaee331785f58cd6c0d46190', - 'info_dict': { - 'id': 'Cinemassacre-19911', - 'ext': 'mp4', - 'upload_date': '20121110', - 'title': '“Angry Video Game Nerd: The Movie” – Trailer', - 'description': 'md5:fb87405fcb42a331742a0dce2708560b', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, - { - 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', - 'md5': 'd72f10cd39eac4215048f62ab477a511', - 'info_dict': { - 'id': 'Cinemassacre-521be8ef82b16', - 'ext': 'mp4', - 'upload_date': '20131002', - 'title': 'The Mummy’s Hand (1940)', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, - { - # Youtube embedded video - 'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/', - 'md5': 'ec9838a5520ef5409b3e4e42fcb0a3b9', - 'info_dict': { - 'id': 'OEVzPCY2T-g', - 'ext': 'webm', - 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles', - 'upload_date': '20061207', - 'uploader': 'Cinemassacre', - 'uploader_id': 'JamesNintendoNerd', - 'description': 'md5:784734696c2b8b7f4b8625cc799e07f6', - } - }, - { - # Youtube embedded video - 'url': 'http://cinemassacre.com/2006/09/01/mckids/', - 'md5': '7393c4e0f54602ad110c793eb7a6513a', - 'info_dict': { - 'id': 'FnxsNhuikpo', - 'ext': 'webm', - 'upload_date': '20060901', - 'uploader': 'Cinemassacre Extra', - 'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53', - 'uploader_id': 'Cinemassacre', - 'title': 'AVGN: McKids', - } - }, - { - 'url': 'http://cinemassacre.com/2015/05/25/mario-kart-64-nintendo-64-james-mike-mondays/', - 'md5': '1376908e49572389e7b06251a53cdd08', - 'info_dict': { - 'id': 'Cinemassacre-555779690c440', - 'ext': 'mp4', - 'description': 'Let’s Play Mario Kart 64 !! Mario Kart 64 is a classic go-kart racing game released for the Nintendo 64 (N64). Today James & Mike do 4 player Battle Mode with Kyle and Bootsy!', - 'title': 'Mario Kart 64 (Nintendo 64) James & Mike Mondays', - 'upload_date': '20150525', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - } - ] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('display_id') - video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d') - - webpage = self._download_webpage(url, display_id) - - playerdata_url = self._search_regex( - [ - ScreenwaveMediaIE.EMBED_PATTERN, - r'<iframe[^>]+src="(?P<url>(?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"', - ], - webpage, 'player data URL', default=None, group='url') - if not playerdata_url: - raise ExtractorError('Unable to find player data') - - video_title = self._html_search_regex( - r'<title>(?P<title>.+?)\|', webpage, 'title') - video_description = self._html_search_regex( - r'<div class="entry-content">(?P<description>.+?)</div>', - webpage, 'description', flags=re.DOTALL, fatal=False) - video_thumbnail = self._og_search_thumbnail(webpage) - - return { - '_type': 'url_transparent', - 'display_id': display_id, - 'title': video_title, - 'description': video_description, - 'upload_date': video_date, - 'thumbnail': video_thumbnail, - 'url': playerdata_url, - } diff --git a/youtube_dl/extractor/cliprs.py b/youtube_dl/extractor/cliprs.py index 4f9320ea5..d55b26d59 100644 --- a/youtube_dl/extractor/cliprs.py +++ b/youtube_dl/extractor/cliprs.py @@ -1,16 +1,10 @@ # coding: utf-8 from __future__ import unicode_literals -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - float_or_none, - int_or_none, - parse_iso8601, -) +from .onet import OnetBaseIE -class ClipRsIE(InfoExtractor): +class ClipRsIE(OnetBaseIE): _VALID_URL = r'https?://(?:www\.)?clip\.rs/(?P<id>[^/]+)/\d+' _TEST = { 'url': 'http://www.clip.rs/premijera-frajle-predstavljaju-novi-spot-za-pesmu-moli-me-moli/3732', @@ -27,64 +21,13 @@ class ClipRsIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) + display_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, display_id) - video_id = self._search_regex( - r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id') + mvp_id = self._search_mvp_id(webpage) - response = self._download_json( - 'http://qi.ckm.onetapi.pl/', video_id, - query={ - 'body[id]': video_id, - 'body[jsonrpc]': '2.0', - 'body[method]': 'get_asset_detail', - 'body[params][ID_Publikacji]': video_id, - 'body[params][Service]': 'www.onet.pl', - 'content-type': 'application/jsonp', - 'x-onet-app': 'player.front.onetapi.pl', - }) + info_dict = self._extract_from_id(mvp_id, webpage) + info_dict['display_id'] = display_id - error = response.get('error') - if error: - raise ExtractorError( - '%s said: %s' % (self.IE_NAME, error['message']), expected=True) - - video = response['result'].get('0') - - formats = [] - for _, formats_dict in video['formats'].items(): - if not isinstance(formats_dict, dict): - continue - for format_id, format_list in formats_dict.items(): - if not isinstance(format_list, list): - continue - for f in format_list: - if not f.get('url'): - continue - formats.append({ - 'url': f['url'], - 'format_id': format_id, - 'height': int_or_none(f.get('vertical_resolution')), - 'width': int_or_none(f.get('horizontal_resolution')), - 'abr': float_or_none(f.get('audio_bitrate')), - 'vbr': float_or_none(f.get('video_bitrate')), - }) - self._sort_formats(formats) - - meta = video.get('meta', {}) - - title = self._og_search_title(webpage, default=None) or meta['title'] - description = self._og_search_description(webpage, default=None) or meta.get('description') - duration = meta.get('length') or meta.get('lenght') - timestamp = parse_iso8601(meta.get('addDate'), ' ') - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'duration': duration, - 'timestamp': timestamp, - 'formats': formats, - } + return info_dict diff --git a/youtube_dl/extractor/closertotruth.py b/youtube_dl/extractor/closertotruth.py new file mode 100644 index 000000000..26243d52d --- /dev/null +++ b/youtube_dl/extractor/closertotruth.py @@ -0,0 +1,92 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class CloserToTruthIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?closertotruth\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688', + 'info_dict': { + 'id': '0_zof1ktre', + 'display_id': 'solutions-the-mind-body-problem', + 'ext': 'mov', + 'title': 'Solutions to the Mind-Body Problem?', + 'upload_date': '20140221', + 'timestamp': 1392956007, + 'uploader_id': 'CTTXML' + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://closertotruth.com/episodes/how-do-brains-work', + 'info_dict': { + 'id': '0_iuxai6g6', + 'display_id': 'how-do-brains-work', + 'ext': 'mov', + 'title': 'How do Brains Work?', + 'upload_date': '20140221', + 'timestamp': 1392956024, + 'uploader_id': 'CTTXML' + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://closertotruth.com/interviews/1725', + 'info_dict': { + 'id': '1725', + 'title': 'AyaFr-002', + }, + 'playlist_mincount': 2, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + partner_id = self._search_regex( + r'<script[^>]+src=["\'].*?\b(?:partner_id|p)/(\d+)', + webpage, 'kaltura partner_id') + + title = self._search_regex( + r'<title>(.+?)\s*\|\s*.+?', webpage, 'video title') + + select = self._search_regex( + r'(?s)]+id="select-version"[^>]*>(.+?)', + webpage, 'select version', default=None) + if select: + entry_ids = set() + entries = [] + for mobj in re.finditer( + r']+value=(["\'])(?P[0-9a-z_]+)(?:#.+?)?\1[^>]*>(?P[^<]+)', + webpage): + entry_id = mobj.group('id') + if entry_id in entry_ids: + continue + entry_ids.add(entry_id) + entries.append({ + '_type': 'url_transparent', + 'url': 'kaltura:%s:%s' % (partner_id, entry_id), + 'ie_key': 'Kaltura', + 'title': mobj.group('title'), + }) + if entries: + return self.playlist_result(entries, display_id, title) + + entry_id = self._search_regex( + r'<a[^>]+id=(["\'])embed-kaltura\1[^>]+data-kaltura=(["\'])(?P<id>[0-9a-z_]+)\2', + webpage, 'kaltura entry_id', group='id') + + return { + '_type': 'url_transparent', + 'display_id': display_id, + 'url': 'kaltura:%s:%s' % (partner_id, entry_id), + 'ie_key': 'Kaltura', + 'title': title + } diff --git a/youtube_dl/extractor/cloudy.py b/youtube_dl/extractor/cloudy.py index 9e267e6c0..9a28ef354 100644 --- a/youtube_dl/extractor/cloudy.py +++ b/youtube_dl/extractor/cloudy.py @@ -19,7 +19,7 @@ from ..utils import ( class CloudyIE(InfoExtractor): _IE_DESC = 'cloudy.ec and videoraj.ch' _VALID_URL = r'''(?x) - https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.ch)/ + https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.(?:ch|to))/ (?:v/|embed\.php\?id=) (?P<id>[A-Za-z0-9]+) ''' @@ -37,7 +37,7 @@ class CloudyIE(InfoExtractor): } }, { - 'url': 'http://www.videoraj.ch/v/47f399fd8bb60', + 'url': 'http://www.videoraj.to/v/47f399fd8bb60', 'md5': '7d0f8799d91efd4eda26587421c3c3b0', 'info_dict': { 'id': '47f399fd8bb60', diff --git a/youtube_dl/extractor/collegehumor.py b/youtube_dl/extractor/collegehumor.py deleted file mode 100644 index 002b24037..000000000 --- a/youtube_dl/extractor/collegehumor.py +++ /dev/null @@ -1,101 +0,0 @@ -from __future__ import unicode_literals - -import json -import re - -from .common import InfoExtractor -from ..utils import int_or_none - - -class CollegeHumorIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$' - - _TESTS = [ - { - 'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe', - 'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd', - 'info_dict': { - 'id': '6902724', - 'ext': 'mp4', - 'title': 'Comic-Con Cosplay Catastrophe', - 'description': "Fans get creative this year at San Diego. Too creative. And yes, that's really Joss Whedon.", - 'age_limit': 13, - 'duration': 187, - }, - }, { - 'url': 'http://www.collegehumor.com/video/3505939/font-conference', - 'md5': '72fa701d8ef38664a4dbb9e2ab721816', - 'info_dict': { - 'id': '3505939', - 'ext': 'mp4', - 'title': 'Font Conference', - 'description': "This video wasn't long enough, so we made it double-spaced.", - 'age_limit': 10, - 'duration': 179, - }, - }, { - # embedded youtube video - 'url': 'http://www.collegehumor.com/embed/6950306', - 'info_dict': { - 'id': 'Z-bao9fg6Yc', - 'ext': 'mp4', - 'title': 'Young Americans Think President John F. Kennedy Died THIS MORNING IN A CAR ACCIDENT!!!', - 'uploader': 'Mark Dice', - 'uploader_id': 'MarkDice', - 'description': 'md5:62c3dab9351fac7bb44b53b69511d87f', - 'upload_date': '20140127', - }, - 'params': { - 'skip_download': True, - }, - 'add_ie': ['Youtube'], - }, - ] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - - jsonUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id + '.json' - data = json.loads(self._download_webpage( - jsonUrl, video_id, 'Downloading info JSON')) - vdata = data['video'] - if vdata.get('youtubeId') is not None: - return { - '_type': 'url', - 'url': vdata['youtubeId'], - 'ie_key': 'Youtube', - } - - AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0} - rating = vdata.get('rating') - if rating: - age_limit = AGE_LIMITS.get(rating.lower()) - else: - age_limit = None # None = No idea - - PREFS = {'high_quality': 2, 'low_quality': 0} - formats = [] - for format_key in ('mp4', 'webm'): - for qname, qurl in vdata.get(format_key, {}).items(): - formats.append({ - 'format_id': format_key + '_' + qname, - 'url': qurl, - 'format': format_key, - 'preference': PREFS.get(qname), - }) - self._sort_formats(formats) - - duration = int_or_none(vdata.get('duration'), 1000) - like_count = int_or_none(vdata.get('likes')) - - return { - 'id': video_id, - 'title': vdata['title'], - 'description': vdata.get('description'), - 'thumbnail': vdata.get('thumbnail'), - 'formats': formats, - 'age_limit': age_limit, - 'duration': duration, - 'like_count': like_count, - } diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 0c59102e0..2b6aaa3aa 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -44,10 +44,10 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor): # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524 _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow) |https?://(:www\.)? - (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/ + (?P<showname>thedailyshow|thecolbertreport|tosh)\.(?:cc\.)?com/ ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)| (?P<clip> - (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+)) + (?:(?:guests/[^/]+|videos|video-(?:clips|playlists)|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+)) |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)) )| @@ -129,6 +129,9 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor): }, { 'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel', 'only_matching': True, + }, { + 'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans', + 'only_matching': True, }] _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 02cd2c003..816baa424 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -44,7 +44,9 @@ from ..utils import ( sanitized_Request, unescapeHTML, unified_strdate, + unified_timestamp, url_basename, + xpath_element, xpath_text, xpath_with_ns, determine_protocol, @@ -52,6 +54,7 @@ from ..utils import ( mimetype2ext, update_Request, update_url_query, + parse_m3u8_attributes, ) @@ -159,11 +162,12 @@ class InfoExtractor(object): * "height" (optional, int) * "resolution" (optional, string "{width}x{height"}, deprecated) + * "filesize" (optional, int) thumbnail: Full URL to a video thumbnail image. description: Full video description. uploader: Full name of the video uploader. license: License name the video is licensed under. - creator: The main artist who created the video. + creator: The creator of the video. release_date: The date (YYYYMMDD) when the video was released. timestamp: UNIX timestamp of the moment the video became available. upload_date: Video upload date (YYYYMMDD). @@ -747,10 +751,12 @@ class InfoExtractor(object): return self._og_search_property('url', html, **kargs) def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs): + if not isinstance(name, (list, tuple)): + name = [name] if display_name is None: - display_name = name + display_name = name[0] return self._html_search_regex( - self._meta_regex(name), + [self._meta_regex(n) for n in name], html, display_name, fatal=fatal, group='content', **kwargs) def _dc_search_uploader(self, html): @@ -799,15 +805,17 @@ class InfoExtractor(object): return self._html_search_meta('twitter:player', html, 'twitter card player') - def _search_json_ld(self, html, video_id, **kwargs): + def _search_json_ld(self, html, video_id, expected_type=None, **kwargs): json_ld = self._search_regex( r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>', html, 'JSON-LD', group='json_ld', **kwargs) if not json_ld: return {} - return self._json_ld(json_ld, video_id, fatal=kwargs.get('fatal', True)) + return self._json_ld( + json_ld, video_id, fatal=kwargs.get('fatal', True), + expected_type=expected_type) - def _json_ld(self, json_ld, video_id, fatal=True): + def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None): if isinstance(json_ld, compat_str): json_ld = self._parse_json(json_ld, video_id, fatal=fatal) if not json_ld: @@ -815,6 +823,8 @@ class InfoExtractor(object): info = {} if json_ld.get('@context') == 'http://schema.org': item_type = json_ld.get('@type') + if expected_type is not None and expected_type != item_type: + return info if item_type == 'TVEpisode': info.update({ 'episode': unescapeHTML(json_ld.get('name')), @@ -833,6 +843,19 @@ class InfoExtractor(object): 'title': unescapeHTML(json_ld.get('headline')), 'description': unescapeHTML(json_ld.get('articleBody')), }) + elif item_type == 'VideoObject': + info.update({ + 'url': json_ld.get('contentUrl'), + 'title': unescapeHTML(json_ld.get('name')), + 'description': unescapeHTML(json_ld.get('description')), + 'thumbnail': json_ld.get('thumbnailUrl'), + 'duration': parse_duration(json_ld.get('duration')), + 'timestamp': unified_timestamp(json_ld.get('uploadDate')), + 'filesize': float_or_none(json_ld.get('contentSize')), + 'tbr': int_or_none(json_ld.get('bitrate')), + 'width': int_or_none(json_ld.get('width')), + 'height': int_or_none(json_ld.get('height')), + }) return dict((k, v) for k, v in info.items() if v is not None) @staticmethod @@ -874,7 +897,11 @@ class InfoExtractor(object): f['ext'] = determine_ext(f['url']) if isinstance(field_preference, (list, tuple)): - return tuple(f.get(field) if f.get(field) is not None else -1 for field in field_preference) + return tuple( + f.get(field) + if f.get(field) is not None + else ('' if field == 'format_id' else -1) + for field in field_preference) preference = f.get('preference') if preference is None: @@ -987,7 +1014,7 @@ class InfoExtractor(object): def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None, transform_source=lambda s: fix_xml_ampersands(s).strip(), - fatal=True): + fatal=True, m3u8_id=None): manifest = self._download_xml( manifest_url, video_id, 'Downloading f4m manifest', 'Unable to download f4m manifest', @@ -1001,11 +1028,18 @@ class InfoExtractor(object): return self._parse_f4m_formats( manifest, manifest_url, video_id, preference=preference, f4m_id=f4m_id, - transform_source=transform_source, fatal=fatal) + transform_source=transform_source, fatal=fatal, m3u8_id=m3u8_id) def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None, transform_source=lambda s: fix_xml_ampersands(s).strip(), - fatal=True): + fatal=True, m3u8_id=None): + # currently youtube-dl cannot decode the playerVerificationChallenge as Akamai uses Adobe Alchemy + akamai_pv = manifest.find('{http://ns.adobe.com/f4m/1.0}pv-2.0') + if akamai_pv is not None and ';' in akamai_pv.text: + playerVerificationChallenge = akamai_pv.text.split(';')[0] + if playerVerificationChallenge.strip() != '': + return [] + formats = [] manifest_version = '1.0' media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media') @@ -1022,9 +1056,26 @@ class InfoExtractor(object): 'base URL', default=None) if base_url: base_url = base_url.strip() + + bootstrap_info = xpath_element( + manifest, ['{http://ns.adobe.com/f4m/1.0}bootstrapInfo', '{http://ns.adobe.com/f4m/2.0}bootstrapInfo'], + 'bootstrap info', default=None) + for i, media_el in enumerate(media_nodes): - if manifest_version == '2.0': - media_url = media_el.attrib.get('href') or media_el.attrib.get('url') + tbr = int_or_none(media_el.attrib.get('bitrate')) + width = int_or_none(media_el.attrib.get('width')) + height = int_or_none(media_el.attrib.get('height')) + format_id = '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])) + # If <bootstrapInfo> is present, the specified f4m is a + # stream-level manifest, and only set-level manifests may refer to + # external resources. See section 11.4 and section 4 of F4M spec + if bootstrap_info is None: + media_url = None + # @href is introduced in 2.0, see section 11.6 of F4M spec + if manifest_version == '2.0': + media_url = media_el.attrib.get('href') + if media_url is None: + media_url = media_el.attrib.get('url') if not media_url: continue manifest_url = ( @@ -1034,29 +1085,43 @@ class InfoExtractor(object): # since bitrates in parent manifest (this one) and media_url manifest # may differ leading to inability to resolve the format by requested # bitrate in f4m downloader - if determine_ext(manifest_url) == 'f4m': - formats.extend(self._extract_f4m_formats( + ext = determine_ext(manifest_url) + if ext == 'f4m': + f4m_formats = self._extract_f4m_formats( manifest_url, video_id, preference=preference, f4m_id=f4m_id, - transform_source=transform_source, fatal=fatal)) + transform_source=transform_source, fatal=fatal) + # Sometimes stream-level manifest contains single media entry that + # does not contain any quality metadata (e.g. http://matchtv.ru/#live-player). + # At the same time parent's media entry in set-level manifest may + # contain it. We will copy it from parent in such cases. + if len(f4m_formats) == 1: + f = f4m_formats[0] + f.update({ + 'tbr': f.get('tbr') or tbr, + 'width': f.get('width') or width, + 'height': f.get('height') or height, + 'format_id': f.get('format_id') if not tbr else format_id, + }) + formats.extend(f4m_formats) + continue + elif ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + manifest_url, video_id, 'mp4', preference=preference, + m3u8_id=m3u8_id, fatal=fatal)) continue - tbr = int_or_none(media_el.attrib.get('bitrate')) formats.append({ - 'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])), + 'format_id': format_id, 'url': manifest_url, - 'ext': 'flv', + 'ext': 'flv' if bootstrap_info is not None else None, 'tbr': tbr, - 'width': int_or_none(media_el.attrib.get('width')), - 'height': int_or_none(media_el.attrib.get('height')), + 'width': width, + 'height': height, 'preference': preference, }) return formats - def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None, - entry_protocol='m3u8', preference=None, - m3u8_id=None, note=None, errnote=None, - fatal=True): - - formats = [{ + def _m3u8_meta_format(self, m3u8_url, ext=None, preference=None, m3u8_id=None): + return { 'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])), 'url': m3u8_url, 'ext': ext, @@ -1064,7 +1129,14 @@ class InfoExtractor(object): 'preference': preference - 1 if preference else -1, 'resolution': 'multiple', 'format_note': 'Quality selection URL', - }] + } + + def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None, + entry_protocol='m3u8', preference=None, + m3u8_id=None, note=None, errnote=None, + fatal=True, live=False): + + formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)] format_url = lambda u: ( u @@ -1104,23 +1176,11 @@ class InfoExtractor(object): }] last_info = None last_media = None - kv_rex = re.compile( - r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)') for line in m3u8_doc.splitlines(): if line.startswith('#EXT-X-STREAM-INF:'): - last_info = {} - for m in kv_rex.finditer(line): - v = m.group('val') - if v.startswith('"'): - v = v[1:-1] - last_info[m.group('key')] = v + last_info = parse_m3u8_attributes(line) elif line.startswith('#EXT-X-MEDIA:'): - last_media = {} - for m in kv_rex.finditer(line): - v = m.group('val') - if v.startswith('"'): - v = v[1:-1] - last_media[m.group('key')] = v + last_media = parse_m3u8_attributes(line) elif line.startswith('#') or not line.strip(): continue else: @@ -1131,8 +1191,15 @@ class InfoExtractor(object): format_id = [] if m3u8_id: format_id.append(m3u8_id) - last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') != 'SUBTITLES' else None - format_id.append(last_media_name if last_media_name else '%d' % (tbr if tbr else len(formats))) + last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') not in ('SUBTITLES', 'CLOSED-CAPTIONS') else None + # Despite specification does not mention NAME attribute for + # EXT-X-STREAM-INF it still sometimes may be present + stream_name = last_info.get('NAME') or last_media_name + # Bandwidth of live streams may differ over time thus making + # format_id unpredictable. So it's better to keep provided + # format_id intact. + if not live: + format_id.append(stream_name if stream_name else '%d' % (tbr if tbr else len(formats))) f = { 'format_id': '-'.join(format_id), 'url': format_url(line.strip()), @@ -1264,21 +1331,21 @@ class InfoExtractor(object): m3u8_count = 0 srcs = [] - videos = smil.findall(self._xpath_ns('.//video', namespace)) - for video in videos: - src = video.get('src') + media = smil.findall(self._xpath_ns('.//video', namespace)) + smil.findall(self._xpath_ns('.//audio', namespace)) + for medium in media: + src = medium.get('src') if not src or src in srcs: continue srcs.append(src) - bitrate = float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000) - filesize = int_or_none(video.get('size') or video.get('fileSize')) - width = int_or_none(video.get('width')) - height = int_or_none(video.get('height')) - proto = video.get('proto') - ext = video.get('ext') + bitrate = float_or_none(medium.get('system-bitrate') or medium.get('systemBitrate'), 1000) + filesize = int_or_none(medium.get('size') or medium.get('fileSize')) + width = int_or_none(medium.get('width')) + height = int_or_none(medium.get('height')) + proto = medium.get('proto') + ext = medium.get('ext') src_ext = determine_ext(src) - streamer = video.get('streamer') or base + streamer = medium.get('streamer') or base if proto == 'rtmp' or streamer.startswith('rtmp'): rtmp_count += 1 @@ -1681,6 +1748,13 @@ class InfoExtractor(object): def _mark_watched(self, *args, **kwargs): raise NotImplementedError('This method must be implemented by subclasses') + def geo_verification_headers(self): + headers = {} + geo_verification_proxy = self._downloader.params.get('geo_verification_proxy') + if geo_verification_proxy: + headers['Ytdl-request-proxy'] = geo_verification_proxy + return headers + class SearchInfoExtractor(InfoExtractor): """ diff --git a/youtube_dl/extractor/coub.py b/youtube_dl/extractor/coub.py new file mode 100644 index 000000000..a901b8d22 --- /dev/null +++ b/youtube_dl/extractor/coub.py @@ -0,0 +1,143 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + float_or_none, + int_or_none, + parse_iso8601, + qualities, +) + + +class CoubIE(InfoExtractor): + _VALID_URL = r'(?:coub:|https?://(?:coub\.com/(?:view|embed|coubs)/|c-cdn\.coub\.com/fb-player\.swf\?.*\bcoub(?:ID|id)=))(?P<id>[\da-z]+)' + + _TESTS = [{ + 'url': 'http://coub.com/view/5u5n1', + 'info_dict': { + 'id': '5u5n1', + 'ext': 'mp4', + 'title': 'The Matrix Moonwalk', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 4.6, + 'timestamp': 1428527772, + 'upload_date': '20150408', + 'uploader': 'Артём Лоскутников', + 'uploader_id': 'artyom.loskutnikov', + 'view_count': int, + 'like_count': int, + 'repost_count': int, + 'comment_count': int, + 'age_limit': 0, + }, + }, { + 'url': 'http://c-cdn.coub.com/fb-player.swf?bot_type=vk&coubID=7w5a4', + 'only_matching': True, + }, { + 'url': 'coub:5u5n1', + 'only_matching': True, + }, { + # longer video id + 'url': 'http://coub.com/view/237d5l5h', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + coub = self._download_json( + 'http://coub.com/api/v2/coubs/%s.json' % video_id, video_id) + + if coub.get('error'): + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, coub['error']), expected=True) + + title = coub['title'] + + file_versions = coub['file_versions'] + + QUALITIES = ('low', 'med', 'high') + + MOBILE = 'mobile' + IPHONE = 'iphone' + HTML5 = 'html5' + + SOURCE_PREFERENCE = (MOBILE, IPHONE, HTML5) + + quality_key = qualities(QUALITIES) + preference_key = qualities(SOURCE_PREFERENCE) + + formats = [] + + for kind, items in file_versions.get(HTML5, {}).items(): + if kind not in ('video', 'audio'): + continue + if not isinstance(items, dict): + continue + for quality, item in items.items(): + if not isinstance(item, dict): + continue + item_url = item.get('url') + if not item_url: + continue + formats.append({ + 'url': item_url, + 'format_id': '%s-%s-%s' % (HTML5, kind, quality), + 'filesize': int_or_none(item.get('size')), + 'vcodec': 'none' if kind == 'audio' else None, + 'quality': quality_key(quality), + 'preference': preference_key(HTML5), + }) + + iphone_url = file_versions.get(IPHONE, {}).get('url') + if iphone_url: + formats.append({ + 'url': iphone_url, + 'format_id': IPHONE, + 'preference': preference_key(IPHONE), + }) + + mobile_url = file_versions.get(MOBILE, {}).get('audio_url') + if mobile_url: + formats.append({ + 'url': mobile_url, + 'format_id': '%s-audio' % MOBILE, + 'preference': preference_key(MOBILE), + }) + + self._sort_formats(formats) + + thumbnail = coub.get('picture') + duration = float_or_none(coub.get('duration')) + timestamp = parse_iso8601(coub.get('published_at') or coub.get('created_at')) + uploader = coub.get('channel', {}).get('title') + uploader_id = coub.get('channel', {}).get('permalink') + + view_count = int_or_none(coub.get('views_count') or coub.get('views_increase_count')) + like_count = int_or_none(coub.get('likes_count')) + repost_count = int_or_none(coub.get('recoubs_count')) + comment_count = int_or_none(coub.get('comments_count')) + + age_restricted = coub.get('age_restricted', coub.get('age_restricted_by_admin')) + if age_restricted is not None: + age_limit = 18 if age_restricted is True else 0 + else: + age_limit = None + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'view_count': view_count, + 'like_count': like_count, + 'repost_count': repost_count, + 'comment_count': comment_count, + 'age_limit': age_limit, + 'formats': formats, + } diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 8ae3f2890..90a64303d 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -11,7 +11,6 @@ from math import pow, sqrt, floor from .common import InfoExtractor from ..compat import ( compat_etree_fromstring, - compat_urllib_parse_unquote, compat_urllib_parse_urlencode, compat_urllib_request, compat_urlparse, @@ -27,6 +26,7 @@ from ..utils import ( unified_strdate, urlencode_postdata, xpath_text, + extract_attributes, ) from ..aes import ( aes_cbc_decrypt, @@ -306,28 +306,36 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage, 'video_uploader', fatal=False) - playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url')) - playerdata_req = sanitized_Request(playerdata_url) - playerdata_req.data = urlencode_postdata({'current_page': webpage_url}) - playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') - playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info') - - stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, 'stream_id') - video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False) - + available_fmts = [] + for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage): + attrs = extract_attributes(a) + href = attrs.get('href') + if href and '/freetrial' in href: + continue + available_fmts.append(fmt) + if not available_fmts: + for p in (r'token=["\']showmedia\.([0-9]{3,4})p"', r'showmedia\.([0-9]{3,4})p'): + available_fmts = re.findall(p, webpage) + if available_fmts: + break + video_encode_ids = [] formats = [] - for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage): + for fmt in available_fmts: stream_quality, stream_format = self._FORMAT_IDS[fmt] video_format = fmt + 'p' streamdata_req = sanitized_Request( 'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s' - % (stream_id, stream_format, stream_quality), + % (video_id, stream_format, stream_quality), compat_urllib_parse_urlencode({'current_page': url}).encode('utf-8')) streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') streamdata = self._download_xml( streamdata_req, video_id, note='Downloading media info for %s' % video_format) stream_info = streamdata.find('./{default}preload/stream_info') + video_encode_id = xpath_text(stream_info, './video_encode_id') + if video_encode_id in video_encode_ids: + continue + video_encode_ids.append(video_encode_id) video_url = xpath_text(stream_info, './host') video_play_path = xpath_text(stream_info, './file') if not video_url or not video_play_path: @@ -359,6 +367,14 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'ext': 'flv', }) formats.append(format_info) + self._sort_formats(formats) + + metadata = self._download_xml( + 'http://www.crunchyroll.com/xml', video_id, + note='Downloading media info', query={ + 'req': 'RpcApiVideoPlayer_GetMediaMetadata', + 'media_id': video_id, + }) subtitles = self.extract_subtitles(video_id, webpage) @@ -366,9 +382,12 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'id': video_id, 'title': video_title, 'description': video_description, - 'thumbnail': video_thumbnail, + 'thumbnail': xpath_text(metadata, 'episode_image_url'), 'uploader': video_uploader, 'upload_date': video_upload_date, + 'series': xpath_text(metadata, 'series_title'), + 'episode': xpath_text(metadata, 'episode_title'), + 'episode_number': int_or_none(xpath_text(metadata, 'episode_number')), 'subtitles': subtitles, 'formats': formats, } diff --git a/youtube_dl/extractor/ctv.py b/youtube_dl/extractor/ctv.py new file mode 100644 index 000000000..5807fbac9 --- /dev/null +++ b/youtube_dl/extractor/ctv.py @@ -0,0 +1,30 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class CTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ctv\.ca/video/player\?vid=(?P<id>[0-9.]+)' + _TESTS = [{ + 'url': 'http://www.ctv.ca/video/player?vid=706966', + 'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0', + 'info_dict': { + 'id': '706966', + 'ext': 'mp4', + 'title': 'Larry Day and Richard Jutras on the TIFF red carpet of \'Stonewall\'', + 'description': 'etalk catches up with Larry Day and Richard Jutras on the TIFF red carpet of "Stonewall”.', + 'upload_date': '20150919', + 'timestamp': 1442624700, + }, + 'expected_warnings': ['HTTP Error 404'], + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + return { + '_type': 'url_transparent', + 'id': video_id, + 'url': '9c9media:ctv_web:%s' % video_id, + 'ie_key': 'NineCNineMedia', + } diff --git a/youtube_dl/extractor/ctvnews.py b/youtube_dl/extractor/ctvnews.py new file mode 100644 index 000000000..1023b6130 --- /dev/null +++ b/youtube_dl/extractor/ctvnews.py @@ -0,0 +1,65 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import orderedSet + + +class CTVNewsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P<id>[0-9.]+)' + _TESTS = [{ + 'url': 'http://www.ctvnews.ca/video?clipId=901995', + 'md5': '10deb320dc0ccb8d01d34d12fc2ea672', + 'info_dict': { + 'id': '901995', + 'ext': 'mp4', + 'title': 'Extended: \'That person cannot be me\' Johnson says', + 'description': 'md5:958dd3b4f5bbbf0ed4d045c790d89285', + 'timestamp': 1467286284, + 'upload_date': '20160630', + } + }, { + 'url': 'http://www.ctvnews.ca/video?playlistId=1.2966224', + 'info_dict': + { + 'id': '1.2966224', + }, + 'playlist_mincount': 19, + }, { + 'url': 'http://www.ctvnews.ca/video?binId=1.2876780', + 'info_dict': + { + 'id': '1.2876780', + }, + 'playlist_mincount': 100, + }, { + 'url': 'http://www.ctvnews.ca/1.810401', + 'only_matching': True, + }, { + 'url': 'http://www.ctvnews.ca/canadiens-send-p-k-subban-to-nashville-in-blockbuster-trade-1.2967231', + 'only_matching': True, + }] + + def _real_extract(self, url): + page_id = self._match_id(url) + + def ninecninemedia_url_result(clip_id): + return { + '_type': 'url_transparent', + 'id': clip_id, + 'url': '9c9media:ctvnews_web:%s' % clip_id, + 'ie_key': 'NineCNineMedia', + } + + if page_id.isdigit(): + return ninecninemedia_url_result(page_id) + else: + webpage = self._download_webpage('http://www.ctvnews.ca/%s' % page_id, page_id, query={ + 'ot': 'example.AjaxPageLayout.ot', + 'maxItemsPerPage': 1000000, + }) + entries = [ninecninemedia_url_result(clip_id) for clip_id in orderedSet( + re.findall(r'clip\.id\s*=\s*(\d+);', webpage))] + return self.playlist_result(entries, page_id) diff --git a/youtube_dl/extractor/cwtv.py b/youtube_dl/extractor/cwtv.py index f5cefd966..ebd14cb16 100644 --- a/youtube_dl/extractor/cwtv.py +++ b/youtube_dl/extractor/cwtv.py @@ -9,7 +9,7 @@ from ..utils import ( class CWTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/shows/(?:[^/]+/){2}\?play=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})' + _VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/(?:shows/)?(?:[^/]+/){2}\?.*\bplay=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})' _TESTS = [{ 'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63', 'info_dict': { @@ -48,6 +48,9 @@ class CWTVIE(InfoExtractor): # m3u8 download 'skip_download': True, } + }, { + 'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/dailymail.py b/youtube_dl/extractor/dailymail.py new file mode 100644 index 000000000..b60a1d813 --- /dev/null +++ b/youtube_dl/extractor/dailymail.py @@ -0,0 +1,61 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + determine_protocol, +) + + +class DailyMailIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/video/[^/]+/video-(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.dailymail.co.uk/video/sciencetech/video-1288527/Turn-video-impressionist-masterpiece.html', + 'md5': '2f639d446394f53f3a33658b518b6615', + 'info_dict': { + 'id': '1288527', + 'ext': 'mp4', + 'title': 'Turn any video into an impressionist masterpiece', + 'description': 'md5:88ddbcb504367987b2708bb38677c9d2', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + video_data = self._parse_json(self._search_regex( + r"data-opts='({.+?})'", webpage, 'video data'), video_id) + title = video_data['title'] + video_sources = self._download_json(video_data.get( + 'sources', {}).get('url') or 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id, video_id) + + formats = [] + for rendition in video_sources['renditions']: + rendition_url = rendition.get('url') + if not rendition_url: + continue + tbr = int_or_none(rendition.get('encodingRate'), 1000) + container = rendition.get('videoContainer') + is_hls = container == 'M2TS' + protocol = 'm3u8_native' if is_hls else determine_protocol({'url': rendition_url}) + formats.append({ + 'format_id': ('hls' if is_hls else protocol) + ('-%d' % tbr if tbr else ''), + 'url': rendition_url, + 'width': int_or_none(rendition.get('frameWidth')), + 'height': int_or_none(rendition.get('frameHeight')), + 'tbr': tbr, + 'vcodec': rendition.get('videoCodec'), + 'container': container, + 'protocol': protocol, + 'ext': 'mp4' if is_hls else None, + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': video_data.get('descr'), + 'thumbnail': video_data.get('poster') or video_data.get('thumbnail'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 2e6226ea0..1f92823b7 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -16,6 +16,7 @@ from ..utils import ( sanitized_Request, str_to_int, unescapeHTML, + mimetype2ext, ) @@ -111,6 +112,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor): } ] + @staticmethod + def _extract_urls(webpage): + # Look for embedded Dailymotion player + matches = re.findall( + r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage) + return list(map(lambda m: unescapeHTML(m[1]), matches)) + def _real_extract(self, url): video_id = self._match_id(url) @@ -153,18 +161,19 @@ class DailymotionIE(DailymotionBaseInfoExtractor): type_ = media.get('type') if type_ == 'application/vnd.lumberjack.manifest': continue - ext = determine_ext(media_url) - if type_ == 'application/x-mpegURL' or ext == 'm3u8': + ext = mimetype2ext(type_) or determine_ext(media_url) + if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( media_url, video_id, 'mp4', preference=-1, m3u8_id='hls', fatal=False)) - elif type_ == 'application/f4m' or ext == 'f4m': + elif ext == 'f4m': formats.extend(self._extract_f4m_formats( media_url, video_id, preference=-1, f4m_id='hds', fatal=False)) else: f = { 'url': media_url, 'format_id': 'http-%s' % quality, + 'ext': ext, } m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url) if m: diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 86024a745..b5c310ccb 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -66,22 +66,32 @@ class DaumIE(InfoExtractor): 'view_count': int, 'comment_count': int, }, + }, { + # Requires dte_type=WEB (#9972) + 'url': 'http://tvpot.daum.net/v/s3794Uf1NZeZ1qMpGpeqeRU', + 'md5': 'a8917742069a4dd442516b86e7d66529', + 'info_dict': { + 'id': 's3794Uf1NZeZ1qMpGpeqeRU', + 'ext': 'mp4', + 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny) [쇼! 음악중심] 508회 20160611', + 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\n\n[쇼! 음악중심] 20160611, 507회', + 'upload_date': '20160611', + }, }] def _real_extract(self, url): video_id = compat_urllib_parse_unquote(self._match_id(url)) - query = compat_urllib_parse_urlencode({'vid': video_id}) movie_data = self._download_json( - 'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json?' + query, - video_id, 'Downloading video formats info') + 'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json', + video_id, 'Downloading video formats info', query={'vid': video_id, 'dte_type': 'WEB'}) # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id): return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id) info = self._download_xml( - 'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id, - 'Downloading video info') + 'http://tvpot.daum.net/clip/ClipInfoXml.do', video_id, + 'Downloading video info', query={'vid': video_id}) formats = [] for format_el in movie_data['output_list']['output_list']: diff --git a/youtube_dl/extractor/dcn.py b/youtube_dl/extractor/dcn.py index 5deff5f30..efb8585e8 100644 --- a/youtube_dl/extractor/dcn.py +++ b/youtube_dl/extractor/dcn.py @@ -20,7 +20,7 @@ from ..utils import ( class DCNIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?' + _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?' def _real_extract(self, url): show_id, video_id, season_id = re.match(self._VALID_URL, url).groups() @@ -55,30 +55,32 @@ class DCNBaseIE(InfoExtractor): 'is_live': is_live, } - def _extract_video_formats(self, webpage, video_id, entry_protocol): + def _extract_video_formats(self, webpage, video_id, m3u8_entry_protocol): formats = [] - m3u8_url = self._html_search_regex( - r'file\s*:\s*"([^"]+)', webpage, 'm3u8 url', fatal=False) - if m3u8_url: - formats.extend(self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=None)) - - rtsp_url = self._search_regex( - r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False) - if rtsp_url: - formats.append({ - 'url': rtsp_url, - 'format_id': 'rtsp', - }) - + format_url_base = 'http' + self._html_search_regex( + [ + r'file\s*:\s*"https?(://[^"]+)/playlist.m3u8', + r'<a[^>]+href="rtsp(://[^"]+)"' + ], webpage, 'format url') + # TODO: Current DASH formats are broken - $Time$ pattern in + # <SegmentTemplate> not implemented yet + # formats.extend(self._extract_mpd_formats( + # format_url_base + '/manifest.mpd', + # video_id, mpd_id='dash', fatal=False)) + formats.extend(self._extract_m3u8_formats( + format_url_base + '/playlist.m3u8', video_id, 'mp4', + m3u8_entry_protocol, m3u8_id='hls', fatal=False)) + formats.extend(self._extract_f4m_formats( + format_url_base + '/manifest.f4m', + video_id, f4m_id='hds', fatal=False)) self._sort_formats(formats) return formats class DCNVideoIE(DCNBaseIE): IE_NAME = 'dcn:video' - _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)' + _TESTS = [{ 'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375', 'info_dict': { @@ -94,7 +96,10 @@ class DCNVideoIE(DCNBaseIE): # m3u8 download 'skip_download': True, }, - } + }, { + 'url': 'http://awaan.ae/video/26723981/%D8%AF%D8%A7%D8%B1-%D8%A7%D9%84%D8%B3%D9%84%D8%A7%D9%85:-%D8%AE%D9%8A%D8%B1-%D8%AF%D9%88%D8%B1-%D8%A7%D9%84%D8%A3%D9%86%D8%B5%D8%A7%D8%B1', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -120,7 +125,7 @@ class DCNVideoIE(DCNBaseIE): class DCNLiveIE(DCNBaseIE): IE_NAME = 'dcn:live' - _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P<id>\d+)' def _real_extract(self, url): channel_id = self._match_id(url) @@ -147,7 +152,7 @@ class DCNLiveIE(DCNBaseIE): class DCNSeasonIE(InfoExtractor): IE_NAME = 'dcn:season' - _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))' + _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))' _TEST = { 'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A', 'info_dict': diff --git a/youtube_dl/extractor/dfb.py b/youtube_dl/extractor/dfb.py index cdfeccacb..a4d0448c2 100644 --- a/youtube_dl/extractor/dfb.py +++ b/youtube_dl/extractor/dfb.py @@ -12,39 +12,46 @@ class DFBIE(InfoExtractor): _TEST = { 'url': 'http://tv.dfb.de/video/u-19-em-stimmen-zum-spiel-gegen-russland/11633/', - # The md5 is different each time + 'md5': 'ac0f98a52a330f700b4b3034ad240649', 'info_dict': { 'id': '11633', 'display_id': 'u-19-em-stimmen-zum-spiel-gegen-russland', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'U 19-EM: Stimmen zum Spiel gegen Russland', 'upload_date': '20150714', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') + display_id, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage(url, display_id) player_info = self._download_xml( 'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id, display_id) video_info = player_info.find('video') - - f4m_info = self._download_xml( - self._proto_relative_url(video_info.find('url').text.strip()), display_id) - token_el = f4m_info.find('token') - manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0' - formats = self._extract_f4m_formats(manifest_url, display_id) + stream_access_url = self._proto_relative_url(video_info.find('url').text.strip()) + + formats = [] + # see http://tv.dfb.de/player/js/ajax.js for the method to extract m3u8 formats + for sa_url in (stream_access_url, stream_access_url + '&area=&format=iphone'): + stream_access_info = self._download_xml(sa_url, display_id) + token_el = stream_access_info.find('token') + manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + if '.f4m' in manifest_url: + formats.extend(self._extract_f4m_formats( + manifest_url + '&hdcore=3.2.0', + display_id, f4m_id='hds', fatal=False)) + else: + formats.extend(self._extract_m3u8_formats( + manifest_url, display_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) self._sort_formats(formats) return { 'id': video_id, 'display_id': display_id, 'title': video_info.find('title').text, - 'thumbnail': self._og_search_thumbnail(webpage), + 'thumbnail': 'http://tv.dfb.de/images/%s_640x360.jpg' % video_id, 'upload_date': unified_strdate(video_info.find('time_date').text), 'formats': formats, } diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 5f1275b39..55853f76f 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -33,6 +33,7 @@ class DiscoveryIE(InfoExtractor): 'duration': 156, 'timestamp': 1302032462, 'upload_date': '20110405', + 'uploader_id': '103207', }, 'params': { 'skip_download': True, # requires ffmpeg @@ -54,7 +55,11 @@ class DiscoveryIE(InfoExtractor): 'upload_date': '20140725', 'timestamp': 1406246400, 'duration': 116, + 'uploader_id': '103207', }, + 'params': { + 'skip_download': True, # requires ffmpeg + } }] def _real_extract(self, url): @@ -66,13 +71,19 @@ class DiscoveryIE(InfoExtractor): entries = [] for idx, video_info in enumerate(info['playlist']): - formats = self._extract_m3u8_formats( - video_info['src'], display_id, 'mp4', 'm3u8_native', m3u8_id='hls', - note='Download m3u8 information for video %d' % (idx + 1)) - self._sort_formats(formats) + subtitles = {} + caption_url = video_info.get('captionsUrl') + if caption_url: + subtitles = { + 'en': [{ + 'url': caption_url, + }] + } + entries.append({ + '_type': 'url_transparent', + 'url': 'http://players.brightcove.net/103207/default_default/index.html?videoId=ref:%s' % video_info['referenceId'], 'id': compat_str(video_info['id']), - 'formats': formats, 'title': video_info['title'], 'description': video_info.get('description'), 'duration': parse_duration(video_info.get('video_length')), @@ -80,6 +91,7 @@ class DiscoveryIE(InfoExtractor): 'thumbnail': video_info.get('thumbnailURL'), 'alt_title': video_info.get('secondary_title'), 'timestamp': parse_iso8601(video_info.get('publishedDate')), + 'subtitles': subtitles, }) return self.playlist_result(entries, display_id, video_title) diff --git a/youtube_dl/extractor/douyutv.py b/youtube_dl/extractor/douyutv.py index 3915cb182..ce6962755 100644 --- a/youtube_dl/extractor/douyutv.py +++ b/youtube_dl/extractor/douyutv.py @@ -18,7 +18,7 @@ class DouyuTVIE(InfoExtractor): 'display_id': 'iseven', 'ext': 'flv', 'title': 're:^清晨醒脑！T-ara根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'description': 'md5:f34981259a03e980a3c6404190a3ed61', + 'description': 're:.*m7show@163\.com.*', 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': '7师傅', 'uploader_id': '431925', @@ -43,7 +43,7 @@ class DouyuTVIE(InfoExtractor): 'params': { 'skip_download': True, }, - 'skip': 'Romm not found', + 'skip': 'Room not found', }, { 'url': 'http://www.douyutv.com/17732', 'info_dict': { @@ -51,7 +51,7 @@ class DouyuTVIE(InfoExtractor): 'display_id': '17732', 'ext': 'flv', 'title': 're:^清晨醒脑！T-ara根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'description': 'md5:f34981259a03e980a3c6404190a3ed61', + 'description': 're:.*m7show@163\.com.*', 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': '7师傅', 'uploader_id': '431925', @@ -75,13 +75,28 @@ class DouyuTVIE(InfoExtractor): room_id = self._html_search_regex( r'"room_id"\s*:\s*(\d+),', page, 'room id') - prefix = 'room/%s?aid=android&client_sys=android&time=%d' % ( - room_id, int(time.time())) - - auth = hashlib.md5((prefix + '1231').encode('ascii')).hexdigest() - config = self._download_json( - 'http://www.douyutv.com/api/v1/%s&auth=%s' % (prefix, auth), - video_id) + config = None + # Douyu API sometimes returns error "Unable to load the requested class: eticket_redis_cache" + # Retry with different parameters - same parameters cause same errors + for i in range(5): + prefix = 'room/%s?aid=android&client_sys=android&time=%d' % ( + room_id, int(time.time())) + auth = hashlib.md5((prefix + '1231').encode('ascii')).hexdigest() + + config_page = self._download_webpage( + 'http://www.douyutv.com/api/v1/%s&auth=%s' % (prefix, auth), + video_id) + try: + config = self._parse_json(config_page, video_id, fatal=False) + except ExtractorError: + # Wait some time before retrying to get a different time() value + self._sleep(1, video_id, msg_template='%(video_id)s: Error occurs. ' + 'Waiting for %(timeout)s seconds before retrying') + continue + else: + break + if config is None: + raise ExtractorError('Unable to fetch API result') data = config['data'] diff --git a/youtube_dl/extractor/dw.py b/youtube_dl/extractor/dw.py index ae7c571bd..d740652f1 100644 --- a/youtube_dl/extractor/dw.py +++ b/youtube_dl/extractor/dw.py @@ -2,13 +2,16 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + unified_strdate, +) from ..compat import compat_urlparse class DWIE(InfoExtractor): IE_NAME = 'dw' - _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+(?:av|e)-(?P<id>\d+)' _TESTS = [{ # video 'url': 'http://www.dw.com/en/intelligent-light/av-19112290', @@ -31,6 +34,18 @@ class DWIE(InfoExtractor): 'description': 'md5:bc9ca6e4e063361e21c920c53af12405', 'upload_date': '20160311', } + }, { + # DW documentaries, only last for one or two weeks + 'url': 'http://www.dw.com/en/documentaries-welcome-to-the-90s-2016-05-21/e-19220158-9798', + 'md5': '56b6214ef463bfb9a3b71aeb886f3cf1', + 'info_dict': { + 'id': '19274438', + 'ext': 'mp4', + 'title': 'Welcome to the 90s – Hip Hop', + 'description': 'Welcome to the 90s - The Golden Decade of Hip Hop', + 'upload_date': '20160521', + }, + 'skip': 'Video removed', }] def _real_extract(self, url): @@ -38,6 +53,7 @@ class DWIE(InfoExtractor): webpage = self._download_webpage(url, media_id) hidden_inputs = self._hidden_inputs(webpage) title = hidden_inputs['media_title'] + media_id = hidden_inputs.get('media_id') or media_id if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1': formats = self._extract_smil_formats( @@ -49,13 +65,20 @@ class DWIE(InfoExtractor): else: formats = [{'url': hidden_inputs['file_name']}] + upload_date = hidden_inputs.get('display_date') + if not upload_date: + upload_date = self._html_search_regex( + r'<span[^>]+class="date">([0-9.]+)\s*\|', webpage, + 'upload date', default=None) + upload_date = unified_strdate(upload_date) + return { 'id': media_id, 'title': title, 'description': self._og_search_description(webpage), 'thumbnail': hidden_inputs.get('preview_image'), 'duration': int_or_none(hidden_inputs.get('file_duration')), - 'upload_date': hidden_inputs.get('display_date'), + 'upload_date': upload_date, 'formats': formats, } diff --git a/youtube_dl/extractor/eagleplatform.py b/youtube_dl/extractor/eagleplatform.py index 0f8c73fd7..12d28d3b9 100644 --- a/youtube_dl/extractor/eagleplatform.py +++ b/youtube_dl/extractor/eagleplatform.py @@ -23,7 +23,7 @@ class EaglePlatformIE(InfoExtractor): _TESTS = [{ # http://lenta.ru/news/2015/03/06/navalny/ 'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201', - 'md5': '881ee8460e1b7735a8be938e2ffb362b', + # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used 'info_dict': { 'id': '227304', 'ext': 'mp4', @@ -50,6 +50,14 @@ class EaglePlatformIE(InfoExtractor): 'skip': 'Georestricted', }] + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//.+?\.media\.eagleplatform\.com/index/player\?.+?)\1', + webpage) + if mobj is not None: + return mobj.group('url') + @staticmethod def _handle_error(response): status = int_or_none(response.get('status', 200)) @@ -109,8 +117,11 @@ class EaglePlatformIE(InfoExtractor): mobj = re.search('/([^/]+)/index\.m3u8', m3u8_format['url']) if mobj: http_format = m3u8_format.copy() + video_url = mp4_url.replace(mp4_url_basename, mobj.group(1)) + if not self._is_valid_url(video_url, video_id): + continue http_format.update({ - 'url': mp4_url.replace(mp4_url_basename, mobj.group(1)), + 'url': video_url, 'format_id': m3u8_format['format_id'].replace('hls', 'http'), 'protocol': 'http', }) diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py index e006921ec..ac5d0fe24 100644 --- a/youtube_dl/extractor/eporner.py +++ b/youtube_dl/extractor/eporner.py @@ -11,8 +11,8 @@ from ..utils import ( class EpornerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\w+)/(?P<display_id>[\w-]+)' + _TESTS = [{ 'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/', 'md5': '39d486f046212d8e1b911c52ab4691f8', 'info_dict': { @@ -23,8 +23,12 @@ class EpornerIE(InfoExtractor): 'duration': 1838, 'view_count': int, 'age_limit': 18, - } - } + }, + }, { + # New (May 2016) URL layout + 'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py index db4b263bc..66c08bec4 100644 --- a/youtube_dl/extractor/espn.py +++ b/youtube_dl/extractor/espn.py @@ -8,6 +8,7 @@ class ESPNIE(InfoExtractor): _VALID_URL = r'https?://espn\.go\.com/(?:[^/]+/)*(?P<id>[^/]+)' _TESTS = [{ 'url': 'http://espn.go.com/video/clip?id=10365079', + 'md5': '60e5d097a523e767d06479335d1bdc58', 'info_dict': { 'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG', 'ext': 'mp4', @@ -15,21 +16,22 @@ class ESPNIE(InfoExtractor): 'description': None, }, 'params': { - # m3u8 download 'skip_download': True, }, + 'add_ie': ['OoyalaExternal'], }, { # intl video, from http://www.espnfc.us/video/mls-highlights/150/video/2743663/must-see-moments-best-of-the-mls-season 'url': 'http://espn.go.com/video/clip?id=2743663', + 'md5': 'f4ac89b59afc7e2d7dbb049523df6768', 'info_dict': { 'id': '50NDFkeTqRHB0nXBOK-RGdSG5YQPuxHg', 'ext': 'mp4', 'title': 'Must-See Moments: Best of the MLS season', }, 'params': { - # m3u8 download 'skip_download': True, }, + 'add_ie': ['OoyalaExternal'], }, { 'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079', 'only_matching': True, diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 6de3438fc..9f70ce752 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -3,6 +3,10 @@ from __future__ import unicode_literals from .abc import ABCIE from .abc7news import Abc7NewsIE +from .abcnews import ( + AbcNewsIE, + AbcNewsVideoIE, +) from .academicearth import AcademicEarthCourseIE from .acast import ( ACastIE, @@ -16,7 +20,11 @@ from .adobetv import ( AdobeTVVideoIE, ) from .adultswim import AdultSwimIE -from .aenetworks import AENetworksIE +from .aenetworks import ( + AENetworksIE, + HistoryTopicIE, +) +from .afreecatv import AfreecaTVIE from .aftonbladet import AftonbladetIE from .airmozilla import AirMozillaIE from .aljazeera import AlJazeeraIE @@ -39,7 +47,6 @@ from .archiveorg import ArchiveOrgIE from .ard import ( ARDIE, ARDMediathekIE, - SportschauIE, ) from .arte import ( ArteTvIE, @@ -52,6 +59,7 @@ from .arte import ( ArteTVDDCIE, ArteTVMagazineIE, ArteTVEmbedIE, + ArteTVPlaylistIE, ) from .atresplayer import AtresPlayerIE from .atttechchannel import ATTTechChannelIE @@ -65,6 +73,8 @@ from .bandcamp import BandcampIE, BandcampAlbumIE from .bbc import ( BBCCoUkIE, BBCCoUkArticleIE, + BBCCoUkIPlayerPlaylistIE, + BBCCoUkPlaylistIE, BBCIE, ) from .beeg import BeegIE @@ -75,6 +85,7 @@ from .bigflix import BigflixIE from .bild import BildIE from .bilibili import BiliBiliIE from .biobiochiletv import BioBioChileTVIE +from .biqle import BIQLEIE from .bleacherreport import ( BleacherReportIE, BleacherReportCMSIE, @@ -101,11 +112,16 @@ from .camwithher import CamWithHerIE from .canalplus import CanalplusIE from .canalc2 import Canalc2IE from .canvas import CanvasIE +from .carambatv import ( + CarambaTVIE, + CarambaTVPageIE, +) from .cbc import ( CBCIE, CBCPlayerIE, ) from .cbs import CBSIE +from .cbslocal import CBSLocalIE from .cbsinteractive import CBSInteractiveIE from .cbsnews import ( CBSNewsIE, @@ -123,11 +139,11 @@ from .chirbit import ( ChirbitProfileIE, ) from .cinchcast import CinchcastIE -from .cinemassacre import CinemassacreIE -from .cliprs import ClipRsIE from .clipfish import ClipfishIE from .cliphunter import CliphunterIE +from .cliprs import ClipRsIE from .clipsyndicate import ClipsyndicateIE +from .closertotruth import CloserToTruthIE from .cloudy import CloudyIE from .clubic import ClubicIE from .clyp import ClypIE @@ -138,7 +154,7 @@ from .cnn import ( CNNBlogsIE, CNNArticleIE, ) -from .collegehumor import CollegeHumorIE +from .coub import CoubIE from .collegerama import CollegeRamaIE from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE from .comcarcoff import ComCarCoffIE @@ -155,8 +171,11 @@ from .crunchyroll import ( ) from .cspan import CSpanIE from .ctsnews import CtsNewsIE +from .ctv import CTVIE +from .ctvnews import CTVNewsIE from .cultureunplugged import CultureUnpluggedIE from .cwtv import CWTVIE +from .dailymail import DailyMailIE from .dailymotion import ( DailymotionIE, DailymotionPlaylistIE, @@ -226,6 +245,7 @@ from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE from .expotv import ExpoTVIE from .extremetube import ExtremeTubeIE +from .eyedotv import EyedoTVIE from .facebook import FacebookIE from .faz import FazIE from .fc2 import FC2IE @@ -236,8 +256,10 @@ from .fivemin import FiveMinIE from .fivetv import FiveTVIE from .fktv import FKTVIE from .flickr import FlickrIE +from .flipagram import FlipagramIE from .folketinget import FolketingetIE from .footyroom import FootyRoomIE +from .formula1 import Formula1IE from .fourtube import FourTubeIE from .fox import FOXIE from .foxgay import FoxgayIE @@ -260,6 +282,7 @@ from .freespeech import FreespeechIE from .freevideo import FreeVideoIE from .funimation import FunimationIE from .funnyordie import FunnyOrDieIE +from .fusion import FusionIE from .gameinformer import GameInformerIE from .gamekings import GamekingsIE from .gameone import ( @@ -269,7 +292,6 @@ from .gameone import ( from .gamersyde import GamersydeIE from .gamespot import GameSpotIE from .gamestar import GameStarIE -from .gametrailers import GametrailersIE from .gazeta import GazetaIE from .gdcvault import GDCVaultIE from .generic import GenericIE @@ -282,6 +304,7 @@ from .globo import ( GloboArticleIE, ) from .godtube import GodTubeIE +from .godtv import GodTVIE from .goldenmoustache import GoldenMoustacheIE from .golem import GolemIE from .googledrive import GoogleDriveIE @@ -304,6 +327,10 @@ from .hotnewhiphop import HotNewHipHopIE from .hotstar import HotStarIE from .howcast import HowcastIE from .howstuffworks import HowStuffWorksIE +from .hrti import ( + HRTiIE, + HRTiPlaylistIE, +) from .huffpost import HuffPostIE from .hypem import HypemIE from .iconosquare import IconosquareIE @@ -342,6 +369,7 @@ from .jove import JoveIE from .jwplatform import JWPlatformIE from .jpopsukitv import JpopsukiIE from .kaltura import KalturaIE +from .kamcord import KamcordIE from .kanalplay import KanalPlayIE from .kankan import KankanIE from .karaoketv import KaraoketvIE @@ -365,6 +393,7 @@ from .kuwo import ( ) from .la7 import LA7IE from .laola1tv import Laola1TvIE +from .learnr import LearnrIE from .lecture2go import Lecture2GoIE from .lemonde import LemondeIE from .leeco import ( @@ -372,6 +401,7 @@ from .leeco import ( LePlaylistIE, LetvCloudIE, ) +from .libraryofcongress import LibraryOfCongressIE from .libsyn import LibsynIE from .lifenews import ( LifeNewsIE, @@ -382,6 +412,7 @@ from .limelight import ( LimelightChannelIE, LimelightChannelListIE, ) +from .litv import LiTVIE from .liveleak import LiveLeakIE from .livestream import ( LivestreamIE, @@ -389,6 +420,7 @@ from .livestream import ( LivestreamShortenerIE, ) from .lnkgo import LnkGoIE +from .localnews8 import LocalNews8IE from .lovehomeporn import LoveHomePornIE from .lrt import LRTIE from .lynda import ( @@ -400,13 +432,17 @@ from .macgamestore import MacGameStoreIE from .mailru import MailRuIE from .makerschannel import MakersChannelIE from .makertv import MakerTVIE -from .malemotion import MalemotionIE from .matchtv import MatchTVIE from .mdr import MDRIE +from .meta import METAIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mgoon import MgoonIE from .mgtv import MGTVIE +from .microsoftvirtualacademy import ( + MicrosoftVirtualAcademyIE, + MicrosoftVirtualAcademyCourseIE, +) from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE from .minoto import MinotoIE @@ -431,6 +467,7 @@ from .motherless import MotherlessIE from .motorsport import MotorsportIE from .movieclips import MovieClipsIE from .moviezine import MoviezineIE +from .msn import MSNIE from .mtv import ( MTVIE, MTVServicesEmbeddedIE, @@ -439,8 +476,7 @@ from .mtv import ( ) from .muenchentv import MuenchenTVIE from .musicplayon import MusicPlayOnIE -from .muzu import MuzuTVIE -from .mwave import MwaveIE +from .mwave import MwaveIE, MwaveMeetGreetIE from .myspace import MySpaceIE, MySpaceAlbumIE from .myspass import MySpassIE from .myvi import MyviIE @@ -458,7 +494,6 @@ from .nbc import ( NBCNewsIE, NBCSportsIE, NBCSportsVPlayerIE, - MSNBCIE, ) from .ndr import ( NDRIE, @@ -495,8 +530,12 @@ from .nhl import ( NHLVideocenterCategoryIE, NHLIE, ) -from .nick import NickIE +from .nick import ( + NickIE, + NickDeIE, +) from .niconico import NiconicoIE, NiconicoPlaylistIE +from .ninecninemedia import NineCNineMediaIE from .ninegag import NineGagIE from .noco import NocoIE from .normalboots import NormalbootsIE @@ -544,6 +583,10 @@ from .nytimes import ( from .nuvid import NuvidIE from .odnoklassniki import OdnoklassnikiIE from .oktoberfesttv import OktoberfestTVIE +from .onet import ( + OnetIE, + OnetChannelIE, +) from .onionstudios import OnionStudiosIE from .ooyala import ( OoyalaIE, @@ -562,7 +605,10 @@ from .parliamentliveuk import ParliamentLiveUKIE from .patreon import PatreonIE from .pbs import PBSIE from .people import PeopleIE -from .periscope import PeriscopeIE +from .periscope import ( + PeriscopeIE, + PeriscopeUserIE, +) from .philharmoniedeparis import PhilharmonieDeParisIE from .phoenix import PhoenixIE from .photobucket import PhotobucketIE @@ -579,6 +625,7 @@ from .pluralsight import ( PluralsightCourseIE, ) from .podomatic import PodomaticIE +from .polskieradio import PolskieRadioIE from .porn91 import Porn91IE from .pornhd import PornHdIE from .pornhub import ( @@ -602,7 +649,14 @@ from .qqmusic import ( QQMusicToplistIE, QQMusicPlaylistIE, ) -from .r7 import R7IE +from .r7 import ( + R7IE, + R7ArticleIE, +) +from .radiocanada import ( + RadioCanadaIE, + RadioCanadaAudioVideoIE, +) from .radiode import RadioDeIE from .radiojavan import RadioJavanIE from .radiobremen import RadioBremenIE @@ -616,11 +670,16 @@ from .rds import RDSIE from .redtube import RedTubeIE from .regiotv import RegioTVIE from .restudy import RestudyIE +from .reuters import ReutersIE from .reverbnation import ReverbNationIE -from .revision3 import Revision3IE +from .revision3 import ( + Revision3EmbedIE, + Revision3IE, +) from .rice import RICEIE from .ringtv import RingTVIE from .ro220 import Ro220IE +from .rockstargames import RockstarGamesIE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtbf import RTBFIE @@ -656,18 +715,21 @@ from .screencast import ScreencastIE from .screencastomatic import ScreencastOMaticIE from .screenjunkies import ScreenJunkiesIE from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE +from .seeker import SeekerIE from .senateisvp import SenateISVPIE +from .sendtonews import SendtoNewsIE from .servingsys import ServingSysIE from .sexu import SexuIE -from .sexykarma import SexyKarmaIE from .shahid import ShahidIE from .shared import SharedIE from .sharesix import ShareSixIE from .sina import SinaIE +from .sixplay import SixPlayIE from .skynewsarabia import ( SkyNewsArabiaIE, SkyNewsArabiaArticleIE, ) +from .skysports import SkySportsIE from .slideshare import SlideshareIE from .slutload import SlutloadIE from .smotri import ( @@ -676,10 +738,6 @@ from .smotri import ( SmotriUserIE, SmotriBroadcastIE, ) -from .snagfilms import ( - SnagFilmsIE, - SnagFilmsEmbedIE, -) from .snotr import SnotrIE from .sohu import SohuIE from .soundcloud import ( @@ -712,6 +770,7 @@ from .sportbox import ( SportBoxEmbedIE, ) from .sportdeutschland import SportDeutschlandIE +from .sportschau import SportschauIE from .srgssr import ( SRGSSRIE, SRGSSRPlayIE, @@ -731,7 +790,10 @@ from .svt import ( from .swrmediathek import SWRMediathekIE from .syfy import SyfyIE from .sztvhu import SztvHuIE -from .tagesschau import TagesschauIE +from .tagesschau import ( + TagesschauPlayerIE, + TagesschauIE, +) from .tapely import TapelyIE from .tass import TassIE from .tdslifeway import TDSLifewayIE @@ -749,6 +811,7 @@ from .telecinco import TelecincoIE from .telegraaf import TelegraafIE from .telemb import TeleMBIE from .teletask import TeleTaskIE +from .telewebion import TelewebionIE from .testurl import TestURLIE from .tf1 import TF1IE from .theintercept import TheInterceptIE @@ -761,6 +824,7 @@ from .thesixtyone import TheSixtyOneIE from .thestar import TheStarIE from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE +from .threeqsdn import ThreeQSDNIE from .tinypic import TinyPicIE from .tlc import TlcDeIE from .tmz import ( @@ -813,7 +877,10 @@ from .tvc import ( ) from .tvigle import TvigleIE from .tvland import TVLandIE -from .tvp import TvpIE, TvpSeriesIE +from .tvp import ( + TVPIE, + TVPSeriesIE, +) from .tvplay import TVPlayIE from .tweakers import TweakersIE from .twentyfourvideo import TwentyFourVideoIE @@ -828,8 +895,8 @@ from .twitch import ( TwitchVodIE, TwitchProfileIE, TwitchPastBroadcastsIE, - TwitchBookmarksIE, TwitchStreamIE, + TwitchClipsIE, ) from .twitter import ( TwitterCardIE, @@ -844,16 +911,23 @@ from .udn import UDNEmbedIE from .digiteka import DigitekaIE from .unistra import UnistraIE from .urort import UrortIE +from .urplay import URPlayIE from .usatoday import USATodayIE from .ustream import UstreamIE, UstreamChannelIE -from .ustudio import UstudioIE +from .ustudio import ( + UstudioIE, + UstudioEmbedIE, +) from .varzesh3 import Varzesh3IE from .vbox7 import Vbox7IE from .veehd import VeeHDIE from .veoh import VeohIE from .vessel import VesselIE from .vesti import VestiIE -from .vevo import VevoIE +from .vevo import ( + VevoIE, + VevoPlaylistIE, +) from .vgtv import ( BTArticleIE, BTVestlendingenIE, @@ -864,6 +938,7 @@ from .vice import ( ViceIE, ViceShowIE, ) +from .vidbit import VidbitIE from .viddler import ViddlerIE from .videodetective import VideoDetectiveIE from .videofyme import VideofyMeIE @@ -875,6 +950,7 @@ from .videomore import ( ) from .videopremium import VideoPremiumIE from .videott import VideoTtIE +from .vidio import VidioIE from .vidme import ( VidmeIE, VidmeUserIE, @@ -882,6 +958,10 @@ from .vidme import ( ) from .vidzi import VidziIE from .vier import VierIE, VierVideosIE +from .viewlift import ( + ViewLiftIE, + ViewLiftEmbedIE, +) from .viewster import ViewsterIE from .viidea import ViideaIE from .vimeo import ( @@ -916,25 +996,29 @@ from .vporn import VpornIE from .vrt import VRTIE from .vube import VubeIE from .vuclip import VuClipIE -from .vulture import VultureIE from .walla import WallaIE -from .washingtonpost import WashingtonPostIE +from .washingtonpost import ( + WashingtonPostIE, + WashingtonPostArticleIE, +) from .wat import WatIE +from .watchindianporn import WatchIndianPornIE from .wdr import ( WDRIE, WDRMobileIE, - WDRMausIE, ) from .webofstories import ( WebOfStoriesIE, WebOfStoriesPlaylistIE, ) -from .weibo import WeiboIE from .weiqitv import WeiqiTVIE from .wimp import WimpIE from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE -from .wrzuta import WrzutaIE +from .wrzuta import ( + WrzutaIE, + WrzutaPlaylistIE, +) from .wsj import WSJIE from .xbef import XBefIE from .xboxclips import XboxClipsIE @@ -943,6 +1027,12 @@ from .xhamster import ( XHamsterIE, XHamsterEmbedIE, ) +from .xiami import ( + XiamiSongIE, + XiamiAlbumIE, + XiamiArtistIE, + XiamiCollectionIE +) from .xminus import XMinusIE from .xnxx import XNXXIE from .xstream import XstreamIE @@ -964,7 +1054,10 @@ from .yesjapan import YesJapanIE from .yinyuetai import YinYueTaiIE from .ynet import YnetIE from .youjizz import YouJizzIE -from .youku import YoukuIE +from .youku import ( + YoukuIE, + YoukuShowIE, +) from .youporn import YouPornIE from .yourupload import YourUploadIE from .youtube import ( @@ -979,6 +1072,7 @@ from .youtube import ( YoutubeSearchDateIE, YoutubeSearchIE, YoutubeSearchURLIE, + YoutubeSharedVideoIE, YoutubeShowIE, YoutubeSubscriptionsIE, YoutubeTruncatedIDIE, diff --git a/youtube_dl/extractor/eyedotv.py b/youtube_dl/extractor/eyedotv.py new file mode 100644 index 000000000..2f3035147 --- /dev/null +++ b/youtube_dl/extractor/eyedotv.py @@ -0,0 +1,64 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + xpath_text, + parse_duration, + ExtractorError, +) + + +class EyedoTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?eyedo\.tv/[^/]+/(?:#!/)?Live/Detail/(?P<id>[0-9]+)' + _TEST = { + 'url': 'https://www.eyedo.tv/en-US/#!/Live/Detail/16301', + 'md5': 'ba14f17995cdfc20c36ba40e21bf73f7', + 'info_dict': { + 'id': '16301', + 'ext': 'mp4', + 'title': 'Journée du conseil scientifique de l\'Afnic 2015', + 'description': 'md5:4abe07293b2f73efc6e1c37028d58c98', + 'uploader': 'Afnic Live', + 'uploader_id': '8023', + } + } + _ROOT_URL = 'http://live.eyedo.net:1935/' + + def _real_extract(self, url): + video_id = self._match_id(url) + video_data = self._download_xml('http://eyedo.tv/api/live/GetLive/%s' % video_id, video_id) + + def _add_ns(path): + return self._xpath_ns(path, 'http://schemas.datacontract.org/2004/07/EyeDo.Core.Implementation.Web.ViewModels.Api') + + title = xpath_text(video_data, _add_ns('Titre'), 'title', True) + state_live_code = xpath_text(video_data, _add_ns('StateLiveCode'), 'title', True) + if state_live_code == 'avenir': + raise ExtractorError( + '%s said: We\'re sorry, but this video is not yet available.' % self.IE_NAME, + expected=True) + + is_live = state_live_code == 'live' + m3u8_url = None + # http://eyedo.tv/Content/Html5/Scripts/html5view.js + if is_live: + if xpath_text(video_data, 'Cdn') == 'true': + m3u8_url = 'http://rrr.sz.xlcdn.com/?account=eyedo&file=A%s&type=live&service=wowza&protocol=http&output=playlist.m3u8' % video_id + else: + m3u8_url = self._ROOT_URL + 'w/%s/eyedo_720p/playlist.m3u8' % video_id + else: + m3u8_url = self._ROOT_URL + 'replay-w/%s/mp4:%s.mp4/playlist.m3u8' % (video_id, video_id) + + return { + 'id': video_id, + 'title': title, + 'formats': self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8' if is_live else 'm3u8_native'), + 'description': xpath_text(video_data, _add_ns('Description')), + 'duration': parse_duration(xpath_text(video_data, _add_ns('Duration'))), + 'uploader': xpath_text(video_data, _add_ns('Createur')), + 'uploader_id': xpath_text(video_data, _add_ns('CreateurId')), + 'chapter': xpath_text(video_data, _add_ns('ChapitreTitre')), + 'chapter_id': xpath_text(video_data, _add_ns('ChapitreId')), + } diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index f5bbd39d2..0d43acc4a 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -129,6 +129,21 @@ class FacebookIE(InfoExtractor): 'only_matching': True, }] + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage) + if mobj is not None: + return mobj.group('url') + + # Facebook API embed + # see https://developers.facebook.com/docs/plugins/embedded-video-player + mobj = re.search(r'''(?x)<div[^>]+ + class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+ + data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''', webpage) + if mobj is not None: + return mobj.group('url') + def _login(self): (useremail, password) = self._get_login_info() if useremail is None: @@ -204,12 +219,23 @@ class FacebookIE(InfoExtractor): BEFORE = '{swf.addParam(param[0], param[1]);});' AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' - m = re.search(re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER), webpage) - if m: - swf_params = m.group(1).replace('\\\\', '\\').replace('\\"', '"') + PATTERN = re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER) + + for m in re.findall(PATTERN, webpage): + swf_params = m.replace('\\\\', '\\').replace('\\"', '"') data = dict(json.loads(swf_params)) params_raw = compat_urllib_parse_unquote(data['params']) - video_data = json.loads(params_raw)['video_data'] + video_data_candidate = json.loads(params_raw)['video_data'] + for _, f in video_data_candidate.items(): + if not f: + continue + if isinstance(f, dict): + f = [f] + if isinstance(f, list): + continue + if f[0].get('video_id') == video_id: + video_data = video_data_candidate + break def video_data_list2dict(video_data): ret = {} @@ -239,6 +265,8 @@ class FacebookIE(InfoExtractor): formats = [] for format_id, f in video_data.items(): + if f and isinstance(f, dict): + f = [f] if not f or not isinstance(f, list): continue for quality in ('sd', 'hd'): diff --git a/youtube_dl/extractor/fczenit.py b/youtube_dl/extractor/fczenit.py index f1f150ef2..8d1010b88 100644 --- a/youtube_dl/extractor/fczenit.py +++ b/youtube_dl/extractor/fczenit.py @@ -1,20 +1,19 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..compat import compat_urlparse class FczenitIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/gl(?P<id>[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/(?P<id>[0-9]+)' _TEST = { - 'url': 'http://fc-zenit.ru/video/gl6785/', - 'md5': '458bacc24549173fe5a5aa29174a5606', + 'url': 'http://fc-zenit.ru/video/41044/', + 'md5': '0e3fab421b455e970fa1aa3891e57df0', 'info_dict': { - 'id': '6785', + 'id': '41044', 'ext': 'mp4', - 'title': '«Зенит-ТВ»: как Олег Шатов играл против «Урала»', + 'title': 'Так пишется история: казанский разгром ЦСКА на «Зенит-ТВ»', }, } @@ -22,15 +21,23 @@ class FczenitIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - video_title = self._html_search_regex(r'<div class=\"photoalbum__title\">([^<]+)', webpage, 'title') + video_title = self._html_search_regex( + r'<[^>]+class=\"photoalbum__title\">([^<]+)', webpage, 'title') + + video_items = self._parse_json(self._search_regex( + r'arrPath\s*=\s*JSON\.parse\(\'(.+)\'\)', webpage, 'video items'), + video_id) - bitrates_raw = self._html_search_regex(r'bitrates:.*\n(.*)\]', webpage, 'video URL') - bitrates = re.findall(r'url:.?\'(.+?)\'.*?bitrate:.?([0-9]{3}?)', bitrates_raw) + def merge_dicts(*dicts): + ret = {} + for a_dict in dicts: + ret.update(a_dict) + return ret formats = [{ - 'url': furl, - 'tbr': tbr, - } for furl, tbr in bitrates] + 'url': compat_urlparse.urljoin(url, video_url), + 'tbr': int(tbr), + } for tbr, video_url in merge_dicts(*video_items).items()] self._sort_formats(formats) diff --git a/youtube_dl/extractor/flickr.py b/youtube_dl/extractor/flickr.py index 0a3de1498..a8e1bf42a 100644 --- a/youtube_dl/extractor/flickr.py +++ b/youtube_dl/extractor/flickr.py @@ -24,13 +24,28 @@ class FlickrIE(InfoExtractor): 'upload_date': '20110423', 'uploader_id': '10922353@N03', 'uploader': 'Forest Wander', + 'uploader_url': 'https://www.flickr.com/photos/forestwander-nature-pictures/', 'comment_count': int, 'view_count': int, 'tags': list, + 'license': 'Attribution-ShareAlike', } } - _API_BASE_URL = 'https://api.flickr.com/services/rest?' + # https://help.yahoo.com/kb/flickr/SLN25525.html + _LICENSES = { + '0': 'All Rights Reserved', + '1': 'Attribution-NonCommercial-ShareAlike', + '2': 'Attribution-NonCommercial', + '3': 'Attribution-NonCommercial-NoDerivs', + '4': 'Attribution', + '5': 'Attribution-ShareAlike', + '6': 'Attribution-NoDerivs', + '7': 'No known copyright restrictions', + '8': 'United States government work', + '9': 'Public Domain Dedication (CC0)', + '10': 'Public Domain Work', + } def _call_api(self, method, video_id, api_key, note, secret=None): query = { @@ -75,6 +90,9 @@ class FlickrIE(InfoExtractor): self._sort_formats(formats) owner = video_info.get('owner', {}) + uploader_id = owner.get('nsid') + uploader_path = owner.get('path_alias') or uploader_id + uploader_url = 'https://www.flickr.com/photos/%s/' % uploader_path if uploader_path else None return { 'id': video_id, @@ -83,11 +101,13 @@ class FlickrIE(InfoExtractor): 'formats': formats, 'timestamp': int_or_none(video_info.get('dateuploaded')), 'duration': int_or_none(video_info.get('video', {}).get('duration')), - 'uploader_id': owner.get('nsid'), + 'uploader_id': uploader_id, 'uploader': owner.get('realname'), + 'uploader_url': uploader_url, 'comment_count': int_or_none(video_info.get('comments', {}).get('_content')), 'view_count': int_or_none(video_info.get('views')), - 'tags': [tag.get('_content') for tag in video_info.get('tags', {}).get('tag', [])] + 'tags': [tag.get('_content') for tag in video_info.get('tags', {}).get('tag', [])], + 'license': self._LICENSES.get(video_info.get('license')), } else: raise ExtractorError('not a video', expected=True) diff --git a/youtube_dl/extractor/flipagram.py b/youtube_dl/extractor/flipagram.py new file mode 100644 index 000000000..acb6133ff --- /dev/null +++ b/youtube_dl/extractor/flipagram.py @@ -0,0 +1,115 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + int_or_none, + float_or_none, + try_get, + unified_timestamp, +) + + +class FlipagramIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?flipagram\.com/f/(?P<id>[^/?#&]+)' + _TEST = { + 'url': 'https://flipagram.com/f/nyvTSJMKId', + 'md5': '888dcf08b7ea671381f00fab74692755', + 'info_dict': { + 'id': 'nyvTSJMKId', + 'ext': 'mp4', + 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction', + 'description': 'md5:d55e32edc55261cae96a41fa85ff630e', + 'duration': 35.571, + 'timestamp': 1461244995, + 'upload_date': '20160421', + 'uploader': 'kitty juria', + 'uploader_id': 'sjuria101', + 'creator': 'kitty juria', + 'view_count': int, + 'like_count': int, + 'repost_count': int, + 'comment_count': int, + 'comments': list, + 'formats': 'mincount:2', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + video_data = self._parse_json( + self._search_regex( + r'window\.reactH2O\s*=\s*({.+});', webpage, 'video data'), + video_id) + + flipagram = video_data['flipagram'] + video = flipagram['video'] + + json_ld = self._search_json_ld(webpage, video_id, default=False) + title = json_ld.get('title') or flipagram['captionText'] + description = json_ld.get('description') or flipagram.get('captionText') + + formats = [{ + 'url': video['url'], + 'width': int_or_none(video.get('width')), + 'height': int_or_none(video.get('height')), + 'filesize': int_or_none(video_data.get('size')), + }] + + preview_url = try_get( + flipagram, lambda x: x['music']['track']['previewUrl'], compat_str) + if preview_url: + formats.append({ + 'url': preview_url, + 'ext': 'm4a', + 'vcodec': 'none', + }) + + self._sort_formats(formats) + + counts = flipagram.get('counts', {}) + user = flipagram.get('user', {}) + video_data = flipagram.get('video', {}) + + thumbnails = [{ + 'url': self._proto_relative_url(cover['url']), + 'width': int_or_none(cover.get('width')), + 'height': int_or_none(cover.get('height')), + 'filesize': int_or_none(cover.get('size')), + } for cover in flipagram.get('covers', []) if cover.get('url')] + + # Note that this only retrieves comments that are initally loaded. + # For videos with large amounts of comments, most won't be retrieved. + comments = [] + for comment in video_data.get('comments', {}).get(video_id, {}).get('items', []): + text = comment.get('comment') + if not text or not isinstance(text, list): + continue + comments.append({ + 'author': comment.get('user', {}).get('name'), + 'author_id': comment.get('user', {}).get('username'), + 'id': comment.get('id'), + 'text': text[0], + 'timestamp': unified_timestamp(comment.get('created')), + }) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': float_or_none(flipagram.get('duration'), 1000), + 'thumbnails': thumbnails, + 'timestamp': unified_timestamp(flipagram.get('iso8601Created')), + 'uploader': user.get('name'), + 'uploader_id': user.get('username'), + 'creator': user.get('name'), + 'view_count': int_or_none(counts.get('plays')), + 'like_count': int_or_none(counts.get('likes')), + 'repost_count': int_or_none(counts.get('reflips')), + 'comment_count': int_or_none(counts.get('comments')), + 'comments': comments, + 'formats': formats, + } diff --git a/youtube_dl/extractor/formula1.py b/youtube_dl/extractor/formula1.py new file mode 100644 index 000000000..322c41e5a --- /dev/null +++ b/youtube_dl/extractor/formula1.py @@ -0,0 +1,26 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class Formula1IE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?formula1\.com/content/fom-website/en/video/\d{4}/\d{1,2}/(?P<id>.+?)\.html' + _TEST = { + 'url': 'http://www.formula1.com/content/fom-website/en/video/2016/5/Race_highlights_-_Spain_2016.html', + 'md5': '8c79e54be72078b26b89e0e111c0502b', + 'info_dict': { + 'id': 'JvYXJpMzE6pArfHWm5ARp5AiUmD-gibV', + 'ext': 'flv', + 'title': 'Race highlights - Spain 2016', + }, + 'add_ie': ['Ooyala'], + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + ooyala_embed_code = self._search_regex( + r'data-videoid="([^"]+)"', webpage, 'ooyala embed code') + return self.url_result( + 'ooyala:%s' % ooyala_embed_code, 'Ooyala', ooyala_embed_code) diff --git a/youtube_dl/extractor/foxsports.py b/youtube_dl/extractor/foxsports.py index df7665176..a3bb98377 100644 --- a/youtube_dl/extractor/foxsports.py +++ b/youtube_dl/extractor/foxsports.py @@ -1,7 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import smuggle_url +from ..utils import ( + smuggle_url, + update_url_query, +) class FoxSportsIE(InfoExtractor): @@ -9,11 +12,15 @@ class FoxSportsIE(InfoExtractor): _TEST = { 'url': 'http://www.foxsports.com/video?vid=432609859715', + 'md5': 'b49050e955bebe32c301972e4012ac17', 'info_dict': { - 'id': 'gA0bHB3Ladz3', - 'ext': 'flv', + 'id': 'i0qKWsk3qJaM', + 'ext': 'mp4', 'title': 'Courtney Lee on going up 2-0 in series vs. Blazers', 'description': 'Courtney Lee talks about Memphis being focused.', + 'upload_date': '20150423', + 'timestamp': 1429761109, + 'uploader': 'NEWA-FNG-FOXSPORTS', }, 'add_ie': ['ThePlatform'], } @@ -28,5 +35,8 @@ class FoxSportsIE(InfoExtractor): r"data-player-config='([^']+)'", webpage, 'data player config'), video_id) - return self.url_result(smuggle_url( - config['releaseURL'] + '&manifest=f4m', {'force_smil_url': True})) + return self.url_result(smuggle_url(update_url_query( + config['releaseURL'], { + 'mbr': 'true', + 'switch': 'http', + }), {'force_smil_url': True})) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index ad94e31f3..7653975e3 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -14,7 +14,10 @@ from ..utils import ( parse_duration, determine_ext, ) -from .dailymotion import DailymotionCloudIE +from .dailymotion import ( + DailymotionIE, + DailymotionCloudIE, +) class FranceTVBaseInfoExtractor(InfoExtractor): @@ -188,6 +191,21 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): 'params': { 'skip_download': True, }, + }, { + # Dailymotion embed + 'url': 'http://www.francetvinfo.fr/politique/notre-dame-des-landes/video-sur-france-inter-cecile-duflot-denonce-le-regard-meprisant-de-patrick-cohen_1520091.html', + 'md5': 'ee7f1828f25a648addc90cb2687b1f12', + 'info_dict': { + 'id': 'x4iiko0', + 'ext': 'mp4', + 'title': 'NDDL, référendum, Brexit : Cécile Duflot répond à Patrick Cohen', + 'description': 'Au lendemain de la victoire du "oui" au référendum sur l\'aéroport de Notre-Dame-des-Landes, l\'ancienne ministre écologiste est l\'invitée de Patrick Cohen. Plus d\'info : https://www.franceinter.fr/emissions/le-7-9/le-7-9-27-juin-2016', + 'timestamp': 1467011958, + 'upload_date': '20160627', + 'uploader': 'France Inter', + 'uploader_id': 'x2q2ez', + }, + 'add_ie': ['Dailymotion'], }] def _real_extract(self, url): @@ -197,7 +215,13 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage) if dmcloud_url: - return self.url_result(dmcloud_url, 'DailymotionCloud') + return self.url_result(dmcloud_url, DailymotionCloudIE.ie_key()) + + dailymotion_urls = DailymotionIE._extract_urls(webpage) + if dailymotion_urls: + return self.playlist_result([ + self.url_result(dailymotion_url, DailymotionIE.ie_key()) + for dailymotion_url in dailymotion_urls]) video_id, catalogue = self._search_regex( (r'id-video=([^@]+@[^"]+)', diff --git a/youtube_dl/extractor/funimation.py b/youtube_dl/extractor/funimation.py index 1eb528f31..0ad0d9b6a 100644 --- a/youtube_dl/extractor/funimation.py +++ b/youtube_dl/extractor/funimation.py @@ -2,6 +2,10 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import ( + compat_HTTPError, + compat_urllib_parse_unquote_plus, +) from ..utils import ( clean_html, determine_ext, @@ -27,6 +31,7 @@ class FunimationIE(InfoExtractor): 'description': 'md5:1769f43cd5fc130ace8fd87232207892', 'thumbnail': 're:https?://.*\.jpg', }, + 'skip': 'Access without user interaction is forbidden by CloudFlare, and video removed', }, { 'url': 'http://www.funimation.com/shows/hacksign/videos/official/role-play', 'info_dict': { @@ -37,6 +42,7 @@ class FunimationIE(InfoExtractor): 'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd', 'thumbnail': 're:https?://.*\.jpg', }, + 'skip': 'Access without user interaction is forbidden by CloudFlare', }, { 'url': 'http://www.funimation.com/shows/attack-on-titan-junior-high/videos/promotional/broadcast-dub-preview', 'info_dict': { @@ -47,8 +53,36 @@ class FunimationIE(InfoExtractor): 'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803', 'thumbnail': 're:https?://.*\.(?:jpg|png)', }, + 'skip': 'Access without user interaction is forbidden by CloudFlare', }] + _LOGIN_URL = 'http://www.funimation.com/login' + + def _download_webpage(self, *args, **kwargs): + try: + return super(FunimationIE, self)._download_webpage(*args, **kwargs) + except ExtractorError as ee: + if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: + response = ee.cause.read() + if b'>Please complete the security check to access<' in response: + raise ExtractorError( + 'Access to funimation.com is blocked by CloudFlare. ' + 'Please browse to http://www.funimation.com/, solve ' + 'the reCAPTCHA, export browser cookies to a text file,' + ' and then try again with --cookies YOUR_COOKIE_FILE.', + expected=True) + raise + + def _extract_cloudflare_session_ua(self, url): + ci_session_cookie = self._get_cookies(url).get('ci_session') + if ci_session_cookie: + ci_session = compat_urllib_parse_unquote_plus(ci_session_cookie.value) + # ci_session is a string serialized by PHP function serialize() + # This case is simple enough to use regular expressions only + return self._search_regex( + r'"user_agent";s:\d+:"([^"]+)"', ci_session, 'user agent', + default=None) + def _login(self): (username, password) = self._get_login_info() if username is None: @@ -57,8 +91,11 @@ class FunimationIE(InfoExtractor): 'email_field': username, 'password_field': password, }) - login_request = sanitized_Request('http://www.funimation.com/login', data, headers={ - 'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0', + user_agent = self._extract_cloudflare_session_ua(self._LOGIN_URL) + if not user_agent: + user_agent = 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0' + login_request = sanitized_Request(self._LOGIN_URL, data, headers={ + 'User-Agent': user_agent, 'Content-Type': 'application/x-www-form-urlencoded' }) login_page = self._download_webpage( @@ -103,11 +140,16 @@ class FunimationIE(InfoExtractor): ('mobile', 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'), ) + user_agent = self._extract_cloudflare_session_ua(url) + if user_agent: + USER_AGENTS = ((None, user_agent),) + for kind, user_agent in USER_AGENTS: request = sanitized_Request(url) request.add_header('User-Agent', user_agent) webpage = self._download_webpage( - request, display_id, 'Downloading %s webpage' % kind) + request, display_id, + 'Downloading %s webpage' % kind if kind else 'Downloading webpage') playlist = self._parse_json( self._search_regex( diff --git a/youtube_dl/extractor/fusion.py b/youtube_dl/extractor/fusion.py new file mode 100644 index 000000000..b4ab4cbb7 --- /dev/null +++ b/youtube_dl/extractor/fusion.py @@ -0,0 +1,35 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from .ooyala import OoyalaIE + + +class FusionIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?fusion\.net/video/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://fusion.net/video/201781/u-s-and-panamanian-forces-work-together-to-stop-a-vessel-smuggling-drugs/', + 'info_dict': { + 'id': 'ZpcWNoMTE6x6uVIIWYpHh0qQDjxBuq5P', + 'ext': 'mp4', + 'title': 'U.S. and Panamanian forces work together to stop a vessel smuggling drugs', + 'description': 'md5:0cc84a9943c064c0f46b128b41b1b0d7', + 'duration': 140.0, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['Ooyala'], + }, { + 'url': 'http://fusion.net/video/201781', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + ooyala_code = self._search_regex( + r'data-video-id=(["\'])(?P<code>.+?)\1', + webpage, 'ooyala code', group='code') + + return OoyalaIE._build_url_result(ooyala_code) diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 4ffdd7515..621257c9f 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -1,19 +1,19 @@ from __future__ import unicode_literals import re -import json -from .common import InfoExtractor +from .once import OnceIE from ..compat import ( compat_urllib_parse_unquote, - compat_urlparse, ) from ..utils import ( unescapeHTML, + url_basename, + dict_get, ) -class GameSpotIE(InfoExtractor): +class GameSpotIE(OnceIE): _VALID_URL = r'https?://(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?' _TESTS = [{ 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/', @@ -39,29 +39,73 @@ class GameSpotIE(InfoExtractor): webpage = self._download_webpage(url, page_id) data_video_json = self._search_regex( r'data-video=["\'](.*?)["\']', webpage, 'data video') - data_video = json.loads(unescapeHTML(data_video_json)) + data_video = self._parse_json(unescapeHTML(data_video_json), page_id) streams = data_video['videoStreams'] + manifest_url = None formats = [] f4m_url = streams.get('f4m_stream') - if f4m_url is not None: - # Transform the manifest url to a link to the mp4 files - # they are used in mobile devices. - f4m_path = compat_urlparse.urlparse(f4m_url).path - QUALITIES_RE = r'((,\d+)+,?)' - qualities = self._search_regex(QUALITIES_RE, f4m_path, 'qualities').strip(',').split(',') - http_path = f4m_path[1:].split('/', 1)[1] - http_template = re.sub(QUALITIES_RE, r'%s', http_path) - http_template = http_template.replace('.csmil/manifest.f4m', '') - http_template = compat_urlparse.urljoin( - 'http://video.gamespotcdn.com/', http_template) - for q in qualities: - formats.append({ - 'url': http_template % q, - 'ext': 'mp4', - 'format_id': q, - }) - else: + if f4m_url: + manifest_url = f4m_url + formats.extend(self._extract_f4m_formats( + f4m_url + '?hdcore=3.7.0', page_id, f4m_id='hds', fatal=False)) + m3u8_url = streams.get('m3u8_stream') + if m3u8_url: + manifest_url = m3u8_url + m3u8_formats = self._extract_m3u8_formats( + m3u8_url, page_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False) + formats.extend(m3u8_formats) + progressive_url = dict_get( + streams, ('progressive_hd', 'progressive_high', 'progressive_low')) + if progressive_url and manifest_url: + qualities_basename = self._search_regex( + '/([^/]+)\.csmil/', + manifest_url, 'qualities basename', default=None) + if qualities_basename: + QUALITIES_RE = r'((,\d+)+,?)' + qualities = self._search_regex( + QUALITIES_RE, qualities_basename, + 'qualities', default=None) + if qualities: + qualities = list(map(lambda q: int(q), qualities.strip(',').split(','))) + qualities.sort() + http_template = re.sub(QUALITIES_RE, r'%d', qualities_basename) + http_url_basename = url_basename(progressive_url) + if m3u8_formats: + self._sort_formats(m3u8_formats) + m3u8_formats = list(filter( + lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', + m3u8_formats)) + if len(qualities) == len(m3u8_formats): + for q, m3u8_format in zip(qualities, m3u8_formats): + f = m3u8_format.copy() + f.update({ + 'url': progressive_url.replace( + http_url_basename, http_template % q), + 'format_id': f['format_id'].replace('hls', 'http'), + 'protocol': 'http', + }) + formats.append(f) + else: + for q in qualities: + formats.append({ + 'url': progressive_url.replace( + http_url_basename, http_template % q), + 'ext': 'mp4', + 'format_id': 'http-%d' % q, + 'tbr': q, + }) + + onceux_json = self._search_regex( + r'data-onceux-options=["\'](.*?)["\']', webpage, 'data video', default=None) + if onceux_json: + onceux_url = self._parse_json(unescapeHTML(onceux_json), page_id).get('metadataUri') + if onceux_url: + formats.extend(self._extract_once_formats(re.sub( + r'https?://[^/]+', 'http://once.unicornmedia.com', onceux_url).replace('ads/vmap/', ''))) + + if not formats: for quality in ['sd', 'hd']: # It's actually a link to a flv file flv_url = streams.get('f4m_{0}'.format(quality)) @@ -71,6 +115,7 @@ class GameSpotIE(InfoExtractor): 'ext': 'flv', 'format_id': quality, }) + self._sort_formats(formats) return { 'id': data_video['guid'], diff --git a/youtube_dl/extractor/gametrailers.py b/youtube_dl/extractor/gametrailers.py deleted file mode 100644 index 1e7948ab8..000000000 --- a/youtube_dl/extractor/gametrailers.py +++ /dev/null @@ -1,62 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - parse_age_limit, - url_basename, -) - - -class GametrailersIE(InfoExtractor): - _VALID_URL = r'https?://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)' - - _TEST = { - 'url': 'http://www.gametrailers.com/videos/view/gametrailers-com/116437-Just-Cause-3-Review', - 'md5': 'f28c4efa0bdfaf9b760f6507955b6a6a', - 'info_dict': { - 'id': '2983958', - 'ext': 'mp4', - 'display_id': '116437-Just-Cause-3-Review', - 'title': 'Just Cause 3 - Review', - 'description': 'It\'s a lot of fun to shoot at things and then watch them explode in Just Cause 3, but should there be more to the experience than that?', - }, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - title = self._html_search_regex( - r'<title>(.+?)\|', webpage, 'title').strip() - embed_url = self._proto_relative_url( - self._search_regex( - r'src=\'(//embed.gametrailers.com/embed/[^\']+)\'', webpage, - 'embed url'), - scheme='http:') - video_id = url_basename(embed_url) - embed_page = self._download_webpage(embed_url, video_id) - embed_vars_json = self._search_regex( - r'(?s)var embedVars = (\{.*?\})\s*</script>', embed_page, - 'embed vars') - info = self._parse_json(embed_vars_json, video_id) - - formats = [] - for media in info['media']: - if media['mediaPurpose'] == 'play': - formats.append({ - 'url': media['uri'], - 'height': media['height'], - 'width:': media['width'], - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'formats': formats, - 'thumbnail': info.get('thumbUri'), - 'description': self._og_search_description(webpage), - 'duration': int_or_none(info.get('videoLengthInSeconds')), - 'age_limit': parse_age_limit(info.get('audienceRating')), - } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 95d233259..4efdf146e 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -49,9 +49,12 @@ from .pornhub import PornHubIE from .xhamster import XHamsterEmbedIE from .tnaflix import TNAFlixNetworkEmbedIE from .vimeo import VimeoIE -from .dailymotion import DailymotionCloudIE +from .dailymotion import ( + DailymotionIE, + DailymotionCloudIE, +) from .onionstudios import OnionStudiosIE -from .snagfilms import SnagFilmsEmbedIE +from .viewlift import ViewLiftEmbedIE from .screenwavemedia import ScreenwaveMediaIE from .mtv import MTVServicesEmbeddedIE from .pladform import PladformIE @@ -61,6 +64,12 @@ from .jwplatform import JWPlatformIE from .digiteka import DigitekaIE from .instagram import InstagramIE from .liveleak import LiveLeakIE +from .threeqsdn import ThreeQSDNIE +from .theplatform import ThePlatformIE +from .vessel import VesselIE +from .kaltura import KalturaIE +from .eagleplatform import EaglePlatformIE +from .facebook import FacebookIE class GenericIE(InfoExtractor): @@ -237,6 +246,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': 'car-20120827-manifest', 'formats': 'mincount:9', + 'upload_date': '20130904', }, 'params': { 'format': 'bestvideo', @@ -596,7 +606,11 @@ class GenericIE(InfoExtractor): 'id': 'k2mm4bCdJ6CQ2i7c8o2', 'ext': 'mp4', 'title': 'Le Zap de Spi0n n°216 - Zapping du Web', + 'description': 'md5:faf028e48a461b8b7fad38f1e104b119', 'uploader': 'Spi0n', + 'uploader_id': 'xgditw', + 'upload_date': '20140425', + 'timestamp': 1398441542, }, 'add_ie': ['Dailymotion'], }, @@ -619,13 +633,13 @@ class GenericIE(InfoExtractor): }, # MTVSercices embed { - 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too', - 'md5': '35727f82f58c76d996fc188f9755b0d5', + 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html', + 'md5': 'ca1aef97695ef2c1d6973256a57e5252', 'info_dict': { - 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9', + 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1', 'ext': 'mp4', - 'title': 'Review', - 'description': 'Mario\'s life in the fast lane has never looked so good.', + 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored', + 'description': 'Two valets share their love for movie star Liam Neesons.', }, }, # YouTube embed via <data-embed-url=""> @@ -711,15 +725,18 @@ class GenericIE(InfoExtractor): }, # Wistia embed { - 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson', - 'md5': '8788b683c777a5cf25621eaf286d0c23', + 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson', + 'md5': '1953f3a698ab51cfc948ed3992a0b7ff', 'info_dict': { - 'id': '1cfaf6b7ea', + 'id': '6e2wtrbdaf', 'ext': 'mov', - 'title': 'md5:51364a8d3d009997ba99656004b5e20d', - 'duration': 643.0, - 'filesize': 182808282, - 'uploader': 'education-portal.com', + 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england', + 'description': 'a Paywall Videos video from Remilon', + 'duration': 644.072, + 'uploader': 'study.com', + 'timestamp': 1459678540, + 'upload_date': '20160403', + 'filesize': 24687186, }, }, { @@ -728,10 +745,29 @@ class GenericIE(InfoExtractor): 'info_dict': { 'id': 'uxjb0lwrcz', 'ext': 'mp4', - 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks', + 'title': 'Conversation about Hexagonal Rails Part 1', + 'description': 'a Martin Fowler video from ThoughtWorks', 'duration': 1715.0, 'uploader': 'thoughtworks.wistia.com', + 'timestamp': 1401832161, + 'upload_date': '20140603', + }, + }, + # Wistia standard embed (async) + { + 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/', + 'info_dict': { + 'id': '807fafadvk', + 'ext': 'mp4', + 'title': 'Drip Brennan Dunn Workshop', + 'description': 'a JV Webinars video from getdrip-1', + 'duration': 4986.95, + 'timestamp': 1463607249, + 'upload_date': '20160518', }, + 'params': { + 'skip_download': True, + } }, # Soundcloud embed { @@ -755,6 +791,19 @@ class GenericIE(InfoExtractor): 'title': 'Rosetta #CometLanding webcast HL 10', } }, + # Another Livestream embed, without 'new.' in URL + { + 'url': 'https://www.freespeech.org/', + 'info_dict': { + 'id': '123537347', + 'ext': 'mp4', + 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + }, + 'params': { + # Live stream + 'skip_download': True, + }, + }, # LazyYT { 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986', @@ -839,18 +888,6 @@ class GenericIE(InfoExtractor): 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !', } }, - # Kaltura embed - { - 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15', - 'info_dict': { - 'id': '1_eergr3h1', - 'ext': 'mp4', - 'upload_date': '20150226', - 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com', - 'timestamp': int, - 'title': 'John Carlson Postgame 2/25/15', - }, - }, # Kaltura embed (different embed code) { 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014', @@ -876,9 +913,41 @@ class GenericIE(InfoExtractor): 'uploader_id': 'echojecka', }, }, + # Kaltura embed with single quotes + { + 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY', + 'info_dict': { + 'id': '0_izeg5utt', + 'ext': 'mp4', + 'title': '35871', + 'timestamp': 1355743100, + 'upload_date': '20121217', + 'uploader_id': 'batchUser', + }, + 'add_ie': ['Kaltura'], + }, + { + # Kaltura embedded via quoted entry_id + 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures', + 'info_dict': { + 'id': '0_utuok90b', + 'ext': 'mp4', + 'title': '06_matthew_brender_raj_dutt', + 'timestamp': 1466638791, + 'upload_date': '20160622', + }, + 'add_ie': ['Kaltura'], + 'expected_warnings': [ + 'Could not send HEAD request' + ], + 'params': { + 'skip_download': True, + } + }, # Eagle.Platform embed (generic URL) { 'url': 'http://lenta.ru/news/2015/03/06/navalny/', + # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used 'info_dict': { 'id': '227304', 'ext': 'mp4', @@ -893,6 +962,7 @@ class GenericIE(InfoExtractor): # ClipYou (Eagle.Platform) embed (custom URL) { 'url': 'http://muz-tv.ru/play/7129/', + # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used 'info_dict': { 'id': '12820', 'ext': 'mp4', @@ -981,18 +1051,36 @@ class GenericIE(InfoExtractor): 'ext': 'flv', 'title': "PFT Live: New leader in the 'new-look' defense", 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e', + 'uploader': 'NBCU-SPORTS', + 'upload_date': '20140107', + 'timestamp': 1389118457, + }, + }, + # NBC News embed + { + 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html', + 'md5': '1aa589c675898ae6d37a17913cf68d66', + 'info_dict': { + 'id': '701714499682', + 'ext': 'mp4', + 'title': 'PREVIEW: On Assignment: David Letterman', + 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.', }, }, # UDN embed { - 'url': 'http://www.udn.com/news/story/7314/822787', + 'url': 'https://video.udn.com/news/300346', 'md5': 'fd2060e988c326991037b9aff9df21a6', 'info_dict': { 'id': '300346', 'ext': 'mp4', 'title': '中一中男師變性 全校師生力挺', 'thumbnail': 're:^https?://.*\.jpg$', - } + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, # Ooyala embed { @@ -1009,20 +1097,6 @@ class GenericIE(InfoExtractor): 'skip_download': True, } }, - # Contains a SMIL manifest - { - 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html', - 'info_dict': { - 'id': 'file', - 'ext': 'flv', - 'title': '+ Football: Lottery Champions League Europe', - 'uploader': 'www.telewebion.com', - }, - 'params': { - # rtmpe downloads - 'skip_download': True, - } - }, # Brightcove URL in single quotes { 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/', @@ -1033,17 +1107,25 @@ class GenericIE(InfoExtractor): 'title': 'SN Presents: Russell Martin, World Citizen', 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.', 'uploader': 'Rogers Sportsnet', + 'uploader_id': '1704050871', + 'upload_date': '20150525', + 'timestamp': 1432570283, }, }, # Dailymotion Cloud video { 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910', - 'md5': '49444254273501a64675a7e68c502681', + 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38', 'info_dict': { - 'id': '5585de919473990de4bee11b', + 'id': 'x2uy8t3', 'ext': 'mp4', - 'title': 'Le débat', + 'title': 'Sauvons les abeilles ! - Le débat', + 'description': 'md5:d9082128b1c5277987825d684939ca26', 'thumbnail': 're:^https?://.*\.jpe?g$', + 'timestamp': 1434970506, + 'upload_date': '20150622', + 'uploader': 'Public Sénat', + 'uploader_id': 'xa9gza', } }, # OnionStudios embed @@ -1124,6 +1206,9 @@ class GenericIE(InfoExtractor): 'title': 'The Cardinal Pell Interview', 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ', 'uploader': 'GlobeCast Australia - GlobeStream', + 'uploader_id': '2733773828001', + 'upload_date': '20160304', + 'timestamp': 1457083087, }, 'params': { # m3u8 downloads @@ -1154,6 +1239,97 @@ class GenericIE(InfoExtractor): 'uploader': 'Lake8737', } }, + # Duplicated embedded video URLs + { + 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443', + 'info_dict': { + 'id': '149298443_480_16c25b74_2', + 'ext': 'mp4', + 'title': 'vs. Blue Orange Spring Game', + 'uploader': 'www.hudl.com', + }, + }, + # twitter:player embed + { + 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/', + 'md5': 'a3e0df96369831de324f0778e126653c', + 'info_dict': { + 'id': '4909620399001', + 'ext': 'mp4', + 'title': 'What Do Black Holes Sound Like?', + 'description': 'what do black holes sound like', + 'upload_date': '20160524', + 'uploader_id': '29913724001', + 'timestamp': 1464107587, + 'uploader': 'TheAtlantic', + }, + 'add_ie': ['BrightcoveLegacy'], + }, + # Facebook <iframe> embed + { + 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html', + 'md5': 'fbcde74f534176ecb015849146dd3aee', + 'info_dict': { + 'id': '599637780109885', + 'ext': 'mp4', + 'title': 'Facebook video #599637780109885', + }, + }, + # Facebook API embed + { + 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/', + 'md5': 'a47372ee61b39a7b90287094d447d94e', + 'info_dict': { + 'id': '10153467542406923', + 'ext': 'mp4', + 'title': 'Facebook video #10153467542406923', + }, + }, + # Wordpress "YouTube Video Importer" plugin + { + 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/', + 'md5': 'd16797741b560b485194eddda8121b48', + 'info_dict': { + 'id': 'HNTXWDXV9Is', + 'ext': 'mp4', + 'title': 'Blue Devils Drumline Stanford lot 2016', + 'upload_date': '20160627', + 'uploader_id': 'GENOCIDE8GENERAL10', + 'uploader': 'cylus cyrus', + }, + }, + { + # video stored on custom kaltura server + 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv', + 'md5': '537617d06e64dfed891fa1593c4b30cc', + 'info_dict': { + 'id': '0_1iotm5bh', + 'ext': 'mp4', + 'title': 'Elecciones británicas: 5 lecciones para Rajoy', + 'description': 'md5:435a89d68b9760b92ce67ed227055f16', + 'uploader_id': 'videos.expansion@el-mundo.net', + 'upload_date': '20150429', + 'timestamp': 1430303472, + }, + 'add_ie': ['Kaltura'], + }, + # { + # # TODO: find another test + # # http://schema.org/VideoObject + # 'url': 'https://flipagram.com/f/nyvTSJMKId', + # 'md5': '888dcf08b7ea671381f00fab74692755', + # 'info_dict': { + # 'id': 'nyvTSJMKId', + # 'ext': 'mp4', + # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction', + # 'description': '#love for cats.', + # 'timestamp': 1461244995, + # 'upload_date': '20160421', + # }, + # 'params': { + # 'force_generic_extractor': True, + # }, + # } ] def report_following_redirect(self, new_url): @@ -1408,7 +1584,8 @@ class GenericIE(InfoExtractor): # Site Name | Video Title # Video Title - Tagline | Site Name # and so on and so forth; it's just not practical - video_title = self._html_search_regex( + video_title = self._og_search_title( + webpage, default=None) or self._html_search_regex( r'(?s)<title>(.*?)', webpage, 'video title', default='video') @@ -1426,6 +1603,9 @@ class GenericIE(InfoExtractor): video_uploader = self._search_regex( r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') + video_description = self._og_search_description(webpage, default=None) + video_thumbnail = self._og_search_thumbnail(webpage, default=None) + # Helper method def _playlist_from_matches(matches, getter=None, ie=None): urlrs = orderedSet( @@ -1456,6 +1636,16 @@ class GenericIE(InfoExtractor): if bc_urls: return _playlist_from_matches(bc_urls, ie='BrightcoveNew') + # Look for ThePlatform embeds + tp_urls = ThePlatformIE._extract_urls(webpage) + if tp_urls: + return _playlist_from_matches(tp_urls, ie='ThePlatform') + + # Look for Vessel embeds + vessel_urls = VesselIE._extract_urls(webpage) + if vessel_urls: + return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key()) + # Look for embedded rtl.nl player matches = re.findall( r']+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"', @@ -1496,12 +1686,16 @@ class GenericIE(InfoExtractor): if matches: return _playlist_from_matches(matches, lambda m: unescapeHTML(m)) - # Look for embedded Dailymotion player - matches = re.findall( - r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage) + # Look for Wordpress "YouTube Video Importer" plugin + matches = re.findall(r'''(?x)]+ + class=(?P[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ + data-video_id=(?P[\'"])([^\'"]+)(?P=q2)''', webpage) if matches: - return _playlist_from_matches( - matches, lambda m: unescapeHTML(m[1])) + return _playlist_from_matches(matches, lambda m: m[-1]) + + matches = DailymotionIE._extract_urls(webpage) + if matches: + return _playlist_from_matches(matches) # Look for embedded Dailymotion playlist player (#3822) m = re.search( @@ -1524,21 +1718,26 @@ class GenericIE(InfoExtractor): 'url': embed_url, 'ie_key': 'Wistia', 'uploader': video_uploader, - 'title': video_title, - 'id': video_id, } match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P[^"\']+)', webpage) if match: return { '_type': 'url_transparent', - 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')), + 'url': 'wistia:%s' % match.group('id'), 'ie_key': 'Wistia', 'uploader': video_uploader, - 'title': video_title, - 'id': match.group('id') } + match = re.search( + r'''(?sx) + ]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*? + ]+class=(["']).*?\bwistia_async_(?P[a-z0-9]+)\b.*?\2 + ''', webpage) + if match: + return self.url_result(self._proto_relative_url( + 'wistia:%s' % match.group('id')), 'Wistia') + # Look for SVT player svt_url = SVTIE._extract_url(webpage) if svt_url: @@ -1633,10 +1832,9 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url')) # Look for embedded Facebook player - mobj = re.search( - r']+?src=(["\'])(?Phttps://www\.facebook\.com/video/embed.+?)\1', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'Facebook') + facebook_url = FacebookIE._extract_url(webpage) + if facebook_url is not None: + return self.url_result(facebook_url, 'Facebook') # Look for embedded VK player mobj = re.search(r']+?src=(["\'])(?Phttps?://vk\.com/video_ext\.php.+?)\1', webpage) @@ -1758,14 +1956,6 @@ class GenericIE(InfoExtractor): url = unescapeHTML(mobj.group('url')) return self.url_result(url) - # Look for embedded vulture.com player - mobj = re.search( - r'