From: Sergey M․ Date: Fri, 13 Nov 2015 19:23:15 +0000 (+0600) Subject: Merge branch 'brightcove_in_page_embed' of https://github.com/remitamine/youtube... X-Git-Url: http://git.bitcoin.ninja/index.cgi?p=youtube-dl;a=commitdiff_plain;h=a2973eb59733c5f86a249c627d654b789020bc7d;hp=9550ca506fccf9c9d795816cc0a7817ff262ef45 Merge branch 'brightcove_in_page_embed' of https://github.com/remitamine/youtube-dl into remitamine-brightcove_in_page_embed --- diff --git a/.travis.yml b/.travis.yml index e78a2fa76..cc21fae8f 100644 --- a/.travis.yml +++ b/.travis.yml @@ -5,6 +5,7 @@ python: - "3.2" - "3.3" - "3.4" + - "3.5" sudo: false script: nosetests test --verbose notifications: diff --git a/AUTHORS b/AUTHORS index 901c1b263..f465d20ed 100644 --- a/AUTHORS +++ b/AUTHORS @@ -143,3 +143,6 @@ Shaun Walbridge Lee Jenkins Anssi Hannula Lukáš Lalinský +Qijiang Fan +Rémy Léone +Marco Ferragina diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index f8ab29631..09ce98ca2 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -1,6 +1,6 @@ **Please include the full output of youtube-dl when run with `-v`**. -The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever. +The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever. Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist): @@ -16,15 +16,15 @@ So please elaborate on what feature you are requesting, or what bug you want to If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over. -For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information. +For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the `-v` flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information. -If your server has multiple IPs or you suspect censorship, adding --call-home may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/). +If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/). **Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL. ### Are you using the latest version? -Before reporting any issue, type youtube-dl -U. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well. +Before reporting any issue, type `youtube-dl -U`. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well. ### Is the issue already documented? @@ -114,17 +114,18 @@ If you want to add support for a new site, you can follow this quick list (assum webpage = self._download_webpage(url, video_id) # TODO more code goes here, for example ... - title = self._html_search_regex(r'

(.*?)

', webpage, 'title') + title = self._html_search_regex(r'

(.+?)

', webpage, 'title') return { 'id': video_id, 'title': title, 'description': self._og_search_description(webpage), + 'uploader': self._search_regex(r']+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), # TODO more properties (see youtube_dl/extractor/common.py) } ``` 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.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 be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. +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/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want. 8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8). 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: diff --git a/README.md b/README.md index 24bfe38a2..38db97c59 100644 --- a/README.md +++ b/README.md @@ -9,6 +9,7 @@ youtube-dl - download videos from youtube.com or other video platforms - [VIDEO SELECTION](#video-selection) - [FAQ](#faq) - [DEVELOPER INSTRUCTIONS](#developer-instructions) +- [EMBEDDING YOUTUBE-DL](#embedding-youtube-dl) - [BUGS](#bugs) - [COPYRIGHT](#copyright) @@ -48,110 +49,220 @@ which means you can modify it, redistribute it or use it however you like. # OPTIONS -h, --help Print this help text and exit --version Print program version and exit - -U, --update Update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed) - -i, --ignore-errors Continue on download errors, for example to skip unavailable videos in a playlist - --abort-on-error Abort downloading of further videos (in the playlist or the command line) if an error occurs + -U, --update Update this program to latest version. Make + sure that you have sufficient permissions + (run with sudo if needed) + -i, --ignore-errors Continue on download errors, for example to + skip unavailable videos in a playlist + --abort-on-error Abort downloading of further videos (in the + playlist or the command line) if an error + occurs --dump-user-agent Display the current browser identification --list-extractors List all supported extractors - --extractor-descriptions Output descriptions of all supported extractors - --force-generic-extractor Force extraction to use the generic extractor - --default-search PREFIX Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". - Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The - default value "fixup_error" 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 configuration - in ~/.config/youtube-dl/config (%APPDATA%/youtube-dl/config.txt on Windows) - --flat-playlist Do not extract the videos of a playlist, only list them. + --extractor-descriptions Output descriptions of all supported + extractors + --force-generic-extractor Force extraction to use the generic + extractor + --default-search PREFIX Use this prefix for unqualified URLs. For + example "gvsearch2:" downloads two videos + from google videos for youtube-dl "large + apple". Use the value "auto" to let + youtube-dl guess ("auto_warning" to emit a + warning when guessing). "error" just throws + an error. The default value "fixup_error" + 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 + configuration in ~/.config/youtube- + dl/config (%APPDATA%/youtube-dl/config.txt + on Windows) + --flat-playlist Do not extract the videos of a playlist, + only list them. --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 proxy. 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) - -4, --force-ipv4 Make all connections via IPv4 (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 options is - not present) is used for the actual downloading. (experimental) + --source-address IP Client-side IP address to bind to + (experimental) + -4, --force-ipv4 Make all connections via IPv4 + (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 + options is not present) is used for the + actual downloading. (experimental) ## Video Selection: --playlist-start NUMBER Playlist video to start at (default is 1) --playlist-end NUMBER Playlist video to end at (default is last) - --playlist-items ITEM_SPEC Playlist video items to download. Specify indices of the videos in the playlist separated by commas like: "--playlist-items 1,2,5,8" - if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will - download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13. - --match-title REGEX Download only matching titles (regex or caseless sub-string) - --reject-title REGEX Skip download for matching titles (regex or caseless sub-string) + --playlist-items ITEM_SPEC Playlist video items to download. Specify + indices of the videos in the playlist + separated by commas like: "--playlist-items + 1,2,5,8" if you want to download videos + indexed 1, 2, 5, 8 in the playlist. You can + specify range: "--playlist-items + 1-3,7,10-13", it will download the videos + at index 1, 2, 3, 7, 10, 11, 12 and 13. + --match-title REGEX Download only matching titles (regex or + caseless sub-string) + --reject-title REGEX Skip download for matching titles (regex or + caseless sub-string) --max-downloads NUMBER Abort after downloading NUMBER files - --min-filesize SIZE Do not download any videos smaller than SIZE (e.g. 50k or 44.6m) - --max-filesize SIZE Do not download any videos larger than SIZE (e.g. 50k or 44.6m) + --min-filesize SIZE Do not download any videos smaller than + SIZE (e.g. 50k or 44.6m) + --max-filesize SIZE Do not download any videos larger than SIZE + (e.g. 50k or 44.6m) --date DATE Download only videos uploaded in this date - --datebefore DATE Download only videos uploaded on or before this date (i.e. inclusive) - --dateafter DATE Download only videos uploaded on or after this date (i.e. inclusive) - --min-views COUNT Do not download any videos with less than COUNT views - --max-views COUNT Do not download any videos with more than COUNT views - --match-filter FILTER Generic video filter (experimental). Specify any key (see help for -o for a list of available keys) to match if the key is present, - !key to check if the key is not present,key > NUMBER (like "comment_count > 12", also works with >=, <, <=, !=, =) to compare against - a number, and & to require multiple matches. Values which are not known are excluded unless you put a question mark (?) after the - operator.For example, to only match videos that have been liked more than 100 times and disliked less than 50 times (or the dislike - functionality is not available at the given service), but who also have a description, use --match-filter "like_count > 100 & + --datebefore DATE Download only videos uploaded on or before + this date (i.e. inclusive) + --dateafter DATE Download only videos uploaded on or after + this date (i.e. inclusive) + --min-views COUNT Do not download any videos with less than + COUNT views + --max-views COUNT Do not download any videos with more than + COUNT views + --match-filter FILTER Generic video filter (experimental). + Specify any key (see help for -o for a list + of available keys) to match if the key is + present, !key to check if the key is not + present,key > NUMBER (like "comment_count > + 12", also works with >=, <, <=, !=, =) to + compare against a number, and & to require + multiple matches. Values which are not + known are excluded unless you put a + question mark (?) after the operator.For + example, to only match videos that have + been liked more than 100 times and disliked + less than 50 times (or the dislike + functionality is not available at the given + service), but who also have a description, + use --match-filter "like_count > 100 & dislike_count \youtube-dl.conf`. For example, with the following configration file youtube-dl will always extract the audio, not copy the mtime and use proxy: +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\\youtube-dl.conf`. For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime and use a proxy: ``` --extract-audio --no-mtime --proxy 127.0.0.1:3128 ``` -You can use `--ignore-config` if you want to disable configuration file for a particular youtube-dl run. +You can use `--ignore-config` if you want to disable the configuration file for a particular youtube-dl run. ### 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 shell command history. You can achieve this using [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create `.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 @@ -261,13 +429,13 @@ For example: machine youtube login myaccount@gmail.com password my_youtube_password machine twitch login my_twitch_account_name password my_twitch_password ``` -To activate authentication with `.netrc` file you should pass `--netrc` to youtube-dl or to place it in [configuration file](#configuration). +To activate authentication with the `.netrc` file you should pass `--netrc` to youtube-dl or place it in the [configuration file](#configuration). -On Windows you may also need to setup `%HOME%` environment variable manually. +On Windows you may also need to setup the `%HOME%` environment variable manually. # OUTPUT TEMPLATE -The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parenthesis, followed by a lowercase S. Allowed names are: +The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a lowercase S. Allowed names are: - `id`: The sequence will be replaced by the video identifier. - `url`: The sequence will be replaced by the video URL. @@ -277,9 +445,10 @@ The `-o` option allows users to indicate a template for the output file names. T - `ext`: The sequence will be replaced by the appropriate extension (like flv or mp4). - `epoch`: The sequence will be replaced by the Unix epoch when creating the file. - `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero. - - `playlist`: The name or the id of the playlist that contains the video. - - `playlist_index`: The index of the video in the playlist, a five-digit number. + - `playlist`: The sequence will be replaced by the name or the id of the playlist that contains the video. + - `playlist_index`: The sequence will be replaced by the index of the video in the playlist padded with leading zeros according to the total length of the playlist. - `format_id`: The sequence will be replaced by the format code specified by `--format`. + - `duration`: The sequence will be replaced by the length of the video in seconds. The current default template is `%(title)s-%(id)s.%(ext)s`. @@ -294,18 +463,18 @@ youtube-dl_test_video_.mp4 # A simple file name # FORMAT SELECTION -By default youtube-dl tries to download the best quality, but sometimes you may want to download other format. +By default youtube-dl tries to download the best quality, but sometimes you may want to download in a different format. The simplest case is requesting a specific format, for example `-f 22`. You can get the list of available formats using `--list-formats`, you can also use a file extension (currently it supports aac, m4a, mp3, mp4, ogg, wav, webm) or the special names `best`, `bestvideo`, `bestaudio` and `worst`. If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`). This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f +` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`. Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`. -Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed. +Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed. -If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl. +If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download the best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl. # VIDEO SELECTION -Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`, they accept dates in two formats: +Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`. They accept dates in two formats: - Absolute dates: Dates in the format `YYYYMMDD`. - Relative dates: Dates in the format `(now|today)[+-][0-9](day|week|month|year)(s)?` @@ -319,7 +488,7 @@ $ youtube-dl --dateafter now-6months # Download only the videos uploaded on January 1, 1970 $ youtube-dl --date 19700101 -$ # will only download the videos uploaded in the 200x decade +$ # Download only the videos uploaded in the 200x decade $ youtube-dl --dateafter 20000101 --datebefore 20091231 ``` @@ -331,7 +500,7 @@ If you've followed [our manual installation instructions](http://rg3.github.io/y If you have used pip, a simple `sudo pip install -U youtube-dl` is sufficient to update. -If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to http://yt-dl.org/ to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distributions serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum. +If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to http://yt-dl.org/ to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distribution serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum. As a last resort, you can also uninstall the version installed by your package manager and follow our manual installation instructions. For that, remove the distribution's package, with a line like @@ -357,7 +526,7 @@ If you have installed youtube-dl with a package manager, pip, setup.py or a tarb 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`. -### Can you please put the -b option back? +### Can you please put the `-b` option back? Most people asking this question are not aware that youtube-dl now defaults to downloading the highest available quality as reported by YouTube, which will be 1080p or 720p in some cases, so you no longer need the `-b` option. For some specific videos, maybe YouTube does not report them to be available in a specific high quality format you're interested in. In that case, simply request it with the `-f` option and youtube-dl will try to download it. @@ -369,13 +538,13 @@ Apparently YouTube requires you to pass a CAPTCHA test if you download too much. Once the video is fully downloaded, use any video player, such as [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. +### I extracted a video URL with `-g`, but it does not play on another machine / in my webbrowser. It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl. It may be beneficial to use IPv6; in some cases, the restrictions are only applied to IPv4. Some services (sometimes only for a subset of videos) do not restrict the video URL by IP address, cookie, or user-agent, but these are the exception rather than the rule. -Please bear in mind that some URL protocols are **not** supported by browsers out of the box, including RTMP. If you are using -g, your own downloader must support these as well. +Please bear in mind that some URL protocols are **not** supported by browsers out of the box, including RTMP. If you are using `-g`, your own downloader must support these as well. If you want to play the video on a machine that is not running youtube-dl, you can relay the video content from the machine that runs youtube-dl. You can use `-o -` to let youtube-dl stream a video to stdout, or simply allow the player to download the files written by youtube-dl in turn. @@ -389,7 +558,7 @@ YouTube requires an additional signature since September 2012 which is not suppo ### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` ### -That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell). +That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by the shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell). For example if your URL is https://www.youtube.com/watch?t=4&v=BaW_jenozKc you should end up with following command: @@ -449,9 +618,9 @@ Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the opt ### How do I pass cookies to youtube-dl? -Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that cookies file must be in Mozilla/Netscape format and the first line of cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in cookies file and convert newlines if necessary to correspond your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format. +Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format. -Passing cookies to youtube-dl is a good way to workaround login when particular extractor does not implement it explicitly. +Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. ### Can you add support for this anime video site, or site which shows current movies for free? @@ -541,17 +710,18 @@ If you want to add support for a new site, you can follow this quick list (assum webpage = self._download_webpage(url, video_id) # TODO more code goes here, for example ... - title = self._html_search_regex(r'

(.*?)

', webpage, 'title') + title = self._html_search_regex(r'

(.+?)

', webpage, 'title') return { 'id': video_id, 'title': title, 'description': self._og_search_description(webpage), + 'uploader': self._search_regex(r']+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False), # TODO more properties (see youtube_dl/extractor/common.py) } ``` 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.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 be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. +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/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want. 8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8). 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: @@ -625,7 +795,7 @@ Bugs and suggestions should be reported at: log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/). +If your server has multiple IPs or you suspect censorship, adding `--call-home` may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/). **Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL. ### Are you using the latest version? -Before reporting any issue, type youtube-dl -U. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well. +Before reporting any issue, type `youtube-dl -U`. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well. ### Is the issue already documented? diff --git a/devscripts/bash-completion.py b/devscripts/bash-completion.py index cd26cc089..ce68f26f9 100755 --- a/devscripts/bash-completion.py +++ b/devscripts/bash-completion.py @@ -5,7 +5,7 @@ import os from os.path import dirname as dirn import sys -sys.path.append(dirn(dirn((os.path.abspath(__file__))))) +sys.path.insert(0, dirn(dirn((os.path.abspath(__file__))))) import youtube_dl BASH_COMPLETION_FILE = "youtube-dl.bash-completion" diff --git a/devscripts/fish-completion.py b/devscripts/fish-completion.py index c2f238798..41629d87d 100755 --- a/devscripts/fish-completion.py +++ b/devscripts/fish-completion.py @@ -6,7 +6,7 @@ import os from os.path import dirname as dirn import sys -sys.path.append(dirn(dirn((os.path.abspath(__file__))))) +sys.path.insert(0, dirn(dirn((os.path.abspath(__file__))))) import youtube_dl from youtube_dl.utils import shell_quote diff --git a/devscripts/gh-pages/update-sites.py b/devscripts/gh-pages/update-sites.py index d3ef5f0b5..503c1372f 100755 --- a/devscripts/gh-pages/update-sites.py +++ b/devscripts/gh-pages/update-sites.py @@ -6,7 +6,7 @@ import os import textwrap # We must be able to import youtube_dl -sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))) +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))) import youtube_dl diff --git a/devscripts/make_supportedsites.py b/devscripts/make_supportedsites.py index 3df4385a6..8cb4a4638 100644 --- a/devscripts/make_supportedsites.py +++ b/devscripts/make_supportedsites.py @@ -9,7 +9,7 @@ import sys # Import youtube_dl ROOT_DIR = os.path.join(os.path.dirname(__file__), '..') -sys.path.append(ROOT_DIR) +sys.path.insert(0, ROOT_DIR) import youtube_dl diff --git a/devscripts/prepare_manpage.py b/devscripts/prepare_manpage.py index 7ece37754..776e6556e 100644 --- a/devscripts/prepare_manpage.py +++ b/devscripts/prepare_manpage.py @@ -8,6 +8,35 @@ import re ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) README_FILE = os.path.join(ROOT_DIR, 'README.md') + +def filter_options(readme): + ret = '' + in_options = False + for line in readme.split('\n'): + if line.startswith('# '): + if line[2:].startswith('OPTIONS'): + in_options = True + else: + in_options = False + + if in_options: + if line.lstrip().startswith('-'): + option, description = re.split(r'\s{2,}', line.lstrip()) + split_option = option.split(' ') + + if not split_option[-1].startswith('-'): # metavar + option = ' '.join(split_option[:-1] + ['*%s*' % split_option[-1]]) + + # Pandoc's definition_lists. See http://pandoc.org/README.html + # for more information. + ret += '\n%s\n: %s\n' % (option, description) + else: + ret += line.lstrip() + '\n' + else: + ret += line + '\n' + + return ret + with io.open(README_FILE, encoding='utf-8') as f: readme = f.read() @@ -26,6 +55,8 @@ 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: diff --git a/devscripts/zsh-completion.py b/devscripts/zsh-completion.py index f200f2c80..04728e8e2 100755 --- a/devscripts/zsh-completion.py +++ b/devscripts/zsh-completion.py @@ -5,7 +5,7 @@ import os from os.path import dirname as dirn import sys -sys.path.append(dirn(dirn((os.path.abspath(__file__))))) +sys.path.insert(0, dirn(dirn((os.path.abspath(__file__))))) import youtube_dl ZSH_COMPLETION_FILE = "youtube-dl.zsh" diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 66091e6be..5016ba4bc 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -53,6 +53,7 @@ - **Bandcamp:album** - **bbc**: BBC - **bbc.co.uk**: BBC iPlayer + - **bbc.co.uk:article**: BBC articles - **BeatportPro** - **Beeg** - **BehindKink** @@ -81,6 +82,7 @@ - **CBSSports** - **CeskaTelevize** - **channel9**: Channel 9 + - **Chaturbate** - **Chilloutzone** - **chirbit** - **chirbit:profile** @@ -91,6 +93,7 @@ - **Clipsyndicate** - **Cloudy** - **Clubic** + - **Clyp** - **cmt.com** - **CNET** - **CNN** @@ -101,7 +104,7 @@ - **ComCarCoff** - **ComedyCentral** - **ComedyCentralShows**: The Daily Show / The Colbert Report - - **CondeNast**: Condé Nast media group: Condé Nast, GQ, Glamour, Vanity Fair, Vogue, W Magazine, WIRED + - **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 - **Cracked** - **Criterion** - **CrooksAndLiars** @@ -120,9 +123,9 @@ - **DctpTv** - **DeezerPlaylist** - **defense.gouv.fr** + - **democracynow** - **DHM**: Filmarchiv - Deutsches Historisches Museum - **Discovery** - - **divxstage**: DivxStage - **Dotsub** - **DouyuTV**: 斗鱼 - **dramafever** @@ -151,6 +154,7 @@ - **Escapist** - **ESPN** (Currently broken) - **EsriVideo** + - **Europa** - **EveryonesMixtape** - **exfm**: ex.fm - **ExpoTV** @@ -158,8 +162,8 @@ - **facebook** - **faz.net** - **fc2** + - **Fczenit** - **fernsehkritik.tv** - - **fernsehkritik.tv:postecke** - **Firstpost** - **FiveTV** - **Flickr** @@ -192,10 +196,10 @@ - **Giga** - **Glide**: Glide mobile video messages (glide.me) - **Globo** + - **GloboArticle** - **GodTube** - **GoldenMoustache** - **Golem** - - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net and filehoot.com - **Goshgay** - **Groupon** - **Hark** @@ -209,7 +213,6 @@ - **hitbox** - **hitbox:live** - **HornBunny** - - **HostingBulk** - **HotNewHipHop** - **Howcast** - **HowStuffWorks** @@ -266,6 +269,9 @@ - **Libsyn** - **life:embed** - **lifenews**: LIFE | NEWS + - **limelight** + - **limelight:channel** + - **limelight:channel_list** - **LiveLeak** - **livestream** - **livestream:original** @@ -277,16 +283,15 @@ - **macgamestore**: MacGameStore trailers - **mailru**: Видео@Mail.Ru - **Malemotion** - - **MDR** + - **MDR**: MDR.DE and KiKA - **media.ccc.de** - - **MegaVideoz** - **metacafe** - **Metacritic** - **Mgoon** - **Minhateca** - **MinistryGrid** - **miomio.tv** - - **mitele.es** + - **MiTele**: mitele.es - **mixcloud** - **MLB** - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net @@ -317,7 +322,6 @@ - **Myvi** - **myvideo** - **MyVidster** - - **N-JOY** - **n-tv.de** - **NationalGeographic** - **Naver** @@ -326,7 +330,9 @@ - **NBCNews** - **NBCSports** - **NBCSportsVPlayer** - - **ndr**: NDR.de - Mediathek + - **ndr**: NDR.de - Norddeutscher Rundfunk + - **ndr:embed** + - **ndr:embed:base** - **NDTV** - **NerdCubedFeed** - **Nerdist** @@ -349,12 +355,16 @@ - **nhl.com:videocenter**: NHL videocenter category - **niconico**: ニコニコ動画 - **NiconicoPlaylist** + - **njoy**: N-JOY + - **njoy:embed** - **Noco** - **Normalboots** - **NosVideo** - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz - **novamov**: NovaMov - - **Nowness** + - **nowness** + - **nowness:playlist** + - **nowness:series** - **NowTV** - **nowvideo**: NowVideo - **npo**: npo.nl and ntr.nl @@ -375,7 +385,6 @@ - **OnionStudios** - **Ooyala** - **OoyalaExternal** - - **OpenFilm** - **orf:fm4**: radio FM4 - **orf:iptv**: iptv.ORF.at - **orf:oe1**: Radio Österreich 1 @@ -509,6 +518,7 @@ - **SSA** - **stanfordoc**: Stanford Open ClassRoom - **Steam** + - **Stitcher** - **streamcloud.eu** - **StreamCZ** - **StreetVoice** @@ -530,7 +540,7 @@ - **techtv.mit.edu** - **ted** - **TeleBruxelles** - - **telecinco.es** + - **Telecinco**: telecinco.es, cuatro.com and mediaset.es - **Telegraaf** - **TeleMB** - **TeleTask** @@ -582,7 +592,8 @@ - **twitch:stream** - **twitch:video** - **twitch:vod** - - **TwitterCard** + - **twitter** + - **twitter:card** - **Ubu** - **udemy** - **udemy:course** @@ -607,7 +618,6 @@ - **video.mit.edu** - **VideoDetective** - **videofy.me** - - **videolectures.net** - **VideoMega** - **VideoPremium** - **VideoTt**: video.tt - Your True Tube @@ -617,6 +627,7 @@ - **vier** - **vier:videos** - **Viewster** + - **Viidea** - **viki** - **viki:channel** - **vimeo** @@ -659,6 +670,7 @@ - **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 - **XHamster** - **XHamsterEmbed** - **XMinus** diff --git a/setup.py b/setup.py index 4686260e0..bfe931f5b 100644 --- a/setup.py +++ b/setup.py @@ -28,7 +28,7 @@ py2exe_options = { "compressed": 1, "optimize": 2, "dist_dir": '.', - "dll_excludes": ['w9xpopen.exe'], + "dll_excludes": ['w9xpopen.exe', 'crypt32.dll'], } py2exe_console = [{ diff --git a/test/helper.py b/test/helper.py index cb6eec8d9..bdd7acca4 100644 --- a/test/helper.py +++ b/test/helper.py @@ -89,66 +89,81 @@ def gettestcases(include_onlymatching=False): md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest() -def expect_info_dict(self, got_dict, expected_dict): +def expect_value(self, got, expected, field): + if isinstance(expected, compat_str) and expected.startswith('re:'): + match_str = expected[len('re:'):] + match_rex = re.compile(match_str) + + self.assertTrue( + isinstance(got, compat_str), + 'Expected a %s object, but got %s for field %s' % ( + compat_str.__name__, type(got).__name__, field)) + self.assertTrue( + match_rex.match(got), + 'field %s (value: %r) should match %r' % (field, got, match_str)) + elif isinstance(expected, compat_str) and expected.startswith('startswith:'): + start_str = expected[len('startswith:'):] + self.assertTrue( + isinstance(got, compat_str), + 'Expected a %s object, but got %s for field %s' % ( + compat_str.__name__, type(got).__name__, field)) + self.assertTrue( + got.startswith(start_str), + 'field %s (value: %r) should start with %r' % (field, got, start_str)) + elif isinstance(expected, compat_str) and expected.startswith('contains:'): + contains_str = expected[len('contains:'):] + self.assertTrue( + isinstance(got, compat_str), + 'Expected a %s object, but got %s for field %s' % ( + compat_str.__name__, type(got).__name__, field)) + self.assertTrue( + contains_str in got, + 'field %s (value: %r) should contain %r' % (field, got, contains_str)) + elif isinstance(expected, type): + self.assertTrue( + isinstance(got, expected), + 'Expected type %r for field %s, but got value %r of type %r' % (expected, field, got, type(got))) + elif isinstance(expected, dict) and isinstance(got, dict): + expect_dict(self, got, expected) + elif isinstance(expected, list) and isinstance(got, list): + self.assertEqual( + len(expected), len(got), + 'Expect a list of length %d, but got a list of length %d for field %s' % ( + len(expected), len(got), field)) + for index, (item_got, item_expected) in enumerate(zip(got, expected)): + type_got = type(item_got) + type_expected = type(item_expected) + self.assertEqual( + type_expected, type_got, + 'Type mismatch for list item at index %d for field %s, expected %r, got %r' % ( + index, field, type_expected, type_got)) + expect_value(self, item_got, item_expected, field) + else: + if isinstance(expected, compat_str) and expected.startswith('md5:'): + got = 'md5:' + md5(got) + elif isinstance(expected, compat_str) and expected.startswith('mincount:'): + self.assertTrue( + isinstance(got, (list, dict)), + 'Expected field %s to be a list or a dict, but it is of type %s' % ( + field, type(got).__name__)) + expected_num = int(expected.partition(':')[2]) + assertGreaterEqual( + self, len(got), expected_num, + 'Expected %d items in field %s, but only got %d' % (expected_num, field, len(got))) + return + self.assertEqual( + expected, got, + 'Invalid value for field %s, expected %r, got %r' % (field, expected, got)) + + +def expect_dict(self, got_dict, expected_dict): for info_field, expected in expected_dict.items(): - if isinstance(expected, compat_str) and expected.startswith('re:'): - got = got_dict.get(info_field) - match_str = expected[len('re:'):] - match_rex = re.compile(match_str) + got = got_dict.get(info_field) + expect_value(self, got, expected, info_field) - self.assertTrue( - isinstance(got, compat_str), - 'Expected a %s object, but got %s for field %s' % ( - compat_str.__name__, type(got).__name__, info_field)) - self.assertTrue( - match_rex.match(got), - 'field %s (value: %r) should match %r' % (info_field, got, match_str)) - elif isinstance(expected, compat_str) and expected.startswith('startswith:'): - got = got_dict.get(info_field) - start_str = expected[len('startswith:'):] - self.assertTrue( - isinstance(got, compat_str), - 'Expected a %s object, but got %s for field %s' % ( - compat_str.__name__, type(got).__name__, info_field)) - self.assertTrue( - got.startswith(start_str), - 'field %s (value: %r) should start with %r' % (info_field, got, start_str)) - elif isinstance(expected, compat_str) and expected.startswith('contains:'): - got = got_dict.get(info_field) - contains_str = expected[len('contains:'):] - self.assertTrue( - isinstance(got, compat_str), - 'Expected a %s object, but got %s for field %s' % ( - compat_str.__name__, type(got).__name__, info_field)) - self.assertTrue( - contains_str in got, - 'field %s (value: %r) should contain %r' % (info_field, got, contains_str)) - elif isinstance(expected, type): - got = got_dict.get(info_field) - self.assertTrue(isinstance(got, expected), - 'Expected type %r for field %s, but got value %r of type %r' % (expected, info_field, got, type(got))) - else: - if isinstance(expected, compat_str) and expected.startswith('md5:'): - got = 'md5:' + md5(got_dict.get(info_field)) - elif isinstance(expected, compat_str) and expected.startswith('mincount:'): - got = got_dict.get(info_field) - self.assertTrue( - isinstance(got, (list, dict)), - 'Expected field %s to be a list or a dict, but it is of type %s' % ( - info_field, type(got).__name__)) - expected_num = int(expected.partition(':')[2]) - assertGreaterEqual( - self, len(got), expected_num, - 'Expected %d items in field %s, but only got %d' % ( - expected_num, info_field, len(got) - ) - ) - continue - else: - got = got_dict.get(info_field) - self.assertEqual(expected, got, - 'invalid value for field %s, expected %r, got %r' % (info_field, expected, got)) +def expect_info_dict(self, got_dict, expected_dict): + expect_dict(self, got_dict, expected_dict) # Check for the presence of mandatory fields if got_dict.get('_type') not in ('playlist', 'multi_video'): for key in ('id', 'url', 'title', 'ext'): diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index be8d12997..938466a80 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -35,10 +35,18 @@ class TestInfoExtractor(unittest.TestCase): + + + + ''' self.assertEqual(ie._og_search_title(html), 'Foo') self.assertEqual(ie._og_search_description(html), 'Some video\'s description ') self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2') + self.assertEqual(ie._og_search_video_url(html, default=None), None) + self.assertEqual(ie._og_search_property('foobar', html), 'Foo') + self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar') + self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar') def test_html_search_meta(self): ie = self.ie diff --git a/test/test_compat.py b/test/test_compat.py index 4ee0dc99d..b6bfad05e 100644 --- a/test/test_compat.py +++ b/test/test_compat.py @@ -13,8 +13,10 @@ 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_etree_fromstring, compat_expanduser, compat_shlex_split, + compat_str, compat_urllib_parse_unquote, compat_urllib_parse_unquote_plus, ) @@ -71,5 +73,20 @@ class TestCompat(unittest.TestCase): def test_compat_shlex_split(self): self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two']) + def test_compat_etree_fromstring(self): + xml = ''' + + foo + 中文 + spam + + ''' + doc = compat_etree_fromstring(xml.encode('utf-8')) + self.assertTrue(isinstance(doc.attrib['foo'], compat_str)) + self.assertTrue(isinstance(doc.attrib['spam'], compat_str)) + self.assertTrue(isinstance(doc.find('normal').text, compat_str)) + self.assertTrue(isinstance(doc.find('chinese').text, compat_str)) + self.assertTrue(isinstance(doc.find('foo/bar').text, compat_str)) + if __name__ == '__main__': unittest.main() diff --git a/test/test_download.py b/test/test_download.py index 284418834..a3f1c0644 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -102,7 +102,7 @@ def generator(test_case): params = get_params(test_case.get('params', {})) if is_playlist and 'playlist' not in test_case: - params.setdefault('extract_flat', True) + params.setdefault('extract_flat', 'in_playlist') params.setdefault('skip_download', True) ydl = YoutubeDL(params, auto_init=False) diff --git a/test/test_jsinterp.py b/test/test_jsinterp.py index fc73e5dc2..63c350b8f 100644 --- a/test/test_jsinterp.py +++ b/test/test_jsinterp.py @@ -19,6 +19,9 @@ class TestJSInterpreter(unittest.TestCase): jsi = JSInterpreter('function x3(){return 42;}') self.assertEqual(jsi.call_function('x3'), 42) + jsi = JSInterpreter('var x5 = function(){return 42;}') + self.assertEqual(jsi.call_function('x5'), 42) + def test_calc(self): jsi = JSInterpreter('function x4(a){return 2*a+1;}') self.assertEqual(jsi.call_function('x4', 3), 7) diff --git a/test/test_subtitles.py b/test/test_subtitles.py index 0343967d9..75f0ea75f 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -28,6 +28,7 @@ from youtube_dl.extractor import ( ThePlatformFeedIE, RTVEALaCartaIE, FunnyOrDieIE, + DemocracynowIE, ) @@ -346,5 +347,25 @@ class TestFunnyOrDieSubtitles(BaseTestSubtitles): self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4') +class TestDemocracynowSubtitles(BaseTestSubtitles): + url = 'http://www.democracynow.org/shows/2015/7/3' + IE = DemocracynowIE + + def test_allsubtitles(self): + self.DL.params['writesubtitles'] = True + self.DL.params['allsubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(set(subtitles.keys()), set(['en'])) + self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c') + + def test_subtitles_in_page(self): + self.url = 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree' + self.DL.params['writesubtitles'] = True + self.DL.params['allsubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(set(subtitles.keys()), set(['en'])) + self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c') + + if __name__ == '__main__': unittest.main() diff --git a/test/test_utils.py b/test/test_utils.py index a5f164c49..01829f71e 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -68,6 +68,9 @@ from youtube_dl.utils import ( cli_valueless_option, cli_bool_option, ) +from youtube_dl.compat import ( + compat_etree_fromstring, +) class TestUtil(unittest.TestCase): @@ -233,6 +236,7 @@ class TestUtil(unittest.TestCase): unified_strdate('2/2/2015 6:47:40 PM', day_first=False), '20150202') self.assertEqual(unified_strdate('25-09-2014'), '20140925') + self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None) def test_find_xpath_attr(self): testxml = ''' @@ -242,7 +246,7 @@ class TestUtil(unittest.TestCase): ''' - doc = xml.etree.ElementTree.fromstring(testxml) + doc = compat_etree_fromstring(testxml) self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None) self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None) @@ -263,7 +267,7 @@ class TestUtil(unittest.TestCase): http://server.com/download.mp3 ''' - doc = xml.etree.ElementTree.fromstring(testxml) + doc = compat_etree_fromstring(testxml) find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'})) self.assertTrue(find('media:song') is not None) self.assertEqual(find('media:song/media:author').text, 'The Author') @@ -275,9 +279,16 @@ class TestUtil(unittest.TestCase): p = xml.etree.ElementTree.SubElement(div, 'p') p.text = 'Foo' self.assertEqual(xpath_element(doc, 'div/p'), p) + self.assertEqual(xpath_element(doc, ['div/p']), p) + self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p) self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default') + self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default') self.assertTrue(xpath_element(doc, 'div/bar') is None) + self.assertTrue(xpath_element(doc, ['div/bar']) is None) + self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None) self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True) + self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True) + self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True) def test_xpath_text(self): testxml = ''' @@ -285,7 +296,7 @@ class TestUtil(unittest.TestCase):

Foo

''' - doc = xml.etree.ElementTree.fromstring(testxml) + doc = compat_etree_fromstring(testxml) self.assertEqual(xpath_text(doc, 'div/p'), 'Foo') self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default') self.assertTrue(xpath_text(doc, 'div/bar') is None) @@ -297,7 +308,7 @@ class TestUtil(unittest.TestCase):

Foo

''' - doc = xml.etree.ElementTree.fromstring(testxml) + doc = compat_etree_fromstring(testxml) self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a') self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None) self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None) @@ -425,6 +436,8 @@ class TestUtil(unittest.TestCase): self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266) self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266) self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266) + self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251) + self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None) def test_strip_jsonp(self): stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);') @@ -495,6 +508,9 @@ class TestUtil(unittest.TestCase): "playlist":[{"controls":{"all":null}}] }''') + inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"''' + self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''') + inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"' json_code = js_to_json(inp) self.assertEqual(json.loads(json_code), json.loads(inp)) diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py index c889b6f15..26aadb34f 100644 --- a/test/test_youtube_lists.py +++ b/test/test_youtube_lists.py @@ -57,5 +57,14 @@ class TestYoutubeLists(unittest.TestCase): entries = result['entries'] self.assertEqual(len(entries), 100) + def test_youtube_flat_playlist_titles(self): + dl = FakeYDL() + dl.params['extract_flat'] = True + ie = YoutubePlaylistIE(dl) + result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re') + self.assertIsPlaylist(result) + for entry in result['entries']: + self.assertTrue(entry.get('title')) + if __name__ == '__main__': unittest.main() diff --git a/tox.ini b/tox.ini index cd805fe8a..48504329f 100644 --- a/tox.ini +++ b/tox.ini @@ -1,5 +1,5 @@ [tox] -envlist = py26,py27,py33,py34 +envlist = py26,py27,py33,py34,py35 [testenv] deps = nose diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index d65253882..1783ce01b 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -37,6 +37,7 @@ from .compat import ( compat_tokenize_tokenize, compat_urllib_error, compat_urllib_request, + compat_urllib_request_DataHandler, ) from .utils import ( ContentTooShortError, @@ -571,7 +572,7 @@ class YoutubeDL(object): if v is not None) template_dict = collections.defaultdict(lambda: 'NA', template_dict) - outtmpl = sanitize_path(self.params.get('outtmpl', DEFAULT_OUTTMPL)) + outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) tmpl = compat_expanduser(outtmpl) filename = tmpl % template_dict # Temporary fix for #4787 @@ -579,7 +580,7 @@ class YoutubeDL(object): # to workaround encoding issues with subprocess on python2 @ Windows if sys.version_info < (3, 0) and sys.platform == 'win32': filename = encodeFilename(filename, True).decode(preferredencoding()) - return filename + return sanitize_path(filename) except ValueError as err: self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')') return None @@ -1232,13 +1233,20 @@ class YoutubeDL(object): except (ValueError, OverflowError, OSError): pass + subtitles = info_dict.get('subtitles') + if subtitles: + for _, subtitle in subtitles.items(): + for subtitle_format in subtitle: + if 'ext' not in subtitle_format: + subtitle_format['ext'] = determine_ext(subtitle_format['url']).lower() + if self.params.get('listsubtitles', False): if 'automatic_captions' in info_dict: self.list_subtitles(info_dict['id'], info_dict.get('automatic_captions'), 'automatic captions') - self.list_subtitles(info_dict['id'], info_dict.get('subtitles'), 'subtitles') + self.list_subtitles(info_dict['id'], subtitles, 'subtitles') return info_dict['requested_subtitles'] = self.process_subtitles( - info_dict['id'], info_dict.get('subtitles'), + info_dict['id'], subtitles, info_dict.get('automatic_captions')) # We now pick which formats have to be downloaded @@ -1960,8 +1968,9 @@ class YoutubeDL(object): debuglevel = 1 if self.params.get('debug_printtraffic') else 0 https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel) ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel) + data_handler = compat_urllib_request_DataHandler() opener = compat_urllib_request.build_opener( - proxy_handler, https_handler, cookie_processor, ydlh) + proxy_handler, https_handler, cookie_processor, ydlh, data_handler) # Delete the default user-agent header, which would otherwise apply in # cases where our custom HTTP handler doesn't come into play diff --git a/youtube_dl/__main__.py b/youtube_dl/__main__.py index 65a0f891c..42a0f8c6f 100755 --- a/youtube_dl/__main__.py +++ b/youtube_dl/__main__.py @@ -11,7 +11,7 @@ if __package__ is None and not hasattr(sys, "frozen"): # direct call of __main__.py import os.path path = os.path.realpath(os.path.abspath(__file__)) - sys.path.append(os.path.dirname(os.path.dirname(path))) + sys.path.insert(0, os.path.dirname(os.path.dirname(path))) import youtube_dl diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index e32bef279..a3e85264a 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -1,7 +1,10 @@ from __future__ import unicode_literals +import binascii import collections +import email import getpass +import io import optparse import os import re @@ -11,6 +14,7 @@ import socket import subprocess import sys import itertools +import xml.etree.ElementTree try: @@ -38,6 +42,11 @@ try: except ImportError: # Python 2 import urlparse as compat_urlparse +try: + import urllib.response as compat_urllib_response +except ImportError: # Python 2 + import urllib as compat_urllib_response + try: import http.cookiejar as compat_cookiejar except ImportError: # Python 2 @@ -80,6 +89,11 @@ try: except ImportError: import BaseHTTPServer as compat_http_server +try: + compat_str = unicode # Python 2 +except NameError: + compat_str = str + try: from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes from urllib.parse import unquote as compat_urllib_parse_unquote @@ -100,7 +114,7 @@ except ImportError: # Python 2 # Is it a string-like object? string.split return b'' - if isinstance(string, unicode): + if isinstance(string, compat_str): string = string.encode('utf-8') bits = string.split(b'%') if len(bits) == 1: @@ -151,9 +165,38 @@ except ImportError: # Python 2 return compat_urllib_parse_unquote(string, encoding, errors) try: - compat_str = unicode # Python 2 -except NameError: - compat_str = str + from urllib.request import DataHandler as compat_urllib_request_DataHandler +except ImportError: # Python < 3.4 + # Ported from CPython 98774:1733b3bd46db, Lib/urllib/request.py + class compat_urllib_request_DataHandler(compat_urllib_request.BaseHandler): + def data_open(self, req): + # data URLs as specified in RFC 2397. + # + # ignores POSTed data + # + # syntax: + # dataurl := "data:" [ mediatype ] [ ";base64" ] "," data + # mediatype := [ type "/" subtype ] *( ";" parameter ) + # data := *urlchar + # parameter := attribute "=" value + url = req.get_full_url() + + scheme, data = url.split(":", 1) + mediatype, data = data.split(",", 1) + + # even base64 encoded data URLs might be quoted so unquote in any case: + data = compat_urllib_parse_unquote_to_bytes(data) + if mediatype.endswith(";base64"): + data = binascii.a2b_base64(data) + mediatype = mediatype[:-7] + + if not mediatype: + mediatype = "text/plain;charset=US-ASCII" + + headers = email.message_from_string( + "Content-type: %s\nContent-length: %d\n" % (mediatype, len(data))) + + return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url) try: compat_basestring = basestring # Python 2 @@ -170,6 +213,43 @@ try: except ImportError: # Python 2.6 from xml.parsers.expat import ExpatError as compat_xml_parse_error +if sys.version_info[0] >= 3: + compat_etree_fromstring = xml.etree.ElementTree.fromstring +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 + def _etree_iter(root): + for el in root.findall('*'): + yield el + for sub in _etree_iter(el): + yield sub + + # on 2.6 XML doesn't have a parser argument, function copied from CPython + # 2.7 source + def _XML(text, parser=None): + if not parser: + parser = etree.XMLParser(target=etree.TreeBuilder()) + parser.feed(text) + return parser.close() + + def _element_factory(*args, **kwargs): + el = etree.Element(*args, **kwargs) + for k, v in el.items(): + if isinstance(v, bytes): + el.set(k, v.decode('utf-8')) + return el + + def compat_etree_fromstring(text): + doc = _XML(text, parser=etree.XMLParser(target=etree.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') + return doc try: from urllib.parse import parse_qs as compat_parse_qs @@ -234,7 +314,7 @@ else: # 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, unicode): + if isinstance(s, compat_str): s = s.encode('utf-8') return shlex.split(s, comments, posix) @@ -416,26 +496,32 @@ if hasattr(shutil, 'get_terminal_size'): # Python >= 3.3 else: _terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines']) - def compat_get_terminal_size(): - columns = compat_getenv('COLUMNS', None) + def compat_get_terminal_size(fallback=(80, 24)): + columns = compat_getenv('COLUMNS') if columns: columns = int(columns) else: columns = None - lines = compat_getenv('LINES', None) + lines = compat_getenv('LINES') if lines: lines = int(lines) else: lines = None - try: - sp = subprocess.Popen( - ['stty', 'size'], - stdout=subprocess.PIPE, stderr=subprocess.PIPE) - out, err = sp.communicate() - lines, columns = map(int, out.split()) - except Exception: - pass + if columns is None or lines is None or columns <= 0 or lines <= 0: + try: + sp = subprocess.Popen( + ['stty', 'size'], + stdout=subprocess.PIPE, stderr=subprocess.PIPE) + out, err = sp.communicate() + _lines, _columns = map(int, out.split()) + except Exception: + _columns, _lines = _terminal_size(*fallback) + + if columns is None or columns <= 0: + columns = _columns + if lines is None or lines <= 0: + lines = _lines return _terminal_size(columns, lines) try: @@ -459,6 +545,7 @@ __all__ = [ 'compat_chr', 'compat_cookiejar', 'compat_cookies', + 'compat_etree_fromstring', 'compat_expanduser', 'compat_get_terminal_size', 'compat_getenv', @@ -483,6 +570,8 @@ __all__ = [ 'compat_urllib_parse_unquote_to_bytes', 'compat_urllib_parse_urlparse', 'compat_urllib_request', + 'compat_urllib_request_DataHandler', + 'compat_urllib_response', 'compat_urlparse', 'compat_urlretrieve', 'compat_xml_parse_error', diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py index 97e755d4b..29a4500d3 100644 --- a/youtube_dl/downloader/common.py +++ b/youtube_dl/downloader/common.py @@ -325,7 +325,7 @@ class FileDownloader(object): ) # Check file already present - if filename != '-' and nooverwrites_and_exists or continuedl_and_exists: + if filename != '-' and (nooverwrites_and_exists or continuedl_and_exists): self.report_file_already_downloaded(filename) self._hook_progress({ 'filename': filename, diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index 174180db5..6170cc155 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -5,12 +5,13 @@ import io import itertools import os import time -import xml.etree.ElementTree as etree from .fragment import FragmentFD from ..compat import ( + compat_etree_fromstring, compat_urlparse, compat_urllib_error, + compat_urllib_parse_urlparse, ) from ..utils import ( encodeFilename, @@ -285,9 +286,11 @@ class F4mFD(FragmentFD): man_url = info_dict['url'] requested_bitrate = info_dict.get('tbr') self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME) - manifest = self.ydl.urlopen(man_url).read() + urlh = self.ydl.urlopen(man_url) + man_url = urlh.geturl() + manifest = urlh.read() - doc = etree.fromstring(manifest) + 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: @@ -329,20 +332,25 @@ class F4mFD(FragmentFD): if not live: write_metadata_tag(dest_stream, metadata) + base_url_parsed = compat_urllib_parse_urlparse(base_url) + self._start_frag_download(ctx) frags_filenames = [] while fragments_list: seg_i, frag_i = fragments_list.pop(0) name = 'Seg%d-Frag%d' % (seg_i, frag_i) - url = base_url + name + query = [] + if base_url_parsed.query: + query.append(base_url_parsed.query) if akamai_pv: - url += '?' + akamai_pv.strip(';') + query.append(akamai_pv.strip(';')) if info_dict.get('extra_param_to_segment_url'): - url += info_dict.get('extra_param_to_segment_url') + query.append(info_dict['extra_param_to_segment_url']) + url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query)) frag_filename = '%s-%s' % (ctx['tmpfilename'], name) try: - success = ctx['dl'].download(frag_filename, {'url': url}) + success = ctx['dl'].download(frag_filename, {'url': url_parsed.geturl()}) if not success: return False (down, frag_sanitized) = sanitize_open(frag_filename, 'rb') diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index b2436e732..9a83a73dd 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -28,10 +28,19 @@ class HlsFD(FileDownloader): return False ffpp.check_version() - args = [ - encodeArgument(opt) - for opt in (ffpp.executable, '-y', '-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc')] - args.append(encodeFilename(tmpfilename, True)) + args = [ffpp.executable, '-y'] + + if info_dict['http_headers'] and re.match(r'^https?://', url): + # Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv: + # [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header. + args += [ + '-headers', + ''.join('%s: %s\r\n' % (key, val) for key, val in info_dict['http_headers'].items())] + + args += ['-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc'] + + args = [encodeArgument(opt) for opt in args] + args.append(encodeFilename(ffpp._ffmpeg_filename_argument(tmpfilename), True)) self._debug_cmd(args) diff --git a/youtube_dl/downloader/rtmp.py b/youtube_dl/downloader/rtmp.py index 7d19bb808..f1d219ba9 100644 --- a/youtube_dl/downloader/rtmp.py +++ b/youtube_dl/downloader/rtmp.py @@ -105,7 +105,7 @@ class RtmpFD(FileDownloader): protocol = info_dict.get('rtmp_protocol', None) real_time = info_dict.get('rtmp_real_time', False) no_resume = info_dict.get('no_resume', False) - continue_dl = info_dict.get('continuedl', True) + continue_dl = self.params.get('continuedl', True) self.report_destination(filename) tmpfilename = self.temp_name(filename) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index fcd9edec3..08cb93d76 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -45,6 +45,7 @@ from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE from .bbc import ( BBCCoUkIE, + BBCCoUkArticleIE, BBCIE, ) from .beeg import BeegIE @@ -79,6 +80,7 @@ from .cbssports import CBSSportsIE from .ccc import CCCIE from .ceskatelevize import CeskaTelevizeIE from .channel9 import Channel9IE +from .chaturbate import ChaturbateIE from .chilloutzone import ChilloutzoneIE from .chirbit import ( ChirbitIE, @@ -91,6 +93,7 @@ from .cliphunter import CliphunterIE from .clipsyndicate import ClipsyndicateIE from .cloudy import CloudyIE from .clubic import ClubicIE +from .clyp import ClypIE from .cmt import CMTIE from .cnet import CNETIE from .cnn import ( @@ -124,6 +127,7 @@ from .dbtv import DBTVIE from .dcn import DCNIE from .dctp import DctpTvIE from .deezer import DeezerPlaylistIE +from .democracynow import DemocracynowIE from .dfb import DFBIE from .dhm import DHMIE from .dotsub import DotsubIE @@ -141,7 +145,6 @@ from .dump import DumpIE from .dumpert import DumpertIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE -from .divxstage import DivxStageIE from .dropbox import DropboxIE from .eagleplatform import EaglePlatformIE from .ebaumsworld import EbaumsWorldIE @@ -162,6 +165,7 @@ from .eroprofile import EroProfileIE from .escapist import EscapistIE from .espn import ESPNIE from .esri import EsriVideoIE +from .europa import EuropaIE from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE from .expotv import ExpoTVIE @@ -169,14 +173,12 @@ from .extremetube import ExtremeTubeIE from .facebook import FacebookIE from .faz import FazIE from .fc2 import FC2IE +from .fczenit import FczenitIE from .firstpost import FirstpostIE from .firsttv import FirstTVIE from .fivemin import FiveMinIE from .fivetv import FiveTVIE -from .fktv import ( - FKTVIE, - FKTVPosteckeIE, -) +from .fktv import FKTVIE from .flickr import FlickrIE from .folketinget import FolketingetIE from .footyroom import FootyRoomIE @@ -213,13 +215,15 @@ from .gfycat import GfycatIE from .giantbomb import GiantBombIE from .giga import GigaIE from .glide import GlideIE -from .globo import GloboIE +from .globo import ( + GloboIE, + GloboArticleIE, +) from .godtube import GodTubeIE from .goldenmoustache import GoldenMoustacheIE from .golem import GolemIE from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE -from .gorillavid import GorillaVidIE from .goshgay import GoshgayIE from .groupon import GrouponIE from .hark import HarkIE @@ -232,7 +236,6 @@ from .historicfilms import HistoricFilmsIE from .history import HistoryIE from .hitbox import HitboxIE, HitboxLiveIE from .hornbunny import HornBunnyIE -from .hostingbulk import HostingBulkIE from .hotnewhiphop import HotNewHipHopIE from .howcast import HowcastIE from .howstuffworks import HowStuffWorksIE @@ -302,6 +305,11 @@ from .lifenews import ( LifeNewsIE, LifeEmbedIE, ) +from .limelight import ( + LimelightMediaIE, + LimelightChannelIE, + LimelightChannelListIE, +) from .liveleak import LiveLeakIE from .livestream import ( LivestreamIE, @@ -319,7 +327,6 @@ from .macgamestore import MacGameStoreIE from .mailru import MailRuIE from .malemotion import MalemotionIE from .mdr import MDRIE -from .megavideoz import MegaVideozIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mgoon import MgoonIE @@ -370,6 +377,9 @@ from .nbc import ( from .ndr import ( NDRIE, NJoyIE, + NDREmbedBaseIE, + NDREmbedIE, + NJoyEmbedIE, ) from .ndtv import NDTVIE from .netzkino import NetzkinoIE @@ -405,7 +415,11 @@ from .normalboots import NormalbootsIE from .nosvideo import NosVideoIE from .nova import NovaIE from .novamov import NovaMovIE -from .nowness import NownessIE +from .nowness import ( + NownessIE, + NownessPlaylistIE, + NownessSeriesIE, +) from .nowtv import NowTVIE from .nowvideo import NowVideoIE from .npo import ( @@ -435,7 +449,6 @@ from .ooyala import ( OoyalaIE, OoyalaExternalIE, ) -from .openfilm import OpenFilmIE from .orf import ( ORFTVthekIE, ORFOE1IE, @@ -581,6 +594,7 @@ from .spankwire import SpankwireIE from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegeltv import SpiegeltvIE from .spike import SpikeIE +from .stitcher import StitcherIE from .sport5 import Sport5IE from .sportbox import ( SportBoxIE, @@ -685,7 +699,7 @@ from .twitch import ( TwitchBookmarksIE, TwitchStreamIE, ) -from .twitter import TwitterCardIE +from .twitter import TwitterCardIE, TwitterIE from .ubu import UbuIE from .udemy import ( UdemyIE, @@ -712,7 +726,6 @@ from .vh1 import VH1IE from .vice import ViceIE from .viddler import ViddlerIE from .videodetective import VideoDetectiveIE -from .videolecturesnet import VideoLecturesNetIE from .videofyme import VideofyMeIE from .videomega import VideoMegaIE from .videopremium import VideoPremiumIE @@ -722,6 +735,7 @@ from .vidme import VidmeIE from .vidzi import VidziIE from .vier import VierIE, VierVideosIE from .viewster import ViewsterIE +from .viidea import ViideaIE from .vimeo import ( VimeoIE, VimeoAlbumIE, @@ -774,6 +788,7 @@ from .wrzuta import WrzutaIE from .wsj import WSJIE from .xbef import XBefIE from .xboxclips import XboxClipsIE +from .xfileshare import XFileShareIE from .xhamster import ( XHamsterIE, XHamsterEmbedIE, diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index f9a389f67..c0e5d1abf 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -12,7 +12,7 @@ from ..utils import ( class ABCIE(InfoExtractor): IE_NAME = 'abc.net.au' - _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P\d+)' + _VALID_URL = r'http://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P\d+)' _TESTS = [{ 'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334', @@ -36,6 +36,18 @@ class ABCIE(InfoExtractor): 'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill', }, 'add_ie': ['Youtube'], + }, { + 'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080', + 'md5': 'b96eee7c9edf4fc5a358a0252881cc1f', + 'info_dict': { + 'id': '6880080', + 'ext': 'mp3', + 'title': 'NAB lifts interest rates, following Westpac and CBA', + 'description': 'md5:f13d8edc81e462fce4a0437c7dc04728', + }, + }, { + 'url': 'http://www.abc.net.au/news/2015-10-19/6866214', + 'only_matching': True, }] def _real_extract(self, url): @@ -43,7 +55,7 @@ class ABCIE(InfoExtractor): webpage = self._download_webpage(url, video_id) mobj = re.search( - r'inline(?PVideo|YouTube)Data\.push\((?P[^)]+)\);', + r'inline(?PVideo|Audio|YouTube)Data\.push\((?P[^)]+)\);', webpage) if mobj is None: raise ExtractorError('Unable to extract video urls') @@ -60,11 +72,13 @@ class ABCIE(InfoExtractor): formats = [{ 'url': url_info['url'], + 'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none', 'width': int_or_none(url_info.get('width')), 'height': int_or_none(url_info.get('height')), 'tbr': int_or_none(url_info.get('bitrate')), 'filesize': int_or_none(url_info.get('filesize')), } for url_info in urls_info] + self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py index 4327c2f61..3ae618e71 100644 --- a/youtube_dl/extractor/adultswim.py +++ b/youtube_dl/extractor/adultswim.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( + determine_ext, ExtractorError, float_or_none, xpath_text, @@ -40,7 +41,8 @@ class AdultSwimIE(InfoExtractor): 'id': 'rQxZvXQ4ROaSOqq-or2Mow', 'title': 'Rick and Morty - Pilot', 'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. " - } + }, + 'skip': 'This video is only available for registered users', }, { 'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/', 'playlist': [ @@ -123,7 +125,6 @@ class AdultSwimIE(InfoExtractor): else: collections = bootstrapped_data['show']['collections'] collection, video_info = self.find_collection_containing_video(collections, episode_path) - # Video wasn't found in the collections, let's try `slugged_video`. if video_info is None: if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path: @@ -133,7 +134,15 @@ class AdultSwimIE(InfoExtractor): show = bootstrapped_data['show'] show_title = show['title'] - segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']] + stream = video_info.get('stream') + clips = [stream] if stream else video_info.get('clips') + if not clips: + raise ExtractorError( + 'This video is only available via cable service provider subscription that' + ' is not currently supported. You may want to use --cookies.' + if video_info.get('auth') is True else 'Unable to find stream or clips', + expected=True) + segment_ids = [clip['videoPlaybackID'] for clip in clips] episode_id = video_info['id'] episode_title = video_info['title'] @@ -142,7 +151,7 @@ class AdultSwimIE(InfoExtractor): entries = [] for part_num, segment_id in enumerate(segment_ids): - segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id + segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id segment_title = '%s - %s' % (show_title, episode_title) if len(segment_ids) > 1: @@ -158,17 +167,30 @@ class AdultSwimIE(InfoExtractor): formats = [] file_els = idoc.findall('.//files/file') or idoc.findall('./files/file') + unique_urls = [] + unique_file_els = [] for file_el in file_els: + media_url = file_el.text + if not media_url or determine_ext(media_url) == 'f4m': + continue + if file_el.text not in unique_urls: + unique_urls.append(file_el.text) + unique_file_els.append(file_el) + + for file_el in unique_file_els: bitrate = file_el.attrib.get('bitrate') ftype = file_el.attrib.get('type') - - formats.append({ - 'format_id': '%s_%s' % (bitrate, ftype), - 'url': file_el.text.strip(), - # The bitrate may not be a number (for example: 'iphone') - 'tbr': int(bitrate) if bitrate.isdigit() else None, - 'quality': 1 if ftype == 'hd' else -1 - }) + media_url = file_el.text + if determine_ext(media_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + media_url, segment_title, 'mp4', preference=0, m3u8_id='hls')) + else: + formats.append({ + 'format_id': '%s_%s' % (bitrate, ftype), + 'url': file_el.text.strip(), + # The bitrate may not be a number (for example: 'iphone') + 'tbr': int(bitrate) if bitrate.isdigit() else None, + }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/anitube.py b/youtube_dl/extractor/anitube.py index 31f0d417c..23f942ae2 100644 --- a/youtube_dl/extractor/anitube.py +++ b/youtube_dl/extractor/anitube.py @@ -26,8 +26,8 @@ class AnitubeIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - key = self._html_search_regex( - r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', webpage, 'key') + key = self._search_regex( + r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key') config_xml = self._download_xml( 'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key) diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index 576f03b5b..f68dc3236 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -13,53 +13,53 @@ from ..utils import ( class AppleTrailersIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/(?:trailers|ca)/(?P[^/]+)/(?P[^/]+)' _TESTS = [{ - "url": "http://trailers.apple.com/trailers/wb/manofsteel/", + 'url': 'http://trailers.apple.com/trailers/wb/manofsteel/', 'info_dict': { 'id': 'manofsteel', }, - "playlist": [ + 'playlist': [ { - "md5": "d97a8e575432dbcb81b7c3acb741f8a8", - "info_dict": { - "id": "manofsteel-trailer4", - "ext": "mov", - "duration": 111, - "title": "Trailer 4", - "upload_date": "20130523", - "uploader_id": "wb", + 'md5': 'd97a8e575432dbcb81b7c3acb741f8a8', + 'info_dict': { + 'id': 'manofsteel-trailer4', + 'ext': 'mov', + 'duration': 111, + 'title': 'Trailer 4', + 'upload_date': '20130523', + 'uploader_id': 'wb', }, }, { - "md5": "b8017b7131b721fb4e8d6f49e1df908c", - "info_dict": { - "id": "manofsteel-trailer3", - "ext": "mov", - "duration": 182, - "title": "Trailer 3", - "upload_date": "20130417", - "uploader_id": "wb", + 'md5': 'b8017b7131b721fb4e8d6f49e1df908c', + 'info_dict': { + 'id': 'manofsteel-trailer3', + 'ext': 'mov', + 'duration': 182, + 'title': 'Trailer 3', + 'upload_date': '20130417', + 'uploader_id': 'wb', }, }, { - "md5": "d0f1e1150989b9924679b441f3404d48", - "info_dict": { - "id": "manofsteel-trailer", - "ext": "mov", - "duration": 148, - "title": "Trailer", - "upload_date": "20121212", - "uploader_id": "wb", + 'md5': 'd0f1e1150989b9924679b441f3404d48', + 'info_dict': { + 'id': 'manofsteel-trailer', + 'ext': 'mov', + 'duration': 148, + 'title': 'Trailer', + 'upload_date': '20121212', + 'uploader_id': 'wb', }, }, { - "md5": "5fe08795b943eb2e757fa95cb6def1cb", - "info_dict": { - "id": "manofsteel-teaser", - "ext": "mov", - "duration": 93, - "title": "Teaser", - "upload_date": "20120721", - "uploader_id": "wb", + 'md5': '5fe08795b943eb2e757fa95cb6def1cb', + 'info_dict': { + 'id': 'manofsteel-teaser', + 'ext': 'mov', + 'duration': 93, + 'title': 'Teaser', + 'upload_date': '20120721', + 'uploader_id': 'wb', }, }, ] diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 6f465789b..73be6d204 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -14,8 +14,8 @@ from ..utils import ( parse_duration, unified_strdate, xpath_text, - parse_xml, ) +from ..compat import compat_etree_fromstring class ARDMediathekIE(InfoExtractor): @@ -161,7 +161,7 @@ class ARDMediathekIE(InfoExtractor): raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True) if re.search(r'[\?&]rss($|[=&])', url): - doc = parse_xml(webpage) + doc = compat_etree_fromstring(webpage.encode('utf-8')) if doc.tag == 'rss': return GenericIE()._extract_rss(url, video_id, doc) diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 76de24477..2a00da3ee 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -4,6 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_urllib_parse_urlparse, +) from ..utils import ( find_xpath_attr, unified_strdate, @@ -77,7 +81,13 @@ class ArteTVPlus7IE(InfoExtractor): def _extract_from_webpage(self, webpage, video_id, lang): json_url = self._html_search_regex( [r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'], - webpage, 'json vp url') + webpage, 'json vp url', default=None) + if not json_url: + iframe_url = self._html_search_regex( + r']+src=(["\'])(?P.+\bjson_url=.+?)\1', + webpage, 'iframe url', group='url') + json_url = compat_parse_qs( + compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] return self._extract_from_json_url(json_url, video_id, lang) def _extract_from_json_url(self, json_url, video_id, lang): diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index 505877b77..c1ef8051d 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -10,6 +10,8 @@ from ..compat import ( ) from ..utils import ( ExtractorError, + float_or_none, + int_or_none, ) @@ -52,11 +54,11 @@ class BandcampIE(InfoExtractor): ext, abr_str = format_id.split('-', 1) formats.append({ 'format_id': format_id, - 'url': format_url, + 'url': self._proto_relative_url(format_url, 'http:'), 'ext': ext, 'vcodec': 'none', 'acodec': ext, - 'abr': int(abr_str), + 'abr': int_or_none(abr_str), }) self._sort_formats(formats) @@ -65,7 +67,7 @@ class BandcampIE(InfoExtractor): 'id': compat_str(data['id']), 'title': data['title'], 'formats': formats, - 'duration': float(data['duration']), + 'duration': float_or_none(data.get('duration')), } else: raise ExtractorError('No free songs found') @@ -93,8 +95,8 @@ class BandcampIE(InfoExtractor): final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url') # If we could correctly generate the .rand field the url would be # in the "download_url" key - final_url = self._search_regex( - r'"retry_url":"(.*?)"', final_url_webpage, 'final video URL') + final_url = self._proto_relative_url(self._search_regex( + r'"retry_url":"(.+?)"', final_url_webpage, 'final video URL'), 'http:') return { 'id': video_id, diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index abc5a44a1..a55a6dbc9 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( @@ -11,19 +10,36 @@ from ..utils import ( int_or_none, parse_duration, parse_iso8601, + remove_end, + unescapeHTML, +) +from ..compat import ( + compat_etree_fromstring, + compat_HTTPError, ) -from ..compat import compat_HTTPError class BBCCoUkIE(InfoExtractor): IE_NAME = 'bbc.co.uk' IE_DESC = 'BBC iPlayer' - _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P[\da-z]{8})' + _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P[\da-z]{8})' _MEDIASELECTOR_URLS = [ + # Provides HQ HLS streams with even better quality that pc mediaset but fails + # with geolocation in some cases when it's even not geo restricted at all (e.g. + # http://www.bbc.co.uk/programmes/b06bp7lf) + 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s', 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s', ] + _MEDIASELECTION_NS = 'http://bbc.co.uk/2008/mp/mediaselection' + _EMP_PLAYLIST_NS = 'http://bbc.co.uk/2008/emp/playlist' + + _NAMESPACES = ( + _MEDIASELECTION_NS, + _EMP_PLAYLIST_NS, + ) + _TESTS = [ { 'url': 'http://www.bbc.co.uk/programmes/b039g8p7', @@ -152,6 +168,21 @@ class BBCCoUkIE(InfoExtractor): 'skip_download': True, }, 'skip': 'geolocation', + }, { + # iptv-all mediaset fails with geolocation however there is no geo restriction + # for this programme at all + 'url': 'http://www.bbc.co.uk/programmes/b06bp7lf', + 'info_dict': { + 'id': 'b06bp7kf', + 'ext': 'flv', + 'title': "Annie Mac's Friday Night, B.Traits sits in for Annie", + 'description': 'B.Traits sits in for Annie Mac with a Mini-Mix from Disclosure.', + 'duration': 10800, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, }, { 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', 'only_matching': True, @@ -174,6 +205,7 @@ class BBCCoUkIE(InfoExtractor): def _extract_connection(self, connection, programme_id): formats = [] + kind = connection.get('kind') protocol = connection.get('protocol') supplier = connection.get('supplier') if protocol == 'http': @@ -189,11 +221,17 @@ class BBCCoUkIE(InfoExtractor): # Skip DASH until supported elif transfer_format == 'dash': pass + elif transfer_format == 'hls': + m3u8_formats = self._extract_m3u8_formats( + href, programme_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id=supplier, fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) # Direct link else: formats.append({ 'url': href, - 'format_id': supplier, + 'format_id': supplier or kind or protocol, }) elif protocol == 'rtmp': application = connection.get('application', 'ondemand') @@ -213,16 +251,24 @@ class BBCCoUkIE(InfoExtractor): return formats def _extract_items(self, playlist): - return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item') + return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS) + + def _findall_ns(self, element, xpath): + elements = [] + for ns in self._NAMESPACES: + elements.extend(element.findall(xpath % ns)) + return elements def _extract_medias(self, media_selection): - error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error') + error = media_selection.find('./{%s}error' % self._MEDIASELECTION_NS) + if error is None: + media_selection.find('./{%s}error' % self._EMP_PLAYLIST_NS) if error is not None: raise BBCCoUkIE.MediaSelectionError(error.get('id')) - return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media') + return self._findall_ns(media_selection, './{%s}media') def _extract_connections(self, media): - return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection') + return self._findall_ns(media, './{%s}connection') def _extract_video(self, media, programme_id): formats = [] @@ -236,13 +282,14 @@ class BBCCoUkIE(InfoExtractor): conn_formats = self._extract_connection(connection, programme_id) for format in conn_formats: format.update({ - 'format_id': '%s_%s' % (service, format['format_id']), 'width': width, 'height': height, 'vbr': vbr, 'vcodec': vcodec, 'filesize': file_size, }) + if service: + format['format_id'] = '%s_%s' % (service, format['format_id']) formats.extend(conn_formats) return formats @@ -287,7 +334,7 @@ class BBCCoUkIE(InfoExtractor): return self._download_media_selector_url( mediaselector_url % programme_id, programme_id) except BBCCoUkIE.MediaSelectionError as e: - if e.id == 'notukerror': + if e.id in ('notukerror', 'geolocation'): last_exception = e continue self._raise_extractor_error(e) @@ -299,7 +346,7 @@ class BBCCoUkIE(InfoExtractor): url, programme_id, 'Downloading media selection XML') except ExtractorError as ee: if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: - media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8')) + media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8')) else: raise return self._process_media_selector(media_selection, programme_id) @@ -357,7 +404,7 @@ class BBCCoUkIE(InfoExtractor): url, playlist_id, 'Downloading legacy playlist XML') def _extract_from_legacy_playlist(self, playlist, playlist_id): - no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') + no_items = playlist.find('./{%s}noItems' % self._EMP_PLAYLIST_NS) if no_items is not None: reason = no_items.get('reason') if reason == 'preAvailability': @@ -374,8 +421,9 @@ class BBCCoUkIE(InfoExtractor): kind = item.get('kind') if kind != 'programme' and kind != 'radioProgramme': continue - title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text - description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text + title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text + description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS) + description = description_el.text if description_el is not None else None def get_programme_id(item): def get_from_attributes(item): @@ -384,16 +432,18 @@ class BBCCoUkIE(InfoExtractor): if value and re.match(r'^[pb][\da-z]{7}$', value): return value get_from_attributes(item) - mediator = item.find('./{http://bbc.co.uk/2008/emp/playlist}mediator') + mediator = item.find('./{%s}mediator' % self._EMP_PLAYLIST_NS) if mediator is not None: return get_from_attributes(mediator) programme_id = get_programme_id(item) duration = int_or_none(item.get('duration')) - # TODO: programme_id can be None and media items can be incorporated right inside - # playlist's item (e.g. http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) - # as f4m and m3u8 - formats, subtitles = self._download_media_selector(programme_id) + + if programme_id: + formats, subtitles = self._download_media_selector(programme_id) + else: + formats, subtitles = self._process_media_selector(item, playlist_id) + programme_id = playlist_id return programme_id, title, description, duration, formats, subtitles @@ -445,6 +495,9 @@ class BBCIE(BBCCoUkIE): _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P[^/#?]+)' _MEDIASELECTOR_URLS = [ + # Provides HQ HLS streams but fails with geolocation in some cases when it's + # even not geo restricted at all + 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s', # Provides more formats, namely direct mp4 links, but fails on some videos with # notukerror for non UK (?) users (e.g. # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) @@ -454,8 +507,7 @@ class BBCIE(BBCCoUkIE): ] _TESTS = [{ - # article with multiple videos embedded with data-media-meta containing - # playlist.sxml, externalId and no direct video links + # article with multiple videos embedded with data-playable containing vpids 'url': 'http://www.bbc.com/news/world-europe-32668511', 'info_dict': { 'id': 'world-europe-32668511', @@ -464,7 +516,7 @@ class BBCIE(BBCCoUkIE): }, 'playlist_count': 2, }, { - # article with multiple videos embedded with data-media-meta (more videos) + # article with multiple videos embedded with data-playable (more videos) 'url': 'http://www.bbc.com/news/business-28299555', 'info_dict': { 'id': 'business-28299555', @@ -475,6 +527,7 @@ class BBCIE(BBCCoUkIE): 'skip': 'Save time', }, { # article with multiple videos embedded with `new SMP()` + # broken 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460', 'info_dict': { 'id': '3662a707-0af9-3149-963f-47bea720b460', @@ -482,12 +535,13 @@ class BBCIE(BBCCoUkIE): }, 'playlist_count': 18, }, { - # single video embedded with mediaAssetPage.init() + # single video embedded with data-playable containing vpid 'url': 'http://www.bbc.com/news/world-europe-32041533', 'info_dict': { 'id': 'p02mprgb', 'ext': 'mp4', 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV', + 'description': 'md5:2868290467291b37feda7863f7a83f54', 'duration': 47, 'timestamp': 1427219242, 'upload_date': '20150324', @@ -497,15 +551,14 @@ class BBCIE(BBCCoUkIE): 'skip_download': True, } }, { - # article with single video embedded with data-media-meta containing - # direct video links (for now these are extracted) and playlist.xml (with - # media items as f4m and m3u8 - currently unsupported) + # article with single video embedded with data-playable containing XML playlist + # with direct video links as progressiveDownloadUrl (for now these are extracted) + # and playlist with f4m and m3u8 as streamingUrl 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu', 'info_dict': { 'id': '150615_telabyad_kentin_cogu', 'ext': 'mp4', 'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde", - 'duration': 47, 'timestamp': 1434397334, 'upload_date': '20150615', }, @@ -513,13 +566,12 @@ class BBCIE(BBCCoUkIE): 'skip_download': True, } }, { - # single video embedded with mediaAssetPage.init() (regional section) + # single video embedded with data-playable containing XML playlists (regional section) 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw', 'info_dict': { 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw', 'ext': 'mp4', 'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción', - 'duration': 87, 'timestamp': 1434713142, 'upload_date': '20150619', }, @@ -561,27 +613,35 @@ class BBCIE(BBCCoUkIE): 'ext': 'mp4', 'title': 'Hyundai Santa Fe Sport: Rock star', 'description': 'md5:b042a26142c4154a6e472933cf20793d', - 'timestamp': 1368473503, - 'upload_date': '20130513', + 'timestamp': 1415867444, + 'upload_date': '20141113', }, 'params': { # rtmp download 'skip_download': True, } }, { - # single video with playlist.sxml URL + # single video with playlist.sxml URL in playlist param 'url': 'http://www.bbc.com/sport/0/football/33653409', 'info_dict': { 'id': 'p02xycnp', 'ext': 'mp4', 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?', - 'description': 'md5:398fca0e2e701c609d726e034fa1fc89', + 'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.', 'duration': 140, }, 'params': { # rtmp download 'skip_download': True, } + }, { + # article with multiple videos embedded with playlist.sxml in playlist param + 'url': 'http://www.bbc.com/sport/0/football/34475836', + 'info_dict': { + 'id': '34475836', + 'title': 'What Liverpool can expect from Klopp', + }, + 'playlist_count': 3, }, { # single video with playlist URL from weather section 'url': 'http://www.bbc.com/weather/features/33601775', @@ -594,7 +654,7 @@ class BBCIE(BBCCoUkIE): @classmethod def suitable(cls, url): - return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url) + return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) 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. @@ -623,40 +683,107 @@ class BBCIE(BBCCoUkIE): return [], [] + def _extract_from_playlist_sxml(self, url, playlist_id, timestamp): + programme_id, title, description, duration, formats, subtitles = \ + self._process_legacy_playlist_url(url, playlist_id) + self._sort_formats(formats) + return { + 'id': programme_id, + 'title': title, + 'description': description, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + 'subtitles': subtitles, + } + def _real_extract(self, url): playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) - timestamp = parse_iso8601(self._search_regex( - [r'"datePublished":\s*"([^"]+)', - r']+property="article:published_time"[^>]+content="([^"]+)"', - r'itemprop="datePublished"[^>]+datetime="([^"]+)"'], - webpage, 'date', default=None)) - - # single video with playlist.sxml URL (e.g. http://www.bbc.com/sport/0/football/3365340ng) - playlist = self._search_regex( - r']+name="playlist"[^>]+value="([^"]+)"', - webpage, 'playlist', default=None) - if playlist: - programme_id, title, description, duration, formats, subtitles = \ - self._process_legacy_playlist_url(playlist, playlist_id) - self._sort_formats(formats) - return { - 'id': programme_id, - 'title': title, - 'description': description, - 'duration': duration, - 'timestamp': timestamp, - 'formats': formats, - 'subtitles': subtitles, - } + timestamp = None + playlist_title = None + playlist_description = None + + ld = self._parse_json( + self._search_regex( + r'(?s)', + webpage, 'ld json', default='{}'), + playlist_id, fatal=False) + if ld: + timestamp = parse_iso8601(ld.get('datePublished')) + playlist_title = ld.get('headline') + playlist_description = ld.get('articleBody') + + if not timestamp: + timestamp = parse_iso8601(self._search_regex( + [r']+property="article:published_time"[^>]+content="([^"]+)"', + r'itemprop="datePublished"[^>]+datetime="([^"]+)"', + r'"datePublished":\s*"([^"]+)'], + webpage, 'date', default=None)) + + entries = [] + + # article with multiple videos embedded with playlist.sxml (e.g. + # http://www.bbc.com/sport/0/football/34475836) + playlists = re.findall(r']+name="playlist"[^>]+value="([^"]+)"', webpage) + if playlists: + entries = [ + self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp) + for playlist_url in playlists] + + # news article with multiple videos embedded with data-playable + data_playables = re.findall(r'data-playable=(["\'])({.+?})\1', webpage) + if data_playables: + for _, data_playable_json in data_playables: + data_playable = self._parse_json( + unescapeHTML(data_playable_json), playlist_id, fatal=False) + if not data_playable: + continue + settings = data_playable.get('settings', {}) + if settings: + # data-playable with video vpid in settings.playlistObject.items (e.g. + # http://www.bbc.com/news/world-us-canada-34473351) + playlist_object = settings.get('playlistObject', {}) + if playlist_object: + items = playlist_object.get('items') + if items and isinstance(items, list): + title = playlist_object['title'] + description = playlist_object.get('summary') + duration = int_or_none(items[0].get('duration')) + programme_id = items[0].get('vpid') + formats, subtitles = self._download_media_selector(programme_id) + self._sort_formats(formats) + entries.append({ + 'id': programme_id, + 'title': title, + 'description': description, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + 'subtitles': subtitles, + }) + else: + # data-playable without vpid but with a playlist.sxml URLs + # in otherSettings.playlist (e.g. + # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani) + playlist = data_playable.get('otherSettings', {}).get('playlist', {}) + if playlist: + entries.append(self._extract_from_playlist_sxml( + playlist.get('progressiveDownloadUrl'), playlist_id, timestamp)) + + if entries: + playlist_title = playlist_title or remove_end(self._og_search_title(webpage), ' - BBC News') + playlist_description = playlist_description or self._og_search_description(webpage, default=None) + return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) programme_id = self._search_regex( [r'data-video-player-vpid="([\da-z]{8})"', r']+name="externalIdentifier"[^>]+value="([\da-z]{8})"'], webpage, 'vpid', default=None) + if programme_id: formats, subtitles = self._download_media_selector(programme_id) self._sort_formats(formats) @@ -778,3 +905,33 @@ class BBCIE(BBCCoUkIE): }) return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) + + +class BBCCoUkArticleIE(InfoExtractor): + _VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P[a-zA-Z0-9]+)' + IE_NAME = 'bbc.co.uk:article' + IE_DESC = 'BBC articles' + + _TEST = { + 'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer', + 'info_dict': { + 'id': '3jNQLTMrPlYGTBn0WV6M2MS', + 'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four', + 'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.', + }, + 'playlist_count': 4, + 'add_ie': ['BBCCoUk'], + } + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage).strip() + + entries = [self.url_result(programme_url) for programme_url in re.findall( + r']+typeof="Clip"[^>]+resource="([^"]+)"', webpage)] + + return self.playlist_result(entries, playlist_id, title, description) diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index b38057f2f..61bc2f744 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -1,65 +1,69 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_iso8601, +) class BeegIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P\d+)' _TEST = { 'url': 'http://beeg.com/5416503', - 'md5': '1bff67111adb785c51d1b42959ec10e5', + 'md5': '46c384def73b33dbc581262e5ee67cef', 'info_dict': { 'id': '5416503', 'ext': 'mp4', 'title': 'Sultry Striptease', - 'description': 'md5:6db3c6177972822aaba18652ff59c773', - 'categories': list, # NSFW - 'thumbnail': 're:https?://.*\.jpg$', + 'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2', + 'timestamp': 1391813355, + 'upload_date': '20140207', + 'duration': 383, + 'tags': list, 'age_limit': 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - webpage = self._download_webpage(url, video_id) - - quality_arr = self._search_regex( - r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats') + video_id = self._match_id(url) - formats = [{ - 'url': fmt[1], - 'format_id': fmt[0], - 'height': int(fmt[0][:-1]), - } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)] + video = self._download_json( + 'http://beeg.com/api/v1/video/%s' % video_id, video_id) + formats = [] + for format_id, video_url in video.items(): + if not video_url: + continue + height = self._search_regex( + r'^(\d+)[pP]$', format_id, 'height', default=None) + if not height: + continue + formats.append({ + 'url': self._proto_relative_url(video_url.replace('{DATA_MARKERS}', ''), 'http:'), + 'format_id': format_id, + 'height': int(height), + }) self._sort_formats(formats) - title = self._html_search_regex( - r'([^<]+)\s*-\s*beeg\.?', webpage, 'title') + title = video['title'] + video_id = video.get('id') or video_id + display_id = video.get('code') + description = video.get('desc') - description = self._html_search_regex( - r'\d+)' + _VALID_URL = r'https?://(?:www\.)?canalc2\.tv/video/(?P\d+)' _TEST = { - 'url': 'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui', + 'url': 'http://www.canalc2.tv/video/12163', 'md5': '060158428b650f896c542dfbb3d6487f', 'info_dict': { 'id': '12163', - 'ext': 'mp4', - 'title': 'Terrasses du Numérique' + 'ext': 'flv', + 'title': 'Terrasses du Numérique', + 'duration': 122, + }, + 'params': { + 'skip_download': True, # Requires rtmpdump } } def _real_extract(self, url): - video_id = re.match(self._VALID_URL, url).group('id') - # We need to set the voir field for getting the file name - url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - file_name = self._search_regex( - r"so\.addVariable\('file','(.*?)'\);", - webpage, 'file name') - video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name + video_url = self._search_regex( + r'jwplayer\((["\'])Player\1\)\.setup\({[^}]*file\s*:\s*(["\'])(?P.+?)\2', + webpage, 'video_url', group='file') + formats = [{'url': video_url}] + if video_url.startswith('rtmp://'): + rtmp = re.search(r'^(?Prtmp://[^/]+/(?P.+/))(?Pmp4:.+)$', video_url) + formats[0].update({ + 'url': rtmp.group('url'), + 'ext': 'flv', + 'app': rtmp.group('app'), + 'play_path': rtmp.group('play_path'), + 'page_url': url, + }) title = self._html_search_regex( - r'class="evenement8">(.*?)', webpage, 'title') + r'(?s)class="[^"]*col_description[^"]*">.*?

(.*?)

', webpage, 'title') + duration = parse_duration(self._search_regex( + r'id=["\']video_duree["\'][^>]*>([^<]+)', + webpage, 'duration', fatal=False)) return { 'id': video_id, - 'ext': 'mp4', - 'url': video_url, 'title': title, + 'duration': duration, + 'formats': formats, } diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index 57e0cda2c..004372f8d 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -78,7 +78,8 @@ class CanalplusIE(InfoExtractor): if video_id is None: webpage = self._download_webpage(url, display_id) video_id = self._search_regex( - r']+?videoId="(\d+)"', webpage, 'video id') + [r']+?videoId=(["\'])(?P\d+)', r'id=["\']canal_video_player(?P\d+)'], + webpage, 'video id', group='id') info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id) doc = self._download_xml(info_url, video_id, 'Downloading video XML') diff --git a/youtube_dl/extractor/cbs.py b/youtube_dl/extractor/cbs.py index 75fffb156..43f05d278 100644 --- a/youtube_dl/extractor/cbs.py +++ b/youtube_dl/extractor/cbs.py @@ -1,6 +1,8 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import compat_urllib_request +from ..utils import smuggle_url class CBSIE(InfoExtractor): @@ -46,13 +48,19 @@ class CBSIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) + request = compat_urllib_request.Request(url) + # Android UA is served with higher quality (720p) streams (see + # https://github.com/rg3/youtube-dl/issues/7490) + request.add_header('User-Agent', 'Mozilla/5.0 (Linux; Android 4.4; Nexus 5)') + webpage = self._download_webpage(request, display_id) real_id = self._search_regex( [r"video\.settings\.pid\s*=\s*'([^']+)';", r"cbsplayer\.pid\s*=\s*'([^']+)';"], webpage, 'real video ID') return { '_type': 'url_transparent', 'ie_key': 'ThePlatform', - 'url': 'theplatform:%s' % real_id, + 'url': smuggle_url( + 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true&manifest=m3u' % real_id, + {'force_smil_url': True}), 'display_id': display_id, } diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py index 52e61d85b..f9a64a0a2 100644 --- a/youtube_dl/extractor/cbsnews.py +++ b/youtube_dl/extractor/cbsnews.py @@ -67,9 +67,12 @@ class CBSNewsIE(InfoExtractor): 'format_id': format_id, } if uri.startswith('rtmp'): + play_path = re.sub( + r'{slistFilePath}', '', + uri.split('')[-1].split('{break}')[-1]) fmt.update({ 'app': 'ondemand?auth=cbs', - 'play_path': 'mp4:' + uri.split('')[-1], + 'play_path': 'mp4:' + play_path, 'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf', 'page_url': 'http://www.cbsnews.com', 'ext': 'flv', diff --git a/youtube_dl/extractor/channel9.py b/youtube_dl/extractor/channel9.py index 3dfc24f5b..c74553dcf 100644 --- a/youtube_dl/extractor/channel9.py +++ b/youtube_dl/extractor/channel9.py @@ -3,7 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + parse_filesize, + qualities, +) class Channel9IE(InfoExtractor): @@ -28,7 +32,7 @@ class Channel9IE(InfoExtractor): 'title': 'Developer Kick-Off Session: Stuff We Love', 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f', 'duration': 4576, - 'thumbnail': 'http://video.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg', + 'thumbnail': 're:http://.*\.jpg', 'session_code': 'KOS002', 'session_day': 'Day 1', 'session_room': 'Arena 1A', @@ -44,31 +48,29 @@ class Channel9IE(InfoExtractor): 'title': 'Self-service BI with Power BI - nuclear testing', 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b', 'duration': 1540, - 'thumbnail': 'http://video.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg', + '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, + }, } ] _RSS_URL = 'http://channel9.msdn.com/%s/RSS' - # Sorted by quality - _known_formats = ['MP3', 'MP4', 'Mid Quality WMV', 'Mid Quality MP4', 'High Quality WMV', 'High Quality MP4'] - - def _restore_bytes(self, formatted_size): - if not formatted_size: - return 0 - m = re.match(r'^(?P\d+(?:\.\d+)?)\s+(?P[a-zA-Z]+)', formatted_size) - if not m: - return 0 - units = m.group('units') - try: - exponent = ['B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB'].index(units.upper()) - except ValueError: - return 0 - size = float(m.group('size')) - return int(size * (1024 ** exponent)) - def _formats_from_html(self, html): FORMAT_REGEX = r''' (?x) @@ -78,16 +80,20 @@ class Channel9IE(InfoExtractor):

File\s+size

\s*(?P.*?)\s* )? # File size part may be missing ''' - # Extract known formats + quality = qualities(( + 'MP3', 'MP4', + 'Low Quality WMV', 'Low Quality MP4', + 'Mid Quality WMV', 'Mid Quality MP4', + 'High Quality WMV', 'High Quality MP4')) formats = [{ 'url': x.group('url'), 'format_id': x.group('quality'), 'format_note': x.group('note'), 'format': '%s (%s)' % (x.group('quality'), x.group('note')), - 'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate - 'preference': self._known_formats.index(x.group('quality')), + 'filesize_approx': parse_filesize(x.group('filesize')), + 'quality': quality(x.group('quality')), 'vcodec': 'none' if x.group('note') == 'Audio only' else None, - } for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats] + } for x in list(re.finditer(FORMAT_REGEX, html))] self._sort_formats(formats) @@ -158,7 +164,7 @@ class Channel9IE(InfoExtractor): def _extract_session_day(self, html): m = re.search(r'
  • \s*(?P[^<]+)\s*
    • ', html) - return m.group('day') if m is not None else None + return m.group('day').strip() if m is not None else None def _extract_session_room(self, html): m = re.search(r'
  • \s*(?P.+?)\s*
    • ', html) @@ -224,12 +230,12 @@ class Channel9IE(InfoExtractor): if contents is None: return contents - authors = self._extract_authors(html) + if len(contents) > 1: + raise ExtractorError('Got more than one entry') + result = contents[0] + result['authors'] = self._extract_authors(html) - for content in contents: - content['authors'] = authors - - return contents + return result def _extract_session(self, html, content_path): contents = self._extract_content(html, content_path) diff --git a/youtube_dl/extractor/chaturbate.py b/youtube_dl/extractor/chaturbate.py new file mode 100644 index 000000000..0b67ba67d --- /dev/null +++ b/youtube_dl/extractor/chaturbate.py @@ -0,0 +1,50 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class ChaturbateIE(InfoExtractor): + _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P[^/?#]+)' + _TESTS = [{ + 'url': 'https://www.chaturbate.com/siswet19/', + 'info_dict': { + 'id': 'siswet19', + 'ext': 'mp4', + 'title': 're:^siswet19 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'age_limit': 18, + 'is_live': True, + }, + 'params': { + 'skip_download': True, + } + }, { + 'url': 'https://en.chaturbate.com/siswet19/', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + m3u8_url = self._search_regex( + r'src=(["\'])(?Phttp.+?\.m3u8.*?)\1', webpage, + 'playlist', default=None, group='url') + + if not m3u8_url: + error = self._search_regex( + r']+class=(["\'])desc_span\1[^>]*>(?P[^<]+)', + webpage, 'error', group='error') + raise ExtractorError(error, expected=True) + + formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4') + + return { + 'id': video_id, + 'title': self._live_title(video_id), + 'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id, + 'age_limit': self._rta_search(webpage), + 'is_live': True, + 'formats': formats, + } diff --git a/youtube_dl/extractor/clubic.py b/youtube_dl/extractor/clubic.py index 14f215c5c..1dfa7c12e 100644 --- a/youtube_dl/extractor/clubic.py +++ b/youtube_dl/extractor/clubic.py @@ -12,9 +12,9 @@ from ..utils import ( class ClubicIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?clubic\.com/video/[^/]+/video.*-(?P[0-9]+)\.html' + _VALID_URL = r'http://(?:www\.)?clubic\.com/video/(?:[^/]+/)*video.*-(?P[0-9]+)\.html' - _TEST = { + _TESTS = [{ 'url': 'http://www.clubic.com/video/clubic-week/video-clubic-week-2-0-le-fbi-se-lance-dans-la-photo-d-identite-448474.html', 'md5': '1592b694ba586036efac1776b0b43cd3', 'info_dict': { @@ -24,7 +24,10 @@ class ClubicIE(InfoExtractor): 'description': 're:Gueule de bois chez Nokia. Le constructeur a indiqué cette.*', 'thumbnail': 're:^http://img\.clubic\.com/.*\.jpg$', } - } + }, { + 'url': 'http://www.clubic.com/video/video-clubic-week-2-0-apple-iphone-6s-et-plus-mais-surtout-le-pencil-469792.html', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/clyp.py b/youtube_dl/extractor/clyp.py new file mode 100644 index 000000000..57e643799 --- /dev/null +++ b/youtube_dl/extractor/clyp.py @@ -0,0 +1,57 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + float_or_none, + parse_iso8601, +) + + +class ClypIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?clyp\.it/(?P[a-z0-9]+)' + _TEST = { + 'url': 'https://clyp.it/ojz2wfah', + 'md5': '1d4961036c41247ecfdcc439c0cddcbb', + 'info_dict': { + 'id': 'ojz2wfah', + 'ext': 'mp3', + 'title': 'Krisson80 - bits wip wip', + 'description': '#Krisson80BitsWipWip #chiptune\n#wip', + 'duration': 263.21, + 'timestamp': 1443515251, + 'upload_date': '20150929', + }, + } + + def _real_extract(self, url): + audio_id = self._match_id(url) + + metadata = self._download_json( + 'https://api.clyp.it/%s' % audio_id, audio_id) + + formats = [] + for secure in ('', 'Secure'): + for ext in ('Ogg', 'Mp3'): + format_id = '%s%s' % (secure, ext) + format_url = metadata.get('%sUrl' % format_id) + if format_url: + formats.append({ + 'url': format_url, + 'format_id': format_id, + 'vcodec': 'none', + }) + self._sort_formats(formats) + + title = metadata['Title'] + description = metadata.get('Description') + duration = float_or_none(metadata.get('Duration')) + timestamp = parse_iso8601(metadata.get('DateCreated')) + + return { + 'id': audio_id, + 'title': title, + 'description': description, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + } diff --git a/youtube_dl/extractor/cmt.py b/youtube_dl/extractor/cmt.py index e96c59f71..f1311b14f 100644 --- a/youtube_dl/extractor/cmt.py +++ b/youtube_dl/extractor/cmt.py @@ -4,7 +4,7 @@ from .mtv import MTVIE class CMTIE(MTVIE): IE_NAME = 'cmt.com' - _VALID_URL = r'https?://www\.cmt\.com/videos/.+?/(?P[^/]+)\.jhtml' + _VALID_URL = r'https?://www\.cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P\d+)' _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/' _TESTS = [{ @@ -16,4 +16,7 @@ class CMTIE(MTVIE): 'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"', 'description': 'Blame It All On My Roots', }, + }, { + 'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172', + 'only_matching': True, }] diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 91ebb0ce5..3e4bd10b6 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -151,12 +151,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor): mobj = re.match(self._VALID_URL, url) if mobj.group('shortname'): - if mobj.group('shortname') in ('tds', 'thedailyshow'): - url = 'http://thedailyshow.cc.com/full-episodes/' - else: - url = 'http://thecolbertreport.cc.com/full-episodes/' - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - assert mobj is not None + return self.url_result('http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes') if mobj.group('clip'): if mobj.group('videotitle'): diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 5eeeda08d..5e263f8b5 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -10,13 +10,11 @@ import re import socket import sys import time -import xml.etree.ElementTree from ..compat import ( compat_cookiejar, compat_cookies, compat_getpass, - compat_HTTPError, compat_http_client, compat_urllib_error, compat_urllib_parse, @@ -24,6 +22,7 @@ from ..compat import ( compat_urllib_request, compat_urlparse, compat_str, + compat_etree_fromstring, ) from ..utils import ( NO_DEFAULT, @@ -39,6 +38,7 @@ from ..utils import ( RegexNotFoundError, sanitize_filename, unescapeHTML, + unified_strdate, url_basename, xpath_text, xpath_with_ns, @@ -152,6 +152,7 @@ class InfoExtractor(object): description: Full video description. uploader: Full name of the video uploader. creator: The main artist who created 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). If not explicitly set, calculated from timestamp. @@ -163,12 +164,14 @@ class InfoExtractor(object): with the "ext" entry and one of: * "data": The subtitles file contents * "url": A URL pointing to the subtitles file + "ext" will be calculated from URL if missing automatic_captions: Like 'subtitles', used by the YoutubeIE for automatically generated captions duration: Length of the video in seconds, as an integer. view_count: How many users have watched the video on the platform. like_count: Number of positive ratings of the video dislike_count: Number of negative ratings of the video + repost_count: Number of reposts of the video average_rating: Average rating give by users, the scale used depends on the webpage comment_count: Number of comments on the video comments: A list of comments, each with one or more of the following @@ -307,11 +310,11 @@ class InfoExtractor(object): @classmethod def ie_key(cls): """A string for getting the InfoExtractor with get_info_extractor""" - return cls.__name__[:-2] + return compat_str(cls.__name__[:-2]) @property def IE_NAME(self): - return type(self).__name__[:-2] + return compat_str(type(self).__name__[:-2]) def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns the response handle """ @@ -458,7 +461,7 @@ class InfoExtractor(object): return xml_string if transform_source: xml_string = transform_source(xml_string) - return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8')) + return compat_etree_fromstring(xml_string.encode('utf-8')) def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', @@ -516,6 +519,12 @@ class InfoExtractor(object): '%s. Use --username and --password or --netrc to provide account credentials.' % msg, expected=True) + @staticmethod + def raise_geo_restricted(msg='This video is not available from your location due to geo restriction'): + raise ExtractorError( + '%s. You might want to use --proxy to workaround.' % msg, + expected=True) + # Methods for following #608 @staticmethod def url_result(url, ie=None, video_id=None, video_title=None): @@ -636,8 +645,9 @@ class InfoExtractor(object): # Helper functions for extracting OpenGraph info @staticmethod def _og_regexes(prop): - content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')' - property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop) + content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))' + property_re = (r'(?:name|property)=(?:\'og:%(prop)s\'|"og:%(prop)s"|\s*og:%(prop)s\b)' + % {'prop': re.escape(prop)}) template = r']+?%s[^>]+?%s' return [ template % (property_re, content_re), @@ -731,8 +741,9 @@ class InfoExtractor(object): @staticmethod def _hidden_inputs(html): + html = re.sub(r'', '', html) hidden_inputs = {} - for input in re.findall(r']+)>', html): + for input in re.findall(r'(?i)]+)>', html): if not re.search(r'type=(["\'])(?:hidden|submit)\1', input): continue name = re.search(r'name=(["\'])(?P.+?)\1', input) @@ -746,7 +757,7 @@ class InfoExtractor(object): def _form_hidden_inputs(self, form_id, html): form = self._search_regex( - r'(?s)]+?id=(["\'])%s\1[^>]*>(?P
    .+?)
    ' % form_id, + r'(?is)]+?id=(["\'])%s\1[^>]*>(?P
    .+?)
    ' % form_id, html, '%s form' % form_id, group='form') return self._hidden_inputs(form) @@ -830,7 +841,7 @@ class InfoExtractor(object): self._request_webpage(url, video_id, 'Checking %s URL' % item) return True except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError): + if isinstance(e.cause, compat_urllib_error.URLError): self.to_screen( '%s: %s URL is invalid, skipping' % (video_id, item)) return False @@ -861,13 +872,18 @@ class InfoExtractor(object): time.sleep(timeout) def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None, - transform_source=lambda s: fix_xml_ampersands(s).strip()): + transform_source=lambda s: fix_xml_ampersands(s).strip(), + fatal=True): manifest = self._download_xml( manifest_url, video_id, 'Downloading f4m manifest', 'Unable to download f4m manifest', # Some manifests may be malformed, e.g. prosiebensat1 generated manifests # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244) - transform_source=transform_source) + transform_source=transform_source, + fatal=fatal) + + if manifest is False: + return manifest formats = [] manifest_version = '1.0' @@ -888,7 +904,10 @@ class InfoExtractor(object): # 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(manifest_url, video_id, preference, f4m_id)) + f4m_formats = self._extract_f4m_formats( + manifest_url, video_id, preference, f4m_id, fatal=fatal) + if f4m_formats: + formats.extend(f4m_formats) continue tbr = int_or_none(media_el.attrib.get('bitrate')) formats.append({ @@ -924,13 +943,15 @@ class InfoExtractor(object): if re.match(r'^https?://', u) else compat_urlparse.urljoin(m3u8_url, u)) - m3u8_doc = self._download_webpage( + res = self._download_webpage_handle( m3u8_url, video_id, note=note or 'Downloading m3u8 information', errnote=errnote or 'Failed to download m3u8 information', fatal=fatal) - if m3u8_doc is False: - return m3u8_doc + if res is False: + return res + m3u8_doc, urlh = res + m3u8_url = urlh.geturl() last_info = None last_media = None kv_rex = re.compile( @@ -1036,6 +1057,7 @@ class InfoExtractor(object): video_id = os.path.splitext(url_basename(smil_url))[0] title = None description = None + upload_date = None for meta in smil.findall(self._xpath_ns('./head/meta', namespace)): name = meta.attrib.get('name') content = meta.attrib.get('content') @@ -1045,11 +1067,22 @@ class InfoExtractor(object): title = content elif not description and name in ('description', 'abstract'): description = content + elif not upload_date and name == 'date': + upload_date = unified_strdate(content) + + thumbnails = [{ + 'id': image.get('type'), + 'url': image.get('src'), + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + } for image in smil.findall(self._xpath_ns('.//image', namespace)) if image.get('src')] return { 'id': video_id, 'title': title or video_id, 'description': description, + 'upload_date': upload_date, + 'thumbnails': thumbnails, 'formats': formats, 'subtitles': subtitles, } @@ -1076,7 +1109,7 @@ class InfoExtractor(object): if not src: continue - bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000) + 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')) @@ -1108,8 +1141,10 @@ class InfoExtractor(object): src_url = src if src.startswith('http') else compat_urlparse.urljoin(base, src) if proto == 'm3u8' or src_ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - src_url, video_id, ext or 'mp4', m3u8_id='hls')) + m3u8_formats = self._extract_m3u8_formats( + src_url, video_id, ext or 'mp4', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) continue if src_ext == 'f4m': @@ -1121,10 +1156,12 @@ class InfoExtractor(object): } f4m_url += '&' if '?' in f4m_url else '?' f4m_url += compat_urllib_parse.urlencode(f4m_params) - formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds')) + f4m_formats = self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) continue - if src_url.startswith('http'): + if src_url.startswith('http') and self._is_valid_url(src, video_id): http_count += 1 formats.append({ 'url': src_url, diff --git a/youtube_dl/extractor/condenast.py b/youtube_dl/extractor/condenast.py index 3db4db4e4..6f92ae2ed 100644 --- a/youtube_dl/extractor/condenast.py +++ b/youtube_dl/extractor/condenast.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor from ..compat import ( @@ -12,6 +11,7 @@ from ..compat import ( ) from ..utils import ( orderedSet, + remove_end, ) @@ -24,21 +24,33 @@ class CondeNastIE(InfoExtractor): # The keys are the supported sites and the values are the name to be shown # to the user and in the extractor description. _SITES = { - 'wired': 'WIRED', + 'allure': 'Allure', + 'architecturaldigest': 'Architectural Digest', + 'arstechnica': 'Ars Technica', + 'bonappetit': 'Bon Appétit', + 'brides': 'Brides', + 'cnevids': 'Condé Nast', + 'cntraveler': 'Condé Nast Traveler', + 'details': 'Details', + 'epicurious': 'Epicurious', + 'glamour': 'Glamour', + 'golfdigest': 'Golf Digest', 'gq': 'GQ', + 'newyorker': 'The New Yorker', + 'self': 'SELF', + 'teenvogue': 'Teen Vogue', + 'vanityfair': 'Vanity Fair', 'vogue': 'Vogue', - 'glamour': 'Glamour', + 'wired': 'WIRED', 'wmagazine': 'W Magazine', - 'vanityfair': 'Vanity Fair', - 'cnevids': 'Condé Nast', } - _VALID_URL = r'http://(video|www|player)\.(?P%s)\.com/(?Pwatch|series|video|embed)/(?P[^/?#]+)' % '|'.join(_SITES.keys()) + _VALID_URL = r'http://(?:video|www|player)\.(?P%s)\.com/(?Pwatch|series|video|embed(?:js)?)/(?P[^/?#]+)' % '|'.join(_SITES.keys()) IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values())) - EMBED_URL = r'(?:https?:)?//player\.(?P%s)\.com/(?Pembed)/.+?' % '|'.join(_SITES.keys()) + EMBED_URL = r'(?:https?:)?//player\.(?P%s)\.com/(?Pembed(?:js)?)/.+?' % '|'.join(_SITES.keys()) - _TEST = { + _TESTS = [{ 'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led', 'md5': '1921f713ed48aabd715691f774c451f7', 'info_dict': { @@ -47,7 +59,16 @@ class CondeNastIE(InfoExtractor): 'title': '3D Printed Speakers Lit With LED', 'description': 'Check out these beautiful 3D printed LED speakers. You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.', } - } + }, { + # JS embed + 'url': 'http://player.cnevids.com/embedjs/55f9cf8b61646d1acf00000c/5511d76261646d5566020000.js', + 'md5': 'f1a6f9cafb7083bab74a710f65d08999', + 'info_dict': { + 'id': '55f9cf8b61646d1acf00000c', + 'ext': 'mp4', + 'title': '3D printed TSA Travel Sentry keys really do open TSA locks', + } + }] def _extract_series(self, url, webpage): title = self._html_search_regex(r'
    .*?

    (.+?)

    ', @@ -86,8 +107,8 @@ class CondeNastIE(InfoExtractor): info_url = base_info_url + data info_page = self._download_webpage(info_url, video_id, 'Downloading video info') - video_info = self._search_regex(r'var video = ({.+?});', info_page, 'video info') - video_info = json.loads(video_info) + video_info = self._search_regex(r'var\s+video\s*=\s*({.+?});', info_page, 'video info') + video_info = self._parse_json(video_info, video_id) formats = [{ 'format_id': '%s-%s' % (fdata['type'].split('/')[-1], fdata['quality']), @@ -111,6 +132,13 @@ class CondeNastIE(InfoExtractor): url_type = mobj.group('type') item_id = mobj.group('id') + # Convert JS embed to regular embed + if url_type == 'embedjs': + parsed_url = compat_urlparse.urlparse(url) + url = compat_urlparse.urlunparse(parsed_url._replace( + path=remove_end(parsed_url.path, '.js').replace('/embedjs/', '/embed/'))) + url_type = 'embed' + self.to_screen('Extracting from %s with the Condé Nast extractor' % self._SITES[site]) webpage = self._download_webpage(url, item_id) diff --git a/youtube_dl/extractor/criterion.py b/youtube_dl/extractor/criterion.py index 4fb178165..dedb810a0 100644 --- a/youtube_dl/extractor/criterion.py +++ b/youtube_dl/extractor/criterion.py @@ -27,9 +27,7 @@ class CriterionIE(InfoExtractor): final_url = self._search_regex( r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url') title = self._og_search_title(webpage) - description = self._html_search_regex( - r'', - webpage, 'video description') + description = self._html_search_meta('description', webpage) thumbnail = self._search_regex( r'so.addVariable\("thumbnailURL", "(.+?)"\)\;', webpage, 'thumbnail url') diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 95952bc29..6e5999c72 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -5,12 +5,12 @@ import re import json import base64 import zlib -import xml.etree.ElementTree from hashlib import sha1 from math import pow, sqrt, floor from .common import InfoExtractor from ..compat import ( + compat_etree_fromstring, compat_urllib_parse, compat_urllib_parse_unquote, compat_urllib_request, @@ -21,6 +21,7 @@ from ..utils import ( bytes_to_intlist, intlist_to_bytes, int_or_none, + lowercase_escape, remove_end, unified_strdate, urlencode_postdata, @@ -32,6 +33,26 @@ from ..aes import ( class CrunchyrollBaseIE(InfoExtractor): + _NETRC_MACHINE = 'crunchyroll' + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + self.report_login() + login_url = 'https://www.crunchyroll.com/?a=formhandler' + data = urlencode_postdata({ + 'formname': 'RpcApiUser_Login', + 'name': username, + 'password': password, + }) + login_request = compat_urllib_request.Request(login_url, data) + login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') + self._download_webpage(login_request, None, False, 'Wrong login info') + + def _real_initialize(self): + self._login() + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None): request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request) else compat_urllib_request.Request(url_or_request)) @@ -46,10 +67,22 @@ class CrunchyrollBaseIE(InfoExtractor): return super(CrunchyrollBaseIE, self)._download_webpage( request, video_id, note, errnote, fatal, tries, timeout, encoding) + @staticmethod + def _add_skip_wall(url): + parsed_url = compat_urlparse.urlparse(url) + qs = compat_urlparse.parse_qs(parsed_url.query) + # Always force skip_wall to bypass maturity wall, namely 18+ confirmation message: + # > This content may be inappropriate for some people. + # > Are you sure you want to continue? + # since it's not disabled by default in crunchyroll account's settings. + # See https://github.com/rg3/youtube-dl/issues/7202. + qs['skip_wall'] = ['1'] + return compat_urlparse.urlunparse( + parsed_url._replace(query=compat_urllib_parse.urlencode(qs, True))) + class CrunchyrollIE(CrunchyrollBaseIE): _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P[0-9]+))(?:[/?&]|$)' - _NETRC_MACHINE = 'crunchyroll' _TESTS = [{ 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', 'info_dict': { @@ -72,7 +105,7 @@ class CrunchyrollIE(CrunchyrollBaseIE): 'id': '589804', 'ext': 'flv', 'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11', - 'description': 'md5:fe2743efedb49d279552926d0bd0cd9e', + 'description': 'md5:2fbc01f90b87e8e9137296f37b461c12', 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': 'Danny Choo Network', 'upload_date': '20120213', @@ -81,10 +114,13 @@ class CrunchyrollIE(CrunchyrollBaseIE): # rtmp 'skip_download': True, }, - }, { 'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697', 'only_matching': True, + }, { + # geo-restricted (US), 18+ maturity wall, non-premium available + 'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617', + 'only_matching': True, }] _FORMAT_IDS = { @@ -94,24 +130,6 @@ class CrunchyrollIE(CrunchyrollBaseIE): '1080': ('80', '108'), } - def _login(self): - (username, password) = self._get_login_info() - if username is None: - return - self.report_login() - login_url = 'https://www.crunchyroll.com/?a=formhandler' - data = urlencode_postdata({ - 'formname': 'RpcApiUser_Login', - 'name': username, - 'password': password, - }) - login_request = compat_urllib_request.Request(login_url, data) - login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') - self._download_webpage(login_request, None, False, 'Wrong login info') - - def _real_initialize(self): - self._login() - def _decrypt_subtitles(self, data, iv, id): data = bytes_to_intlist(base64.b64decode(data.encode('utf-8'))) iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8'))) @@ -217,7 +235,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text return output def _extract_subtitles(self, subtitle): - sub_root = xml.etree.ElementTree.fromstring(subtitle) + sub_root = compat_etree_fromstring(subtitle) return [{ 'ext': 'srt', 'data': self._convert_subtitles_to_srt(sub_root), @@ -228,7 +246,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text def _get_subtitles(self, video_id, webpage): subtitles = {} - for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): + for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage): sub_page = self._download_webpage( 'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id, video_id, note='Downloading subtitles for ' + sub_name) @@ -254,7 +272,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text else: webpage_url = 'http://www.' + mobj.group('url') - webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage') + webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage') note_m = self._html_search_regex( r'
    (.+?)
    ', webpage, 'trailer-notice', default='') @@ -270,11 +288,15 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text if 'To view this, please log in to verify you are 18 or older.' in webpage: self.raise_login_required() - video_title = self._html_search_regex(r']*>(.+?)', webpage, 'video_title', flags=re.DOTALL) + video_title = self._html_search_regex( + r'(?s)]*>((?:(?!]+itemprop=["\']title["\'][^>]*>(?:(?!', + webpage, 'video_title') video_title = re.sub(r' {2,}', ' ', video_title) - video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='') - if not video_description: - video_description = None + video_description = self._html_search_regex( + r']*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id, + webpage, 'description', default=None) + if video_description: + video_description = lowercase_escape(video_description.replace(r'\r\n', '\n')) video_upload_date = self._html_search_regex( [r'
    Availability for free users:(.+?)
    ', r'
    [^<>]+\s*(.+?\d{4})\s*
    '], webpage, 'video_upload_date', fatal=False, flags=re.DOTALL) @@ -352,7 +374,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE): IE_NAME = "crunchyroll:playlist" - _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P[\w\-]+))/?$' + _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P[\w\-]+))/?(?:\?|$)' _TESTS = [{ 'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', @@ -361,12 +383,25 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE): 'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi' }, 'playlist_count': 13, + }, { + # geo-restricted (US), 18+ maturity wall, non-premium available + 'url': 'http://www.crunchyroll.com/cosplay-complex-ova', + 'info_dict': { + 'id': 'cosplay-complex-ova', + 'title': 'Cosplay Complex OVA' + }, + 'playlist_count': 3, + 'skip': 'Georestricted', + }, { + # geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14 + 'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1', + 'only_matching': True, }] def _real_extract(self, url): show_id = self._match_id(url) - webpage = self._download_webpage(url, show_id) + webpage = self._download_webpage(self._add_skip_wall(url), show_id) title = self._html_search_regex( r'(?s)]*>\s*(.*?)', webpage, 'title') diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 2d90b2224..bc7823931 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -96,6 +96,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'uploader': 'HotWaves1012', 'age_limit': 18, } + }, + # geo-restricted, player v5 + { + 'url': 'http://www.dailymotion.com/video/xhza0o', + 'only_matching': True, } ] @@ -119,11 +124,14 @@ class DailymotionIE(DailymotionBaseInfoExtractor): webpage, 'comment count', fatal=False)) player_v5 = self._search_regex( - r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);', + [r'buildPlayer\(({.+?})\);', r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);'], webpage, 'player v5', default=None) if player_v5: player = self._parse_json(player_v5, video_id) metadata = player['metadata'] + + self._check_error(metadata) + formats = [] for quality, media_list in metadata['qualities'].items(): for media in media_list: @@ -133,9 +141,17 @@ class DailymotionIE(DailymotionBaseInfoExtractor): type_ = media.get('type') if type_ == 'application/vnd.lumberjack.manifest': continue - if type_ == 'application/x-mpegURL' or determine_ext(media_url) == 'm3u8': - formats.extend(self._extract_m3u8_formats( - media_url, video_id, 'mp4', m3u8_id='hls')) + ext = determine_ext(media_url) + if type_ == 'application/x-mpegURL' or ext == 'm3u8': + m3u8_formats = self._extract_m3u8_formats( + media_url, video_id, 'mp4', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + elif type_ == 'application/f4m' or ext == 'f4m': + f4m_formats = self._extract_f4m_formats( + media_url, video_id, preference=-1, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) else: f = { 'url': media_url, @@ -201,9 +217,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'video info', flags=re.MULTILINE), video_id) - if info.get('error') is not None: - msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title'] - raise ExtractorError(msg, expected=True) + self._check_error(info) formats = [] for (key, format_id) in self._FORMATS: @@ -246,6 +260,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'duration': info['duration'] } + def _check_error(self, info): + if info.get('error') is not None: + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, info['error']['title']), expected=True) + def _get_subtitles(self, video_id, webpage): try: sub_list = self._download_webpage( diff --git a/youtube_dl/extractor/democracynow.py b/youtube_dl/extractor/democracynow.py new file mode 100644 index 000000000..6cd395e11 --- /dev/null +++ b/youtube_dl/extractor/democracynow.py @@ -0,0 +1,88 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import os.path + +from .common import InfoExtractor +from ..compat import compat_urlparse +from ..utils import ( + url_basename, + remove_start, +) + + +class DemocracynowIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?democracynow.org/(?P[^\?]*)' + IE_NAME = 'democracynow' + _TESTS = [{ + 'url': 'http://www.democracynow.org/shows/2015/7/3', + 'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d', + 'info_dict': { + 'id': '2015-0703-001', + 'ext': 'mp4', + 'title': 'July 03, 2015 - Democracy Now!', + 'description': 'A daily independent global news hour with Amy Goodman & Juan González "What to the Slave is 4th of July?": James Earl Jones Reads Frederick Douglass\u2019 Historic Speech : "This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag : "We Shall Overcome": Remembering Folk Icon, Activist Pete Seeger in His Own Words & Songs', + }, + }, { + 'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree', + 'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d', + 'info_dict': { + 'id': '2015-0703-001', + 'ext': 'mp4', + 'title': '"This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag', + 'description': 'md5:4d2bc4f0d29f5553c2210a4bc7761a21', + }, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + description = self._og_search_description(webpage) + + json_data = self._parse_json(self._search_regex( + r']+type="text/json"[^>]*>\s*({[^>]+})', webpage, 'json'), + display_id) + video_id = None + formats = [] + + default_lang = 'en' + + subtitles = {} + + def add_subtitle_item(lang, info_dict): + if lang not in subtitles: + subtitles[lang] = [] + subtitles[lang].append(info_dict) + + # chapter_file are not subtitles + if 'caption_file' in json_data: + add_subtitle_item(default_lang, { + 'url': compat_urlparse.urljoin(url, json_data['caption_file']), + }) + + for subtitle_item in json_data.get('captions', []): + lang = subtitle_item.get('language', '').lower() or default_lang + add_subtitle_item(lang, { + 'url': compat_urlparse.urljoin(url, subtitle_item['url']), + }) + + for key in ('file', 'audio', 'video'): + media_url = json_data.get(key, '') + if not media_url: + continue + media_url = re.sub(r'\?.*', '', compat_urlparse.urljoin(url, media_url)) + video_id = video_id or remove_start(os.path.splitext(url_basename(media_url))[0], 'dn') + formats.append({ + 'url': media_url, + }) + + self._sort_formats(formats) + + return { + 'id': video_id or display_id, + 'title': json_data['title'], + 'description': description, + 'subtitles': subtitles, + 'formats': formats, + } diff --git a/youtube_dl/extractor/divxstage.py b/youtube_dl/extractor/divxstage.py deleted file mode 100644 index b88379e06..000000000 --- a/youtube_dl/extractor/divxstage.py +++ /dev/null @@ -1,27 +0,0 @@ -from __future__ import unicode_literals - -from .novamov import NovaMovIE - - -class DivxStageIE(NovaMovIE): - IE_NAME = 'divxstage' - IE_DESC = 'DivxStage' - - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag|to)'} - - _HOST = 'www.divxstage.eu' - - _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' - _TITLE_REGEX = r'
    \s*([^<]+)' - _DESCRIPTION_REGEX = r'
    \s*[^<]+\s*

    ([^<]+)

    ' - - _TEST = { - 'url': 'http://www.divxstage.eu/video/57f238e2e5e01', - 'md5': '63969f6eb26533a1968c4d325be63e72', - 'info_dict': { - 'id': '57f238e2e5e01', - 'ext': 'flv', - 'title': 'youtubedl test video', - 'description': 'This is a test video for youtubedl.', - } - } diff --git a/youtube_dl/extractor/eagleplatform.py b/youtube_dl/extractor/eagleplatform.py index a1ee51568..7bbf617d4 100644 --- a/youtube_dl/extractor/eagleplatform.py +++ b/youtube_dl/extractor/eagleplatform.py @@ -21,7 +21,7 @@ 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': '0b7994faa2bd5c0f69a3db6db28d078d', + 'md5': '70f5187fb620f2c1d503b3b22fd4efe3', 'info_dict': { 'id': '227304', 'ext': 'mp4', @@ -36,7 +36,7 @@ class EaglePlatformIE(InfoExtractor): # http://muz-tv.ru/play/7129/ # http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true 'url': 'eagleplatform:media.clipyou.ru:12820', - 'md5': '6c2ebeab03b739597ce8d86339d5a905', + 'md5': '90b26344ba442c8e44aa4cf8f301164a', 'info_dict': { 'id': '12820', 'ext': 'mp4', @@ -48,7 +48,8 @@ class EaglePlatformIE(InfoExtractor): 'skip': 'Georestricted', }] - def _handle_error(self, response): + @staticmethod + def _handle_error(response): status = int_or_none(response.get('status', 200)) if status != 200: raise ExtractorError(' '.join(response['errors']), expected=True) @@ -58,6 +59,9 @@ class EaglePlatformIE(InfoExtractor): self._handle_error(response) return response + def _get_video_url(self, url_or_request, video_id, note='Downloading JSON metadata'): + return self._download_json(url_or_request, video_id, note)['data'][0] + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id') @@ -69,7 +73,7 @@ class EaglePlatformIE(InfoExtractor): title = media['title'] description = media.get('description') - thumbnail = media.get('snapshot') + thumbnail = self._proto_relative_url(media.get('snapshot'), 'http:') duration = int_or_none(media.get('duration')) view_count = int_or_none(media.get('views')) @@ -78,13 +82,20 @@ class EaglePlatformIE(InfoExtractor): if age_restriction: age_limit = 0 if age_restriction == 'allow_all' else 18 - m3u8_data = self._download_json( - self._proto_relative_url(media['sources']['secure_m3u8']['auto'], 'http:'), - video_id, 'Downloading m3u8 JSON') + secure_m3u8 = self._proto_relative_url(media['sources']['secure_m3u8']['auto'], 'http:') + m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON') formats = self._extract_m3u8_formats( - m3u8_data['data'][0], video_id, - 'mp4', entry_protocol='m3u8_native') + m3u8_url, video_id, + 'mp4', entry_protocol='m3u8_native', m3u8_id='hls') + + mp4_url = self._get_video_url( + # Secure mp4 URL is constructed according to Player.prototype.mp4 from + # http://lentaru.media.eagleplatform.com/player/player.js + re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4', secure_m3u8), + video_id, 'Downloading mp4 JSON') + formats.append({'url': mp4_url, 'format_id': 'mp4'}) + self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/eitb.py b/youtube_dl/extractor/eitb.py index 2cba82532..357a2196c 100644 --- a/youtube_dl/extractor/eitb.py +++ b/youtube_dl/extractor/eitb.py @@ -1,39 +1,92 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from .brightcove import BrightcoveIE -from ..utils import ExtractorError +from ..compat import compat_urllib_request +from ..utils import ( + float_or_none, + int_or_none, + parse_iso8601, +) class EitbIE(InfoExtractor): IE_NAME = 'eitb.tv' - _VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P\d+)/(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?eitb\.tv/(?:eu/bideoa|es/video)/[^/]+/\d+/(?P\d+)' _TEST = { - 'add_ie': ['Brightcove'], - 'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/', + 'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/4104995148001/4090227752001/lasa-y-zabala-30-anos/', 'md5': 'edf4436247185adee3ea18ce64c47998', 'info_dict': { - 'id': '2743577154001', + 'id': '4090227752001', 'ext': 'mp4', 'title': '60 minutos (Lasa y Zabala, 30 años)', - # All videos from eitb has this description in the brightcove info - 'description': '.', - 'uploader': 'Euskal Telebista', + 'description': 'Programa de reportajes de actualidad.', + 'duration': 3996.76, + 'timestamp': 1381789200, + 'upload_date': '20131014', + 'tags': list, }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - chapter_id = mobj.group('chapter_id') - webpage = self._download_webpage(url, chapter_id) - bc_url = BrightcoveIE._extract_brightcove_url(webpage) - if bc_url is None: - raise ExtractorError('Could not extract the Brightcove url') - # The BrightcoveExperience object doesn't contain the video id, we set - # it manually - bc_url += '&%40videoPlayer={0}'.format(chapter_id) - return self.url_result(bc_url, BrightcoveIE.ie_key()) + video_id = self._match_id(url) + + video = self._download_json( + 'http://mam.eitb.eus/mam/REST/ServiceMultiweb/Video/MULTIWEBTV/%s/' % video_id, + video_id, 'Downloading video JSON') + + media = video['web_media'][0] + + formats = [] + for rendition in media['RENDITIONS']: + video_url = rendition.get('PMD_URL') + if not video_url: + continue + tbr = float_or_none(rendition.get('ENCODING_RATE'), 1000) + format_id = 'http' + if tbr: + format_id += '-%d' % int(tbr) + formats.append({ + 'url': rendition['PMD_URL'], + 'format_id': format_id, + 'width': int_or_none(rendition.get('FRAME_WIDTH')), + 'height': int_or_none(rendition.get('FRAME_HEIGHT')), + 'tbr': tbr, + }) + + hls_url = media.get('HLS_SURL') + if hls_url: + request = compat_urllib_request.Request( + 'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/', + headers={'Referer': url}) + token_data = self._download_json( + request, video_id, 'Downloading auth token', fatal=False) + if token_data: + token = token_data.get('token') + if token: + m3u8_formats = self._extract_m3u8_formats( + '%s?hdnts=%s' % (hls_url, token), video_id, m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + + hds_url = media.get('HDS_SURL') + if hds_url: + f4m_formats = self._extract_f4m_formats( + '%s?hdcore=3.7.0' % hds_url.replace('euskalsvod', 'euskalvod'), + video_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': media.get('NAME_ES') or media.get('name') or media['NAME_EU'], + 'description': media.get('SHORT_DESC_ES') or video.get('desc_group') or media.get('SHORT_DESC_EU'), + 'thumbnail': media.get('STILL_URL') or media.get('THUMBNAIL_URL'), + 'duration': float_or_none(media.get('LENGTH'), 1000), + 'timestamp': parse_iso8601(media.get('BROADCST_DATE'), ' '), + 'tags': media.get('TAGS'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/engadget.py b/youtube_dl/extractor/engadget.py index 4ea37ebd9..e4180701d 100644 --- a/youtube_dl/extractor/engadget.py +++ b/youtube_dl/extractor/engadget.py @@ -10,7 +10,7 @@ from ..utils import ( class EngadgetIE(InfoExtractor): _VALID_URL = r'''(?x)https?://www.engadget.com/ - (?:video/5min/(?P\d+)| + (?:video(?:/5min)?/(?P\d+)| [\d/]+/.*?) ''' diff --git a/youtube_dl/extractor/europa.py b/youtube_dl/extractor/europa.py new file mode 100644 index 000000000..adc43919e --- /dev/null +++ b/youtube_dl/extractor/europa.py @@ -0,0 +1,93 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_urlparse +from ..utils import ( + int_or_none, + orderedSet, + parse_duration, + qualities, + unified_strdate, + xpath_text +) + + +class EuropaIE(InfoExtractor): + _VALID_URL = r'https?://ec\.europa\.eu/avservices/(?:video/player|audio/audioDetails)\.cfm\?.*?\bref=(?P[A-Za-z0-9-]+)' + _TESTS = [{ + 'url': 'http://ec.europa.eu/avservices/video/player.cfm?ref=I107758', + 'md5': '574f080699ddd1e19a675b0ddf010371', + 'info_dict': { + 'id': 'I107758', + 'ext': 'mp4', + 'title': 'TRADE - Wikileaks on TTIP', + 'description': 'NEW LIVE EC Midday press briefing of 11/08/2015', + 'thumbnail': 're:^https?://.*\.jpg$', + 'upload_date': '20150811', + 'duration': 34, + 'view_count': int, + 'formats': 'mincount:3', + } + }, { + 'url': 'http://ec.europa.eu/avservices/video/player.cfm?sitelang=en&ref=I107786', + 'only_matching': True, + }, { + 'url': 'http://ec.europa.eu/avservices/audio/audioDetails.cfm?ref=I-109295&sitelang=en', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + playlist = self._download_xml( + 'http://ec.europa.eu/avservices/video/player/playlist.cfm?ID=%s' % video_id, video_id) + + def get_item(type_, preference): + items = {} + for item in playlist.findall('./info/%s/item' % type_): + lang, label = xpath_text(item, 'lg', default=None), xpath_text(item, 'label', default=None) + if lang and label: + items[lang] = label.strip() + for p in preference: + if items.get(p): + return items[p] + + query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + preferred_lang = query.get('sitelang', ('en', ))[0] + + preferred_langs = orderedSet((preferred_lang, 'en', 'int')) + + title = get_item('title', preferred_langs) or video_id + description = get_item('description', preferred_langs) + thumbnmail = xpath_text(playlist, './info/thumburl', 'thumbnail') + upload_date = unified_strdate(xpath_text(playlist, './info/date', 'upload date')) + duration = parse_duration(xpath_text(playlist, './info/duration', 'duration')) + view_count = int_or_none(xpath_text(playlist, './info/views', 'views')) + + language_preference = qualities(preferred_langs[::-1]) + + formats = [] + for file_ in playlist.findall('./files/file'): + video_url = xpath_text(file_, './url') + if not video_url: + continue + lang = xpath_text(file_, './lg') + formats.append({ + 'url': video_url, + 'format_id': lang, + 'format_note': xpath_text(file_, './lglabel'), + 'language_preference': language_preference(lang) + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnmail, + 'upload_date': upload_date, + 'duration': duration, + 'view_count': view_count, + 'formats': formats + } diff --git a/youtube_dl/extractor/expotv.py b/youtube_dl/extractor/expotv.py index a38b773e8..1585a03bb 100644 --- a/youtube_dl/extractor/expotv.py +++ b/youtube_dl/extractor/expotv.py @@ -33,20 +33,27 @@ class ExpoTVIE(InfoExtractor): webpage = self._download_webpage(url, video_id) player_key = self._search_regex( r'extremetube\.com/.*?video/.+?(?P[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P[^/#?&]+)' _TESTS = [{ 'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', 'md5': '344d0c6d50e2f16b06e49ca011d8ac69', 'info_dict': { - 'id': '652431', + 'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431', 'ext': 'mp4', 'title': 'Music Video 14 british euro brit european cumshots swallow', 'uploader': 'unknown', @@ -29,12 +26,16 @@ class ExtremeTubeIE(InfoExtractor): }, { 'url': 'http://www.extremetube.com/gay/video/abcde-1234', 'only_matching': True, + }, { + 'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick', + 'only_matching': True, + }, { + 'url': 'http://www.extremetube.com/video/652431', + 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - url = 'http://www.' + mobj.group('url') + video_id = self._match_id(url) req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1') @@ -49,20 +50,36 @@ class ExtremeTubeIE(InfoExtractor): r'Views:\s*\s*([\d,\.]+)', webpage, 'view count', fatal=False)) - flash_vars = compat_parse_qs(self._search_regex( - r']+?name="flashvars"[^>]+?value="([^"]+)"', webpage, 'flash vars')) + flash_vars = self._parse_json( + self._search_regex( + r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'), + video_id) formats = [] - quality = qualities(['180p', '240p', '360p', '480p', '720p', '1080p']) - for k, vals in flash_vars.items(): - m = re.match(r'quality_(?P[0-9]+p)$', k) - if m is not None: - formats.append({ - 'format_id': m.group('quality'), - 'quality': quality(m.group('quality')), - 'url': vals[0], + for quality_key, video_url in flash_vars.items(): + height = int_or_none(self._search_regex( + r'quality_(\d+)[pP]$', quality_key, 'height', default=None)) + if not height: + continue + f = { + 'url': video_url, + } + mobj = re.search( + r'/(?P\d{3,4})[pP]_(?P\d+)[kK]_\d+', video_url) + if mobj: + height = int(mobj.group('height')) + bitrate = int(mobj.group('bitrate')) + f.update({ + 'format_id': '%dp-%dk' % (height, bitrate), + 'height': height, + 'tbr': bitrate, }) - + else: + f.update({ + 'format_id': '%dp' % height, + 'height': height, + }) + formats.append(f) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 178a7ca4c..f53c51615 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -14,7 +14,6 @@ from ..compat import ( ) from ..utils import ( ExtractorError, - int_or_none, limit_length, urlencode_postdata, get_element_by_id, @@ -142,16 +141,20 @@ class FacebookIE(InfoExtractor): data = dict(json.loads(m.group(1))) params_raw = compat_urllib_parse_unquote(data['params']) params = json.loads(params_raw) - video_data = params['video_data'][0] formats = [] - for quality in ['sd', 'hd']: - src = video_data.get('%s_src' % quality) - if src is not None: - formats.append({ - 'format_id': quality, - 'url': src, - }) + for format_id, f in params['video_data'].items(): + if not f or not isinstance(f, list): + continue + for quality in ('sd', 'hd'): + for src_type in ('src', 'src_no_ratelimit'): + src = f[0].get('%s_%s' % (quality, src_type)) + if src: + formats.append({ + 'format_id': '%s_%s_%s' % (format_id, quality, src_type), + 'url': src, + 'preference': -10 if format_id == 'progressive' else 0, + }) if not formats: raise ExtractorError('Cannot find video formats') @@ -171,7 +174,5 @@ class FacebookIE(InfoExtractor): 'id': video_id, 'title': video_title, 'formats': formats, - 'duration': int_or_none(video_data.get('video_duration')), - 'thumbnail': video_data.get('thumbnail_src'), 'uploader': uploader, } diff --git a/youtube_dl/extractor/fczenit.py b/youtube_dl/extractor/fczenit.py new file mode 100644 index 000000000..f1f150ef2 --- /dev/null +++ b/youtube_dl/extractor/fczenit.py @@ -0,0 +1,41 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class FczenitIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/gl(?P[0-9]+)' + _TEST = { + 'url': 'http://fc-zenit.ru/video/gl6785/', + 'md5': '458bacc24549173fe5a5aa29174a5606', + 'info_dict': { + 'id': '6785', + 'ext': 'mp4', + 'title': '«Зенит-ТВ»: как Олег Шатов играл против «Урала»', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + video_title = self._html_search_regex(r'
    ([^<]+)', webpage, 'title') + + bitrates_raw = self._html_search_regex(r'bitrates:.*\n(.*)\]', webpage, 'video URL') + bitrates = re.findall(r'url:.?\'(.+?)\'.*?bitrate:.?([0-9]{3}?)', bitrates_raw) + + formats = [{ + 'url': furl, + 'tbr': tbr, + } for furl, tbr in bitrates] + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video_title, + 'formats': formats, + } diff --git a/youtube_dl/extractor/fivemin.py b/youtube_dl/extractor/fivemin.py index 157094e8c..2955965d9 100644 --- a/youtube_dl/extractor/fivemin.py +++ b/youtube_dl/extractor/fivemin.py @@ -2,11 +2,15 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..compat import ( - compat_str, compat_urllib_parse, + compat_parse_qs, + compat_urllib_parse_urlparse, + compat_urlparse, ) from ..utils import ( ExtractorError, + parse_duration, + replace_extension, ) @@ -28,6 +32,7 @@ class FiveMinIE(InfoExtractor): 'id': '518013791', 'ext': 'mp4', 'title': 'iPad Mini with Retina Display Review', + 'duration': 177, }, }, { @@ -38,9 +43,52 @@ class FiveMinIE(InfoExtractor): 'id': '518086247', 'ext': 'mp4', 'title': 'How to Make a Next-Level Fruit Salad', + 'duration': 184, }, }, ] + _ERRORS = { + 'ErrorVideoNotExist': 'We\'re sorry, but the video you are trying to watch does not exist.', + 'ErrorVideoNoLongerAvailable': 'We\'re sorry, but the video you are trying to watch is no longer available.', + 'ErrorVideoRejected': 'We\'re sorry, but the video you are trying to watch has been removed.', + 'ErrorVideoUserNotGeo': 'We\'re sorry, but the video you are trying to watch cannot be viewed from your current location.', + 'ErrorVideoLibraryRestriction': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.', + 'ErrorExposurePermission': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.', + } + _QUALITIES = { + 1: { + 'width': 640, + 'height': 360, + }, + 2: { + 'width': 854, + 'height': 480, + }, + 4: { + 'width': 1280, + 'height': 720, + }, + 8: { + 'width': 1920, + 'height': 1080, + }, + 16: { + 'width': 640, + 'height': 360, + }, + 32: { + 'width': 854, + 'height': 480, + }, + 64: { + 'width': 1280, + 'height': 720, + }, + 128: { + 'width': 640, + 'height': 360, + }, + } def _real_extract(self, url): video_id = self._match_id(url) @@ -59,26 +107,36 @@ class FiveMinIE(InfoExtractor): 'https://syn.5min.com/handlers/SenseHandler.ashx?' + query, video_id) if not response['success']: - err_msg = response['errorMessage'] - if err_msg == 'ErrorVideoUserNotGeo': - msg = 'Video not available from your location' - else: - msg = 'Aol said: %s' % err_msg - raise ExtractorError(msg, expected=True, video_id=video_id) + raise ExtractorError( + '%s said: %s' % ( + self.IE_NAME, + self._ERRORS.get(response['errorMessage'], response['errorMessage'])), + expected=True) info = response['binding'][0] - second_id = compat_str(int(video_id[:-2]) + 1) formats = [] - for quality, height in [(1, 320), (2, 480), (4, 720), (8, 1080)]: - if any(r['ID'] == quality for r in info['Renditions']): + parsed_video_url = compat_urllib_parse_urlparse(compat_parse_qs( + compat_urllib_parse_urlparse(info['EmbededURL']).query)['videoUrl'][0]) + for rendition in info['Renditions']: + if rendition['RenditionType'] == 'm3u8': + formats.extend(self._extract_m3u8_formats(rendition['Url'], video_id, m3u8_id='hls')) + elif rendition['RenditionType'] == 'aac': + continue + else: + rendition_url = compat_urlparse.urlunparse(parsed_video_url._replace(path=replace_extension(parsed_video_url.path.replace('//', '/%s/' % rendition['ID']), rendition['RenditionType']))) + quality = self._QUALITIES.get(rendition['ID'], {}) formats.append({ - 'format_id': compat_str(quality), - 'url': 'http://avideos.5min.com/%s/%s/%s_%s.mp4' % (second_id[-3:], second_id, video_id, quality), - 'height': height, + 'format_id': '%s-%d' % (rendition['RenditionType'], rendition['ID']), + 'url': rendition_url, + 'width': quality.get('width'), + 'height': quality.get('height'), }) + self._sort_formats(formats) return { 'id': video_id, 'title': info['Title'], + 'thumbnail': info.get('ThumbURL'), + 'duration': parse_duration(info.get('Duration')), 'formats': formats, } diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py index 190d9f9ad..40ea27895 100644 --- a/youtube_dl/extractor/fktv.py +++ b/youtube_dl/extractor/fktv.py @@ -1,13 +1,12 @@ from __future__ import unicode_literals import re -import random -import json from .common import InfoExtractor from ..utils import ( - get_element_by_id, clean_html, + determine_ext, + ExtractorError, ) @@ -17,66 +16,40 @@ class FKTVIE(InfoExtractor): _TEST = { 'url': 'http://fernsehkritik.tv/folge-1', + 'md5': '21f0b0c99bce7d5b524eb1b17b1c6d79', 'info_dict': { - 'id': '00011', - 'ext': 'flv', + 'id': '1', + 'ext': 'mp4', 'title': 'Folge 1 vom 10. April 2007', - 'description': 'md5:fb4818139c7cfe6907d4b83412a6864f', + 'thumbnail': 're:^https?://.*\.jpg$', }, } def _real_extract(self, url): - episode = int(self._match_id(url)) - - video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%s.jpg' % episode - start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/Start' % episode, - episode) - playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage, - 'playlist', flags=re.DOTALL) - files = json.loads(re.sub('{[^{}]*?}', '{}', playlist)) - - videos = [] - for i, _ in enumerate(files, 1): - video_id = '%04d%d' % (episode, i) - video_url = 'http://fernsehkritik.tv/js/directme.php?file=%s%s.flv' % (episode, '' if i == 1 else '-%d' % i) - videos.append({ - 'ext': 'flv', - 'id': video_id, - 'url': video_url, - 'title': clean_html(get_element_by_id('eptitle', start_webpage)), - 'description': clean_html(get_element_by_id('contentlist', start_webpage)), - 'thumbnail': video_thumbnail - }) - return { - '_type': 'multi_video', - 'entries': videos, - 'id': 'folge-%s' % episode, - } - - -class FKTVPosteckeIE(InfoExtractor): - IE_NAME = 'fernsehkritik.tv:postecke' - _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P[0-9]+)(&|$)' - _TEST = { - 'url': 'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120', - 'md5': '262f0adbac80317412f7e57b4808e5c4', - 'info_dict': { - 'id': '0120', - 'ext': 'flv', - 'title': 'Postecke 120', - } - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - episode = int(mobj.group('ep')) - - server = random.randint(2, 4) - video_id = '%04d' % episode - video_url = 'http://dl%d.fernsehkritik.tv/postecke/postecke%d.flv' % (server, episode) - video_title = 'Postecke %d' % episode + episode = self._match_id(url) + + webpage = self._download_webpage( + 'http://fernsehkritik.tv/folge-%s/play' % episode, episode) + title = clean_html(self._html_search_regex( + '

    ([^<]+)

    ', webpage, 'title')) + matches = re.search( + r'(?s)])+(?:poster="([^"]+)")?[^>]*>(.*)', + webpage) + if matches is None: + raise ExtractorError('Unable to extract the video') + + poster, sources = matches.groups() + if poster is None: + self.report_warning('unable to extract thumbnail') + + urls = re.findall(r']+src="([^"]+)"', sources) + formats = [{ + 'url': furl, + 'format_id': determine_ext(furl), + } for furl in urls] return { - 'id': video_id, - 'url': video_url, - 'title': video_title, + 'id': episode, + 'title': title, + 'formats': formats, + 'thumbnail': poster, } diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py index 3bb4f6239..fb6d108c0 100644 --- a/youtube_dl/extractor/fourtube.py +++ b/youtube_dl/extractor/fourtube.py @@ -46,10 +46,10 @@ class FourTubeIE(InfoExtractor): thumbnail = self._html_search_meta('thumbnailUrl', webpage) uploader_id = self._html_search_regex( r'', - webpage, 'uploader id') + webpage, 'uploader id', fatal=False) uploader = self._html_search_regex( r'', - webpage, 'uploader') + webpage, 'uploader', fatal=False) categories_html = self._search_regex( r'(?s)>\s*Categories / Tags\s*.*?
      (.*?)
    ', @@ -68,13 +68,24 @@ class FourTubeIE(InfoExtractor): webpage, 'like count', fatal=False)) duration = parse_duration(self._html_search_meta('duration', webpage)) - params_js = self._search_regex( - r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)', - webpage, 'initialization parameters' - ) - params = self._parse_json('[%s]' % params_js, video_id) - media_id = params[0] - sources = ['%s' % p for p in params[2]] + media_id = self._search_regex( + r']+data-id=(["\'])(?P\d+)\1[^>]+data-quality=', webpage, + 'media id', default=None, group='id') + sources = [ + quality + for _, quality in re.findall(r']+data-quality=(["\'])(.+?)\1', webpage)] + if not (media_id and sources): + player_js = self._download_webpage( + self._search_regex( + r']id=(["\'])playerembed\1[^>]+src=(["\'])(?P.+?)\2', + webpage, 'player JS', group='url'), + video_id, 'Downloading player JS') + params_js = self._search_regex( + r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)', + player_js, 'initialization parameters') + params = self._parse_json('[%s]' % params_js, video_id) + media_id = params[0] + sources = ['%s' % p for p in params[2]] token_url = 'http://tkn.4tube.com/{0}/desktop/{1}'.format( media_id, '+'.join(sources)) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 129984a5f..8e60cf60f 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -83,6 +83,14 @@ class FranceTVBaseInfoExtractor(InfoExtractor): if subtitle: title += ' - %s' % subtitle + subtitles = {} + subtitles_list = [{ + 'url': subformat['url'], + 'ext': subformat.get('format'), + } for subformat in info.get('subtitles', []) if subformat.get('url')] + if subtitles_list: + subtitles['fr'] = subtitles_list + return { 'id': video_id, 'title': title, @@ -91,20 +99,27 @@ class FranceTVBaseInfoExtractor(InfoExtractor): 'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']), 'timestamp': int_or_none(info['diffusion']['timestamp']), 'formats': formats, + 'subtitles': subtitles, } class PluzzIE(FranceTVBaseInfoExtractor): IE_NAME = 'pluzz.francetv.fr' - _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html' + _VALID_URL = r'https?://(?:m\.)?pluzz\.francetv\.fr/videos/(?P.+?)\.html' # Can't use tests, videos expire in 7 days def _real_extract(self, url): - title = re.match(self._VALID_URL, url).group(1) - webpage = self._download_webpage(url, title) - video_id = self._search_regex( - r'data-diffusion="(\d+)"', webpage, 'ID') + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._html_search_meta( + 'id_video', webpage, 'video id', default=None) + if not video_id: + video_id = self._search_regex( + r'data-diffusion=["\'](\d+)', webpage, 'video id') + return self._extract_video(video_id, 'Pluzz') @@ -120,6 +135,9 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): 'title': 'Soir 3', 'upload_date': '20130826', 'timestamp': 1377548400, + 'subtitles': { + 'fr': 'mincount:2', + }, }, }, { 'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html', diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index f5f13689c..7f21d7410 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -45,11 +45,20 @@ class FunnyOrDieIE(InfoExtractor): links.sort(key=lambda link: 1 if link[1] == 'mp4' else 0) - bitrates = self._html_search_regex(r']+src=(["\'])(?P.+?/master\.m3u8)\1', + webpage, 'm3u8 url', default=None, group='url') formats = [] + + m3u8_formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + + bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)[,/]', m3u8_url)] + bitrates.sort() + for bitrate in bitrates: for link in links: formats.append({ diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 7a3a7f66b..34d930a2d 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -4,10 +4,12 @@ from __future__ import unicode_literals import os import re +import sys from .common import InfoExtractor from .youtube import YoutubeIE from ..compat import ( + compat_etree_fromstring, compat_urllib_parse_unquote, compat_urllib_request, compat_urlparse, @@ -20,7 +22,6 @@ from ..utils import ( HEADRequest, is_html, orderedSet, - parse_xml, smuggle_url, unescapeHTML, unified_strdate, @@ -52,6 +53,7 @@ from .dailymotion import DailymotionCloudIE from .onionstudios import OnionStudiosIE from .snagfilms import SnagFilmsEmbedIE from .screenwavemedia import ScreenwaveMediaIE +from .mtv import MTVServicesEmbeddedIE class GenericIE(InfoExtractor): @@ -142,6 +144,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'title': 'Automatics, robotics and biocybernetics', 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482', + 'upload_date': '20130627', 'formats': 'mincount:16', 'subtitles': 'mincount:1', }, @@ -233,6 +236,22 @@ class GenericIE(InfoExtractor): 'skip_download': False, } }, + { + # redirect in Refresh HTTP header + 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1', + 'info_dict': { + 'id': 'pO8h3EaFRdo', + 'ext': 'mp4', + 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set', + 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5', + 'upload_date': '20150917', + 'uploader_id': 'brtvofficial', + 'uploader': 'Boiler Room', + }, + 'params': { + 'skip_download': False, + }, + }, { 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html', 'md5': '85b90ccc9d73b4acd9138d3af4c27f89', @@ -1233,7 +1252,7 @@ class GenericIE(InfoExtractor): # Is it an RSS feed, a SMIL file or a XSPF playlist? try: - doc = parse_xml(webpage) + doc = compat_etree_fromstring(webpage.encode('utf-8')) if doc.tag == 'rss': return self._extract_rss(url, video_id, doc) elif re.match(r'^(?:{[^}]+})?smil$', doc.tag): @@ -1613,12 +1632,9 @@ class GenericIE(InfoExtractor): return self.url_result(url, ie='Vulture') # Look for embedded mtvservices player - mobj = re.search( - r'', webpage): + url = self._search_regex( + r'src=(["\'])(?P.+?partnerplayer.+?)\1', iframe, + 'player URL', default=None, group='url') + if url: + break + mobj = re.match(self._VALID_URL, url) player_id = mobj.group('player_id') @@ -213,13 +276,11 @@ class PBSIE(InfoExtractor): 'Downloading %s video url info' % encoding_name) if redirect_info['status'] == 'error': - if redirect_info['http_code'] == 403: - message = ( - 'The video is not available in your region due to ' - 'right restrictions') - else: - message = redirect_info['message'] - raise ExtractorError(message, expected=True) + raise ExtractorError( + '%s said: %s' % ( + self.IE_NAME, + self._ERRORS.get(redirect_info['http_code'], redirect_info['message'])), + expected=True) format_url = redirect_info.get('url') if not format_url: diff --git a/youtube_dl/extractor/periscope.py b/youtube_dl/extractor/periscope.py index 8ad936758..887c8020d 100644 --- a/youtube_dl/extractor/periscope.py +++ b/youtube_dl/extractor/periscope.py @@ -12,7 +12,8 @@ from ..utils import parse_iso8601 class PeriscopeIE(InfoExtractor): IE_DESC = 'Periscope' _VALID_URL = r'https?://(?:www\.)?periscope\.tv/w/(?P[^/?#]+)' - _TEST = { + # Alive example URLs can be found here http://onperiscope.com/ + _TESTS = [{ 'url': 'https://www.periscope.tv/w/aJUQnjY3MjA3ODF8NTYxMDIyMDl2zCg2pECBgwTqRpQuQD352EMPTKQjT4uqlM3cgWFA-g==', 'md5': '65b57957972e503fcbbaeed8f4fa04ca', 'info_dict': { @@ -25,11 +26,15 @@ class PeriscopeIE(InfoExtractor): 'uploader_id': '1465763', }, 'skip': 'Expires in 24 hours', - } + }, { + 'url': 'https://www.periscope.tv/w/1ZkKzPbMVggJv', + 'only_matching': True, + }] - def _call_api(self, method, token): + def _call_api(self, method, value): + attribute = 'token' if len(value) > 13 else 'broadcast_id' return self._download_json( - 'https://api.periscope.tv/api/v2/%s?token=%s' % (method, token), token) + 'https://api.periscope.tv/api/v2/%s?%s=%s' % (method, attribute, value), value) def _real_extract(self, url): token = self._match_id(url) diff --git a/youtube_dl/extractor/playwire.py b/youtube_dl/extractor/playwire.py index bdc71017b..6d138ef25 100644 --- a/youtube_dl/extractor/playwire.py +++ b/youtube_dl/extractor/playwire.py @@ -19,7 +19,7 @@ class PlaywireIE(InfoExtractor): 'id': '3353705', 'ext': 'mp4', 'title': 'S04_RM_UCL_Rus', - 'thumbnail': 're:^http://.*\.png$', + 'thumbnail': 're:^https?://.*\.png$', 'duration': 145.94, }, }, { diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 7b0cdc41a..a656ad85a 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -20,7 +20,7 @@ from ..aes import ( class PornHubIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)(?P[0-9a-z]+)' + _VALID_URL = r'https?://(?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)(?P[0-9a-z]+)' _TESTS = [{ 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', 'md5': '882f488fa1f0026f023f33576004a2ed', @@ -34,6 +34,9 @@ class PornHubIE(InfoExtractor): }, { 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d', 'only_matching': True, + }, { + 'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862', + 'only_matching': True, }] @classmethod diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index effcf1db3..baa54a3af 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -20,7 +20,7 @@ from ..utils import ( class ProSiebenSat1IE(InfoExtractor): IE_NAME = 'prosiebensat1' IE_DESC = 'ProSiebenSat.1 Digital' - _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at)|ran\.de|fem\.com)/(?P.+)' + _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at|ch)|ran\.de|fem\.com)/(?P.+)' _TESTS = [ { diff --git a/youtube_dl/extractor/qqmusic.py b/youtube_dl/extractor/qqmusic.py index 1654a641f..c98539f6a 100644 --- a/youtube_dl/extractor/qqmusic.py +++ b/youtube_dl/extractor/qqmusic.py @@ -25,7 +25,7 @@ class QQMusicIE(InfoExtractor): 'id': '004295Et37taLD', 'ext': 'mp3', 'title': '可惜没如果', - 'upload_date': '20141227', + 'release_date': '20141227', 'creator': '林俊杰', 'description': 'md5:d327722d0361576fde558f1ac68a7065', 'thumbnail': 're:^https?://.*\.jpg$', @@ -38,11 +38,26 @@ class QQMusicIE(InfoExtractor): 'id': '004MsGEo3DdNxV', 'ext': 'mp3', 'title': '如果', - 'upload_date': '20050626', + 'release_date': '20050626', 'creator': '李季美', 'description': 'md5:46857d5ed62bc4ba84607a805dccf437', 'thumbnail': 're:^https?://.*\.jpg$', } + }, { + 'note': 'lyrics not in .lrc format', + 'url': 'http://y.qq.com/#type=song&mid=001JyApY11tIp6', + 'info_dict': { + 'id': '001JyApY11tIp6', + 'ext': 'mp3', + 'title': 'Shadows Over Transylvania', + 'release_date': '19970225', + 'creator': 'Dark Funeral', + 'description': 'md5:ed14d5bd7ecec19609108052c25b2c11', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, }] _FORMATS = { @@ -112,15 +127,27 @@ class QQMusicIE(InfoExtractor): self._check_formats(formats, mid) self._sort_formats(formats) - return { + actual_lrc_lyrics = ''.join( + line + '\n' for line in re.findall( + r'(?m)^(\[[0-9]{2}:[0-9]{2}(?:\.[0-9]{2,})?\][^\n]*|\[[^\]]*\])', lrc_content)) + + info_dict = { 'id': mid, 'formats': formats, 'title': song_name, - 'upload_date': publish_time, + 'release_date': publish_time, 'creator': singer, 'description': lrc_content, - 'thumbnail': thumbnail_url, + 'thumbnail': thumbnail_url } + if actual_lrc_lyrics: + info_dict['subtitles'] = { + 'origin': [{ + 'ext': 'lrc', + 'data': actual_lrc_lyrics, + }] + } + return info_dict class QQPlaylistBaseIE(InfoExtractor): diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index 1631faf29..7ff1d06c4 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..compat import ( compat_urllib_parse, + compat_urlparse, ) from ..utils import ( parse_duration, @@ -72,6 +73,18 @@ class RaiIE(InfoExtractor): 'description': 'Primo appuntamento con "Il candidato" con Filippo Timi, alias Piero Zucca presidente!', 'uploader': 'RaiTre', } + }, + { + 'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html', + 'md5': '037104d2c14132887e5e4cf114569214', + 'info_dict': { + 'id': '0c7a664b-d0f4-4b2c-8835-3f82e46f433e', + 'ext': 'flv', + 'title': 'Il pacco', + 'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a', + 'uploader': 'RaiTre', + 'upload_date': '20141221', + }, } ] @@ -90,11 +103,14 @@ class RaiIE(InfoExtractor): relinker_url = self._extract_relinker_url(webpage) if not relinker_url: - iframe_path = self._search_regex( - r']+src="/?(dl/[^"]+\?iframe\b[^"]*)"', + iframe_url = self._search_regex( + [r']+src="([^"]*/dl/[^"]+\?iframe\b[^"]*)"', + r'drawMediaRaiTV\(["\'](.+?)["\']'], webpage, 'iframe') + if not iframe_url.startswith('http'): + iframe_url = compat_urlparse.urljoin(url, iframe_url) webpage = self._download_webpage( - '%s/%s' % (host, iframe_path), video_id) + iframe_url, video_id) relinker_url = self._extract_relinker_url(webpage) relinker = self._download_json( diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py index e4215d546..e42b319a3 100644 --- a/youtube_dl/extractor/rtbf.py +++ b/youtube_dl/extractor/rtbf.py @@ -9,8 +9,8 @@ from ..utils import ( class RTBFIE(InfoExtractor): - _VALID_URL = r'https?://www.rtbf.be/video/[^\?]+\?id=(?P\d+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?rtbf\.be/(?:video/[^?]+\?.*\bid=|ouftivi/(?:[^/]+/)*[^?]+\?.*\bvideoId=)(?P\d+)' + _TESTS = [{ 'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274', 'md5': '799f334ddf2c0a582ba80c44655be570', 'info_dict': { @@ -19,7 +19,14 @@ class RTBFIE(InfoExtractor): 'title': 'Les Diables au coeur (épisode 2)', 'duration': 3099, } - } + }, { + # geo restricted + 'url': 'http://www.rtbf.be/ouftivi/heros/detail_scooby-doo-mysteres-associes?id=1097&videoId=2057442', + 'only_matching': True, + }, { + 'url': 'http://www.rtbf.be/ouftivi/niouzz?videoId=2055858', + 'only_matching': True, + }] _QUALITIES = [ ('mobile', 'mobile'), @@ -36,7 +43,7 @@ class RTBFIE(InfoExtractor): data = self._parse_json( unescapeHTML(self._search_regex( - r'data-video="([^"]+)"', webpage, 'data video')), + r'data-media="([^"]+)"', webpage, 'data video')), video_id) if data.get('provider').lower() == 'youtube': diff --git a/youtube_dl/extractor/rte.py b/youtube_dl/extractor/rte.py index 04158b993..d9cfbf180 100644 --- a/youtube_dl/extractor/rte.py +++ b/youtube_dl/extractor/rte.py @@ -9,16 +9,16 @@ from ..utils import ( class RteIE(InfoExtractor): - _VALID_URL = r'http?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/(?P[0-9]+)/' + _VALID_URL = r'https?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/[^/]+/(?P[0-9]+)' _TEST = { - 'url': 'http://www.rte.ie/player/de/show/10363114/', + 'url': 'http://www.rte.ie/player/ie/show/iwitness-862/10478715/', 'info_dict': { - 'id': '10363114', + 'id': '10478715', 'ext': 'mp4', - 'title': 'One News', + 'title': 'Watch iWitness online', 'thumbnail': 're:^https?://.*\.jpg$', - 'description': 'The One O\'Clock News followed by Weather.', - 'duration': 436.844, + 'description': 'iWitness : The spirit of Ireland, one voice and one minute at a time.', + 'duration': 60.046, }, 'params': { 'skip_download': 'f4m fails with --test atm' diff --git a/youtube_dl/extractor/ruutu.py b/youtube_dl/extractor/ruutu.py index c67ad25ce..e417bf661 100644 --- a/youtube_dl/extractor/ruutu.py +++ b/youtube_dl/extractor/ruutu.py @@ -57,16 +57,21 @@ class RuutuIE(InfoExtractor): extract_formats(child) elif child.tag.endswith('File'): video_url = child.text - if not video_url or video_url in processed_urls or 'NOT_USED' in video_url: + if (not video_url or video_url in processed_urls or + any(p in video_url for p in ('NOT_USED', 'NOT-USED'))): return processed_urls.append(video_url) ext = determine_ext(video_url) if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - video_url, video_id, 'mp4', m3u8_id='hls')) + m3u8_formats = self._extract_m3u8_formats( + video_url, video_id, 'mp4', m3u8_id='hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) elif ext == 'f4m': - formats.extend(self._extract_f4m_formats( - video_url, video_id, f4m_id='hds')) + f4m_formats = self._extract_f4m_formats( + video_url, video_id, f4m_id='hds', fatal=False) + if f4m_formats: + formats.extend(f4m_formats) else: proto = compat_urllib_parse_urlparse(video_url).scheme if not child.tag.startswith('HTTP') and proto != 'rtmp': @@ -74,7 +79,7 @@ class RuutuIE(InfoExtractor): preference = -1 if proto == 'rtmp' else 1 label = child.get('label') tbr = int_or_none(child.get('bitrate')) - width, height = [int_or_none(x) for x in child.get('resolution', '').split('x')] + width, height = [int_or_none(x) for x in child.get('resolution', 'x').split('x')[:2]] formats.append({ 'format_id': '%s-%s' % (proto, label if label else tbr), 'url': video_url, diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py index 9c53704ea..474ebb49b 100644 --- a/youtube_dl/extractor/senateisvp.py +++ b/youtube_dl/extractor/senateisvp.py @@ -121,9 +121,9 @@ class SenateISVPIE(InfoExtractor): 'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=', }] else: - hdcore_sign = '?hdcore=3.1.0' + hdcore_sign = 'hdcore=3.1.0' url_params = (domain, video_id, stream_num) - f4m_url = '%s/z/%s_1@%s/manifest.f4m' % url_params + hdcore_sign + f4m_url = '%s/z/%s_1@%s/manifest.f4m?' % url_params + hdcore_sign m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'): # URLs without the extra param induce an 404 error diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py index 6e9903d5e..f76fb12c0 100644 --- a/youtube_dl/extractor/shahid.py +++ b/youtube_dl/extractor/shahid.py @@ -16,7 +16,7 @@ class ShahidIE(InfoExtractor): 'url': 'https://shahid.mbc.net/ar/episode/90574/%D8%A7%D9%84%D9%85%D9%84%D9%83-%D8%B9%D8%A8%D8%AF%D8%A7%D9%84%D9%84%D9%87-%D8%A7%D9%84%D8%A5%D9%86%D8%B3%D8%A7%D9%86-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-3.html', 'info_dict': { 'id': '90574', - 'ext': 'm3u8', + 'ext': 'mp4', 'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3', 'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان', 'duration': 2972, @@ -81,7 +81,7 @@ class ShahidIE(InfoExtractor): compat_urllib_parse.urlencode({ 'apiKey': 'sh@hid0nlin3', 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=', - }).encode('utf-8')), + })), video_id, 'Downloading video JSON') video = video[api_vars['playerType']] diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index ed5dcc0d3..2b60d354a 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -113,7 +113,7 @@ class SoundcloudIE(InfoExtractor): }, ] - _CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28' + _CLIENT_ID = '02gUJC0hH2ct1EGOcYXQIzRFU91c72Ea' _IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf' def report_resolve(self, video_id): diff --git a/youtube_dl/extractor/spiegeltv.py b/youtube_dl/extractor/spiegeltv.py index 27f4033c5..034bd47ff 100644 --- a/youtube_dl/extractor/spiegeltv.py +++ b/youtube_dl/extractor/spiegeltv.py @@ -77,17 +77,21 @@ class SpiegeltvIE(InfoExtractor): 'rtmp_live': True, }) elif determine_ext(endpoint) == 'm3u8': - m3u8_formats = self._extract_m3u8_formats( - endpoint.replace('[video]', play_path), - video_id, 'm4v', - preference=1, # Prefer hls since it allows to workaround georestriction - m3u8_id='hls', fatal=False) - if m3u8_formats is not False: - formats.extend(m3u8_formats) + formats.append({ + 'url': endpoint.replace('[video]', play_path), + 'ext': 'm4v', + 'format_id': 'hls', # Prefer hls since it allows to workaround georestriction + 'protocol': 'm3u8', + 'preference': 1, + 'http_headers': { + 'Accept-Encoding': 'deflate', # gzip causes trouble on the server side + }, + }) else: formats.append({ 'url': endpoint, }) + self._check_formats(formats, video_id) thumbnails = [] for image in media_json['images']: diff --git a/youtube_dl/extractor/stitcher.py b/youtube_dl/extractor/stitcher.py new file mode 100644 index 000000000..d5c852f52 --- /dev/null +++ b/youtube_dl/extractor/stitcher.py @@ -0,0 +1,81 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + int_or_none, + js_to_json, + unescapeHTML, +) + + +class StitcherIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?stitcher\.com/podcast/(?:[^/]+/)+e/(?:(?P[^/#?&]+?)-)?(?P\d+)(?:[/#?&]|$)' + _TESTS = [{ + 'url': 'http://www.stitcher.com/podcast/the-talking-machines/e/40789481?autoplay=true', + 'md5': '391dd4e021e6edeb7b8e68fbf2e9e940', + 'info_dict': { + 'id': '40789481', + 'ext': 'mp3', + 'title': 'Machine Learning Mastery and Cancer Clusters', + 'description': 'md5:55163197a44e915a14a1ac3a1de0f2d3', + 'duration': 1604, + 'thumbnail': 're:^https?://.*\.jpg', + }, + }, { + 'url': 'http://www.stitcher.com/podcast/panoply/vulture-tv/e/the-rare-hourlong-comedy-plus-40846275?autoplay=true', + 'info_dict': { + 'id': '40846275', + 'display_id': 'the-rare-hourlong-comedy-plus', + 'ext': 'mp3', + 'title': "The CW's 'Crazy Ex-Girlfriend'", + 'description': 'md5:04f1e2f98eb3f5cbb094cea0f9e19b17', + 'duration': 2235, + 'thumbnail': 're:^https?://.*\.jpg', + }, + 'params': { + 'skip_download': True, + }, + }, { + # escaped title + 'url': 'http://www.stitcher.com/podcast/marketplace-on-stitcher/e/40910226?autoplay=true', + 'only_matching': True, + }, { + 'url': 'http://www.stitcher.com/podcast/panoply/getting-in/e/episode-2a-how-many-extracurriculars-should-i-have-40876278?autoplay=true', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + audio_id = mobj.group('id') + display_id = mobj.group('display_id') or audio_id + + webpage = self._download_webpage(url, display_id) + + episode = self._parse_json( + js_to_json(self._search_regex( + r'(?s)var\s+stitcher\s*=\s*({.+?});\n', webpage, 'episode config')), + display_id)['config']['episode'] + + title = unescapeHTML(episode['title']) + formats = [{ + 'url': episode[episode_key], + 'ext': determine_ext(episode[episode_key]) or 'mp3', + 'vcodec': 'none', + } for episode_key in ('episodeURL',) if episode.get(episode_key)] + description = self._search_regex( + r'Episode Info:\s*([^<]+)<', webpage, 'description', fatal=False) + duration = int_or_none(episode.get('duration')) + thumbnail = episode.get('episodeImage') + + return { + 'id': audio_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'duration': duration, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/tapely.py b/youtube_dl/extractor/tapely.py index f1f43d0a7..744f9db38 100644 --- a/youtube_dl/extractor/tapely.py +++ b/youtube_dl/extractor/tapely.py @@ -16,7 +16,7 @@ from ..utils import ( class TapelyIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tape\.ly/(?P[A-Za-z0-9\-_]+)(?:/(?P\d+))?' + _VALID_URL = r'https?://(?:www\.)?(?:tape\.ly|tapely\.com)/(?P[A-Za-z0-9\-_]+)(?:/(?P\d+))?' _API_URL = 'http://tape.ly/showtape?id={0:}' _S3_SONG_URL = 'http://mytape.s3.amazonaws.com/{0:}' _SOUNDCLOUD_SONG_URL = 'http://api.soundcloud.com{0:}' @@ -42,6 +42,10 @@ class TapelyIE(InfoExtractor): 'ext': 'm4a', }, }, + { + 'url': 'https://tapely.com/my-grief-as-told-by-water', + 'only_matching': True, + }, ] def _real_extract(self, url): diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py index ae94f055c..2c8e9b941 100644 --- a/youtube_dl/extractor/telecinco.py +++ b/youtube_dl/extractor/telecinco.py @@ -1,24 +1,51 @@ # coding: utf-8 from __future__ import unicode_literals -from .mitele import MiTeleIE +import json +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urllib_parse_unquote, + compat_urlparse, +) +from ..utils import ( + get_element_by_attribute, + parse_duration, + strip_jsonp, +) -class TelecincoIE(MiTeleIE): - IE_NAME = 'telecinco.es' - _VALID_URL = r'https?://www\.telecinco\.es/(?:[^/]+/)+(?P.+?)\.html' + +class TelecincoIE(InfoExtractor): + IE_DESC = 'telecinco.es, cuatro.com and mediaset.es' + _VALID_URL = r'https?://www\.(?:telecinco\.es|cuatro\.com|mediaset\.es)/(?:[^/]+/)+(?P.+?)\.html' _TESTS = [{ 'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html', + 'md5': '5cbef3ad5ef17bf0d21570332d140729', 'info_dict': { 'id': 'MDSVID20141015_0058', 'ext': 'mp4', 'title': 'Con Martín Berasategui, hacer un bacalao al ...', 'duration': 662, }, - 'params': { - # m3u8 download - 'skip_download': True, + }, { + 'url': 'http://www.cuatro.com/deportes/futbol/barcelona/Leo_Messi-Champions-Roma_2_2052780128.html', + 'md5': '0a5b9f3cc8b074f50a0578f823a12694', + 'info_dict': { + 'id': 'MDSVID20150916_0128', + 'ext': 'mp4', + 'title': '¿Quién es este ex futbolista con el que hablan ...', + 'duration': 79, + }, + }, { + 'url': 'http://www.mediaset.es/12meses/campanas/doylacara/conlatratanohaytrato/Ayudame-dar-cara-trata-trato_2_1986630220.html', + 'md5': 'ad1bfaaba922dd4a295724b05b68f86a', + 'info_dict': { + 'id': 'MDSVID20150513_0220', + 'ext': 'mp4', + 'title': '#DOYLACARA. Con la trata no hay trato', + 'duration': 50, }, }, { 'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html', @@ -27,3 +54,41 @@ class TelecincoIE(MiTeleIE): 'url': 'http://www.telecinco.es/espanasinirmaslejos/Espana-gran-destino-turistico_2_1240605043.html', 'only_matching': True, }] + + def _real_extract(self, url): + episode = self._match_id(url) + webpage = self._download_webpage(url, episode) + embed_data_json = self._search_regex( + r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data', + ).replace('\'', '"') + embed_data = json.loads(embed_data_json) + + domain = embed_data['mediaUrl'] + if not domain.startswith('http'): + # only happens in telecinco.es videos + domain = 'http://' + domain + info_url = compat_urlparse.urljoin( + domain, + compat_urllib_parse_unquote(embed_data['flashvars']['host']) + ) + info_el = self._download_xml(info_url, episode).find('./video/info') + + video_link = info_el.find('videoUrl/link').text + token_query = compat_urllib_parse.urlencode({'id': video_link}) + token_info = self._download_json( + embed_data['flashvars']['ov_tk'] + '?' + token_query, + episode, + transform_source=strip_jsonp + ) + formats = self._extract_m3u8_formats( + token_info['tokenizedUrl'], episode, ext='mp4', entry_protocol='m3u8_native') + + return { + 'id': embed_data['videoId'], + 'display_id': episode, + 'title': info_el.find('title').text, + 'formats': formats, + 'description': get_element_by_attribute('class', 'text', webpage), + 'thumbnail': info_el.find('thumb').text, + 'duration': parse_duration(info_el.find('duration').text), + } diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index 84fe71aef..5f7ac4b35 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -2,14 +2,12 @@ from __future__ import unicode_literals -import re -import json - from .common import InfoExtractor +from ..compat import compat_str class TudouIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/.*?/(?P[^/?#]+?)(?:\.html)?/?(?:$|[?#])' + _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/([^/]+/)*(?P[^/?#]+?)(?:\.html)?/?(?:$|[?#])' _TESTS = [{ 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', 'md5': '140a49ed444bd22f93330985d8475fcb', @@ -27,41 +25,41 @@ class TudouIE(InfoExtractor): 'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012', 'thumbnail': 're:^https?://.*\.jpg$', } + }, { + 'url': 'http://www.tudou.com/albumplay/cJAHGih4yYg.html', + 'only_matching': True, }] _PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf' - def _url_for_id(self, id, quality=None): - info_url = "http://v2.tudou.com/f?id=" + str(id) + def _url_for_id(self, video_id, quality=None): + info_url = 'http://v2.tudou.com/f?id=' + compat_str(video_id) if quality: info_url += '&hd' + quality - webpage = self._download_webpage(info_url, id, "Opening the info webpage") - final_url = self._html_search_regex('>(.+?)', webpage, 'video url') + xml_data = self._download_xml(info_url, video_id, "Opening the info XML page") + final_url = xml_data.text return final_url def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - m = re.search(r'vcode:\s*[\'"](.+?)[\'"]', webpage) - if m and m.group(1): - return { - '_type': 'url', - 'url': 'youku:' + m.group(1), - 'ie_key': 'Youku' - } + youku_vcode = self._search_regex( + r'vcode\s*:\s*[\'"]([^\'"]*)[\'"]', webpage, 'youku vcode', default=None) + if youku_vcode: + return self.url_result('youku:' + youku_vcode, ie='Youku') title = self._search_regex( - r",kw:\s*['\"](.+?)[\"']", webpage, 'title') + r',kw\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'title') thumbnail_url = self._search_regex( - r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False) + r',pic\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'thumbnail URL', fatal=False) player_url = self._search_regex( - r"playerUrl\s*:\s*['\"](.+?\.swf)[\"']", + r'playerUrl\s*:\s*[\'"]([^\'"]+\.swf)[\'"]', webpage, 'player URL', default=self._PLAYER_URL) - segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments') - segments = json.loads(segs_json) + segments = self._parse_json(self._search_regex( + r'segs: \'([^\']+)\'', webpage, 'segments'), video_id) # It looks like the keys are the arguments that have to be passed as # the hd field in the request url, we pick the higher # Also, filter non-number qualities (see issue #3643). diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py index 3d3b635e4..4f844706d 100644 --- a/youtube_dl/extractor/tumblr.py +++ b/youtube_dl/extractor/tumblr.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import int_or_none class TumblrIE(InfoExtractor): @@ -28,6 +29,19 @@ class TumblrIE(InfoExtractor): 'description': 'md5:dba62ac8639482759c8eb10ce474586a', 'thumbnail': 're:http://.*\.jpg', } + }, { + 'url': 'http://hdvideotest.tumblr.com/post/130323439814/test-description-for-my-hd-video', + 'md5': '7ae503065ad150122dc3089f8cf1546c', + 'info_dict': { + 'id': '130323439814', + 'ext': 'mp4', + 'title': 'HD Video Testing \u2014 Test description for my HD video', + 'description': 'md5:97cc3ab5fcd27ee4af6356701541319c', + 'thumbnail': 're:http://.*\.jpg', + }, + 'params': { + 'format': 'hd', + }, }, { 'url': 'http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching', 'md5': 'de07e5211d60d4f3a2c3df757ea9f6ab', @@ -37,6 +51,9 @@ class TumblrIE(InfoExtractor): 'title': 'naked smoking & stretching', 'upload_date': '20150506', 'timestamp': 1430931613, + 'age_limit': 18, + 'uploader_id': '1638622', + 'uploader': 'naked-yogi', }, 'add_ie': ['Vidme'], }, { @@ -66,10 +83,38 @@ class TumblrIE(InfoExtractor): if iframe_url is None: return self.url_result(urlh.geturl(), 'Generic') - iframe = self._download_webpage(iframe_url, video_id, - 'Downloading iframe page') - video_url = self._search_regex(r']+src=(["\'])(?P.+?)\1', iframe, + 'sd video url', default=None, group='url') + if sd_url: + sources.append((sd_url, 'sd')) + + options = self._parse_json( + self._search_regex( + r'data-crt-options=(["\'])(?P.+?)\1', iframe, + 'hd video url', default='', group='options'), + video_id, fatal=False) + if options: + duration = int_or_none(options.get('duration')) + hd_url = options.get('hdUrl') + if hd_url: + sources.append((hd_url, 'hd')) + + formats = [{ + 'url': video_url, + 'ext': 'mp4', + 'format_id': format_id, + 'height': int_or_none(self._search_regex( + r'/(\d{3,4})$', video_url, 'height', default=None)), + 'quality': quality, + } for quality, (video_url, format_id) in enumerate(sources)] + + self._sort_formats(formats) # The only place where you can get a title, it's not complete, # but searching in other places doesn't work for all videos @@ -79,9 +124,9 @@ class TumblrIE(InfoExtractor): return { 'id': video_id, - 'url': video_url, - 'ext': 'mp4', 'title': video_title, 'description': self._og_search_description(webpage, default=None), 'thumbnail': self._og_search_thumbnail(webpage, default=None), + 'duration': duration, + 'formats': formats, } diff --git a/youtube_dl/extractor/tutv.py b/youtube_dl/extractor/tutv.py index fad720b68..822372ea1 100644 --- a/youtube_dl/extractor/tutv.py +++ b/youtube_dl/extractor/tutv.py @@ -10,10 +10,10 @@ class TutvIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P[^/?]+)' _TEST = { 'url': 'http://tu.tv/videos/robots-futbolistas', - 'md5': '627c7c124ac2a9b5ab6addb94e0e65f7', + 'md5': '0cd9e28ad270488911b0d2a72323395d', 'info_dict': { 'id': '2973058', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Robots futbolistas', }, } diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 023911c41..3ec08b674 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -15,6 +15,7 @@ from ..compat import ( compat_urlparse, ) from ..utils import ( + encode_dict, ExtractorError, int_or_none, parse_duration, @@ -27,8 +28,7 @@ class TwitchBaseIE(InfoExtractor): _API_BASE = 'https://api.twitch.tv' _USHER_BASE = 'http://usher.twitch.tv' - _LOGIN_URL = 'https://secure.twitch.tv/login' - _LOGIN_POST_URL = 'https://passport.twitch.tv/authentications/new' + _LOGIN_URL = 'http://www.twitch.tv/login' _NETRC_MACHINE = 'twitch' def _handle_error(self, response): @@ -61,26 +61,28 @@ class TwitchBaseIE(InfoExtractor): if username is None: return - login_page = self._download_webpage( + login_page, handle = self._download_webpage_handle( self._LOGIN_URL, None, 'Downloading login page') login_form = self._hidden_inputs(login_page) login_form.update({ - 'login': username.encode('utf-8'), - 'password': password.encode('utf-8'), + 'username': username, + 'password': password, }) + redirect_url = handle.geturl() + post_url = self._search_regex( r']+action=(["\'])(?P.+?)\1', login_page, - 'post url', default=self._LOGIN_POST_URL, group='url') + 'post url', default=redirect_url, group='url') if not post_url.startswith('http'): - post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url) + post_url = compat_urlparse.urljoin(redirect_url, post_url) request = compat_urllib_request.Request( - post_url, compat_urllib_parse.urlencode(login_form).encode('utf-8')) - request.add_header('Referer', self._LOGIN_URL) + post_url, compat_urllib_parse.urlencode(encode_dict(login_form)).encode('utf-8')) + request.add_header('Referer', redirect_url) response = self._download_webpage( request, None, 'Logging in as %s' % username) @@ -238,14 +240,24 @@ class TwitchVodIE(TwitchItemBaseIE): def _real_extract(self, url): item_id = self._match_id(url) + info = self._download_info(self._ITEM_SHORTCUT, item_id) access_token = self._download_json( '%s/api/vods/%s/access_token' % (self._API_BASE, item_id), item_id, 'Downloading %s access token' % self._ITEM_TYPE) + formats = self._extract_m3u8_formats( - '%s/vod/%s?nauth=%s&nauthsig=%s&allow_source=true' - % (self._USHER_BASE, item_id, access_token['token'], access_token['sig']), + '%s/vod/%s?%s' % ( + self._USHER_BASE, item_id, + compat_urllib_parse.urlencode({ + 'allow_source': 'true', + 'allow_spectre': 'true', + 'player': 'twitchweb', + 'nauth': access_token['token'], + 'nauthsig': access_token['sig'], + })), item_id, 'mp4') + self._prefer_source(formats) info['formats'] = formats diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index 1aaa06305..2bd5946ac 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import re @@ -6,23 +7,53 @@ from .common import InfoExtractor from ..compat import compat_urllib_request from ..utils import ( float_or_none, - unescapeHTML, + xpath_text, + remove_end, + int_or_none, + ExtractorError, ) class TwitterCardIE(InfoExtractor): + IE_NAME = 'twitter:card' _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P\d+)' - _TEST = { - 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889', - 'md5': 'a74f50b310c83170319ba16de6955192', - 'info_dict': { - 'id': '560070183650213889', - 'ext': 'mp4', - 'title': 'TwitterCard', - 'thumbnail': 're:^https?://.*\.jpg$', - 'duration': 30.033, + _TESTS = [ + { + 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889', + 'md5': '4fa26a35f9d1bf4b646590ba8e84be19', + 'info_dict': { + 'id': '560070183650213889', + 'ext': 'mp4', + 'title': 'TwitterCard', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 30.033, + } }, - } + { + 'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768', + 'md5': '7ee2a553b63d1bccba97fbed97d9e1c8', + 'info_dict': { + 'id': '623160978427936768', + 'ext': 'mp4', + 'title': 'TwitterCard', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 80.155, + }, + }, + { + 'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977', + 'md5': 'b6f35e8b08a0bec6c8af77a2f4b3a814', + 'info_dict': { + 'id': 'dq4Oj5quskI', + 'ext': 'mp4', + 'title': 'Ubuntu 11.10 Overview', + 'description': 'Take a quick peek at what\'s new and improved in Ubuntu 11.10.\n\nOnce installed take a look at 10 Things to Do After Installing: http://www.omgubuntu.co.uk/2011/10/10-things-to-do-after-installing-ubuntu-11-10/', + 'upload_date': '20111013', + 'uploader': 'OMG! Ubuntu!', + 'uploader_id': 'omgubuntu', + }, + } + ] def _real_extract(self, url): video_id = self._match_id(url) @@ -40,10 +71,24 @@ class TwitterCardIE(InfoExtractor): request.add_header('User-Agent', user_agent) webpage = self._download_webpage(request, video_id) - config = self._parse_json( - unescapeHTML(self._search_regex( - r'data-player-config="([^"]+)"', webpage, 'data player config')), + youtube_url = self._html_search_regex( + r']+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"', + webpage, 'youtube iframe', default=None) + if youtube_url: + return self.url_result(youtube_url, 'Youtube') + + config = self._parse_json(self._html_search_regex( + r'data-player-config="([^"]+)"', webpage, 'data player config'), video_id) + if 'playlist' not in config: + if 'vmapUrl' in config: + vmap_data = self._download_xml(config['vmapUrl'], video_id) + video_url = xpath_text(vmap_data, './/MediaFile').strip() + formats.append({ + 'url': video_url, + }) + break # same video regardless of UA + continue video_url = config['playlist'][0]['source'] @@ -70,3 +115,100 @@ class TwitterCardIE(InfoExtractor): 'duration': duration, 'formats': formats, } + + +class TwitterIE(InfoExtractor): + IE_NAME = 'twitter' + _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?P[^/]+)/status/(?P\d+)' + _TEMPLATE_URL = 'https://twitter.com/%s/status/%s' + + _TESTS = [{ + 'url': 'https://twitter.com/freethenipple/status/643211948184596480', + 'md5': 'db6612ec5d03355953c3ca9250c97e5e', + 'info_dict': { + 'id': '643211948184596480', + 'ext': 'mp4', + 'title': 'FREE THE NIPPLE - FTN supporters on Hollywood Blvd today!', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 12.922, + 'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"', + 'uploader': 'FREE THE NIPPLE', + 'uploader_id': 'freethenipple', + }, + }, { + 'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1', + 'md5': 'f36dcd5fb92bf7057f155e7d927eeb42', + 'info_dict': { + 'id': '657991469417025536', + 'ext': 'mp4', + 'title': 'Gifs - tu vai cai tu vai cai tu nao eh capaz disso tu vai cai', + 'description': 'Gifs on Twitter: "tu vai cai tu vai cai tu nao eh capaz disso tu vai cai https://t.co/tM46VHFlO5"', + 'thumbnail': 're:^https?://.*\.png', + 'uploader': 'Gifs', + 'uploader_id': 'giphz', + }, + }, { + 'url': 'https://twitter.com/starwars/status/665052190608723968', + 'md5': '39b7199856dee6cd4432e72c74bc69d4', + 'info_dict': { + 'id': '665052190608723968', + 'ext': 'mp4', + 'title': 'Star Wars - A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens.', + 'description': 'Star Wars on Twitter: "A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens."', + 'uploader_id': 'starwars', + 'uploader': 'Star Wars', + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + user_id = mobj.group('user_id') + twid = mobj.group('id') + + webpage = self._download_webpage(self._TEMPLATE_URL % (user_id, twid), twid) + + username = remove_end(self._og_search_title(webpage), ' on Twitter') + + title = description = self._og_search_description(webpage).strip('').replace('\n', ' ').strip('“”') + + # strip 'https -_t.co_BJYgOjSeGA' junk from filenames + title = re.sub(r'\s+(https?://[^ ]+)', '', title) + + info = { + 'uploader_id': user_id, + 'uploader': username, + 'webpage_url': url, + 'description': '%s on Twitter: "%s"' % (username, description), + 'title': username + ' - ' + title, + } + + card_id = self._search_regex( + r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url', default=None) + if card_id: + card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id + info.update({ + '_type': 'url_transparent', + 'ie_key': 'TwitterCard', + 'url': card_url, + }) + return info + + mobj = re.search(r'''(?x) + ]+class="animated-gif"[^>]+ + (?:data-height="(?P\d+)")?[^>]+ + (?:data-width="(?P\d+)")?[^>]+ + (?:poster="(?P[^"]+)")?[^>]*>\s* + ]+video-src="(?P[^"]+)" + ''', webpage) + + if mobj: + info.update({ + 'id': twid, + 'url': mobj.group('url'), + 'height': int_or_none(mobj.group('height')), + 'width': int_or_none(mobj.group('width')), + 'thumbnail': mobj.group('poster'), + }) + return info + + raise ExtractorError('There\'s not video in this tweet.') diff --git a/youtube_dl/extractor/ustream.py b/youtube_dl/extractor/ustream.py index c39c278ab..73b05ecab 100644 --- a/youtube_dl/extractor/ustream.py +++ b/youtube_dl/extractor/ustream.py @@ -1,17 +1,20 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor from ..compat import ( compat_urlparse, ) -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + int_or_none, + float_or_none, +) class UstreamIE(InfoExtractor): - _VALID_URL = r'https?://www\.ustream\.tv/(?Precorded|embed|embed/recorded)/(?P\d+)' + _VALID_URL = r'https?://www\.ustream\.tv/(?Precorded|embed|embed/recorded)/(?P\d+)' IE_NAME = 'ustream' _TESTS = [{ 'url': 'http://www.ustream.tv/recorded/20274954', @@ -19,8 +22,12 @@ class UstreamIE(InfoExtractor): 'info_dict': { 'id': '20274954', 'ext': 'flv', - 'uploader': 'Young Americans for Liberty', 'title': 'Young Americans for Liberty February 7, 2012 2:28 AM', + 'description': 'Young Americans for Liberty February 7, 2012 2:28 AM', + 'timestamp': 1328577035, + 'upload_date': '20120207', + 'uploader': 'yaliberty', + 'uploader_id': '6780869', }, }, { # From http://sportscanada.tv/canadagames/index.php/week2/figure-skating/444 @@ -32,20 +39,21 @@ class UstreamIE(InfoExtractor): 'ext': 'flv', 'title': '-CG11- Canada Games Figure Skating', 'uploader': 'sportscanadatv', - } + }, + 'skip': 'This Pro Broadcaster has chosen to remove this video from the ustream.tv site.', }] def _real_extract(self, url): m = re.match(self._VALID_URL, url) - video_id = m.group('videoID') + video_id = m.group('id') # some sites use this embed format (see: http://github.com/rg3/youtube-dl/issues/2990) if m.group('type') == 'embed/recorded': - video_id = m.group('videoID') + video_id = m.group('id') desktop_url = 'http://www.ustream.tv/recorded/' + video_id return self.url_result(desktop_url, 'Ustream') if m.group('type') == 'embed': - video_id = m.group('videoID') + video_id = m.group('id') webpage = self._download_webpage(url, video_id) desktop_video_id = self._html_search_regex( r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id') @@ -53,52 +61,50 @@ class UstreamIE(InfoExtractor): return self.url_result(desktop_url, 'Ustream') params = self._download_json( - 'http://cdngw.ustream.tv/rgwjson/Viewer.getVideo/' + json.dumps({ - 'brandId': 1, - 'videoId': int(video_id), - 'autoplay': False, - }), video_id) - - if 'error' in params: - raise ExtractorError(params['error']['message'], expected=True) - - video_url = params['flv'] + 'https://api.ustream.tv/videos/%s.json' % video_id, video_id) - webpage = self._download_webpage(url, video_id) + error = params.get('error') + if error: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, error), expected=True) - self.report_extraction(video_id) + video = params['video'] - video_title = self._html_search_regex(r'data-title="(?P.+)"', - webpage, 'title', default=None) + title = video['title'] + filesize = float_or_none(video.get('file_size')) - if not video_title: - try: - video_title = params['moduleConfig']['meta']['title'] - except KeyError: - pass - - if not video_title: - video_title = 'Ustream video ' + video_id + formats = [{ + 'id': video_id, + 'url': video_url, + 'ext': format_id, + 'filesize': filesize, + } for format_id, video_url in video['media_urls'].items()] + self._sort_formats(formats) - uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>', - webpage, 'uploader', fatal=False, flags=re.DOTALL, default=None) + description = video.get('description') + timestamp = int_or_none(video.get('created_at')) + duration = float_or_none(video.get('length')) + view_count = int_or_none(video.get('views')) - if not uploader: - try: - uploader = params['moduleConfig']['meta']['userName'] - except KeyError: - uploader = None + uploader = video.get('owner', {}).get('username') + uploader_id = video.get('owner', {}).get('id') - thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"', - webpage, 'thumbnail', fatal=False) + thumbnails = [{ + 'id': thumbnail_id, + 'url': thumbnail_url, + } for thumbnail_id, thumbnail_url in video.get('thumbnail', {}).items()] return { 'id': video_id, - 'url': video_url, - 'ext': 'flv', - 'title': video_title, + 'title': title, + 'description': description, + 'thumbnails': thumbnails, + 'timestamp': timestamp, + 'duration': duration, + 'view_count': view_count, 'uploader': uploader, - 'thumbnail': thumbnail, + 'uploader_id': uploader_id, + 'formats': formats, } diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index c17094f81..4c0de354f 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -1,10 +1,10 @@ from __future__ import unicode_literals import re -import xml.etree.ElementTree from .common import InfoExtractor from ..compat import ( + compat_etree_fromstring, compat_urllib_request, ) from ..utils import ( @@ -97,7 +97,7 @@ class VevoIE(InfoExtractor): if last_version['version'] == -1: raise ExtractorError('Unable to extract last version of the video') - renditions = xml.etree.ElementTree.fromstring(last_version['data']) + renditions = compat_etree_fromstring(last_version['data']) formats = [] # Already sorted from worst to best quality for rend in renditions.findall('rendition'): @@ -114,7 +114,7 @@ class VevoIE(InfoExtractor): def _formats_from_smil(self, smil_xml): formats = [] - smil_doc = xml.etree.ElementTree.fromstring(smil_xml.encode('utf-8')) + smil_doc = compat_etree_fromstring(smil_xml.encode('utf-8')) els = smil_doc.findall('.//{http://www.w3.org/2001/SMIL20/Language}video') for el in els: src = el.attrib['src'] diff --git a/youtube_dl/extractor/videofyme.py b/youtube_dl/extractor/videofyme.py index 94f9e9be9..cd3f50a63 100644 --- a/youtube_dl/extractor/videofyme.py +++ b/youtube_dl/extractor/videofyme.py @@ -2,8 +2,8 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( - find_xpath_attr, int_or_none, + parse_iso8601, ) @@ -18,33 +18,35 @@ class VideofyMeIE(InfoExtractor): 'id': '1100701', 'ext': 'mp4', 'title': 'This is VideofyMe', - 'description': None, + 'description': '', + 'upload_date': '20130326', + 'timestamp': 1364288959, 'uploader': 'VideofyMe', 'uploader_id': 'thisisvideofyme', 'view_count': int, + 'likes': int, + 'comment_count': int, }, - } def _real_extract(self, url): video_id = self._match_id(url) - config = self._download_xml('http://sunshine.videofy.me/?videoId=%s' % video_id, - video_id) - video = config.find('video') - sources = video.find('sources') - url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key) - for key in ['on', 'av', 'off']] if node is not None) - video_url = url_node.find('url').text - view_count = int_or_none(self._search_regex( - r'([0-9]+)', video.find('views').text, 'view count', fatal=False)) + + config = self._download_json('http://vf-player-info-loader.herokuapp.com/%s.json' % video_id, video_id)['videoinfo'] + + video = config.get('video') + blog = config.get('blog', {}) return { 'id': video_id, - 'title': video.find('title').text, - 'url': video_url, - 'thumbnail': video.find('thumb').text, - 'description': video.find('description').text, - 'uploader': config.find('blog/name').text, - 'uploader_id': video.find('identifier').text, - 'view_count': view_count, + 'title': video['title'], + 'url': video['sources']['source']['url'], + 'thumbnail': video.get('thumb'), + 'description': video.get('description'), + 'timestamp': parse_iso8601(video.get('date')), + 'uploader': blog.get('name'), + 'uploader_id': blog.get('identifier'), + 'view_count': int_or_none(self._search_regex(r'([0-9]+)', video.get('views'), 'view count', fatal=False)), + 'likes': int_or_none(video.get('likes')), + 'comment_count': int_or_none(video.get('nrOfComments')), } diff --git a/youtube_dl/extractor/videolecturesnet.py b/youtube_dl/extractor/videolecturesnet.py deleted file mode 100644 index ef2da5632..000000000 --- a/youtube_dl/extractor/videolecturesnet.py +++ /dev/null @@ -1,86 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - find_xpath_attr, - int_or_none, - parse_duration, - unified_strdate, -) - - -class VideoLecturesNetIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/#?]+)/*(?:[#?].*)?$' - IE_NAME = 'videolectures.net' - - _TEST = { - 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/', - 'info_dict': { - 'id': 'promogram_igor_mekjavic_eng', - 'ext': 'mp4', - 'title': 'Automatics, robotics and biocybernetics', - 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482', - 'upload_date': '20130627', - 'duration': 565, - 'thumbnail': 're:http://.*\.jpg', - }, - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id - smil = self._download_xml(smil_url, video_id) - - title = find_xpath_attr(smil, './/meta', 'name', 'title').attrib['content'] - description_el = find_xpath_attr(smil, './/meta', 'name', 'abstract') - description = ( - None if description_el is None - else description_el.attrib['content']) - upload_date = unified_strdate( - find_xpath_attr(smil, './/meta', 'name', 'date').attrib['content']) - - switch = smil.find('.//switch') - duration = parse_duration(switch.attrib.get('dur')) - thumbnail_el = find_xpath_attr(switch, './image', 'type', 'thumbnail') - thumbnail = ( - None if thumbnail_el is None else thumbnail_el.attrib.get('src')) - - formats = [] - for v in switch.findall('./video'): - proto = v.attrib.get('proto') - if proto not in ['http', 'rtmp']: - continue - f = { - 'width': int_or_none(v.attrib.get('width')), - 'height': int_or_none(v.attrib.get('height')), - 'filesize': int_or_none(v.attrib.get('size')), - 'tbr': int_or_none(v.attrib.get('systemBitrate')) / 1000.0, - 'ext': v.attrib.get('ext'), - } - src = v.attrib['src'] - if proto == 'http': - if self._is_valid_url(src, video_id): - f['url'] = src - formats.append(f) - elif proto == 'rtmp': - f.update({ - 'url': v.attrib['streamer'], - 'play_path': src, - 'rtmp_real_time': True, - }) - formats.append(f) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'upload_date': upload_date, - 'duration': duration, - 'thumbnail': thumbnail, - 'formats': formats, - } diff --git a/youtube_dl/extractor/vidme.py b/youtube_dl/extractor/vidme.py index 9a794e609..3d63ed4f0 100644 --- a/youtube_dl/extractor/vidme.py +++ b/youtube_dl/extractor/vidme.py @@ -14,7 +14,7 @@ class VidmeIE(InfoExtractor): _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)' _TESTS = [{ 'url': 'https://vid.me/QNB', - 'md5': 'c62f1156138dc3323902188c5b5a8bd6', + 'md5': 'f42d05e7149aeaec5c037b17e5d3dc82', 'info_dict': { 'id': 'QNB', 'ext': 'mp4', @@ -93,6 +93,39 @@ class VidmeIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + # nsfw, user-disabled + 'url': 'https://vid.me/dzGJ', + 'only_matching': True, + }, { + # suspended + 'url': 'https://vid.me/Ox3G', + 'only_matching': True, + }, { + # deleted + 'url': 'https://vid.me/KTPm', + 'only_matching': True, + }, { + # no formats in the API response + 'url': 'https://vid.me/e5g', + 'info_dict': { + 'id': 'e5g', + 'ext': 'mp4', + 'title': 'Video upload (e5g)', + 'thumbnail': 're:^https?://.*\.jpg', + 'timestamp': 1401480195, + 'upload_date': '20140530', + 'uploader': None, + 'uploader_id': None, + 'age_limit': 0, + 'duration': 483, + 'view_count': int, + 'like_count': int, + 'comment_count': int, + }, + 'params': { + 'skip_download': True, + }, }] def _real_extract(self, url): @@ -114,12 +147,32 @@ class VidmeIE(InfoExtractor): video = response['video'] + if video.get('state') == 'deleted': + raise ExtractorError( + 'Vidme said: Sorry, this video has been deleted.', + expected=True) + + if video.get('state') in ('user-disabled', 'suspended'): + raise ExtractorError( + 'Vidme said: This video has been suspended either due to a copyright claim, ' + 'or for violating the terms of use.', + expected=True) + formats = [{ 'format_id': f.get('type'), 'url': f['uri'], 'width': int_or_none(f.get('width')), 'height': int_or_none(f.get('height')), + 'preference': 0 if f.get('type', '').endswith('clip') else 1, } for f in video.get('formats', []) if f.get('uri')] + + if not formats and video.get('complete_url'): + formats.append({ + 'url': video.get('complete_url'), + 'width': int_or_none(video.get('width')), + 'height': int_or_none(video.get('height')), + }) + self._sort_formats(formats) title = video['title'] @@ -136,7 +189,7 @@ class VidmeIE(InfoExtractor): return { 'id': video_id, - 'title': title, + 'title': title or 'Video upload (%s)' % video_id, 'description': description, 'thumbnail': thumbnail, 'uploader': uploader, diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py index 08a5a7b8d..2ba9f31df 100644 --- a/youtube_dl/extractor/vidzi.py +++ b/youtube_dl/extractor/vidzi.py @@ -20,8 +20,14 @@ class VidziIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - video_url = self._html_search_regex( - r'{\s*file\s*:\s*"([^"]+)"\s*}', webpage, 'video url') + video_host = self._html_search_regex( + r'id=\'vplayer\'><img src="http://(.*?)/i', webpage, + 'video host') + video_hash = self._html_search_regex( + r'\|([a-z0-9]+)\|hls\|type', webpage, 'video_hash') + ext = self._html_search_regex( + r'\|tracks\|([a-z0-9]+)\|', webpage, 'video ext') + video_url = 'http://' + video_host + '/' + video_hash + '/v.' + ext title = self._html_search_regex( r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title') diff --git a/youtube_dl/extractor/viewster.py b/youtube_dl/extractor/viewster.py index cda02ba24..7cf930d69 100644 --- a/youtube_dl/extractor/viewster.py +++ b/youtube_dl/extractor/viewster.py @@ -3,12 +3,14 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..compat import ( + compat_HTTPError, compat_urllib_request, compat_urllib_parse, compat_urllib_parse_unquote, ) from ..utils import ( determine_ext, + ExtractorError, int_or_none, parse_iso8601, HEADRequest, @@ -16,14 +18,14 @@ from ..utils import ( class ViewsterIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?viewster\.com/(?:serie|movie)/(?P<id>\d+-\d+-\d+)' + _VALID_URL = r'https?://(?:www\.)?viewster\.com/(?:serie|movie)/(?P<id>\d+-\d+-\d+)' _TESTS = [{ # movie, Type=Movie 'url': 'http://www.viewster.com/movie/1140-11855-000/the-listening-project/', - 'md5': '14d3cfffe66d57b41ae2d9c873416f01', + 'md5': 'e642d1b27fcf3a4ffa79f194f5adde36', 'info_dict': { 'id': '1140-11855-000', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'The listening Project', 'description': 'md5:bac720244afd1a8ea279864e67baa071', 'timestamp': 1214870400, @@ -33,10 +35,10 @@ class ViewsterIE(InfoExtractor): }, { # series episode, Type=Episode 'url': 'http://www.viewster.com/serie/1284-19427-001/the-world-and-a-wall/', - 'md5': 'd5434c80fcfdb61651cc2199a88d6ba3', + 'md5': '9243079a8531809efe1b089db102c069', 'info_dict': { 'id': '1284-19427-001', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'The World and a Wall', 'description': 'md5:24814cf74d3453fdf5bfef9716d073e3', 'timestamp': 1428192000, @@ -61,6 +63,14 @@ class ViewsterIE(InfoExtractor): 'description': 'md5:e7097a8fc97151e25f085c9eb7a1cdb1', }, 'playlist_mincount': 16, + }, { + # geo restricted series + 'url': 'https://www.viewster.com/serie/1280-18794-002/', + 'only_matching': True, + }, { + # geo restricted video + 'url': 'https://www.viewster.com/serie/1280-18794-002/what-is-extraterritoriality-lawo/', + 'only_matching': True, }] _ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01' @@ -74,8 +84,8 @@ class ViewsterIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) # Get 'api_token' cookie - self._request_webpage(HEADRequest(url), video_id) - cookies = self._get_cookies(url) + self._request_webpage(HEADRequest('http://www.viewster.com/'), video_id) + cookies = self._get_cookies('http://www.viewster.com/') self._AUTH_TOKEN = compat_urllib_parse_unquote(cookies['api_token'].value) info = self._download_json( @@ -85,10 +95,16 @@ class ViewsterIE(InfoExtractor): entry_id = info.get('Id') or info['id'] # unfinished serie has no Type - if info.get('Type') in ['Serie', None]: - episodes = self._download_json( - 'https://public-api.viewster.com/series/%s/episodes' % entry_id, - video_id, 'Downloading series JSON') + if info.get('Type') in ('Serie', None): + try: + episodes = self._download_json( + 'https://public-api.viewster.com/series/%s/episodes' % entry_id, + video_id, 'Downloading series JSON') + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: + self.raise_geo_restricted() + else: + raise entries = [ self.url_result( 'http://www.viewster.com/movie/%s' % episode['OriginId'], 'Viewster') @@ -98,7 +114,7 @@ class ViewsterIE(InfoExtractor): return self.playlist_result(entries, video_id, title, description) formats = [] - for media_type in ('application/f4m+xml', 'application/x-mpegURL'): + for media_type in ('application/f4m+xml', 'application/x-mpegURL', 'video/mp4'): media = self._download_json( 'https://public-api.viewster.com/movies/%s/video?mediaType=%s' % (entry_id, compat_urllib_parse.quote(media_type)), @@ -115,14 +131,28 @@ class ViewsterIE(InfoExtractor): formats.extend(self._extract_f4m_formats( video_url, video_id, f4m_id='hds')) elif ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( + m3u8_formats = self._extract_m3u8_formats( video_url, video_id, 'mp4', m3u8_id='hls', - fatal=False # m3u8 sometimes fail - )) + fatal=False) # m3u8 sometimes fail + if m3u8_formats: + formats.extend(m3u8_formats) else: - formats.append({ + format_id = media.get('Bitrate') + f = { 'url': video_url, - }) + 'format_id': 'mp4-%s' % format_id, + 'height': int_or_none(media.get('Height')), + 'width': int_or_none(media.get('Width')), + 'preference': 1, + } + if format_id and not f['height']: + f['height'] = int_or_none(self._search_regex( + r'^(\d+)[pP]$', format_id, 'height', default=None)) + formats.append(f) + + if not formats and not info.get('LanguageSets') and not info.get('VODSettings'): + self.raise_geo_restricted() + self._sort_formats(formats) synopsis = info.get('Synopsis', {}) diff --git a/youtube_dl/extractor/viidea.py b/youtube_dl/extractor/viidea.py new file mode 100644 index 000000000..525e303d4 --- /dev/null +++ b/youtube_dl/extractor/viidea.py @@ -0,0 +1,188 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urlparse, + compat_str, +) +from ..utils import ( + parse_duration, + js_to_json, + parse_iso8601, +) + + +class ViideaIE(InfoExtractor): + _VALID_URL = r'''(?x)http://(?:www\.)?(?: + videolectures\.net| + flexilearn\.viidea\.net| + presentations\.ocwconsortium\.org| + video\.travel-zoom\.si| + video\.pomp-forum\.si| + tv\.nil\.si| + video\.hekovnik.com| + video\.szko\.si| + kpk\.viidea\.com| + inside\.viidea\.net| + video\.kiberpipa\.org| + bvvideo\.si| + kongres\.viidea\.net| + edemokracija\.viidea\.com + )(?:/lecture)?/(?P<id>[^/]+)(?:/video/(?P<part>\d+))?/*(?:[#?].*)?$''' + + _TESTS = [{ + 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/', + 'info_dict': { + 'id': '20171', + 'display_id': 'promogram_igor_mekjavic_eng', + 'ext': 'mp4', + 'title': 'Automatics, robotics and biocybernetics', + 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482', + 'thumbnail': 're:http://.*\.jpg', + 'timestamp': 1372349289, + 'upload_date': '20130627', + 'duration': 565, + }, + }, { + # video with invalid direct format links (HTTP 403) + 'url': 'http://videolectures.net/russir2010_filippova_nlp/', + 'info_dict': { + 'id': '14891', + 'display_id': 'russir2010_filippova_nlp', + 'ext': 'flv', + 'title': 'NLP at Google', + 'description': 'md5:fc7a6d9bf0302d7cc0e53f7ca23747b3', + 'thumbnail': 're:http://.*\.jpg', + 'timestamp': 1284375600, + 'upload_date': '20100913', + 'duration': 5352, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + # event playlist + 'url': 'http://videolectures.net/deeplearning2015_montreal/', + 'info_dict': { + 'id': '23181', + 'title': 'Deep Learning Summer School, Montreal 2015', + 'description': 'md5:0533a85e4bd918df52a01f0e1ebe87b7', + 'thumbnail': 're:http://.*\.jpg', + 'timestamp': 1438560000, + }, + 'playlist_count': 30, + }, { + # multi part lecture + 'url': 'http://videolectures.net/mlss09uk_bishop_ibi/', + 'info_dict': { + 'id': '9737', + 'display_id': 'mlss09uk_bishop_ibi', + 'title': 'Introduction To Bayesian Inference', + 'thumbnail': 're:http://.*\.jpg', + 'timestamp': 1251622800, + }, + 'playlist': [{ + 'info_dict': { + 'id': '9737_part1', + 'display_id': 'mlss09uk_bishop_ibi_part1', + 'ext': 'wmv', + 'title': 'Introduction To Bayesian Inference (Part 1)', + 'thumbnail': 're:http://.*\.jpg', + 'duration': 4622, + 'timestamp': 1251622800, + 'upload_date': '20090830', + }, + }, { + 'info_dict': { + 'id': '9737_part2', + 'display_id': 'mlss09uk_bishop_ibi_part2', + 'ext': 'wmv', + 'title': 'Introduction To Bayesian Inference (Part 2)', + 'thumbnail': 're:http://.*\.jpg', + 'duration': 5641, + 'timestamp': 1251622800, + 'upload_date': '20090830', + }, + }], + 'playlist_count': 2, + }] + + def _real_extract(self, url): + lecture_slug, explicit_part_id = re.match(self._VALID_URL, url).groups() + + webpage = self._download_webpage(url, lecture_slug) + + cfg = self._parse_json(self._search_regex( + [r'cfg\s*:\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*:\s*\(?\s*function', + r'cfg\s*:\s*({[^}]+})'], + webpage, 'cfg'), lecture_slug, js_to_json) + + lecture_id = compat_str(cfg['obj_id']) + + base_url = self._proto_relative_url(cfg['livepipe'], 'http:') + + lecture_data = self._download_json( + '%s/site/api/lecture/%s?format=json' % (base_url, lecture_id), + lecture_id)['lecture'][0] + + lecture_info = { + 'id': lecture_id, + 'display_id': lecture_slug, + 'title': lecture_data['title'], + 'timestamp': parse_iso8601(lecture_data.get('time')), + 'description': lecture_data.get('description_wiki'), + 'thumbnail': lecture_data.get('thumb'), + } + + playlist_entries = [] + lecture_type = lecture_data.get('type') + parts = [compat_str(video) for video in cfg.get('videos', [])] + if parts: + multipart = len(parts) > 1 + + def extract_part(part_id): + smil_url = '%s/%s/video/%s/smil.xml' % (base_url, lecture_slug, part_id) + smil = self._download_smil(smil_url, lecture_id) + info = self._parse_smil(smil, smil_url, lecture_id) + info['id'] = lecture_id if not multipart else '%s_part%s' % (lecture_id, part_id) + info['display_id'] = lecture_slug if not multipart else '%s_part%s' % (lecture_slug, part_id) + if multipart: + info['title'] += ' (Part %s)' % part_id + switch = smil.find('.//switch') + if switch is not None: + info['duration'] = parse_duration(switch.attrib.get('dur')) + item_info = lecture_info.copy() + item_info.update(info) + return item_info + + if explicit_part_id or not multipart: + result = extract_part(explicit_part_id or parts[0]) + else: + result = { + '_type': 'multi_video', + 'entries': [extract_part(part) for part in parts], + } + result.update(lecture_info) + + # Immediately return explicitly requested part or non event item + if explicit_part_id or lecture_type != 'evt': + return result + + playlist_entries.append(result) + + # It's probably a playlist + if not parts or lecture_type == 'evt': + playlist_webpage = self._download_webpage( + '%s/site/ajax/drilldown/?id=%s' % (base_url, lecture_id), lecture_id) + entries = [ + self.url_result(compat_urlparse.urljoin(url, video_url), 'Viidea') + for _, video_url in re.findall( + r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', playlist_webpage)] + playlist_entries.extend(entries) + + playlist = self.playlist_result(playlist_entries, lecture_id) + playlist.update(lecture_info) + return playlist diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 50df79ca1..b72341a2b 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -8,11 +8,11 @@ import itertools from .common import InfoExtractor from ..compat import ( compat_HTTPError, - compat_urllib_parse, compat_urllib_request, compat_urlparse, ) from ..utils import ( + encode_dict, ExtractorError, InAdvancePagedList, int_or_none, @@ -39,23 +39,31 @@ class VimeoBaseInfoExtractor(InfoExtractor): return self.report_login() webpage = self._download_webpage(self._LOGIN_URL, None, False) - token = self._extract_xsrft(webpage) - data = urlencode_postdata({ + token, vuid = self._extract_xsrft_and_vuid(webpage) + data = urlencode_postdata(encode_dict({ 'action': 'login', 'email': username, 'password': password, 'service': 'vimeo', 'token': token, - }) + })) login_request = compat_urllib_request.Request(self._LOGIN_URL, data) login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') login_request.add_header('Referer', self._LOGIN_URL) + self._set_vimeo_cookie('vuid', vuid) self._download_webpage(login_request, None, False, 'Wrong login info') - def _extract_xsrft(self, webpage): - return self._search_regex( + def _extract_xsrft_and_vuid(self, webpage): + xsrft = self._search_regex( r'xsrft\s*[=:]\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)', webpage, 'login token', group='xsrft') + vuid = self._search_regex( + r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1', + webpage, 'vuid', group='vuid') + return xsrft, vuid + + def _set_vimeo_cookie(self, name, value): + self._set_cookie('vimeo.com', name, value) class VimeoIE(VimeoBaseInfoExtractor): @@ -80,12 +88,12 @@ class VimeoIE(VimeoBaseInfoExtractor): 'info_dict': { 'id': '56015672', 'ext': 'mp4', - "upload_date": "20121220", - "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", - "uploader_id": "user7108434", - "uploader": "Filippo Valsorda", - "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", - "duration": 10, + 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", + 'description': 'md5:2d3305bad981a06ff79f027f19865021', + 'upload_date': '20121220', + 'uploader_id': 'user7108434', + 'uploader': 'Filippo Valsorda', + 'duration': 10, }, }, { @@ -98,7 +106,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'uploader_id': 'openstreetmapus', 'uploader': 'OpenStreetMap US', 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', - 'description': 'md5:380943ec71b89736ff4bf27183233d09', + 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30', 'duration': 1595, }, }, @@ -128,7 +136,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'uploader_id': 'user18948128', 'uploader': 'Jaime Marquínez Ferrándiz', 'duration': 10, - 'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people who love them.', + 'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people\u2026', }, 'params': { 'videopassword': 'youtube-dl', @@ -152,7 +160,6 @@ class VimeoIE(VimeoBaseInfoExtractor): }, { 'url': 'http://vimeo.com/76979871', - 'md5': '3363dd6ffebe3784d56f4132317fd446', 'note': 'Video with subtitles', 'info_dict': { 'id': '76979871', @@ -177,6 +184,11 @@ class VimeoIE(VimeoBaseInfoExtractor): 'uploader_id': 'user28849593', }, }, + { + 'url': 'https://vimeo.com/109815029', + 'note': 'Video not completely processed, "failed" seed status', + 'only_matching': True, + }, ] @staticmethod @@ -198,17 +210,18 @@ class VimeoIE(VimeoBaseInfoExtractor): password = self._downloader.params.get('videopassword', None) if password is None: raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) - token = self._extract_xsrft(webpage) - data = urlencode_postdata({ + token, vuid = self._extract_xsrft_and_vuid(webpage) + data = urlencode_postdata(encode_dict({ 'password': password, 'token': token, - }) + })) if url.startswith('http://'): # vimeo only supports https now, but the user can give an http url url = url.replace('http://', 'https://') password_request = compat_urllib_request.Request(url + '/password', data) password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') password_request.add_header('Referer', url) + self._set_vimeo_cookie('vuid', vuid) return self._download_webpage( password_request, video_id, 'Verifying the password', 'Wrong password') @@ -217,7 +230,7 @@ class VimeoIE(VimeoBaseInfoExtractor): password = self._downloader.params.get('videopassword', None) if password is None: raise ExtractorError('This video is protected by a password, use the --video-password option') - data = compat_urllib_parse.urlencode({'password': password}) + data = urlencode_postdata(encode_dict({'password': password})) pass_url = url + '/check-password' password_request = compat_urllib_request.Request(pass_url, data) password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') @@ -268,20 +281,30 @@ class VimeoIE(VimeoBaseInfoExtractor): self.report_extraction(video_id) vimeo_config = self._search_regex( - r'vimeo\.config\s*=\s*({.+?});', webpage, + r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage, 'vimeo config', default=None) if vimeo_config: seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {}) if seed_status.get('state') == 'failed': raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, seed_status['title']), + '%s said: %s' % (self.IE_NAME, seed_status['title']), expected=True) # Extract the config JSON try: try: config_url = self._html_search_regex( - r' data-config-url="(.+?)"', webpage, 'config URL') + r' data-config-url="(.+?)"', webpage, + 'config URL', default=None) + if not config_url: + # Sometimes new react-based page is served instead of old one that require + # different config URL extraction approach (see + # https://github.com/rg3/youtube-dl/pull/7209) + vimeo_clip_page_config = self._search_regex( + r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage, + 'vimeo clip page config') + config_url = self._parse_json( + vimeo_clip_page_config, video_id)['player']['config_url'] config_json = self._download_webpage(config_url, video_id) config = json.loads(config_json) except RegexNotFoundError: @@ -364,41 +387,29 @@ class VimeoIE(VimeoBaseInfoExtractor): like_count = None comment_count = None - # Vimeo specific: extract request signature and timestamp - sig = config['request']['signature'] - timestamp = config['request']['timestamp'] - - # Vimeo specific: extract video codec and quality information - # First consider quality, then codecs, then take everything - codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')] - files = {'hd': [], 'sd': [], 'other': []} - config_files = config["video"].get("files") or config["request"].get("files") - for codec_name, codec_extension in codecs: - for quality in config_files.get(codec_name, []): - format_id = '-'.join((codec_name, quality)).lower() - key = quality if quality in files else 'other' - video_url = None - if isinstance(config_files[codec_name], dict): - file_info = config_files[codec_name][quality] - video_url = file_info.get('url') - else: - file_info = {} - if video_url is None: - video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \ - % (video_id, sig, timestamp, quality, codec_name.upper()) - - files[key].append({ - 'ext': codec_extension, - 'url': video_url, - 'format_id': format_id, - 'width': file_info.get('width'), - 'height': file_info.get('height'), - }) formats = [] - for key in ('other', 'sd', 'hd'): - formats += files[key] - if len(formats) == 0: - raise ExtractorError('No known codec found') + config_files = config['video'].get('files') or config['request'].get('files', {}) + for f in config_files.get('progressive', []): + video_url = f.get('url') + if not video_url: + continue + formats.append({ + 'url': video_url, + 'format_id': 'http-%s' % f.get('quality'), + 'width': int_or_none(f.get('width')), + 'height': int_or_none(f.get('height')), + 'fps': int_or_none(f.get('fps')), + 'tbr': int_or_none(f.get('bitrate')), + }) + m3u8_url = config_files.get('hls', {}).get('url') + if m3u8_url: + m3u8_formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', 0, 'hls', fatal=False) + if m3u8_formats: + formats.extend(m3u8_formats) + # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps + # at the same time without actual units specified. This lead to wrong sorting. + self._sort_formats(formats, field_preference=('height', 'width', 'fps', 'format_id')) subtitles = {} text_tracks = config['request'].get('text_tracks') @@ -459,16 +470,17 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): if password is None: raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True) fields = self._hidden_inputs(login_form) - token = self._extract_xsrft(webpage) + token, vuid = self._extract_xsrft_and_vuid(webpage) fields['token'] = token fields['password'] = password - post = urlencode_postdata(fields) + post = urlencode_postdata(encode_dict(fields)) password_path = self._search_regex( r'action="([^"]+)"', login_form, 'password URL') password_url = compat_urlparse.urljoin(page_url, password_path) password_request = compat_urllib_request.Request(password_url, post) password_request.add_header('Content-type', 'application/x-www-form-urlencoded') - self._set_cookie('vimeo.com', 'xsrft', token) + self._set_vimeo_cookie('vuid', vuid) + self._set_vimeo_cookie('xsrft', token) return self._download_webpage( password_request, list_id, diff --git a/youtube_dl/extractor/vine.py b/youtube_dl/extractor/vine.py index c733a48fa..cb2a4b0b5 100644 --- a/youtube_dl/extractor/vine.py +++ b/youtube_dl/extractor/vine.py @@ -1,10 +1,14 @@ +# coding: utf-8 from __future__ import unicode_literals import re import itertools from .common import InfoExtractor -from ..utils import unified_strdate +from ..utils import ( + int_or_none, + unified_strdate, +) class VineIE(InfoExtractor): @@ -17,10 +21,12 @@ class VineIE(InfoExtractor): 'ext': 'mp4', 'title': 'Chicken.', 'alt_title': 'Vine by Jack Dorsey', - 'description': 'Chicken.', 'upload_date': '20130519', 'uploader': 'Jack Dorsey', 'uploader_id': '76', + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, }, { 'url': 'https://vine.co/v/MYxVapFvz2z', @@ -29,11 +35,13 @@ class VineIE(InfoExtractor): 'id': 'MYxVapFvz2z', 'ext': 'mp4', 'title': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14', - 'alt_title': 'Vine by Luna', - 'description': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14', + 'alt_title': 'Vine by Mars Ruiz', 'upload_date': '20140815', - 'uploader': 'Luna', + 'uploader': 'Mars Ruiz', 'uploader_id': '1102363502380728320', + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, }, { 'url': 'https://vine.co/v/bxVjBbZlPUH', @@ -43,14 +51,33 @@ class VineIE(InfoExtractor): 'ext': 'mp4', 'title': '#mw3 #ac130 #killcam #angelofdeath', 'alt_title': 'Vine by Z3k3', - 'description': '#mw3 #ac130 #killcam #angelofdeath', 'upload_date': '20130430', 'uploader': 'Z3k3', 'uploader_id': '936470460173008896', + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, }, { 'url': 'https://vine.co/oembed/MYxVapFvz2z.json', 'only_matching': True, + }, { + 'url': 'https://vine.co/v/e192BnZnZ9V', + 'info_dict': { + 'id': 'e192BnZnZ9V', + 'ext': 'mp4', + 'title': 'ยิ้ม~ เขิน~ อาย~ น่าร้ากอ้ะ >//< @n_whitewo @orlameena #lovesicktheseries #lovesickseason2', + 'alt_title': 'Vine by Pimry_zaa', + 'upload_date': '20150705', + 'uploader': 'Pimry_zaa', + 'uploader_id': '1135760698325307392', + 'like_count': int, + 'comment_count': int, + 'repost_count': int, + }, + 'params': { + 'skip_download': True, + }, }] def _real_extract(self, url): @@ -58,32 +85,33 @@ class VineIE(InfoExtractor): webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id) data = self._parse_json( - self._html_search_regex( - r'window\.POST_DATA = { %s: ({.+?}) };\s*</script>' % video_id, + self._search_regex( + r'window\.POST_DATA\s*=\s*{\s*%s\s*:\s*({.+?})\s*};\s*</script>' % video_id, webpage, 'vine data'), video_id) formats = [{ 'format_id': '%(format)s-%(rate)s' % f, - 'vcodec': f['format'], - 'quality': f['rate'], + 'vcodec': f.get('format'), + 'quality': f.get('rate'), 'url': f['videoUrl'], - } for f in data['videoUrls']] + } for f in data['videoUrls'] if f.get('videoUrl')] self._sort_formats(formats) + username = data.get('username') + return { 'id': video_id, - 'title': self._og_search_title(webpage), - 'alt_title': self._og_search_description(webpage, default=None), - 'description': data['description'], - 'thumbnail': data['thumbnailUrl'], - 'upload_date': unified_strdate(data['created']), - 'uploader': data['username'], - 'uploader_id': data['userIdStr'], - 'like_count': data['likes']['count'], - 'comment_count': data['comments']['count'], - 'repost_count': data['reposts']['count'], + 'title': data.get('description') or self._og_search_title(webpage), + 'alt_title': 'Vine by %s' % username if username else self._og_search_description(webpage, default=None), + 'thumbnail': data.get('thumbnailUrl'), + 'upload_date': unified_strdate(data.get('created')), + 'uploader': username, + 'uploader_id': data.get('userIdStr'), + 'like_count': int_or_none(data.get('likes', {}).get('count')), + 'comment_count': int_or_none(data.get('comments', {}).get('count')), + 'repost_count': int_or_none(data.get('reposts', {}).get('count')), 'formats': formats, } diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index c30c5a8e5..01960b827 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -17,6 +17,7 @@ from ..utils import ( unescapeHTML, unified_strdate, ) +from .vimeo import VimeoIE class VKIE(InfoExtractor): @@ -249,6 +250,10 @@ class VKIE(InfoExtractor): if youtube_url: return self.url_result(youtube_url, 'Youtube') + vimeo_url = VimeoIE._extract_vimeo_url(url, info_page) + if vimeo_url is not None: + return self.url_result(vimeo_url) + m_rutube = re.search( r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page) if m_rutube is not None: @@ -276,9 +281,13 @@ class VKIE(InfoExtractor): mobj.group(1) + ' ' + mobj.group(2) upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2)) - view_count = str_to_int(self._search_regex( - r'"mv_views_count_number"[^>]*>([\d,.]+) views<', - info_page, 'view count', fatal=False)) + view_count = None + views = self._html_search_regex( + r'"mv_views_count_number"[^>]*>(.+?\bviews?)<', + info_page, 'view count', fatal=False) + if views: + view_count = str_to_int(self._search_regex( + r'([\d,.]+)', views, 'view count', fatal=False)) formats = [{ 'format_id': k, diff --git a/youtube_dl/extractor/wsj.py b/youtube_dl/extractor/wsj.py index 2ddf29a69..5a897371d 100644 --- a/youtube_dl/extractor/wsj.py +++ b/youtube_dl/extractor/wsj.py @@ -84,6 +84,5 @@ class WSJIE(InfoExtractor): 'duration': duration, 'upload_date': upload_date, 'title': title, - 'formats': formats, 'categories': categories, } diff --git a/youtube_dl/extractor/xfileshare.py b/youtube_dl/extractor/xfileshare.py new file mode 100644 index 000000000..7610dc627 --- /dev/null +++ b/youtube_dl/extractor/xfileshare.py @@ -0,0 +1,138 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, +) +from ..utils import ( + ExtractorError, + encode_dict, + int_or_none, +) + + +class XFileShareIE(InfoExtractor): + IE_DESC = 'XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me' + _VALID_URL = r'''(?x) + https?://(?P<host>(?:www\.)? + (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com|vidto.\me))/ + (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)? + ''' + + _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<' + + _TESTS = [{ + 'url': 'http://gorillavid.in/06y9juieqpmi', + 'md5': '5ae4a3580620380619678ee4875893ba', + 'info_dict': { + 'id': '06y9juieqpmi', + 'ext': 'flv', + 'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html', + 'only_matching': True, + }, { + 'url': 'http://daclips.in/3rso4kdn6f9m', + 'md5': '1ad8fd39bb976eeb66004d3a4895f106', + 'info_dict': { + 'id': '3rso4kdn6f9m', + 'ext': 'mp4', + 'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc', + 'thumbnail': 're:http://.*\.jpg', + } + }, { + # video with countdown timeout + 'url': 'http://fastvideo.in/1qmdn1lmsmbw', + 'md5': '8b87ec3f6564a3108a0e8e66594842ba', + 'info_dict': { + 'id': '1qmdn1lmsmbw', + 'ext': 'mp4', + 'title': 'Man of Steel - Trailer', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://realvid.net/ctn2y6p2eviw', + 'md5': 'b2166d2cf192efd6b6d764c18fd3710e', + 'info_dict': { + 'id': 'ctn2y6p2eviw', + 'ext': 'flv', + 'title': 'rdx 1955', + 'thumbnail': 're:http://.*\.jpg', + }, + }, { + 'url': 'http://movpod.in/0wguyyxi1yca', + 'only_matching': True, + }, { + 'url': 'http://filehoot.com/3ivfabn7573c.html', + 'info_dict': { + 'id': '3ivfabn7573c', + 'ext': 'mp4', + 'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4', + 'thumbnail': 're:http://.*\.jpg', + } + }, { + 'url': 'http://vidto.me/ku5glz52nqe1.html', + 'info_dict': { + 'id': 'ku5glz52nqe1', + 'ext': 'mp4', + 'title': 'test' + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://%s/%s' % (mobj.group('host'), video_id) + webpage = self._download_webpage(url, video_id) + + if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + + fields = self._hidden_inputs(webpage) + + if fields['op'] == 'download1': + countdown = int_or_none(self._search_regex( + r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>', + webpage, 'countdown', default=None)) + if countdown: + self._sleep(countdown, video_id) + + post = compat_urllib_parse.urlencode(encode_dict(fields)) + + req = compat_urllib_request.Request(url, post) + req.add_header('Content-type', 'application/x-www-form-urlencoded') + + webpage = self._download_webpage(req, video_id, 'Downloading video page') + + title = (self._search_regex( + [r'style="z-index: [0-9]+;">([^<]+)</span>', + r'<td nowrap>([^<]+)</td>', + r'>Watch (.+) ', + r'<h2 class="video-page-head">([^<]+)</h2>'], + webpage, 'title', default=None) or self._og_search_title(webpage)).strip() + video_url = self._search_regex( + [r'file\s*:\s*["\'](http[^"\']+)["\'],', + r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'], + webpage, 'file url') + thumbnail = self._search_regex( + r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None) + + formats = [{ + 'format_id': 'sd', + 'url': video_url, + 'quality': 1, + }] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 97315750f..8938c0e45 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -63,7 +63,9 @@ class XHamsterIE(InfoExtractor): mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo) webpage = self._download_webpage(mrss_url, video_id) - title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com', webpage, 'title') + title = self._html_search_regex( + [r'(?P<title>.+?)(?:, (?:[^,]+? )?Porn: xHamster| - xHamster\.com)', + r'

    ([^<]+)

    '], webpage, 'title') # Only a few videos have an description mobj = re.search(r'Description: ([^<]+)', webpage) diff --git a/youtube_dl/extractor/yandexmusic.py b/youtube_dl/extractor/yandexmusic.py index 4098e4629..08dc81f3a 100644 --- a/youtube_dl/extractor/yandexmusic.py +++ b/youtube_dl/extractor/yandexmusic.py @@ -46,6 +46,12 @@ class YandexMusicTrackIE(InfoExtractor): % (data['host'], key, data['ts'] + data['path'], storage[1])) def _get_track_info(self, track): + thumbnail = None + cover_uri = track.get('albums', [{}])[0].get('coverUri') + if cover_uri: + thumbnail = cover_uri.replace('%%', 'orig') + if not thumbnail.startswith('http'): + thumbnail = 'http://' + thumbnail return { 'id': track['id'], 'ext': 'mp3', @@ -53,6 +59,7 @@ class YandexMusicTrackIE(InfoExtractor): 'title': '%s - %s' % (track['artists'][0]['name'], track['title']), 'filesize': int_or_none(track.get('fileSize')), 'duration': float_or_none(track.get('durationMs'), 1000), + 'thumbnail': thumbnail, } def _real_extract(self, url): diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index 4ba7c36db..9bf8d1eeb 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -1,121 +1,171 @@ from __future__ import unicode_literals - -import json import re -import sys from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_urlparse, - compat_urllib_request, -) +from ..compat import compat_urllib_request from ..utils import ( - ExtractorError, + int_or_none, + str_to_int, unescapeHTML, unified_strdate, ) -from ..aes import ( - aes_decrypt_text -) +from ..aes import aes_decrypt_text class YouPornIE(InfoExtractor): - _VALID_URL = r'^(?Phttps?://)(?:www\.)?(?Pyouporn\.com/watch/(?P[0-9]+)/(?P[^/]+))' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)' + _TESTS = [{ 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', + 'md5': '71ec5fcfddacf80f495efa8b6a8d9a89', 'info_dict': { 'id': '505835', + 'display_id': 'sex-ed-is-it-safe-to-masturbate-daily', 'ext': 'mp4', - 'upload_date': '20101221', + 'title': 'Sex Ed: Is It Safe To Masturbate Daily?', 'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?', + 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': 'Ask Dan And Jennifer', - 'title': 'Sex Ed: Is It Safe To Masturbate Daily?', + 'upload_date': '20101221', + 'average_rating': int, + 'view_count': int, + 'comment_count': int, + 'categories': list, + 'tags': list, 'age_limit': 18, - } - } + }, + }, { + # Anonymous User uploader + 'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4', + 'info_dict': { + 'id': '561726', + 'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show', + 'ext': 'mp4', + 'title': 'Big Tits Awesome Brunette On amazing webcam show', + 'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'Anonymous User', + 'upload_date': '20111125', + 'average_rating': int, + 'view_count': int, + 'comment_count': int, + 'categories': list, + 'tags': list, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + }, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - url = mobj.group('proto') + 'www.' + mobj.group('url') + video_id = mobj.group('id') + display_id = mobj.group('display_id') - req = compat_urllib_request.Request(url) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) - age_limit = self._rta_search(webpage) + request = compat_urllib_request.Request(url) + request.add_header('Cookie', 'age_verified=1') + webpage = self._download_webpage(request, display_id) + + title = self._search_regex( + [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>.+?)\1', + r'<h1[^>]+class=["\']heading\d?["\'][^>]*>([^<])<'], + webpage, 'title', group='title') - # Get JSON parameters - json_params = self._search_regex( - [r'videoJa?son\s*=\s*({.+})', - r'var\s+currentVideo\s*=\s*new\s+Video\((.+?)\)[,;]'], - webpage, 'JSON parameters') - try: - params = json.loads(json_params) - except ValueError: - raise ExtractorError('Invalid JSON') - - self.report_extraction(video_id) - try: - video_title = params['title'] - upload_date = unified_strdate(params['release_date_f']) - video_description = params['description'] - video_uploader = params['submitted_by'] - thumbnail = params['thumbnails'][0]['image'] - except KeyError: - raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1]) - - # Get all of the links from the page - DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' - download_list_html = self._search_regex(DOWNLOAD_LIST_RE, - webpage, 'download list').strip() - LINK_RE = r'<a href="([^"]+)">' - links = re.findall(LINK_RE, download_list_html) - - # Get all encrypted links - encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage) - for encrypted_link in encrypted_links: - link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8') + links = [] + + sources = self._search_regex( + r'sources\s*:\s*({.+?})', webpage, 'sources', default=None) + if sources: + for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources): + links.append(link) + + # Fallback #1 + for _, link in re.findall( + r'(?:videoUrl|videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage): + links.append(link) + + # Fallback #2, this also contains extra low quality 180p format + for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage): links.append(link) + # Fallback #3, encrypted links + for _, encrypted_link in re.findall( + r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage): + links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8')) + formats = [] - for link in links: - # A link looks like this: - # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0 - # A path looks like this: - # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4 - video_url = unescapeHTML(link) - path = compat_urllib_parse_urlparse(video_url).path - format_parts = path.split('/')[4].split('_')[:2] - - dn = compat_urllib_parse_urlparse(video_url).netloc.partition('.')[0] - - resolution = format_parts[0] - height = int(resolution[:-len('p')]) - bitrate = int(format_parts[1][:-len('k')]) - format = '-'.join(format_parts) + '-' + dn - - formats.append({ + for video_url in set(unescapeHTML(link) for link in links): + f = { 'url': video_url, - 'format': format, - 'format_id': format, - 'height': height, - 'tbr': bitrate, - 'resolution': resolution, - }) - + } + # Video URL's path looks like this: + # /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4 + # We will benefit from it by extracting some metadata + mobj = re.search(r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url) + if mobj: + height = int(mobj.group('height')) + bitrate = int(mobj.group('bitrate')) + f.update({ + 'format_id': '%dp-%dk' % (height, bitrate), + 'height': height, + 'tbr': bitrate, + }) + formats.append(f) self._sort_formats(formats) - if not formats: - raise ExtractorError('ERROR: no known formats available for video') + description = self._html_search_regex( + r'(?s)<div[^>]+class=["\']video-description["\'][^>]*>(.+?)</div>', + webpage, 'description', default=None) + thumbnail = self._search_regex( + r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1', + webpage, 'thumbnail', fatal=False, group='thumbnail') + + uploader = self._html_search_regex( + r'(?s)<div[^>]+class=["\']videoInfoBy["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>', + webpage, 'uploader', fatal=False) + upload_date = unified_strdate(self._html_search_regex( + r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</div>', + webpage, 'upload date', fatal=False)) + + age_limit = self._rta_search(webpage) + + average_rating = int_or_none(self._search_regex( + r'<div[^>]+class=["\']videoInfoRating["\'][^>]*>\s*<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>', + webpage, 'average rating', fatal=False)) + + view_count = str_to_int(self._search_regex( + r'(?s)<div[^>]+class=["\']videoInfoViews["\'][^>]*>.*?([\d,.]+)\s*</div>', + webpage, 'view count', fatal=False)) + comment_count = str_to_int(self._search_regex( + r'>All [Cc]omments? \(([\d,.]+)\)', + webpage, 'comment count', fatal=False)) + + def extract_tag_box(title): + tag_box = self._search_regex( + (r'<div[^>]+class=["\']tagBoxTitle["\'][^>]*>\s*%s\b.*?</div>\s*' + '<div[^>]+class=["\']tagBoxContent["\']>(.+?)</div>') % re.escape(title), + webpage, '%s tag box' % title, default=None) + if not tag_box: + return [] + return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box) + + categories = extract_tag_box('Category') + tags = extract_tag_box('Tags') return { 'id': video_id, - 'uploader': video_uploader, - 'upload_date': upload_date, - 'title': video_title, + 'display_id': display_id, + 'title': title, + 'description': description, 'thumbnail': thumbnail, - 'description': video_description, + 'uploader': uploader, + 'upload_date': upload_date, + 'average_rating': average_rating, + 'view_count': view_count, + 'comment_count': comment_count, + 'categories': categories, + 'tags': tags, 'age_limit': age_limit, 'formats': formats, } diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 97ce36550..687e0b4db 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -178,6 +178,52 @@ class YoutubeBaseInfoExtractor(InfoExtractor): return +class YoutubePlaylistBaseInfoExtractor(InfoExtractor): + # Extract the video ids from the playlist pages + def _entries(self, page, playlist_id): + more_widget_html = content_html = page + for page_num in itertools.count(1): + for video_id, video_title in self.extract_videos_from_page(content_html): + yield self.url_result( + video_id, 'Youtube', video_id=video_id, + video_title=video_title) + + mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) + if not mobj: + break + + more = self._download_json( + 'https://youtube.com/%s' % mobj.group('more'), playlist_id, + 'Downloading page #%s' % page_num, + transform_source=uppercase_escape) + content_html = more['content_html'] + if not content_html.strip(): + # Some webpages show a "Load more" button but they don't + # have more videos + break + more_widget_html = more['load_more_widget_html'] + + def extract_videos_from_page(self, page): + ids_in_page = [] + titles_in_page = [] + for mobj in re.finditer(self._VIDEO_RE, page): + # The link with index 0 is not the first video of the playlist (not sure if still actual) + if 'index' in mobj.groupdict() and mobj.group('id') == '0': + continue + video_id = mobj.group('id') + video_title = unescapeHTML(mobj.group('title')) + if video_title: + video_title = video_title.strip() + try: + idx = ids_in_page.index(video_id) + if video_title and not titles_in_page[idx]: + titles_in_page[idx] = video_title + except ValueError: + ids_in_page.append(video_id) + titles_in_page.append(video_title) + return zip(ids_in_page, titles_in_page) + + class YoutubeIE(YoutubeBaseInfoExtractor): IE_DESC = 'YouTube.com' _VALID_URL = r"""(?x)^ @@ -657,7 +703,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _extract_signature_function(self, video_id, player_url, example_sig): id_m = re.match( - r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?)?\.(?P<ext>[a-z]+)$', + r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$', player_url) if not id_m: raise ExtractorError('Cannot identify player %r' % player_url) @@ -1061,6 +1107,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if not video_info: video_info = get_video_info if 'token' in get_video_info: + # Different get_video_info requests may report different results, e.g. + # some may report video unavailability, but some may serve it without + # any complaint (see https://github.com/rg3/youtube-dl/issues/7362, + # the original webpage as well as el=info and el=embedded get_video_info + # requests report video unavailability due to geo restriction while + # el=detailpage succeeds and returns valid data). This is probably + # due to YouTube measures against IP ranges of hosting providers. + # Working around by preferring the first succeeded video_info containing + # the token if no such video_info yet was found. + if 'token' not in video_info: + video_info = get_video_info break if 'token' not in video_info: if 'reason' in video_info: @@ -1286,7 +1343,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): player_desc = 'flash player %s' % player_version else: player_version = self._search_regex( - r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', + [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'], player_url, 'html5 player', fatal=False) player_desc = 'html5 player %s' % player_version @@ -1419,7 +1476,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): } -class YoutubePlaylistIE(YoutubeBaseInfoExtractor): +class YoutubePlaylistIE(YoutubeBaseInfoExtractor, YoutubePlaylistBaseInfoExtractor): IE_DESC = 'YouTube.com playlists' _VALID_URL = r"""(?x)(?: (?:https?://)? @@ -1440,7 +1497,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,}) )""" _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' - _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)' + _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?' IE_NAME = 'youtube:playlist' _TESTS = [{ 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', @@ -1557,37 +1614,11 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): else: self.report_warning('Youtube gives an alert message: ' + match) - # Extract the video ids from the playlist pages - def _entries(): - more_widget_html = content_html = page - for page_num in itertools.count(1): - matches = re.finditer(self._VIDEO_RE, content_html) - # We remove the duplicates and the link with index 0 - # (it's not the first video of the playlist) - new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0') - for vid_id in new_ids: - yield self.url_result(vid_id, 'Youtube', video_id=vid_id) - - mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) - if not mobj: - break - - more = self._download_json( - 'https://youtube.com/%s' % mobj.group('more'), playlist_id, - 'Downloading page #%s' % page_num, - transform_source=uppercase_escape) - content_html = more['content_html'] - if not content_html.strip(): - # Some webpages show a "Load more" button but they don't - # have more videos - break - more_widget_html = more['load_more_widget_html'] - playlist_title = self._html_search_regex( r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>', page, 'title') - return self.playlist_result(_entries(), playlist_id, playlist_title) + return self.playlist_result(self._entries(page, playlist_id), playlist_id, playlist_title) def _real_extract(self, url): # Extract playlist id @@ -1613,36 +1644,31 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): return self._extract_playlist(playlist_id) -class YoutubeChannelIE(InfoExtractor): +class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): IE_DESC = 'YouTube.com channels' _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)' _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos' + _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?' IE_NAME = 'youtube:channel' _TESTS = [{ 'note': 'paginated channel', 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', 'playlist_mincount': 91, 'info_dict': { - 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', + 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w', + 'title': 'Uploads from lex will', } + }, { + 'note': 'Age restricted channel', + # from https://www.youtube.com/user/DeusExOfficial + 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w', + 'playlist_mincount': 64, + 'info_dict': { + 'id': 'UUs0ifCMCm1icqRbqhUINa0w', + 'title': 'Uploads from Deus Ex', + }, }] - @staticmethod - def extract_videos_from_page(page): - ids_in_page = [] - titles_in_page = [] - for mobj in re.finditer(r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?', page): - video_id = mobj.group('id') - video_title = unescapeHTML(mobj.group('title')) - try: - idx = ids_in_page.index(video_id) - if video_title and not titles_in_page[idx]: - titles_in_page[idx] = video_title - except ValueError: - ids_in_page.append(video_id) - titles_in_page.append(video_title) - return zip(ids_in_page, titles_in_page) - def _real_extract(self, url): channel_id = self._match_id(url) @@ -1654,12 +1680,15 @@ class YoutubeChannelIE(InfoExtractor): channel_page = self._download_webpage( url + '?view=57', channel_id, 'Downloading channel page', fatal=False) - channel_playlist_id = self._html_search_meta( - 'channelId', channel_page, 'channel id', default=None) - if not channel_playlist_id: - channel_playlist_id = self._search_regex( - r'data-channel-external-id="([^"]+)"', - channel_page, 'channel id', default=None) + if channel_page is False: + channel_playlist_id = False + else: + channel_playlist_id = self._html_search_meta( + 'channelId', channel_page, 'channel id', default=None) + if not channel_playlist_id: + channel_playlist_id = self._search_regex( + r'data-(?:channel-external-|yt)id="([^"]+)"', + channel_page, 'channel id', default=None) if channel_playlist_id and channel_playlist_id.startswith('UC'): playlist_id = 'UU' + channel_playlist_id[2:] return self.url_result( @@ -1682,29 +1711,7 @@ class YoutubeChannelIE(InfoExtractor): for video_id, video_title in self.extract_videos_from_page(channel_page)] return self.playlist_result(entries, channel_id) - def _entries(): - more_widget_html = content_html = channel_page - for pagenum in itertools.count(1): - - for video_id, video_title in self.extract_videos_from_page(content_html): - yield self.url_result( - video_id, 'Youtube', video_id=video_id, - video_title=video_title) - - mobj = re.search( - r'data-uix-load-more-href="/?(?P<more>[^"]+)"', - more_widget_html) - if not mobj: - break - - more = self._download_json( - 'https://youtube.com/%s' % mobj.group('more'), channel_id, - 'Downloading page #%s' % (pagenum + 1), - transform_source=uppercase_escape) - content_html = more['content_html'] - more_widget_html = more['load_more_widget_html'] - - return self.playlist_result(_entries(), channel_id) + return self.playlist_result(self._entries(channel_page, channel_id), channel_id) class YoutubeUserIE(YoutubeChannelIE): @@ -1970,6 +1977,7 @@ class YoutubeTruncatedURLIE(InfoExtractor): annotation_id=annotation_[^&]+| x-yt-cl=[0-9]+| hl=[^&]*| + t=[0-9]+ )? | attribution_link\?a=[^&]+ @@ -1992,6 +2000,9 @@ class YoutubeTruncatedURLIE(InfoExtractor): }, { 'url': 'https://www.youtube.com/watch?hl=en-GB', 'only_matching': True, + }, { + 'url': 'https://www.youtube.com/watch?t=2372', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index 98f15177b..a795f56b3 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -9,6 +9,7 @@ from ..utils import ( int_or_none, unified_strdate, OnDemandPagedList, + xpath_text, ) @@ -19,13 +20,11 @@ def extract_from_xml_url(ie, video_id, xml_url): errnote='Failed to download video info') title = doc.find('.//information/title').text - description = doc.find('.//information/detail').text - duration = int(doc.find('.//details/lengthSec').text) - uploader_node = doc.find('.//details/originChannelTitle') - uploader = None if uploader_node is None else uploader_node.text - uploader_id_node = doc.find('.//details/originChannelId') - uploader_id = None if uploader_id_node is None else uploader_id_node.text - upload_date = unified_strdate(doc.find('.//details/airtime').text) + description = xpath_text(doc, './/information/detail', 'description') + duration = int_or_none(xpath_text(doc, './/details/lengthSec', 'duration')) + uploader = xpath_text(doc, './/details/originChannelTitle', 'uploader') + uploader_id = xpath_text(doc, './/details/originChannelId', 'uploader id') + upload_date = unified_strdate(xpath_text(doc, './/details/airtime', 'upload date')) def xml_to_format(fnode): video_url = fnode.find('url').text @@ -40,15 +39,14 @@ def extract_from_xml_url(ie, video_id, xml_url): ext = format_m.group('container') proto = format_m.group('proto').lower() - quality = fnode.find('./quality').text - abr = int(fnode.find('./audioBitrate').text) // 1000 - vbr_node = fnode.find('./videoBitrate') - vbr = None if vbr_node is None else int(vbr_node.text) // 1000 + quality = xpath_text(fnode, './quality', 'quality') + abr = int_or_none(xpath_text(fnode, './audioBitrate', 'abr'), 1000) + vbr = int_or_none(xpath_text(fnode, './videoBitrate', 'vbr'), 1000) - width_node = fnode.find('./width') - width = None if width_node is None else int_or_none(width_node.text) - height_node = fnode.find('./height') - height = None if height_node is None else int_or_none(height_node.text) + width = int_or_none(xpath_text(fnode, './width', 'width')) + height = int_or_none(xpath_text(fnode, './height', 'height')) + + filesize = int_or_none(xpath_text(fnode, './filesize', 'filesize')) format_note = '' if not format_note: @@ -64,12 +62,31 @@ def extract_from_xml_url(ie, video_id, xml_url): 'vbr': vbr, 'width': width, 'height': height, - 'filesize': int_or_none(fnode.find('./filesize').text), + 'filesize': filesize, 'format_note': format_note, 'protocol': proto, '_available': is_available, } + def xml_to_thumbnails(fnode): + thumbnails = [] + for node in fnode: + thumbnail_url = node.text + if not thumbnail_url: + continue + thumbnail = { + 'url': thumbnail_url, + } + if 'key' in node.attrib: + m = re.match('^([0-9]+)x([0-9]+)$', node.attrib['key']) + if m: + thumbnail['width'] = int(m.group(1)) + thumbnail['height'] = int(m.group(2)) + thumbnails.append(thumbnail) + return thumbnails + + thumbnails = xml_to_thumbnails(doc.findall('.//teaserimages/teaserimage')) + format_nodes = doc.findall('.//formitaeten/formitaet') formats = list(filter( lambda f: f['_available'], @@ -81,6 +98,7 @@ def extract_from_xml_url(ie, video_id, xml_url): 'title': title, 'description': description, 'duration': duration, + 'thumbnails': thumbnails, 'uploader': uploader, 'uploader_id': uploader_id, 'upload_date': upload_date, diff --git a/youtube_dl/extractor/zingmp3.py b/youtube_dl/extractor/zingmp3.py index 7dc1e2f2b..437eecb67 100644 --- a/youtube_dl/extractor/zingmp3.py +++ b/youtube_dl/extractor/zingmp3.py @@ -9,9 +9,11 @@ from ..utils import ExtractorError class ZingMp3BaseInfoExtractor(InfoExtractor): - def _extract_item(self, item): + def _extract_item(self, item, fatal=True): error_message = item.find('./errormessage').text if error_message: + if not fatal: + return raise ExtractorError( '%s returned error: %s' % (self.IE_NAME, error_message), expected=True) @@ -43,7 +45,9 @@ class ZingMp3BaseInfoExtractor(InfoExtractor): entries = [] for i, item in enumerate(items, 1): - entry = self._extract_item(item) + entry = self._extract_item(item, fatal=False) + if not entry: + continue entry['id'] = '%s-%d' % (id, i) entries.append(entry) @@ -85,7 +89,7 @@ class ZingMp3SongIE(ZingMp3BaseInfoExtractor): class ZingMp3AlbumIE(ZingMp3BaseInfoExtractor): - _VALID_URL = r'https?://mp3\.zing\.vn/album/(?P<slug>[^/]+)/(?P<album_id>\w+)\.html' + _VALID_URL = r'https?://mp3\.zing\.vn/(?:album|playlist)/(?P<slug>[^/]+)/(?P<album_id>\w+)\.html' _TESTS = [{ 'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html', 'info_dict': { @@ -94,6 +98,9 @@ class ZingMp3AlbumIE(ZingMp3BaseInfoExtractor): 'title': 'Lâu Đài Tình Ái - Bằng Kiều ft. Minh Tuyết | Album 320 lossless', }, 'playlist_count': 10, + }, { + 'url': 'http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html', + 'only_matching': True, }] IE_NAME = 'zingmp3:album' IE_DESC = 'mp3.zing.vn albums' diff --git a/youtube_dl/jsinterp.py b/youtube_dl/jsinterp.py index 0e0c7d90d..9bc855144 100644 --- a/youtube_dl/jsinterp.py +++ b/youtube_dl/jsinterp.py @@ -232,10 +232,10 @@ class JSInterpreter(object): def extract_function(self, funcname): func_m = re.search( r'''(?x) - (?:function\s+%s|[{;]%s\s*=\s*function)\s* + (?:function\s+%s|[{;]%s\s*=\s*function|var\s+%s\s*=\s*function)\s* \((?P<args>[^)]*)\)\s* \{(?P<code>[^}]+)\}''' % ( - re.escape(funcname), re.escape(funcname)), + re.escape(funcname), re.escape(funcname), re.escape(funcname)), self.code) if func_m is None: raise ExtractorError('Could not find JS function %r' % funcname) diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 5eccc0a70..3dd6d290b 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -276,7 +276,7 @@ def parseOpts(overrideArguments=None): 'For example, to only match videos that have been liked more than ' '100 times and disliked less than 50 times (or the dislike ' 'functionality is not available at the given service), but who ' - 'also have a description, use --match-filter ' + 'also have a description, use --match-filter ' '"like_count > 100 & dislike_count <? 50 & description" .' )) selection.add_option( @@ -602,7 +602,7 @@ def parseOpts(overrideArguments=None): filesystem.add_option( '-A', '--auto-number', action='store_true', dest='autonumber', default=False, - help='[deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] Number downloaded files starting from 00000') + help='[deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] Number downloaded files starting from 00000') filesystem.add_option( '-t', '--title', action='store_true', dest='usetitle', default=False, diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 1f723908b..5ed723bc6 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -135,7 +135,10 @@ class FFmpegPostProcessor(PostProcessor): files_cmd = [] for path in input_paths: - files_cmd.extend([encodeArgument('-i'), encodeFilename(path, True)]) + files_cmd.extend([ + encodeArgument('-i'), + encodeFilename(self._ffmpeg_filename_argument(path), True) + ]) cmd = ([encodeFilename(self.executable, True), encodeArgument('-y')] + files_cmd + [encodeArgument(o) for o in opts] + @@ -155,10 +158,10 @@ class FFmpegPostProcessor(PostProcessor): self.run_ffmpeg_multiple_files([path], out_path, opts) def _ffmpeg_filename_argument(self, fn): - # ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details - if fn.startswith('-'): - return './' + fn - return fn + # Always use 'file:' because the filename may contain ':' (ffmpeg + # interprets that as a protocol) or can start with '-' (-- is broken in + # ffmpeg, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details) + return 'file:' + fn class FFmpegExtractAudioPP(FFmpegPostProcessor): @@ -269,7 +272,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor): return [], information try: - self._downloader.to_screen('[' + self.basename + '] Destination: ' + new_path) + self._downloader.to_screen('[ffmpeg] Destination: ' + new_path) self.run_ffmpeg(path, new_path, acodec, more_opts) except AudioConversionError as e: raise PostProcessingError( diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 518cea98b..65556d056 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals +import base64 import calendar import codecs import contextlib @@ -35,6 +36,7 @@ import zlib from .compat import ( compat_basestring, compat_chr, + compat_etree_fromstring, compat_html_entities, compat_http_client, compat_kwargs, @@ -177,10 +179,19 @@ def xpath_with_ns(path, ns_map): def xpath_element(node, xpath, name=None, fatal=False, default=NO_DEFAULT): - if sys.version_info < (2, 7): # Crazy 2.6 - xpath = xpath.encode('ascii') + def _find_xpath(xpath): + if sys.version_info < (2, 7): # Crazy 2.6 + xpath = xpath.encode('ascii') + return node.find(xpath) + + if isinstance(xpath, (str, compat_str)): + n = _find_xpath(xpath) + else: + for xp in xpath: + n = _find_xpath(xp) + if n is not None: + break - n = node.find(xpath) if n is None: if default is not NO_DEFAULT: return default @@ -364,7 +375,7 @@ def sanitize_path(s): if drive_or_unc: norm_path.pop(0) sanitized_path = [ - path_part if path_part in ['.', '..'] else re.sub('(?:[/<>:"\\|\\\\?\\*]|\.$)', '#', path_part) + path_part if path_part in ['.', '..'] else re.sub('(?:[/<>:"\\|\\\\?\\*]|[\s.]$)', '#', path_part) for path_part in norm_path] if drive_or_unc: sanitized_path.insert(0, drive_or_unc + os.path.sep) @@ -628,7 +639,7 @@ def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs): # expected HTTP responses to meet HTTP/1.0 or later (see also # https://github.com/rg3/youtube-dl/issues/6727) if sys.version_info < (3, 0): - kwargs['strict'] = True + kwargs[b'strict'] = True hc = http_class(*args, **kwargs) source_address = ydl_handler._params.get('source_address') if source_address is not None: @@ -822,9 +833,11 @@ def parse_iso8601(date_str, delimiter='T', timezone=None): if date_str is None: return None + date_str = re.sub(r'\.[0-9]+', '', date_str) + if timezone is None: m = re.search( - r'(\.[0-9]+)?(?:Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)', + r'(?:Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)', date_str) if not m: timezone = datetime.timedelta() @@ -837,9 +850,12 @@ def parse_iso8601(date_str, delimiter='T', timezone=None): timezone = datetime.timedelta( hours=sign * int(m.group('hours')), minutes=sign * int(m.group('minutes'))) - date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter) - dt = datetime.datetime.strptime(date_str, date_format) - timezone - return calendar.timegm(dt.timetuple()) + try: + date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter) + dt = datetime.datetime.strptime(date_str, date_format) - timezone + return calendar.timegm(dt.timetuple()) + except ValueError: + pass def unified_strdate(date_str, day_first=True): @@ -904,7 +920,8 @@ def unified_strdate(date_str, day_first=True): timetuple = email.utils.parsedate_tz(date_str) if timetuple: upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d') - return upload_date + if upload_date is not None: + return compat_str(upload_date) def determine_ext(url, default_ext='unknown_video'): @@ -1380,7 +1397,12 @@ def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1): v = getattr(v, get_attr, None) if v == '': v = None - return default if v is None else (int(v) * invscale // scale) + if v is None: + return default + try: + return int(v) * invscale // scale + except ValueError: + return default def str_or_none(v, default=None): @@ -1396,7 +1418,12 @@ def str_to_int(int_str): def float_or_none(v, scale=1, invscale=1, default=None): - return default if v is None else (float(v) * invscale / scale) + if v is None: + return default + try: + return float(v) * invscale / scale + except ValueError: + return default def parse_duration(s): @@ -1649,29 +1676,6 @@ def encode_dict(d, encoding='utf-8'): return dict((k.encode(encoding), v.encode(encoding)) for k, v in d.items()) -try: - etree_iter = xml.etree.ElementTree.Element.iter -except AttributeError: # Python <=2.6 - etree_iter = lambda n: n.findall('.//*') - - -def parse_xml(s): - class TreeBuilder(xml.etree.ElementTree.TreeBuilder): - def doctype(self, name, pubid, system): - pass # Ignore doctypes - - parser = xml.etree.ElementTree.XMLParser(target=TreeBuilder()) - kwargs = {'parser': parser} if sys.version_info >= (2, 7) else {} - tree = xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs) - # Fix up XML parser in Python 2.x - if sys.version_info < (3, 0): - for n in etree_iter(tree): - if n.text is not None: - if not isinstance(n.text, compat_str): - n.text = n.text.decode('utf-8') - return tree - - US_RATINGS = { 'G': 0, 'PG': 10, @@ -1699,8 +1703,8 @@ def js_to_json(code): if v in ('true', 'false', 'null'): return v if v.startswith('"'): - return v - if v.startswith("'"): + v = re.sub(r"\\'", "'", v[1:-1]) + elif v.startswith("'"): v = v[1:-1] v = re.sub(r"\\\\|\\'|\"", lambda m: { '\\\\': '\\\\', @@ -1794,6 +1798,10 @@ def urlhandle_detect_ext(url_handle): return mimetype2ext(getheader('Content-Type')) +def encode_data_uri(data, mime_type): + return 'data:%s;base64,%s' % (mime_type, base64.b64encode(data).decode('ascii')) + + def age_restricted(content_limit, age_limit): """ Returns True iff the content should be blocked """ @@ -1968,7 +1976,7 @@ def dfxp2srt(dfxp_data): return out - dfxp = xml.etree.ElementTree.fromstring(dfxp_data.encode('utf-8')) + dfxp = compat_etree_fromstring(dfxp_data.encode('utf-8')) out = [] paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall('.//p') diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 0cc7411f2..6585d60d5 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2015.09.09' +__version__ = '2015.11.13'