--list-extractors List all supported extractors and the URLs they
would handle
--extractor-descriptions Output descriptions of all supported extractors
- --proxy URL Use the specified HTTP/HTTPS proxy
+ --proxy URL Use the specified HTTP/HTTPS proxy. Pass in an
+ empty string (--proxy "") for direct connection
--no-check-certificate Suppress HTTPS certificate validation.
--cache-dir DIR Location in the filesystem where youtube-dl can
store downloaded information permanently. By
default $XDG_CACHE_HOME/youtube-dl or ~/.cache
/youtube-dl .
--no-cache-dir Disable filesystem caching
+ --bidi-workaround Work around terminals that lack bidirectional
+ text support. Requires fribidi executable in PATH
## Video Selection:
--playlist-start NUMBER playlist video to start at (default is 1)
--date DATE download only videos uploaded in this date
--datebefore DATE download only videos uploaded before this date
--dateafter DATE download only videos uploaded after this date
+ --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
--no-playlist download only the currently playing video
--age-limit YEARS download only videos suitable for the given age
- --download-archive FILE Download only videos not present in the archive
- file. Record all downloaded videos in it.
+ --download-archive FILE Download only videos not listed in the archive
+ file. Record the IDs of all downloaded videos in
+ it.
## Download Options:
-r, --rate-limit LIMIT maximum download rate in bytes per second (e.g.
ownloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
--autonumber-size NUMBER Specifies the number of digits in %(autonumber)s
when it is present in output filename template or
- --autonumber option is given
+ --auto-number option is given
--restrict-filenames Restrict filenames to only ASCII characters, and
avoid "&" and spaces in filenames
-a, --batch-file FILE file containing URLs to download ('-' for stdin)
+ --load-info FILE json file containing the video information
+ (created with the "--write-json" option
-w, --no-overwrites do not overwrite files
- -c, --continue resume partially downloaded files
+ -c, --continue force resume of partially downloaded files. By
+ default, youtube-dl will resume downloads if
+ possible.
--no-continue do not resume partially downloaded files (restart
from beginning)
--cookies FILE file to read cookies from and dump cookie jar in
--get-id simulate, quiet but print id
--get-thumbnail simulate, quiet but print thumbnail URL
--get-description simulate, quiet but print video description
+ --get-duration simulate, quiet but print video length
--get-filename simulate, quiet but print output filename
--get-format simulate, quiet but print output format
+ -j, --dump-json simulate, quiet but print JSON information
--newline output progress bar as new lines
--no-progress do not print progress bar
--console-title display progress in console titlebar
-v, --verbose print various debugging information
--dump-intermediate-pages print downloaded pages to debug problems(very
verbose)
- --write-pages Write downloaded pages to files in the current
- directory
+ --write-pages Write downloaded intermediary pages to files in
+ the current directory to debug problems
## Video Format Options:
- -f, --format FORMAT video format code, specifiy the order of
+ -f, --format FORMAT video format code, specify the order of
preference using slashes: "-f 22/17/18". "-f mp4"
and "-f flv" are also supported
--all-formats download all available video formats
# CONFIGURATION
-You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl.conf`.
+You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl.conf`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
# OUTPUT TEMPLATE
# BUGS
-Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>
+Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email.
-Please include:
-
-* Your exact command line, like `youtube-dl -t "http://www.youtube.com/watch?v=uHlDtZ6Oc3s&feature=channel_video_title"`. A common mistake is not to escape the `&`. Putting URLs in quotes should solve this problem.
-* If possible re-run the command with `--verbose`, and include the full output, it is really helpful to us.
-* The output of `youtube-dl --version`
-* The output of `python --version`
-* The name and version of your Operating System ("Ubuntu 11.04 x64" or "Windows 7 x64" is usually enough).
+Please include the full output of the command when run with `--verbose`. 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.
For discussions, join us in the irc channel #youtube-dl on freenode.
+
+When you submit a request, please re-read it once to avoid a couple of mistakes (you can and should use this as a checklist):
+
+### Is the description of the issue itself sufficient?
+
+We often get issue reports that we cannot really decipher. While in most cases we eventually get the required information after asking back multiple times, this poses an unnecessary drain on our resources. Many contributors, including myself, are also not native speakers, so we may misread some parts.
+
+So please elaborate on what feature you are requesting, or what bug you want to be fixed. Make sure that it's obvious
+
+- What the problem is
+- How it could be fixed
+- How your proposed solution would look like
+
+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.
+
+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. Ábout 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?
+
+Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
+
+### Why are existing options not enough?
+
+Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
+
+### Is there enough context in your bug report?
+
+People want to solve problems, and often think they do us a favor by breaking down their larger problems (e.g. wanting to skip already downloaded files) to a specific request (e.g. requesting us to look whether the file exists before downloading the info page). However, what often happens is that they break down the problem into two steps: One simple, and one impossible (or extremely complicated one).
+
+We are then presented with a very complicated request when the original problem could be solved far easier, e.g. by recording the downloaded video IDs in a separate file. To avoid this, you must include the greater context where it is non-obvious. In particular, every feature request that does not consist of adding support for a new site should contain a use case scenario that explains in what situation the missing feature would be useful.
+
+### Does the issue involve one problem, and one problem only?
+
+Some of our users seem to think there is a limit of issues they can or should open. There is no limit of issues they can or should open. While it may seem appealing to be able to dump all your issues into one ticket, that means that someone who solves one of your issues cannot mark the issue as closed. Typically, reporting a bunch of issues leads to the ticket lingering since nobody wants to attack that behemoth, until someone mercifully splits the issue into multiple ones.
+
+In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, Whitehouse podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
+
+### Is anyone going to need the feature?
+
+Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
__youtube_dl()
{
- local cur prev opts
+ local cur prev opts fileopts diropts keywords
COMPREPLY=()
cur="${COMP_WORDS[COMP_CWORD]}"
+ prev="${COMP_WORDS[COMP_CWORD-1]}"
opts="{{flags}}"
- keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater"
+ keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory"
+ fileopts="-a|--batch-file|--download-archive|--cookies"
+ diropts="--cache-dir"
+
+ if [[ ${prev} =~ ${fileopts} ]]; then
+ COMPREPLY=( $(compgen -f -- ${cur}) )
+ return 0
+ elif [[ ${prev} =~ ${diropts} ]]; then
+ COMPREPLY=( $(compgen -d -- ${cur}) )
+ return 0
+ fi
if [[ ${cur} =~ : ]]; then
COMPREPLY=( $(compgen -W "${keywords}" -- ${cur}) )
'data_files': [ # Installing system-wide would require sudo...
('etc/bash_completion.d', ['youtube-dl.bash-completion']),
('share/doc/youtube_dl', ['README.txt']),
- ('share/man/man1/', ['youtube-dl.1'])
+ ('share/man/man1', ['youtube-dl.1'])
]
}
if setuptools_available:
from youtube_dl.utils import preferredencoding
-def global_setup():
- youtube_dl._setup_opener(timeout=10)
-
-
def get_params(override=None):
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)),
"parameters.json")
"writeinfojson": true,
"writesubtitles": false,
"allsubtitles": false,
- "listssubtitles": false
+ "listssubtitles": false,
+ "socket_timeout": 20
}
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL
+from youtube_dl import YoutubeDL
class YDL(FakeYDL):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], u'35')
+ def test_add_extra_info(self):
+ test_dict = {
+ 'extractor': 'Foo',
+ }
+ extra_info = {
+ 'extractor': 'Bar',
+ 'playlist': 'funny videos',
+ }
+ YDL.add_extra_info(test_dict, extra_info)
+ self.assertEqual(test_dict['extractor'], 'Foo')
+ self.assertEqual(test_dict['playlist'], 'funny videos')
+
+ def test_prepare_filename(self):
+ info = {
+ u'id': u'1234',
+ u'ext': u'mp4',
+ u'width': None,
+ }
+ def fname(templ):
+ ydl = YoutubeDL({'outtmpl': templ})
+ return ydl.prepare_filename(info)
+ self.assertEqual(fname(u'%(id)s.%(ext)s'), u'1234.mp4')
+ self.assertEqual(fname(u'%(id)s-%(width)s.%(ext)s'), u'1234-NA.mp4')
+ # Replace missing fields with 'NA'
+ self.assertEqual(fname(u'%(uploader_date)s-%(id)s.%(ext)s'), u'NA-1234.mp4')
+
if __name__ == '__main__':
unittest.main()
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from test.helper import global_setup, try_rm
-global_setup()
+from test.helper import try_rm
from youtube_dl import YoutubeDL
}
ydl = YoutubeDL(params)
ydl.add_default_info_extractors()
- json_filename = filename + '.info.json'
+ json_filename = os.path.splitext(filename)[0] + '.info.json'
try_rm(json_filename)
ydl.download([url])
res = os.path.exists(json_filename)
from test.helper import get_testcases
from youtube_dl.extractor import (
+ FacebookIE,
gen_extractors,
JustinTVIE,
YoutubeIE,
assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
+ def test_facebook_matching(self):
+ self.assertTrue(FacebookIE.suitable(u'https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
+
def test_no_duplicates(self):
ies = gen_extractors()
for tc in get_testcases():
url = tc['url']
for ie in ies:
- if type(ie).__name__ in ['GenericIE', tc['name'] + 'IE']:
+ if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
else:
self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))
def test_keywords(self):
self.assertMatch(':ytsubs', ['youtube:subscriptions'])
self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
- self.assertMatch(':thedailyshow', ['ComedyCentral'])
- self.assertMatch(':tds', ['ComedyCentral'])
- self.assertMatch(':colbertreport', ['ComedyCentral'])
- self.assertMatch(':cr', ['ComedyCentral'])
-
+ self.assertMatch(':ythistory', ['youtube:history'])
+ self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
+ self.assertMatch(':tds', ['ComedyCentralShows'])
+ self.assertMatch(':colbertreport', ['ComedyCentralShows'])
+ self.assertMatch(':cr', ['ComedyCentralShows'])
+
+ def test_vimeo_matching(self):
+ self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
+ self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user'])
+
+ # https://github.com/rg3/youtube-dl/issues/1930
+ def test_soundcloud_not_matching_sets(self):
+ self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
if __name__ == '__main__':
unittest.main()
+++ /dev/null
-#!/usr/bin/env python
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from test.helper import FakeYDL, global_setup, md5
-global_setup()
-
-
-from youtube_dl.extractor import DailymotionIE
-
-class TestDailymotionSubtitles(unittest.TestCase):
- def setUp(self):
- self.DL = FakeYDL()
- self.url = 'http://www.dailymotion.com/video/xczg00'
- def getInfoDict(self):
- IE = DailymotionIE(self.DL)
- info_dict = IE.extract(self.url)
- return info_dict
- def getSubtitles(self):
- info_dict = self.getInfoDict()
- return info_dict['subtitles']
- def test_no_writesubtitles(self):
- subtitles = self.getSubtitles()
- self.assertEqual(subtitles, None)
- def test_subtitles(self):
- self.DL.params['writesubtitles'] = True
- subtitles = self.getSubtitles()
- self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f')
- def test_subtitles_lang(self):
- self.DL.params['writesubtitles'] = True
- self.DL.params['subtitleslangs'] = ['fr']
- subtitles = self.getSubtitles()
- self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792')
- def test_allsubtitles(self):
- self.DL.params['writesubtitles'] = True
- self.DL.params['allsubtitles'] = True
- subtitles = self.getSubtitles()
- self.assertEqual(len(subtitles.keys()), 5)
- def test_list_subtitles(self):
- self.DL.expect_warning(u'Automatic Captions not supported by this server')
- self.DL.params['listsubtitles'] = True
- info_dict = self.getInfoDict()
- self.assertEqual(info_dict, None)
- def test_automatic_captions(self):
- self.DL.expect_warning(u'Automatic Captions not supported by this server')
- self.DL.params['writeautomaticsub'] = True
- self.DL.params['subtitleslang'] = ['en']
- subtitles = self.getSubtitles()
- self.assertTrue(len(subtitles.keys()) == 0)
- def test_nosubtitles(self):
- self.DL.expect_warning(u'video doesn\'t have subtitles')
- self.url = 'http://www.dailymotion.com/video/x12u166_le-zapping-tele-star-du-08-aout-2013_tv'
- self.DL.params['writesubtitles'] = True
- self.DL.params['allsubtitles'] = True
- subtitles = self.getSubtitles()
- self.assertEqual(len(subtitles), 0)
- def test_multiple_langs(self):
- self.DL.params['writesubtitles'] = True
- langs = ['es', 'fr', 'de']
- self.DL.params['subtitleslangs'] = langs
- subtitles = self.getSubtitles()
- for lang in langs:
- self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
-
-if __name__ == '__main__':
- unittest.main()
from test.helper import (
get_params,
get_testcases,
- global_setup,
try_rm,
md5,
report_warning
)
-global_setup()
import hashlib
ExtractorError,
UnavailableVideoError,
)
+from youtube_dl.extractor import get_info_extractor
RETRIES = 3
def test_template(self):
ie = youtube_dl.extractor.get_info_extractor(test_case['name'])
+ other_ies = [get_info_extractor(ie_key) for ie_key in test_case.get('add_ie', [])]
def print_skipping(reason):
print('Skipping %s: %s' % (test_case['name'], reason))
- if not ie._WORKING:
+ if not ie.working():
print_skipping('IE marked as not _WORKING')
return
if 'playlist' not in test_case:
if 'skip' in test_case:
print_skipping(test_case['skip'])
return
+ for other_ie in other_ies:
+ if not other_ie.working():
+ print_skipping(u'test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
+ return
params = get_params(test_case.get('params', {}))
tc_filename = get_tc_filename(tc)
try_rm(tc_filename)
try_rm(tc_filename + '.part')
- try_rm(tc_filename + '.info.json')
+ try_rm(os.path.splitext(tc_filename)[0] + '.info.json')
try_rm_tcs_files()
try:
try_num = 1
if not test_case.get('params', {}).get('skip_download', False):
self.assertTrue(os.path.exists(tc_filename), msg='Missing file ' + tc_filename)
self.assertTrue(tc_filename in finished_hook_called)
- self.assertTrue(os.path.exists(tc_filename + '.info.json'))
+ info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
+ self.assertTrue(os.path.exists(info_json_fn))
if 'md5' in tc:
md5_for_file = _file_md5(tc_filename)
self.assertEqual(md5_for_file, tc['md5'])
- with io.open(tc_filename + '.info.json', encoding='utf-8') as infof:
+ with io.open(info_json_fn, encoding='utf-8') as infof:
info_dict = json.load(infof)
for (info_field, expected) in tc.get('info_dict', {}).items():
if isinstance(expected, compat_str) and expected.startswith('md5:'):
# Check for the presence of mandatory fields
for key in ('id', 'url', 'title', 'ext'):
self.assertTrue(key in info_dict.keys() and info_dict[key])
+ # Check for mandatory fields that are automatically set by YoutubeDL
+ for key in ['webpage_url', 'extractor', 'extractor_key']:
+ self.assertTrue(info_dict.get(key), u'Missing field: %s' % key)
finally:
try_rm_tcs_files()
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from test.helper import FakeYDL, global_setup
-global_setup()
+from test.helper import FakeYDL
from youtube_dl.extractor import (
+ AcademicEarthCourseIE,
DailymotionPlaylistIE,
DailymotionUserIE,
VimeoChannelIE,
+ VimeoUserIE,
+ VimeoAlbumIE,
+ VimeoGroupsIE,
UstreamChannelIE,
+ SoundcloudSetIE,
SoundcloudUserIE,
LivestreamIE,
NHLVideocenterIE,
+ BambuserChannelIE,
+ BandcampAlbumIE,
+ SmotriCommunityIE,
+ SmotriUserIE,
+ IviCompilationIE
)
self.assertEqual(result['title'], u'Vimeo Tributes')
self.assertTrue(len(result['entries']) > 24)
+ def test_vimeo_user(self):
+ dl = FakeYDL()
+ ie = VimeoUserIE(dl)
+ result = ie.extract('http://vimeo.com/nkistudio/videos')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['title'], u'Nki')
+ self.assertTrue(len(result['entries']) > 65)
+
+ def test_vimeo_album(self):
+ dl = FakeYDL()
+ ie = VimeoAlbumIE(dl)
+ result = ie.extract('http://vimeo.com/album/2632481')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['title'], u'Staff Favorites: November 2013')
+ self.assertTrue(len(result['entries']) > 12)
+
+ def test_vimeo_groups(self):
+ dl = FakeYDL()
+ ie = VimeoGroupsIE(dl)
+ result = ie.extract('http://vimeo.com/groups/rolexawards')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['title'], u'Rolex Awards for Enterprise')
+ self.assertTrue(len(result['entries']) > 72)
+
def test_ustream_channel(self):
dl = FakeYDL()
ie = UstreamChannelIE(dl)
self.assertEqual(result['id'], u'5124905')
self.assertTrue(len(result['entries']) >= 11)
+ def test_soundcloud_set(self):
+ dl = FakeYDL()
+ ie = SoundcloudSetIE(dl)
+ result = ie.extract('https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['title'], u'The Royal Concept EP')
+ self.assertTrue(len(result['entries']) >= 6)
+
def test_soundcloud_user(self):
dl = FakeYDL()
ie = SoundcloudUserIE(dl)
self.assertEqual(result['title'], u'Highlights')
self.assertEqual(len(result['entries']), 12)
+ def test_bambuser_channel(self):
+ dl = FakeYDL()
+ ie = BambuserChannelIE(dl)
+ result = ie.extract('http://bambuser.com/channel/pixelversity')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['title'], u'pixelversity')
+ self.assertTrue(len(result['entries']) >= 60)
+
+ def test_bandcamp_album(self):
+ dl = FakeYDL()
+ ie = BandcampAlbumIE(dl)
+ result = ie.extract('http://mpallante.bandcamp.com/album/nightmare-night-ep')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['title'], u'Nightmare Night EP')
+ self.assertTrue(len(result['entries']) >= 4)
+
+ def test_smotri_community(self):
+ dl = FakeYDL()
+ ie = SmotriCommunityIE(dl)
+ result = ie.extract('http://smotri.com/community/video/kommuna')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['id'], u'kommuna')
+ self.assertEqual(result['title'], u'КПРФ')
+ self.assertTrue(len(result['entries']) >= 4)
+
+ def test_smotri_user(self):
+ dl = FakeYDL()
+ ie = SmotriUserIE(dl)
+ result = ie.extract('http://smotri.com/user/inspector')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['id'], u'inspector')
+ self.assertEqual(result['title'], u'Inspector')
+ self.assertTrue(len(result['entries']) >= 9)
+
+ def test_AcademicEarthCourse(self):
+ dl = FakeYDL()
+ ie = AcademicEarthCourseIE(dl)
+ result = ie.extract(u'http://academicearth.org/courses/building-dynamic-websites/')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['id'], u'building-dynamic-websites')
+ self.assertEqual(result['title'], u'Building Dynamic Websites')
+ self.assertEqual(result['description'], u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
+ self.assertEqual(len(result['entries']), 10)
+
+ def test_ivi_compilation(self):
+ dl = FakeYDL()
+ ie = IviCompilationIE(dl)
+ result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['id'], u'dezhurnyi_angel')
+ self.assertEqual(result['title'], u'Дежурный ангел (2010 - 2012)')
+ self.assertTrue(len(result['entries']) >= 36)
+
+ def test_ivi_compilation_season(self):
+ dl = FakeYDL()
+ ie = IviCompilationIE(dl)
+ result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel/season2')
+ self.assertIsPlaylist(result)
+ self.assertEqual(result['id'], u'dezhurnyi_angel/season2')
+ self.assertEqual(result['title'], u'Дежурный ангел (2010 - 2012) 2 сезон')
+ self.assertTrue(len(result['entries']) >= 20)
+
+
if __name__ == '__main__':
unittest.main()
--- /dev/null
+#!/usr/bin/env python
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import FakeYDL, md5
+
+
+from youtube_dl.extractor import (
+ YoutubeIE,
+ DailymotionIE,
+ TEDIE,
+)
+
+
+class BaseTestSubtitles(unittest.TestCase):
+ url = None
+ IE = None
+ def setUp(self):
+ self.DL = FakeYDL()
+ self.ie = self.IE(self.DL)
+
+ def getInfoDict(self):
+ info_dict = self.ie.extract(self.url)
+ return info_dict
+
+ def getSubtitles(self):
+ info_dict = self.getInfoDict()
+ return info_dict['subtitles']
+
+
+class TestYoutubeSubtitles(BaseTestSubtitles):
+ url = 'QRS8MkLhQmM'
+ IE = YoutubeIE
+
+ def getSubtitles(self):
+ info_dict = self.getInfoDict()
+ return info_dict[0]['subtitles']
+
+ def test_youtube_no_writesubtitles(self):
+ self.DL.params['writesubtitles'] = False
+ subtitles = self.getSubtitles()
+ self.assertEqual(subtitles, None)
+
+ def test_youtube_subtitles(self):
+ self.DL.params['writesubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
+
+ def test_youtube_subtitles_lang(self):
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['subtitleslangs'] = ['it']
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
+
+ def test_youtube_allsubtitles(self):
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['allsubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(len(subtitles.keys()), 13)
+
+ def test_youtube_subtitles_sbv_format(self):
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['subtitlesformat'] = 'sbv'
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['en']), '13aeaa0c245a8bed9a451cb643e3ad8b')
+
+ def test_youtube_subtitles_vtt_format(self):
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['subtitlesformat'] = 'vtt'
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
+
+ def test_youtube_list_subtitles(self):
+ self.DL.expect_warning(u'Video doesn\'t have automatic captions')
+ self.DL.params['listsubtitles'] = True
+ info_dict = self.getInfoDict()
+ self.assertEqual(info_dict, None)
+
+ def test_youtube_automatic_captions(self):
+ self.url = '8YoUxe5ncPo'
+ self.DL.params['writeautomaticsub'] = True
+ self.DL.params['subtitleslangs'] = ['it']
+ subtitles = self.getSubtitles()
+ self.assertTrue(subtitles['it'] is not None)
+
+ def test_youtube_nosubtitles(self):
+ self.DL.expect_warning(u'video doesn\'t have subtitles')
+ self.url = 'sAjKT8FhjI8'
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['allsubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(len(subtitles), 0)
+
+ def test_youtube_multiple_langs(self):
+ self.url = 'QRS8MkLhQmM'
+ self.DL.params['writesubtitles'] = True
+ langs = ['it', 'fr', 'de']
+ self.DL.params['subtitleslangs'] = langs
+ subtitles = self.getSubtitles()
+ for lang in langs:
+ self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
+
+
+class TestDailymotionSubtitles(BaseTestSubtitles):
+ url = 'http://www.dailymotion.com/video/xczg00'
+ IE = DailymotionIE
+
+ def test_no_writesubtitles(self):
+ subtitles = self.getSubtitles()
+ self.assertEqual(subtitles, None)
+
+ def test_subtitles(self):
+ self.DL.params['writesubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f')
+
+ def test_subtitles_lang(self):
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['subtitleslangs'] = ['fr']
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792')
+
+ def test_allsubtitles(self):
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['allsubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(len(subtitles.keys()), 5)
+
+ def test_list_subtitles(self):
+ self.DL.expect_warning(u'Automatic Captions not supported by this server')
+ self.DL.params['listsubtitles'] = True
+ info_dict = self.getInfoDict()
+ self.assertEqual(info_dict, None)
+
+ def test_automatic_captions(self):
+ self.DL.expect_warning(u'Automatic Captions not supported by this server')
+ self.DL.params['writeautomaticsub'] = True
+ self.DL.params['subtitleslang'] = ['en']
+ subtitles = self.getSubtitles()
+ self.assertTrue(len(subtitles.keys()) == 0)
+
+ def test_nosubtitles(self):
+ self.DL.expect_warning(u'video doesn\'t have subtitles')
+ self.url = 'http://www.dailymotion.com/video/x12u166_le-zapping-tele-star-du-08-aout-2013_tv'
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['allsubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(len(subtitles), 0)
+
+ def test_multiple_langs(self):
+ self.DL.params['writesubtitles'] = True
+ langs = ['es', 'fr', 'de']
+ self.DL.params['subtitleslangs'] = langs
+ subtitles = self.getSubtitles()
+ for lang in langs:
+ self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
+
+
+class TestTedSubtitles(BaseTestSubtitles):
+ url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html'
+ IE = TEDIE
+
+ def test_no_writesubtitles(self):
+ subtitles = self.getSubtitles()
+ self.assertEqual(subtitles, None)
+
+ def test_subtitles(self):
+ self.DL.params['writesubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['en']), '2154f31ff9b9f89a0aa671537559c21d')
+
+ def test_subtitles_lang(self):
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['subtitleslangs'] = ['fr']
+ subtitles = self.getSubtitles()
+ self.assertEqual(md5(subtitles['fr']), '7616cbc6df20ec2c1204083c83871cf6')
+
+ def test_allsubtitles(self):
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['allsubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(len(subtitles.keys()), 28)
+
+ def test_list_subtitles(self):
+ self.DL.expect_warning(u'Automatic Captions not supported by this server')
+ self.DL.params['listsubtitles'] = True
+ info_dict = self.getInfoDict()
+ self.assertEqual(info_dict, None)
+
+ def test_automatic_captions(self):
+ self.DL.expect_warning(u'Automatic Captions not supported by this server')
+ self.DL.params['writeautomaticsub'] = True
+ self.DL.params['subtitleslang'] = ['en']
+ subtitles = self.getSubtitles()
+ self.assertTrue(len(subtitles.keys()) == 0)
+
+ def test_multiple_langs(self):
+ self.DL.params['writesubtitles'] = True
+ langs = ['es', 'fr', 'de']
+ self.DL.params['subtitleslangs'] = langs
+ subtitles = self.getSubtitles()
+ for lang in langs:
+ self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
+
+if __name__ == '__main__':
+ unittest.main()
#from youtube_dl.utils import htmlentity_transform
from youtube_dl.utils import (
- timeconvert,
- sanitize_filename,
- unescapeHTML,
- orderedSet,
DateRange,
- unified_strdate,
+ encodeFilename,
find_xpath_attr,
get_meta_content,
- xpath_with_ns,
+ orderedSet,
+ sanitize_filename,
+ shell_quote,
smuggle_url,
+ str_to_int,
+ timeconvert,
+ unescapeHTML,
+ unified_strdate,
unsmuggle_url,
+ url_basename,
+ xpath_with_ns,
)
if sys.version_info < (3, 0):
self.assertEqual(res_url, url)
self.assertEqual(res_data, None)
+ def test_shell_quote(self):
+ args = ['ffmpeg', '-i', encodeFilename(u'ñ€ß\'.mp4')]
+ self.assertEqual(shell_quote(args), u"""ffmpeg -i 'ñ€ß'"'"'.mp4'""")
+
+ def test_str_to_int(self):
+ self.assertEqual(str_to_int('123,456'), 123456)
+ self.assertEqual(str_to_int('123.456'), 123456)
+
+ def test_url_basename(self):
+ self.assertEqual(url_basename(u'http://foo.de/'), u'')
+ self.assertEqual(url_basename(u'http://foo.de/bar/baz'), u'baz')
+ self.assertEqual(url_basename(u'http://foo.de/bar/baz?x=y'), u'baz')
+ self.assertEqual(url_basename(u'http://foo.de/bar/baz#x=y'), u'baz')
+ self.assertEqual(url_basename(u'http://foo.de/bar/baz/'), u'baz')
+ self.assertEqual(
+ url_basename(u'http://media.w3.org/2010/05/sintel/trailer.mp4'),
+ u'trailer.mp4')
if __name__ == '__main__':
unittest.main()
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from test.helper import get_params, global_setup, try_rm
-global_setup()
+from test.helper import get_params, try_rm
import io
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from test.helper import get_params, global_setup
-global_setup()
+from test.helper import get_params
import io
TEST_ID = 'BaW_jenozKc'
-INFO_JSON_FILE = TEST_ID + '.mp4.info.json'
+INFO_JSON_FILE = TEST_ID + '.info.json'
DESCRIPTION_FILE = TEST_ID + '.mp4.description'
EXPECTED_DESCRIPTION = u'''test chars: "'/\ä↭𝕐
+test URL: https://github.com/rg3/youtube-dl/issues/1892
This is a test video for youtube-dl.
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from test.helper import FakeYDL, global_setup
-global_setup()
+from test.helper import FakeYDL
from youtube_dl.extractor import (
YoutubeIE,
YoutubeChannelIE,
YoutubeShowIE,
+ YoutubeTopListIE,
)
def test_youtube_playlist(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
- result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')[0]
+ result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'ytdl test PL')
ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
def test_issue_673(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
- result = ie.extract('PLBB231211A4F62143')[0]
+ result = ie.extract('PLBB231211A4F62143')
self.assertTrue(len(result['entries']) > 25)
def test_youtube_playlist_long(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
- result = ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')[0]
+ result = ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
self.assertIsPlaylist(result)
self.assertTrue(len(result['entries']) >= 799)
#651
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
- result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')[0]
+ result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
self.assertFalse('pElCt5oNDuI' in ytie_results)
self.assertFalse('KdPEApIVdWM' in ytie_results)
def test_youtube_playlist_empty(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
- result = ie.extract('https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx')[0]
+ result = ie.extract('https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx')
self.assertIsPlaylist(result)
self.assertEqual(len(result['entries']), 0)
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
# TODO find a > 100 (paginating?) videos course
- result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')[0]
+ result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
entries = result['entries']
self.assertEqual(YoutubeIE()._extract_id(entries[0]['url']), 'j9WZyLZCBzs')
self.assertEqual(len(entries), 25)
dl = FakeYDL()
ie = YoutubeChannelIE(dl)
#test paginated channel
- result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')[0]
+ result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')
self.assertTrue(len(result['entries']) > 90)
#test autogenerated channel
- result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')[0]
+ result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
self.assertTrue(len(result['entries']) >= 18)
def test_youtube_user(self):
dl = FakeYDL()
ie = YoutubeUserIE(dl)
- result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')[0]
+ result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')
self.assertTrue(len(result['entries']) >= 320)
def test_youtube_safe_search(self):
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
- result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')[0]
+ result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')
self.assertEqual(len(result['entries']), 2)
def test_youtube_show(self):
result = ie.extract('http://www.youtube.com/show/airdisasters')
self.assertTrue(len(result) >= 3)
+ def test_youtube_mix(self):
+ dl = FakeYDL()
+ ie = YoutubePlaylistIE(dl)
+ result = ie.extract('http://www.youtube.com/watch?v=lLJf9qJHR3E&list=RDrjFaenf1T-Y')
+ entries = result['entries']
+ self.assertTrue(len(entries) >= 20)
+ original_video = entries[0]
+ self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
+
+ def test_youtube_toplist(self):
+ dl = FakeYDL()
+ ie = YoutubeTopListIE(dl)
+ result = ie.extract('yttoplist:music:Top Tracks')
+ entries = result['entries']
+ self.assertTrue(len(entries) >= 5)
+
if __name__ == '__main__':
unittest.main()
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from test.helper import global_setup
-global_setup()
-
import io
import re
+++ /dev/null
-#!/usr/bin/env python
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from test.helper import FakeYDL, global_setup, md5
-global_setup()
-
-
-from youtube_dl.extractor import YoutubeIE
-
-
-class TestYoutubeSubtitles(unittest.TestCase):
- def setUp(self):
- self.DL = FakeYDL()
- self.url = 'QRS8MkLhQmM'
-
- def getInfoDict(self):
- IE = YoutubeIE(self.DL)
- info_dict = IE.extract(self.url)
- return info_dict
-
- def getSubtitles(self):
- info_dict = self.getInfoDict()
- return info_dict[0]['subtitles']
-
- def test_youtube_no_writesubtitles(self):
- self.DL.params['writesubtitles'] = False
- subtitles = self.getSubtitles()
- self.assertEqual(subtitles, None)
-
- def test_youtube_subtitles(self):
- self.DL.params['writesubtitles'] = True
- subtitles = self.getSubtitles()
- self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
-
- def test_youtube_subtitles_lang(self):
- self.DL.params['writesubtitles'] = True
- self.DL.params['subtitleslangs'] = ['it']
- subtitles = self.getSubtitles()
- self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
-
- def test_youtube_allsubtitles(self):
- self.DL.params['writesubtitles'] = True
- self.DL.params['allsubtitles'] = True
- subtitles = self.getSubtitles()
- self.assertEqual(len(subtitles.keys()), 13)
-
- def test_youtube_subtitles_sbv_format(self):
- self.DL.params['writesubtitles'] = True
- self.DL.params['subtitlesformat'] = 'sbv'
- subtitles = self.getSubtitles()
- self.assertEqual(md5(subtitles['en']), '13aeaa0c245a8bed9a451cb643e3ad8b')
-
- def test_youtube_subtitles_vtt_format(self):
- self.DL.params['writesubtitles'] = True
- self.DL.params['subtitlesformat'] = 'vtt'
- subtitles = self.getSubtitles()
- self.assertEqual(md5(subtitles['en']), '356cdc577fde0c6783b9b822e7206ff7')
-
- def test_youtube_list_subtitles(self):
- self.DL.expect_warning(u'Video doesn\'t have automatic captions')
- self.DL.params['listsubtitles'] = True
- info_dict = self.getInfoDict()
- self.assertEqual(info_dict, None)
-
- def test_youtube_automatic_captions(self):
- self.url = '8YoUxe5ncPo'
- self.DL.params['writeautomaticsub'] = True
- self.DL.params['subtitleslangs'] = ['it']
- subtitles = self.getSubtitles()
- self.assertTrue(subtitles['it'] is not None)
-
- def test_youtube_nosubtitles(self):
- self.DL.expect_warning(u'video doesn\'t have subtitles')
- self.url = 'sAjKT8FhjI8'
- self.DL.params['writesubtitles'] = True
- self.DL.params['allsubtitles'] = True
- subtitles = self.getSubtitles()
- self.assertEqual(len(subtitles), 0)
-
- def test_youtube_multiple_langs(self):
- self.url = 'QRS8MkLhQmM'
- self.DL.params['writesubtitles'] = True
- langs = ['it', 'fr', 'de']
- self.DL.params['subtitleslangs'] = langs
- subtitles = self.getSubtitles()
- for lang in langs:
- self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
-
-if __name__ == '__main__':
- unittest.main()
-import math
import os
import re
import subprocess
import sys
import time
-import traceback
-if os.name == 'nt':
- import ctypes
-
-from .utils import *
+from .utils import (
+ compat_urllib_error,
+ compat_urllib_request,
+ ContentTooShortError,
+ determine_ext,
+ encodeFilename,
+ format_bytes,
+ sanitize_open,
+ timeconvert,
+)
class FileDownloader(object):
self._progress_hooks = []
self.params = params
- @staticmethod
- def format_bytes(bytes):
- if bytes is None:
- return 'N/A'
- if type(bytes) is str:
- bytes = float(bytes)
- if bytes == 0.0:
- exponent = 0
- else:
- exponent = int(math.log(bytes, 1024.0))
- suffix = ['B','KiB','MiB','GiB','TiB','PiB','EiB','ZiB','YiB'][exponent]
- converted = float(bytes) / float(1024 ** exponent)
- return '%.2f%s' % (converted, suffix)
-
@staticmethod
def format_seconds(seconds):
(mins, secs) = divmod(seconds, 60)
def format_speed(speed):
if speed is None:
return '%10s' % '---b/s'
- return '%10s' % ('%s/s' % FileDownloader.format_bytes(speed))
+ return '%10s' % ('%s/s' % format_bytes(speed))
@staticmethod
def best_block_size(elapsed_time, bytes):
def to_stderr(self, message):
self.ydl.to_screen(message)
- def to_cons_title(self, message):
- """Set console/terminal window title to message."""
- if not self.params.get('consoletitle', False):
- return
- if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
- # c_wchar_p() might not be necessary if `message` is
- # already of type unicode()
- ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
- elif 'TERM' in os.environ:
- self.to_screen('\033]0;%s\007' % message, skip_eol=True)
+ def to_console_title(self, message):
+ self.ydl.to_console_title(message)
def trouble(self, *args, **kargs):
self.ydl.trouble(*args, **kargs)
if old_filename == new_filename:
return
os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
- except (IOError, OSError) as err:
+ except (IOError, OSError):
self.report_error(u'unable to rename file')
def try_utime(self, filename, last_modified_hdr):
"""Report destination filename."""
self.to_screen(u'[download] Destination: ' + filename)
+ def _report_progress_status(self, msg, is_last_line=False):
+ fullmsg = u'[download] ' + msg
+ if self.params.get('progress_with_newline', False):
+ self.to_screen(fullmsg)
+ else:
+ if os.name == 'nt':
+ prev_len = getattr(self, '_report_progress_prev_line_length',
+ 0)
+ if prev_len > len(fullmsg):
+ fullmsg += u' ' * (prev_len - len(fullmsg))
+ self._report_progress_prev_line_length = len(fullmsg)
+ clear_line = u'\r'
+ else:
+ clear_line = (u'\r\x1b[K' if sys.stderr.isatty() else u'\r')
+ self.to_screen(clear_line + fullmsg, skip_eol=not is_last_line)
+ self.to_console_title(u'youtube-dl ' + msg)
+
def report_progress(self, percent, data_len_str, speed, eta):
"""Report download progress."""
if self.params.get('noprogress', False):
return
- clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
- eta_str = self.format_eta(eta)
- percent_str = self.format_percent(percent)
+ if eta is not None:
+ eta_str = self.format_eta(eta)
+ else:
+ eta_str = 'Unknown ETA'
+ if percent is not None:
+ percent_str = self.format_percent(percent)
+ else:
+ percent_str = 'Unknown %'
speed_str = self.format_speed(speed)
- if self.params.get('progress_with_newline', False):
- self.to_screen(u'[download] %s of %s at %s ETA %s' %
- (percent_str, data_len_str, speed_str, eta_str))
+
+ msg = (u'%s of %s at %s ETA %s' %
+ (percent_str, data_len_str, speed_str, eta_str))
+ self._report_progress_status(msg)
+
+ def report_progress_live_stream(self, downloaded_data_len, speed, elapsed):
+ if self.params.get('noprogress', False):
+ return
+ downloaded_str = format_bytes(downloaded_data_len)
+ speed_str = self.format_speed(speed)
+ elapsed_str = FileDownloader.format_seconds(elapsed)
+ msg = u'%s at %s (%s)' % (downloaded_str, speed_str, elapsed_str)
+ self._report_progress_status(msg)
+
+ def report_finish(self, data_len_str, tot_time):
+ """Report download finished."""
+ if self.params.get('noprogress', False):
+ self.to_screen(u'[download] Download completed')
else:
- self.to_screen(u'\r%s[download] %s of %s at %s ETA %s' %
- (clear_line, percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
- self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
- (percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
+ self._report_progress_status(
+ (u'100%% of %s in %s' %
+ (data_len_str, self.format_seconds(tot_time))),
+ is_last_line=True)
def report_resuming_byte(self, resume_len):
"""Report attempt to resume at given byte."""
"""Report file has already been fully downloaded."""
try:
self.to_screen(u'[download] %s has already been downloaded' % file_name)
- except (UnicodeEncodeError) as err:
+ except UnicodeEncodeError:
self.to_screen(u'[download] The file has already been downloaded')
def report_unable_to_resume(self):
"""Report it was impossible to resume download."""
self.to_screen(u'[download] Unable to resume')
- def report_finish(self, data_len_str, tot_time):
- """Report download finished."""
- if self.params.get('noprogress', False):
- self.to_screen(u'[download] Download completed')
- else:
- clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
- self.to_screen(u'\r%s[download] 100%% of %s in %s' %
- (clear_line, data_len_str, self.format_seconds(tot_time)))
+ def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url, live, conn):
+ def run_rtmpdump(args):
+ start = time.time()
+ resume_percent = None
+ resume_downloaded_data_len = None
+ proc = subprocess.Popen(args, stderr=subprocess.PIPE)
+ cursor_in_new_line = True
+ proc_stderr_closed = False
+ while not proc_stderr_closed:
+ # read line from stderr
+ line = u''
+ while True:
+ char = proc.stderr.read(1)
+ if not char:
+ proc_stderr_closed = True
+ break
+ if char in [b'\r', b'\n']:
+ break
+ line += char.decode('ascii', 'replace')
+ if not line:
+ # proc_stderr_closed is True
+ continue
+ mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line)
+ if mobj:
+ downloaded_data_len = int(float(mobj.group(1))*1024)
+ percent = float(mobj.group(2))
+ if not resume_percent:
+ resume_percent = percent
+ resume_downloaded_data_len = downloaded_data_len
+ eta = self.calc_eta(start, time.time(), 100-resume_percent, percent-resume_percent)
+ speed = self.calc_speed(start, time.time(), downloaded_data_len-resume_downloaded_data_len)
+ data_len = None
+ if percent > 0:
+ data_len = int(downloaded_data_len * 100 / percent)
+ data_len_str = u'~' + format_bytes(data_len)
+ self.report_progress(percent, data_len_str, speed, eta)
+ cursor_in_new_line = False
+ self._hook_progress({
+ 'downloaded_bytes': downloaded_data_len,
+ 'total_bytes': data_len,
+ 'tmpfilename': tmpfilename,
+ 'filename': filename,
+ 'status': 'downloading',
+ 'eta': eta,
+ 'speed': speed,
+ })
+ else:
+ # no percent for live streams
+ mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line)
+ if mobj:
+ downloaded_data_len = int(float(mobj.group(1))*1024)
+ time_now = time.time()
+ speed = self.calc_speed(start, time_now, downloaded_data_len)
+ self.report_progress_live_stream(downloaded_data_len, speed, time_now - start)
+ cursor_in_new_line = False
+ self._hook_progress({
+ 'downloaded_bytes': downloaded_data_len,
+ 'tmpfilename': tmpfilename,
+ 'filename': filename,
+ 'status': 'downloading',
+ 'speed': speed,
+ })
+ elif self.params.get('verbose', False):
+ if not cursor_in_new_line:
+ self.to_screen(u'')
+ cursor_in_new_line = True
+ self.to_screen(u'[rtmpdump] '+line)
+ proc.wait()
+ if not cursor_in_new_line:
+ self.to_screen(u'')
+ return proc.returncode
- def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
test = self.params.get('test', False)
except (OSError, IOError):
self.report_error(u'RTMP download detected but "rtmpdump" could not be run')
return False
- verbosity_option = '--verbose' if self.params.get('verbose', False) else '--quiet'
# Download using rtmpdump. rtmpdump returns exit code 2 when
# the connection was interrumpted and resuming appears to be
# possible. This is part of rtmpdump's normal usage, AFAIK.
- basic_args = ['rtmpdump', verbosity_option, '-r', url, '-o', tmpfilename]
+ basic_args = ['rtmpdump', '--verbose', '-r', url, '-o', tmpfilename]
if player_url is not None:
basic_args += ['--swfVfy', player_url]
if page_url is not None:
basic_args += ['--tcUrl', url]
if test:
basic_args += ['--stop', '1']
+ if live:
+ basic_args += ['--live']
+ if conn:
+ basic_args += ['--conn', conn]
args = basic_args + [[], ['--resume', '--skip', '1']][self.params.get('continuedl', False)]
+
+ if sys.platform == 'win32' and sys.version_info < (3, 0):
+ # Windows subprocess module does not actually support Unicode
+ # on Python 2.x
+ # See http://stackoverflow.com/a/9951851/35070
+ subprocess_encoding = sys.getfilesystemencoding()
+ args = [a.encode(subprocess_encoding, 'ignore') for a in args]
+ else:
+ subprocess_encoding = None
+
if self.params.get('verbose', False):
+ if subprocess_encoding:
+ str_args = [
+ a.decode(subprocess_encoding) if isinstance(a, bytes) else a
+ for a in args]
+ else:
+ str_args = args
try:
import pipes
- shell_quote = lambda args: ' '.join(map(pipes.quote, args))
+ shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
except ImportError:
shell_quote = repr
- self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(args))
- retval = subprocess.call(args)
+ self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(str_args))
+
+ retval = run_rtmpdump(args)
+
while (retval == 2 or retval == 1) and not test:
prevsize = os.path.getsize(encodeFilename(tmpfilename))
- self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
+ self.to_screen(u'[rtmpdump] %s bytes' % prevsize)
time.sleep(5.0) # This seems to be needed
- retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
+ retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
cursize = os.path.getsize(encodeFilename(tmpfilename))
if prevsize == cursize and retval == 1:
break
# Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
if prevsize == cursize and retval == 2 and cursize > 1024:
- self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
+ self.to_screen(u'[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
retval = 0
break
if retval == 0 or (test and retval == 2):
fsize = os.path.getsize(encodeFilename(tmpfilename))
- self.to_screen(u'\r[rtmpdump] %s bytes' % fsize)
+ self.to_screen(u'[rtmpdump] %s bytes' % fsize)
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
- args = ['ffmpeg', '-y', '-i', url, '-f', 'mp4', tmpfilename]
- # Check for ffmpeg first
- try:
- subprocess.call(['ffmpeg', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
- except (OSError, IOError):
- self.report_error(u'm3u8 download detected but "%s" could not be run' % args[0] )
- return False
+ args = ['-y', '-i', url, '-f', 'mp4', '-c', 'copy',
+ '-bsf:a', 'aac_adtstoasc', tmpfilename]
- retval = subprocess.call(args)
+ for program in ['avconv', 'ffmpeg']:
+ try:
+ subprocess.call([program, '-version'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+ break
+ except (OSError, IOError):
+ pass
+ else:
+ self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found')
+ cmd = [program] + args
+
+ retval = subprocess.call(cmd)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize))
info_dict.get('player_url', None),
info_dict.get('page_url', None),
info_dict.get('play_path', None),
- info_dict.get('tc_url', None))
+ info_dict.get('tc_url', None),
+ info_dict.get('rtmp_live', False),
+ info_dict.get('rtmp_conn', None))
# Attempt to download using mplayer
if url.startswith('mms') or url.startswith('rtsp'):
self.to_screen(u'\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
return False
- data_len_str = self.format_bytes(data_len)
+ data_len_str = format_bytes(data_len)
byte_counter = 0 + resume_len
block_size = self.params.get('buffersize', 1024)
start = time.time()
# Progress message
speed = self.calc_speed(start, time.time(), byte_counter - resume_len)
if data_len is None:
- self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA')
- eta = None
+ eta = percent = None
else:
percent = self.calc_percent(byte_counter, data_len)
eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
- self.report_progress(percent, data_len_str, speed, eta)
+ self.report_progress(percent, data_len_str, speed, eta)
self._hook_progress({
'downloaded_bytes': byte_counter,
options = ['-c', 'copy']
for (name, value) in metadata.items():
- options.extend(['-metadata', '%s="%s"' % (name, value)])
+ options.extend(['-metadata', '%s=%s' % (name, value)])
options.extend(['-f', ext])
self._downloader.to_screen(u'[ffmpeg] Adding metadata to \'%s\'' % filename)
from __future__ import absolute_import
+import collections
import errno
import io
+import json
import os
+import platform
import re
import shutil
+import subprocess
import socket
import sys
import time
import traceback
-from .utils import *
+if os.name == 'nt':
+ import ctypes
+
+from .utils import (
+ compat_cookiejar,
+ compat_http_client,
+ compat_str,
+ compat_urllib_error,
+ compat_urllib_request,
+ ContentTooShortError,
+ date_from_str,
+ DateRange,
+ determine_ext,
+ DownloadError,
+ encodeFilename,
+ ExtractorError,
+ format_bytes,
+ formatSeconds,
+ get_term_width,
+ locked_file,
+ make_HTTPS_handler,
+ MaxDownloadsReached,
+ PostProcessingError,
+ platform_name,
+ preferredencoding,
+ SameFileError,
+ sanitize_filename,
+ subtitles_filename,
+ takewhile_inclusive,
+ UnavailableVideoError,
+ url_basename,
+ write_json_file,
+ write_string,
+ YoutubeDLHandler,
+)
from .extractor import get_info_extractor, gen_extractors
from .FileDownloader import FileDownloader
+from .version import __version__
class YoutubeDL(object):
forcethumbnail: Force printing thumbnail URL.
forcedescription: Force printing description.
forcefilename: Force printing final filename.
+ forceduration: Force printing duration.
+ forcejson: Force printing info_dict as JSON.
simulate: Do not download the video files.
format: Video format code.
format_limit: Highest quality format to try.
playlistend: Playlist item to end at.
matchtitle: Download only matching titles.
rejecttitle: Reject downloads for matching titles.
+ logger: Log messages to a logging.Logger instance.
logtostderr: Log messages to stderr instead of stdout.
writedescription: Write the video description to a .description file
writeinfojson: Write the video description to a .info.json file
noplaylist: Download single video instead of a playlist if in doubt.
age_limit: An integer representing the user's age in years.
Unsuitable videos for the given age are skipped.
- downloadarchive: File name of a file where all downloads are recorded.
+ min_views: An integer representing the minimum view count the video
+ must have in order to not be skipped.
+ Videos without view count information are always
+ downloaded. None for no limit.
+ max_views: An integer representing the maximum view count.
+ Videos that are more popular than that are not
+ downloaded.
+ Videos without view count information are always
+ downloaded. None for no limit.
+ download_archive: File name of a file where all downloads are recorded.
Videos already present in the file are not downloaded
again.
+ cookiefile: File name where cookies should be read from and dumped to.
+ nocheckcertificate:Do not verify SSL certificates
+ proxy: URL of the proxy server to use
+ socket_timeout: Time to wait for unresponsive hosts, in seconds
+ bidi_workaround: Work around buggy terminals without bidirectional text
+ support, using fridibi
The following parameters are not used by YoutubeDL itself, they are used by
the FileDownloader:
_num_downloads = None
_screen_file = None
- def __init__(self, params):
+ def __init__(self, params=None):
"""Create a FileDownloader object with the given options."""
self._ies = []
self._ies_instances = {}
self._download_retcode = 0
self._num_downloads = 0
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
+ self._err_file = sys.stderr
+ self.params = {} if params is None else params
+
+ if params.get('bidi_workaround', False):
+ try:
+ import pty
+ master, slave = pty.openpty()
+ width = get_term_width()
+ if width is None:
+ width_args = []
+ else:
+ width_args = ['-w', str(width)]
+ self._fribidi = subprocess.Popen(
+ ['fribidi', '-c', 'UTF-8'] + width_args,
+ stdin=subprocess.PIPE,
+ stdout=slave,
+ stderr=self._err_file)
+ self._fribidi_channel = os.fdopen(master, 'rb')
+ except OSError as ose:
+ if ose.errno == 2:
+ self.report_warning(u'Could not find fribidi executable, ignoring --bidi-workaround . Make sure that fribidi is an executable file in one of the directories in your $PATH.')
+ else:
+ raise
if (sys.version_info >= (3,) and sys.platform != 'win32' and
sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968']
u'Assuming --restrict-filenames since file system encoding '
u'cannot encode all charactes. '
u'Set the LC_ALL environment variable to fix this.')
- params['restrictfilenames'] = True
+ self.params['restrictfilenames'] = True
- self.params = params
self.fd = FileDownloader(self, self.params)
- if '%(stitle)s' in self.params['outtmpl']:
+ if '%(stitle)s' in self.params.get('outtmpl', ''):
self.report_warning(u'%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
+ self._setup_opener()
+
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
self._pps.append(pp)
pp.set_downloader(self)
+ def _bidi_workaround(self, message):
+ if not hasattr(self, '_fribidi_channel'):
+ return message
+
+ assert type(message) == type(u'')
+ line_count = message.count(u'\n') + 1
+ self._fribidi.stdin.write((message + u'\n').encode('utf-8'))
+ self._fribidi.stdin.flush()
+ res = u''.join(self._fribidi_channel.readline().decode('utf-8')
+ for _ in range(line_count))
+ return res[:-len(u'\n')]
+
def to_screen(self, message, skip_eol=False):
"""Print message to stdout if not in quiet mode."""
- if not self.params.get('quiet', False):
+ return self.to_stdout(message, skip_eol, check_quiet=True)
+
+ def to_stdout(self, message, skip_eol=False, check_quiet=False):
+ """Print message to stdout if not in quiet mode."""
+ if self.params.get('logger'):
+ self.params['logger'].debug(message)
+ elif not check_quiet or not self.params.get('quiet', False):
+ message = self._bidi_workaround(message)
terminator = [u'\n', u''][skip_eol]
output = message + terminator
+
write_string(output, self._screen_file)
def to_stderr(self, message):
"""Print message to stderr."""
assert type(message) == type(u'')
- output = message + u'\n'
- if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
- output = output.encode(preferredencoding())
- sys.stderr.write(output)
+ if self.params.get('logger'):
+ self.params['logger'].error(message)
+ else:
+ message = self._bidi_workaround(message)
+ output = message + u'\n'
+ write_string(output, self._err_file)
+
+ def to_console_title(self, message):
+ if not self.params.get('consoletitle', False):
+ return
+ if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
+ # c_wchar_p() might not be necessary if `message` is
+ # already of type unicode()
+ ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
+ elif 'TERM' in os.environ:
+ write_string(u'\033]0;%s\007' % message, self._screen_file)
+
+ def save_console_title(self):
+ if not self.params.get('consoletitle', False):
+ return
+ if 'TERM' in os.environ:
+ # Save the title on stack
+ write_string(u'\033[22;0t', self._screen_file)
+
+ def restore_console_title(self):
+ if not self.params.get('consoletitle', False):
+ return
+ if 'TERM' in os.environ:
+ # Restore the title from stack
+ write_string(u'\033[23;0t', self._screen_file)
+
+ def __enter__(self):
+ self.save_console_title()
+ return self
- def fixed_template(self):
- """Checks if the output template is fixed."""
- return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None)
+ def __exit__(self, *args):
+ self.restore_console_title()
+
+ if self.params.get('cookiefile') is not None:
+ self.cookiejar.save()
def trouble(self, message=None, tb=None):
"""Determine action to take when a download problem appears.
Print the message to stderr, it will be prefixed with 'WARNING:'
If stderr is a tty file the 'WARNING:' will be colored
'''
- if sys.stderr.isatty() and os.name != 'nt':
+ if self._err_file.isatty() and os.name != 'nt':
_msg_header = u'\033[0;33mWARNING:\033[0m'
else:
_msg_header = u'WARNING:'
Do the same as trouble, but prefixes the message with 'ERROR:', colored
in red if stderr is a tty file.
'''
- if sys.stderr.isatty() and os.name != 'nt':
+ if self._err_file.isatty() and os.name != 'nt':
_msg_header = u'\033[0;31mERROR:\033[0m'
else:
_msg_header = u'ERROR:'
error_message = u'%s %s' % (_msg_header, message)
self.trouble(error_message, tb)
- def report_writedescription(self, descfn):
- """ Report that the description file is being written """
- self.to_screen(u'[info] Writing video description to: ' + descfn)
-
- def report_writesubtitles(self, sub_filename):
- """ Report that the subtitles file is being written """
- self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename)
-
- def report_writeinfojson(self, infofn):
- """ Report that the metadata file has been written """
- self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
-
- def report_writeannotations(self, annofn):
- """ Report that the annotations file has been written. """
- self.to_screen(u'[info] Writing video annotations to: ' + annofn)
-
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
try:
self.to_screen(u'[download] %s has already been downloaded' % file_name)
- except (UnicodeEncodeError) as err:
+ except UnicodeEncodeError:
self.to_screen(u'[download] The file has already been downloaded')
def increment_downloads(self):
template_dict['playlist_index'] = u'%05d' % template_dict['playlist_index']
sanitize = lambda k, v: sanitize_filename(
- u'NA' if v is None else compat_str(v),
+ compat_str(v),
restricted=self.params.get('restrictfilenames'),
is_id=(k == u'id'))
template_dict = dict((k, sanitize(k, v))
- for k, v in template_dict.items())
+ for k, v in template_dict.items()
+ if v is not None)
+ template_dict = collections.defaultdict(lambda: u'NA', template_dict)
tmpl = os.path.expanduser(self.params['outtmpl'])
filename = tmpl % template_dict
return filename
- except KeyError as err:
- self.report_error(u'Erroneous output template')
- return None
except ValueError as err:
self.report_error(u'Error in output template: ' + str(err) + u' (encoding: ' + repr(preferredencoding()) + ')')
return None
def _match_entry(self, info_dict):
""" Returns None iff the file should be downloaded """
- title = info_dict['title']
- matchtitle = self.params.get('matchtitle', False)
- if matchtitle:
- if not re.search(matchtitle, title, re.IGNORECASE):
- return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
- rejecttitle = self.params.get('rejecttitle', False)
- if rejecttitle:
- if re.search(rejecttitle, title, re.IGNORECASE):
- return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
+ video_title = info_dict.get('title', info_dict.get('id', u'video'))
+ if 'title' in info_dict:
+ # This can happen when we're just evaluating the playlist
+ title = info_dict['title']
+ matchtitle = self.params.get('matchtitle', False)
+ if matchtitle:
+ if not re.search(matchtitle, title, re.IGNORECASE):
+ return u'"' + title + '" title did not match pattern "' + matchtitle + '"'
+ rejecttitle = self.params.get('rejecttitle', False)
+ if rejecttitle:
+ if re.search(rejecttitle, title, re.IGNORECASE):
+ return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
date = info_dict.get('upload_date', None)
if date is not None:
dateRange = self.params.get('daterange', DateRange())
if date not in dateRange:
- return u'[download] %s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
+ return u'%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
+ view_count = info_dict.get('view_count', None)
+ if view_count is not None:
+ min_views = self.params.get('min_views')
+ if min_views is not None and view_count < min_views:
+ return u'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views)
+ max_views = self.params.get('max_views')
+ if max_views is not None and view_count > max_views:
+ return u'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
age_limit = self.params.get('age_limit')
if age_limit is not None:
if age_limit < info_dict.get('age_limit', 0):
return u'Skipping "' + title + '" because it is age restricted'
if self.in_download_archive(info_dict):
- return (u'%(title)s has already been recorded in archive'
- % info_dict)
+ return u'%s has already been recorded in archive' % video_title
return None
- def extract_info(self, url, download=True, ie_key=None, extra_info={}):
+ @staticmethod
+ def add_extra_info(info_dict, extra_info):
+ '''Set the keys from extra_info in info dict if they are missing'''
+ for key, value in extra_info.items():
+ info_dict.setdefault(key, value)
+
+ def extract_info(self, url, download=True, ie_key=None, extra_info={},
+ process=True):
'''
Returns a list with a dictionary for each video we find.
If 'download', also downloads the videos.
break
if isinstance(ie_result, list):
# Backwards compatibility: old IE result format
- for result in ie_result:
- result.update(extra_info)
ie_result = {
'_type': 'compat_list',
'entries': ie_result,
}
+ self.add_extra_info(ie_result,
+ {
+ 'extractor': ie.IE_NAME,
+ 'webpage_url': url,
+ 'webpage_url_basename': url_basename(url),
+ 'extractor_key': ie.ie_key(),
+ })
+ if process:
+ return self.process_ie_result(ie_result, download, extra_info)
else:
- ie_result.update(extra_info)
- if 'extractor' not in ie_result:
- ie_result['extractor'] = ie.IE_NAME
- return self.process_ie_result(ie_result, download=download)
+ return ie_result
except ExtractorError as de: # An error we somewhat expected
self.report_error(compat_str(de), de.format_traceback())
break
result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system
if result_type == 'video':
- ie_result.update(extra_info)
- return self.process_video_result(ie_result)
+ self.add_extra_info(ie_result, extra_info)
+ return self.process_video_result(ie_result, download=download)
elif result_type == 'url':
# We have to add extra_info to the results because it may be
# contained in a playlist
download,
ie_key=ie_result.get('ie_key'),
extra_info=extra_info)
+ elif result_type == 'url_transparent':
+ # Use the information from the embedding page
+ info = self.extract_info(
+ ie_result['url'], ie_key=ie_result.get('ie_key'),
+ extra_info=extra_info, download=False, process=False)
+
+ def make_result(embedded_info):
+ new_result = ie_result.copy()
+ for f in ('_type', 'url', 'ext', 'player_url', 'formats',
+ 'entries', 'urlhandle', 'ie_key', 'duration',
+ 'subtitles', 'annotations', 'format',
+ 'thumbnail', 'thumbnails'):
+ if f in new_result:
+ del new_result[f]
+ if f in embedded_info:
+ new_result[f] = embedded_info[f]
+ return new_result
+ new_result = make_result(info)
+
+ assert new_result.get('_type') != 'url_transparent'
+ if new_result.get('_type') == 'compat_list':
+ new_result['entries'] = [
+ make_result(e) for e in new_result['entries']]
+
+ return self.process_ie_result(
+ new_result, download=download, extra_info=extra_info)
elif result_type == 'playlist':
# We process each entry in the playlist
playlist = ie_result.get('title', None) or ie_result.get('id', None)
n_all_entries = len(ie_result['entries'])
playliststart = self.params.get('playliststart', 1) - 1
- playlistend = self.params.get('playlistend', -1)
-
+ playlistend = self.params.get('playlistend', None)
+ # For backwards compatibility, interpret -1 as whole list
if playlistend == -1:
- entries = ie_result['entries'][playliststart:]
- else:
- entries = ie_result['entries'][playliststart:playlistend]
+ playlistend = None
+ entries = ie_result['entries'][playliststart:playlistend]
n_entries = len(entries)
- self.to_screen(u"[%s] playlist '%s': Collected %d video ids (downloading %d of them)" %
+ self.to_screen(
+ u"[%s] playlist '%s': Collected %d video ids (downloading %d of them)" %
(ie_result['extractor'], playlist, n_all_entries, n_entries))
for i, entry in enumerate(entries, 1):
extra = {
'playlist': playlist,
'playlist_index': i + playliststart,
+ 'extractor': ie_result['extractor'],
+ 'webpage_url': ie_result['webpage_url'],
+ 'webpage_url_basename': url_basename(ie_result['webpage_url']),
+ 'extractor_key': ie_result['extractor_key'],
}
- if not 'extractor' in entry:
- # We set the extractor, if it's an url it will be set then to
- # the new extractor, but if it's already a video we must make
- # sure it's present: see issue #877
- entry['extractor'] = ie_result['extractor']
+
+ reason = self._match_entry(entry)
+ if reason is not None:
+ self.to_screen(u'[download] ' + reason)
+ continue
+
entry_result = self.process_ie_result(entry,
download=download,
extra_info=extra)
return ie_result
elif result_type == 'compat_list':
def _fixup(r):
- r.setdefault('extractor', ie_result['extractor'])
+ self.add_extra_info(r,
+ {
+ 'extractor': ie_result['extractor'],
+ 'webpage_url': ie_result['webpage_url'],
+ 'webpage_url_basename': url_basename(ie_result['webpage_url']),
+ 'extractor_key': ie_result['extractor_key'],
+ })
return r
ie_result['entries'] = [
- self.process_ie_result(_fixup(r), download=download)
+ self.process_ie_result(_fixup(r), download, extra_info)
for r in ie_result['entries']
]
return ie_result
# Forced printings
if self.params.get('forcetitle', False):
- compat_print(info_dict['title'])
+ self.to_stdout(info_dict['fulltitle'])
if self.params.get('forceid', False):
- compat_print(info_dict['id'])
+ self.to_stdout(info_dict['id'])
if self.params.get('forceurl', False):
# For RTMP URLs, also include the playpath
- compat_print(info_dict['url'] + info_dict.get('play_path', u''))
+ self.to_stdout(info_dict['url'] + info_dict.get('play_path', u''))
if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None:
- compat_print(info_dict['thumbnail'])
+ self.to_stdout(info_dict['thumbnail'])
if self.params.get('forcedescription', False) and info_dict.get('description') is not None:
- compat_print(info_dict['description'])
+ self.to_stdout(info_dict['description'])
if self.params.get('forcefilename', False) and filename is not None:
- compat_print(filename)
+ self.to_stdout(filename)
+ if self.params.get('forceduration', False) and info_dict.get('duration') is not None:
+ self.to_stdout(formatSeconds(info_dict['duration']))
if self.params.get('forceformat', False):
- compat_print(info_dict['format'])
+ self.to_stdout(info_dict['format'])
+ if self.params.get('forcejson', False):
+ info_dict['_filename'] = filename
+ self.to_stdout(json.dumps(info_dict))
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
return
if self.params.get('writedescription', False):
- try:
- descfn = filename + u'.description'
- self.report_writedescription(descfn)
- with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
- descfile.write(info_dict['description'])
- except (KeyError, TypeError):
- self.report_warning(u'There\'s no description to write.')
- except (OSError, IOError):
- self.report_error(u'Cannot write description file ' + descfn)
- return
+ descfn = filename + u'.description'
+ if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)):
+ self.to_screen(u'[info] Video description is already present')
+ else:
+ try:
+ self.to_screen(u'[info] Writing video description to: ' + descfn)
+ with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
+ descfile.write(info_dict['description'])
+ except (KeyError, TypeError):
+ self.report_warning(u'There\'s no description to write.')
+ except (OSError, IOError):
+ self.report_error(u'Cannot write description file ' + descfn)
+ return
if self.params.get('writeannotations', False):
- try:
- annofn = filename + u'.annotations.xml'
- self.report_writeannotations(annofn)
- with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile:
- annofile.write(info_dict['annotations'])
- except (KeyError, TypeError):
- self.report_warning(u'There are no annotations to write.')
- except (OSError, IOError):
- self.report_error(u'Cannot write annotations file: ' + annofn)
- return
+ annofn = filename + u'.annotations.xml'
+ if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)):
+ self.to_screen(u'[info] Video annotations are already present')
+ else:
+ try:
+ self.to_screen(u'[info] Writing video annotations to: ' + annofn)
+ with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile:
+ annofile.write(info_dict['annotations'])
+ except (KeyError, TypeError):
+ self.report_warning(u'There are no annotations to write.')
+ except (OSError, IOError):
+ self.report_error(u'Cannot write annotations file: ' + annofn)
+ return
subtitles_are_requested = any([self.params.get('writesubtitles', False),
self.params.get('writeautomaticsub')])
# subtitles download errors are already managed as troubles in relevant IE
# that way it will silently go on when used with unsupporting IE
subtitles = info_dict['subtitles']
- sub_format = self.params.get('subtitlesformat')
+ sub_format = self.params.get('subtitlesformat', 'srt')
for sub_lang in subtitles.keys():
sub = subtitles[sub_lang]
if sub is None:
continue
try:
sub_filename = subtitles_filename(filename, sub_lang, sub_format)
- self.report_writesubtitles(sub_filename)
- with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
- subfile.write(sub)
+ if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)):
+ self.to_screen(u'[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format))
+ else:
+ self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename)
+ with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
+ subfile.write(sub)
except (OSError, IOError):
self.report_error(u'Cannot write subtitles file ' + descfn)
return
if self.params.get('writeinfojson', False):
- infofn = filename + u'.info.json'
- self.report_writeinfojson(infofn)
- try:
- json_info_dict = dict((k, v) for k, v in info_dict.items() if not k in ['urlhandle'])
- write_json_file(json_info_dict, encodeFilename(infofn))
- except (OSError, IOError):
- self.report_error(u'Cannot write metadata to JSON file ' + infofn)
- return
+ infofn = os.path.splitext(filename)[0] + u'.info.json'
+ if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)):
+ self.to_screen(u'[info] Video description metadata is already present')
+ else:
+ self.to_screen(u'[info] Writing video description metadata as JSON to: ' + infofn)
+ try:
+ json_info_dict = dict((k, v) for k, v in info_dict.items() if not k in ['urlhandle'])
+ write_json_file(json_info_dict, encodeFilename(infofn))
+ except (OSError, IOError):
+ self.report_error(u'Cannot write metadata to JSON file ' + infofn)
+ return
if self.params.get('writethumbnail', False):
if info_dict.get('thumbnail') is not None:
thumb_format = determine_ext(info_dict['thumbnail'], u'jpg')
- thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format
- self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
- (info_dict['extractor'], info_dict['id']))
- try:
- uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
- with open(thumb_filename, 'wb') as thumbf:
- shutil.copyfileobj(uf, thumbf)
- self.to_screen(u'[%s] %s: Writing thumbnail to: %s' %
- (info_dict['extractor'], info_dict['id'], thumb_filename))
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self.report_warning(u'Unable to download thumbnail "%s": %s' %
- (info_dict['thumbnail'], compat_str(err)))
+ thumb_filename = os.path.splitext(filename)[0] + u'.' + thumb_format
+ if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
+ self.to_screen(u'[%s] %s: Thumbnail is already present' %
+ (info_dict['extractor'], info_dict['id']))
+ else:
+ self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
+ (info_dict['extractor'], info_dict['id']))
+ try:
+ uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
+ with open(thumb_filename, 'wb') as thumbf:
+ shutil.copyfileobj(uf, thumbf)
+ self.to_screen(u'[%s] %s: Writing thumbnail to: %s' %
+ (info_dict['extractor'], info_dict['id'], thumb_filename))
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self.report_warning(u'Unable to download thumbnail "%s": %s' %
+ (info_dict['thumbnail'], compat_str(err)))
if not self.params.get('skip_download', False):
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
def download(self, url_list):
"""Download a given list of URLs."""
- if len(url_list) > 1 and self.fixed_template():
+ if (len(url_list) > 1 and
+ '%' not in self.params['outtmpl']
+ and self.params.get('max_downloads') != 1):
raise SameFileError(self.params['outtmpl'])
for url in url_list:
try:
#It also downloads the videos
- videos = self.extract_info(url)
+ self.extract_info(url)
except UnavailableVideoError:
self.report_error(u'unable to download video')
except MaxDownloadsReached:
return self._download_retcode
+ def download_with_info_file(self, info_filename):
+ with io.open(info_filename, 'r', encoding='utf-8') as f:
+ info = json.load(f)
+ try:
+ self.process_ie_result(info, download=True)
+ except DownloadError:
+ webpage_url = info.get('webpage_url')
+ if webpage_url is not None:
+ self.report_warning(u'The info failed to download, trying with "%s"' % webpage_url)
+ return self.download([webpage_url])
+ else:
+ raise
+ return self._download_retcode
+
def post_process(self, filename, ie_info):
"""Run all the postprocessors on the given file."""
info = dict(ie_info)
except (IOError, OSError):
self.report_warning(u'Unable to remove downloaded video file')
+ def _make_archive_id(self, info_dict):
+ # Future-proof against any change in case
+ # and backwards compatibility with prior versions
+ extractor = info_dict.get('extractor_key')
+ if extractor is None:
+ if 'id' in info_dict:
+ extractor = info_dict.get('ie_key') # key in a playlist
+ if extractor is None:
+ return None # Incomplete video information
+ return extractor.lower() + u' ' + info_dict['id']
+
def in_download_archive(self, info_dict):
fn = self.params.get('download_archive')
if fn is None:
return False
- vid_id = info_dict['extractor'] + u' ' + info_dict['id']
+
+ vid_id = self._make_archive_id(info_dict)
+ if vid_id is None:
+ return False # Incomplete video information
+
try:
with locked_file(fn, 'r', encoding='utf-8') as archive_file:
for line in archive_file:
fn = self.params.get('download_archive')
if fn is None:
return
- vid_id = info_dict['extractor'] + u' ' + info_dict['id']
+ vid_id = self._make_archive_id(info_dict)
+ assert vid_id
with locked_file(fn, 'a', encoding='utf-8') as archive_file:
archive_file.write(vid_id + u'\n')
@staticmethod
def format_resolution(format, default='unknown'):
+ if format.get('vcodec') == 'none':
+ return 'audio only'
if format.get('_resolution') is not None:
return format['_resolution']
if format.get('height') is not None:
return res
def list_formats(self, info_dict):
- def line(format):
- return (u'%-15s%-10s%-12s%s' % (
+ def format_note(fdict):
+ res = u''
+ if fdict.get('format_note') is not None:
+ res += fdict['format_note'] + u' '
+ if (fdict.get('vcodec') is not None and
+ fdict.get('vcodec') != 'none'):
+ res += u'%-5s' % fdict['vcodec']
+ elif fdict.get('vbr') is not None:
+ res += u'video'
+ if fdict.get('vbr') is not None:
+ res += u'@%4dk' % fdict['vbr']
+ if fdict.get('acodec') is not None:
+ if res:
+ res += u', '
+ res += u'%-5s' % fdict['acodec']
+ elif fdict.get('abr') is not None:
+ if res:
+ res += u', '
+ res += 'audio'
+ if fdict.get('abr') is not None:
+ res += u'@%3dk' % fdict['abr']
+ if fdict.get('filesize') is not None:
+ if res:
+ res += u', '
+ res += format_bytes(fdict['filesize'])
+ return res
+
+ def line(format, idlen=20):
+ return ((u'%-' + compat_str(idlen + 1) + u's%-10s%-12s%s') % (
format['format_id'],
format['ext'],
self.format_resolution(format),
- format.get('format_note', ''),
- )
- )
+ format_note(format),
+ ))
formats = info_dict.get('formats', [info_dict])
- formats_s = list(map(line, formats))
+ idlen = max(len(u'format code'),
+ max(len(f['format_id']) for f in formats))
+ formats_s = [line(f, idlen) for f in formats]
if len(formats) > 1:
- formats_s[0] += (' ' if formats[0].get('format_note') else '') + '(worst)'
- formats_s[-1] += (' ' if formats[-1].get('format_note') else '') + '(best)'
+ formats_s[0] += (' ' if format_note(formats[0]) else '') + '(worst)'
+ formats_s[-1] += (' ' if format_note(formats[-1]) else '') + '(best)'
header_line = line({
'format_id': u'format code', 'ext': u'extension',
- '_resolution': u'resolution', 'format_note': u'note'})
+ '_resolution': u'resolution', 'format_note': u'note'}, idlen=idlen)
self.to_screen(u'[info] Available formats for %s:\n%s\n%s' %
(info_dict['id'], header_line, u"\n".join(formats_s)))
+
+ def urlopen(self, req):
+ """ Start an HTTP download """
+ return self._opener.open(req)
+
+ def print_debug_header(self):
+ if not self.params.get('verbose'):
+ return
+ write_string(u'[debug] youtube-dl version ' + __version__ + u'\n')
+ try:
+ sp = subprocess.Popen(
+ ['git', 'rev-parse', '--short', 'HEAD'],
+ stdout=subprocess.PIPE, stderr=subprocess.PIPE,
+ cwd=os.path.dirname(os.path.abspath(__file__)))
+ out, err = sp.communicate()
+ out = out.decode().strip()
+ if re.match('[0-9a-f]+', out):
+ write_string(u'[debug] Git HEAD: ' + out + u'\n')
+ except:
+ try:
+ sys.exc_clear()
+ except:
+ pass
+ write_string(u'[debug] Python version %s - %s' %
+ (platform.python_version(), platform_name()) + u'\n')
+
+ proxy_map = {}
+ for handler in self._opener.handlers:
+ if hasattr(handler, 'proxies'):
+ proxy_map.update(handler.proxies)
+ write_string(u'[debug] Proxy map: ' + compat_str(proxy_map) + u'\n')
+
+ def _setup_opener(self):
+ timeout_val = self.params.get('socket_timeout')
+ timeout = 600 if timeout_val is None else float(timeout_val)
+
+ opts_cookiefile = self.params.get('cookiefile')
+ opts_proxy = self.params.get('proxy')
+
+ if opts_cookiefile is None:
+ self.cookiejar = compat_cookiejar.CookieJar()
+ else:
+ self.cookiejar = compat_cookiejar.MozillaCookieJar(
+ opts_cookiefile)
+ if os.access(opts_cookiefile, os.R_OK):
+ self.cookiejar.load()
+
+ cookie_processor = compat_urllib_request.HTTPCookieProcessor(
+ self.cookiejar)
+ if opts_proxy is not None:
+ if opts_proxy == '':
+ proxies = {}
+ else:
+ proxies = {'http': opts_proxy, 'https': opts_proxy}
+ else:
+ proxies = compat_urllib_request.getproxies()
+ # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805)
+ if 'http' in proxies and 'https' not in proxies:
+ proxies['https'] = proxies['http']
+ proxy_handler = compat_urllib_request.ProxyHandler(proxies)
+ https_handler = make_HTTPS_handler(
+ self.params.get('nocheckcertificate', False))
+ opener = compat_urllib_request.build_opener(
+ https_handler, proxy_handler, cookie_processor, YoutubeDLHandler())
+ # Delete the default user-agent header, which would otherwise apply in
+ # cases where our custom HTTP handler doesn't come into play
+ # (See https://github.com/rg3/youtube-dl/issues/1309 for details)
+ opener.addheaders = []
+ self._opener = opener
+
+ # TODO remove this global modification
+ compat_urllib_request.install_opener(opener)
+ socket.setdefaulttimeout(timeout)
'Ismael Mejía',
'Steffan \'Ruirize\' James',
'Andras Elso',
+ 'Jelle van der Waa',
+ 'Marcin Cieślak',
+ 'Anton Larionov',
+ 'Takuya Tsuchida',
+ 'Sergey M.',
+ 'Michael Orlitzky',
)
__license__ = 'Public Domain'
import codecs
-import collections
import getpass
import optparse
import os
import random
import re
import shlex
-import socket
-import subprocess
import sys
-import traceback
-import platform
from .utils import (
- compat_cookiejar,
compat_print,
- compat_str,
- compat_urllib_request,
DateRange,
decodeOption,
determine_ext,
+ get_term_width,
DownloadError,
get_cachedir,
- make_HTTPS_handler,
MaxDownloadsReached,
- platform_name,
preferredencoding,
SameFileError,
+ setproctitle,
std_headers,
write_string,
- YoutubeDLHandler,
)
from .update import update_self
-from .version import __version__
from .FileDownloader import (
FileDownloader,
)
from .extractor import gen_extractors
+from .version import __version__
from .YoutubeDL import YoutubeDL
from .PostProcessor import (
FFmpegMetadataPP,
def parseOpts(overrideArguments=None):
- def _readOptions(filename_bytes):
+ def _readOptions(filename_bytes, default=[]):
try:
optionf = open(filename_bytes)
except IOError:
- return [] # silently skip if file is not present
+ return default # silently skip if file is not present
try:
res = []
for l in optionf:
def _comma_separated_values_options_callback(option, opt_str, value, parser):
setattr(parser.values, option.dest, value.split(','))
- def _find_term_columns():
- columns = os.environ.get('COLUMNS', None)
- if columns:
- return int(columns)
-
- try:
- sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
- out,err = sp.communicate()
- return int(out.split()[1])
- except:
- pass
- return None
-
def _hide_login_info(opts):
opts = list(opts)
for private_opt in ['-p', '--password', '-u', '--username', '--video-password']:
max_help_position = 80
# No need to wrap help messages if we're on a wide console
- columns = _find_term_columns()
+ columns = get_term_width()
if columns: max_width = columns
fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position)
general.add_option('--extractor-descriptions',
action='store_true', dest='list_extractor_descriptions',
help='Output descriptions of all supported extractors', default=False)
- general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy', metavar='URL')
+ general.add_option(
+ '--proxy', dest='proxy', default=None, metavar='URL',
+ help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection')
general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
general.add_option(
'--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',
general.add_option(
'--no-cache-dir', action='store_const', const=None, dest='cachedir',
help='Disable filesystem caching')
-
-
- selection.add_option('--playlist-start',
- dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is %default)', default=1)
- selection.add_option('--playlist-end',
- dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
+ general.add_option(
+ '--socket-timeout', dest='socket_timeout',
+ type=float, default=None, help=optparse.SUPPRESS_HELP)
+ general.add_option(
+ '--bidi-workaround', dest='bidi_workaround', action='store_true',
+ help=u'Work around terminals that lack bidirectional text support. Requires fribidi executable in PATH')
+
+
+ selection.add_option(
+ '--playlist-start',
+ dest='playliststart', metavar='NUMBER', default=1, type=int,
+ help='playlist video to start at (default is %default)')
+ selection.add_option(
+ '--playlist-end',
+ dest='playlistend', metavar='NUMBER', default=None, type=int,
+ help='playlist video to end at (default is last)')
selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
- selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None)
+ selection.add_option('--max-downloads', metavar='NUMBER',
+ dest='max_downloads', type=int, default=None,
+ help='Abort after downloading NUMBER files')
selection.add_option('--min-filesize', metavar='SIZE', dest='min_filesize', help="Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)", default=None)
selection.add_option('--max-filesize', metavar='SIZE', dest='max_filesize', help="Do not download any videos larger than SIZE (e.g. 50k or 44.6m)", default=None)
selection.add_option('--date', metavar='DATE', dest='date', help='download only videos uploaded in this date', default=None)
selection.add_option('--datebefore', metavar='DATE', dest='datebefore', help='download only videos uploaded before this date', default=None)
selection.add_option('--dateafter', metavar='DATE', dest='dateafter', help='download only videos uploaded after this date', default=None)
+ selection.add_option(
+ '--min-views', metavar='COUNT', dest='min_views',
+ default=None, type=int,
+ help="Do not download any videos with less than COUNT views",)
+ selection.add_option(
+ '--max-views', metavar='COUNT', dest='max_views',
+ default=None, type=int,
+ help="Do not download any videos with more than COUNT views",)
selection.add_option('--no-playlist', action='store_true', dest='noplaylist', help='download only the currently playing video', default=False)
selection.add_option('--age-limit', metavar='YEARS', dest='age_limit',
help='download only videos suitable for the given age',
default=None, type=int)
selection.add_option('--download-archive', metavar='FILE',
dest='download_archive',
- help='Download only videos not present in the archive file. Record all downloaded videos in it.')
+ help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.')
authentication.add_option('-u', '--username',
video_format.add_option('-f', '--format',
action='store', dest='format', metavar='FORMAT', default='best',
- help='video format code, specifiy the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported')
+ help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported')
video_format.add_option('--all-formats',
action='store_const', dest='format', help='download all available video formats', const='all')
video_format.add_option('--prefer-free-formats',
verbosity.add_option('--get-description',
action='store_true', dest='getdescription',
help='simulate, quiet but print video description', default=False)
+ verbosity.add_option('--get-duration',
+ action='store_true', dest='getduration',
+ help='simulate, quiet but print video length', default=False)
verbosity.add_option('--get-filename',
action='store_true', dest='getfilename',
help='simulate, quiet but print output filename', default=False)
verbosity.add_option('--get-format',
action='store_true', dest='getformat',
help='simulate, quiet but print output format', default=False)
+ verbosity.add_option('-j', '--dump-json',
+ action='store_true', dest='dumpjson',
+ help='simulate, quiet but print JSON information', default=False)
verbosity.add_option('--newline',
action='store_true', dest='progress_with_newline', help='output progress bar as new lines', default=False)
verbosity.add_option('--no-progress',
help='print downloaded pages to debug problems(very verbose)')
verbosity.add_option('--write-pages',
action='store_true', dest='write_pages', default=False,
- help='Write downloaded pages to files in the current directory')
+ help='Write downloaded intermediary pages to files in the current directory to debug problems')
verbosity.add_option('--youtube-print-sig-code',
action='store_true', dest='youtube_print_sig_code', default=False,
help=optparse.SUPPRESS_HELP)
'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .'))
filesystem.add_option('--autonumber-size',
dest='autonumber_size', metavar='NUMBER',
- help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --autonumber option is given')
+ help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given')
filesystem.add_option('--restrict-filenames',
action='store_true', dest='restrictfilenames',
help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
filesystem.add_option('-a', '--batch-file',
dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
+ filesystem.add_option('--load-info',
+ dest='load_info_filename', metavar='FILE',
+ help='json file containing the video information (created with the "--write-json" option')
filesystem.add_option('-w', '--no-overwrites',
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
filesystem.add_option('-c', '--continue',
- action='store_true', dest='continue_dl', help='resume partially downloaded files', default=True)
+ action='store_true', dest='continue_dl', help='force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.', default=True)
filesystem.add_option('--no-continue',
action='store_false', dest='continue_dl',
help='do not resume partially downloaded files (restart from beginning)')
if opts.verbose:
write_string(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
else:
+ systemConf = _readOptions('/etc/youtube-dl.conf')
+
xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
if xdg_config_home:
userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config')
userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config')
if not os.path.isfile(userConfFile):
userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
- systemConf = _readOptions('/etc/youtube-dl.conf')
- userConf = _readOptions(userConfFile)
+ userConf = _readOptions(userConfFile, None)
+
+ if userConf is None:
+ appdata_dir = os.environ.get('appdata')
+ if appdata_dir:
+ userConf = _readOptions(
+ os.path.join(appdata_dir, 'youtube-dl', 'config'),
+ default=None)
+ if userConf is None:
+ userConf = _readOptions(
+ os.path.join(appdata_dir, 'youtube-dl', 'config.txt'),
+ default=None)
+
+ if userConf is None:
+ userConf = _readOptions(
+ os.path.join(os.path.expanduser('~'), 'youtube-dl.conf'),
+ default=None)
+ if userConf is None:
+ userConf = _readOptions(
+ os.path.join(os.path.expanduser('~'), 'youtube-dl.conf.txt'),
+ default=None)
+
+ if userConf is None:
+ userConf = []
+
commandLineConf = sys.argv[1:]
argv = systemConf + userConf + commandLineConf
opts, args = parser.parse_args(argv)
return parser, opts, args
+
def _real_main(argv=None):
# Compatibility fixes for Windows
if sys.platform == 'win32':
# https://github.com/rg3/youtube-dl/issues/820
codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
+ setproctitle(u'youtube-dl')
+
parser, opts, args = parseOpts(argv)
- # Open appropriate CookieJar
- if opts.cookiefile is None:
- jar = compat_cookiejar.CookieJar()
- else:
- try:
- jar = compat_cookiejar.MozillaCookieJar(opts.cookiefile)
- if os.access(opts.cookiefile, os.R_OK):
- jar.load()
- except (IOError, OSError) as err:
- if opts.verbose:
- traceback.print_exc()
- write_string(u'ERROR: unable to open cookie file\n')
- sys.exit(101)
# Set user agent
if opts.user_agent is not None:
std_headers['User-Agent'] = opts.user_agent
all_urls = batchurls + args
all_urls = [url.strip() for url in all_urls]
- opener = _setup_opener(jar=jar, opts=opts)
-
extractors = gen_extractors()
if opts.list_extractors:
if opts.retries is not None:
try:
opts.retries = int(opts.retries)
- except (TypeError, ValueError) as err:
+ except (TypeError, ValueError):
parser.error(u'invalid retry count specified')
if opts.buffersize is not None:
numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
if numeric_buffersize is None:
parser.error(u'invalid buffer size specified')
opts.buffersize = numeric_buffersize
- try:
- opts.playliststart = int(opts.playliststart)
- if opts.playliststart <= 0:
- raise ValueError(u'Playlist start must be positive')
- except (TypeError, ValueError) as err:
- parser.error(u'invalid playlist start number specified')
- try:
- opts.playlistend = int(opts.playlistend)
- if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
- raise ValueError(u'Playlist end must be greater than playlist start')
- except (TypeError, ValueError) as err:
- parser.error(u'invalid playlist end number specified')
+ if opts.playliststart <= 0:
+ raise ValueError(u'Playlist start must be positive')
+ if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
+ raise ValueError(u'Playlist end must be greater than playlist start')
if opts.extractaudio:
if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
parser.error(u'invalid audio format specified')
or (opts.useid and u'%(id)s.%(ext)s')
or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
or u'%(title)s-%(id)s.%(ext)s')
- if '%(ext)s' not in outtmpl and opts.extractaudio:
+ if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
parser.error(u'Cannot download a video and extract audio into the same'
- u' file! Use "%%(ext)s" instead of %r' %
- determine_ext(outtmpl, u''))
+ u' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
+ u' template'.format(outtmpl))
+
+ any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson
- # YoutubeDL
- ydl = YoutubeDL({
+ ydl_opts = {
'usenetrc': opts.usenetrc,
'username': opts.username,
'password': opts.password,
'videopassword': opts.videopassword,
- 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
+ 'quiet': (opts.quiet or any_printing),
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
'forceid': opts.getid,
'forcethumbnail': opts.getthumbnail,
'forcedescription': opts.getdescription,
+ 'forceduration': opts.getduration,
'forcefilename': opts.getfilename,
'forceformat': opts.getformat,
+ 'forcejson': opts.dumpjson,
'simulate': opts.simulate,
- 'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
+ 'skip_download': (opts.skip_download or opts.simulate or any_printing),
'format': opts.format,
'format_limit': opts.format_limit,
'listformats': opts.listformats,
'keepvideo': opts.keepvideo,
'min_filesize': opts.min_filesize,
'max_filesize': opts.max_filesize,
+ 'min_views': opts.min_views,
+ 'max_views': opts.max_views,
'daterange': date,
'cachedir': opts.cachedir,
'youtube_print_sig_code': opts.youtube_print_sig_code,
'age_limit': opts.age_limit,
'download_archive': opts.download_archive,
- })
-
- if opts.verbose:
- write_string(u'[debug] youtube-dl version ' + __version__ + u'\n')
- try:
- sp = subprocess.Popen(
- ['git', 'rev-parse', '--short', 'HEAD'],
- stdout=subprocess.PIPE, stderr=subprocess.PIPE,
- cwd=os.path.dirname(os.path.abspath(__file__)))
- out, err = sp.communicate()
- out = out.decode().strip()
- if re.match('[0-9a-f]+', out):
- write_string(u'[debug] Git HEAD: ' + out + u'\n')
- except:
- try:
- sys.exc_clear()
- except:
- pass
- write_string(u'[debug] Python version %s - %s' %(platform.python_version(), platform_name()) + u'\n')
-
- proxy_map = {}
- for handler in opener.handlers:
- if hasattr(handler, 'proxies'):
- proxy_map.update(handler.proxies)
- write_string(u'[debug] Proxy map: ' + compat_str(proxy_map) + u'\n')
-
- ydl.add_default_info_extractors()
-
- # PostProcessors
- # Add the metadata pp first, the other pps will copy it
- if opts.addmetadata:
- ydl.add_post_processor(FFmpegMetadataPP())
- if opts.extractaudio:
- ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
- if opts.recodevideo:
- ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
- if opts.embedsubtitles:
- ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
-
- # Update version
- if opts.update_self:
- update_self(ydl.to_screen, opts.verbose)
-
- # Maybe do nothing
- if len(all_urls) < 1:
- if not opts.update_self:
- parser.error(u'you must provide at least one URL')
- else:
- sys.exit()
+ 'cookiefile': opts.cookiefile,
+ 'nocheckcertificate': opts.no_check_certificate,
+ 'proxy': opts.proxy,
+ 'socket_timeout': opts.socket_timeout,
+ 'bidi_workaround': opts.bidi_workaround,
+ }
- try:
- retcode = ydl.download(all_urls)
- except MaxDownloadsReached:
- ydl.to_screen(u'--max-download limit reached, aborting.')
- retcode = 101
+ with YoutubeDL(ydl_opts) as ydl:
+ ydl.print_debug_header()
+ ydl.add_default_info_extractors()
+
+ # PostProcessors
+ # Add the metadata pp first, the other pps will copy it
+ if opts.addmetadata:
+ ydl.add_post_processor(FFmpegMetadataPP())
+ if opts.extractaudio:
+ ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
+ if opts.recodevideo:
+ ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
+ if opts.embedsubtitles:
+ ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
+
+ # Update version
+ if opts.update_self:
+ update_self(ydl.to_screen, opts.verbose)
+
+ # Maybe do nothing
+ if (len(all_urls) < 1) and (opts.load_info_filename is None):
+ if not opts.update_self:
+ parser.error(u'you must provide at least one URL')
+ else:
+ sys.exit()
- # Dump cookie jar if requested
- if opts.cookiefile is not None:
try:
- jar.save()
- except (IOError, OSError):
- sys.exit(u'ERROR: unable to save cookie jar')
+ if opts.load_info_filename is not None:
+ retcode = ydl.download_with_info_file(opts.load_info_filename)
+ else:
+ retcode = ydl.download(all_urls)
+ except MaxDownloadsReached:
+ ydl.to_screen(u'--max-download limit reached, aborting.')
+ retcode = 101
sys.exit(retcode)
-def _setup_opener(jar=None, opts=None, timeout=300):
- if opts is None:
- FakeOptions = collections.namedtuple(
- 'FakeOptions', ['proxy', 'no_check_certificate'])
- opts = FakeOptions(proxy=None, no_check_certificate=False)
-
- cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
- if opts.proxy is not None:
- if opts.proxy == '':
- proxies = {}
- else:
- proxies = {'http': opts.proxy, 'https': opts.proxy}
- else:
- proxies = compat_urllib_request.getproxies()
- # Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805)
- if 'http' in proxies and 'https' not in proxies:
- proxies['https'] = proxies['http']
- proxy_handler = compat_urllib_request.ProxyHandler(proxies)
- https_handler = make_HTTPS_handler(opts)
- opener = compat_urllib_request.build_opener(
- https_handler, proxy_handler, cookie_processor, YoutubeDLHandler())
- # Delete the default user-agent header, which would otherwise apply in
- # cases where our custom HTTP handler doesn't come into play
- # (See https://github.com/rg3/youtube-dl/issues/1309 for details)
- opener.addheaders = []
- compat_urllib_request.install_opener(opener)
- socket.setdefaulttimeout(timeout)
- return opener
-
-
def main(argv=None):
try:
_real_main(argv)
-from .appletrailers import AppleTrailersIE
+from .academicearth import AcademicEarthCourseIE
from .addanime import AddAnimeIE
+from .anitube import AnitubeIE
+from .aparat import AparatIE
+from .appletrailers import AppleTrailersIE
from .archiveorg import ArchiveOrgIE
from .ard import ARDIE
from .arte import (
ArteTVPlus7IE,
ArteTVCreativeIE,
ArteTVFutureIE,
+ ArteTVDDCIE,
)
from .auengine import AUEngineIE
-from .bandcamp import BandcampIE
+from .bambuser import BambuserIE, BambuserChannelIE
+from .bandcamp import BandcampIE, BandcampAlbumIE
+from .blinkx import BlinkxIE
from .bliptv import BlipTVIE, BlipTVUserIE
from .bloomberg import BloombergIE
from .breakcom import BreakIE
from .c56 import C56IE
from .canalplus import CanalplusIE
from .canalc2 import Canalc2IE
+from .cbs import CBSIE
+from .channel9 import Channel9IE
from .cinemassacre import CinemassacreIE
+from .clipfish import ClipfishIE
+from .clipsyndicate import ClipsyndicateIE
from .cnn import CNNIE
from .collegehumor import CollegeHumorIE
-from .comedycentral import ComedyCentralIE
+from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
from .condenast import CondeNastIE
from .criterion import CriterionIE
from .crunchyroll import CrunchyrollIE
from .cspan import CSpanIE
+from .d8 import D8IE
from .dailymotion import (
DailymotionIE,
DailymotionPlaylistIE,
from .ebaumsworld import EbaumsWorldIE
from .ehow import EHowIE
from .eighttracks import EightTracksIE
+from .eitb import EitbIE
from .escapist import EscapistIE
from .exfm import ExfmIE
+from .extremetube import ExtremeTubeIE
from .facebook import FacebookIE
from .faz import FazIE
from .fktv import (
from .francetv import (
PluzzIE,
FranceTvInfoIE,
- France2IE,
+ FranceTVIE,
GenerationQuoiIE
)
from .freesound import FreesoundIE
from .funnyordie import FunnyOrDieIE
+from .gamekings import GamekingsIE
from .gamespot import GameSpotIE
from .gametrailers import GametrailersIE
from .generic import GenericIE
from .howcast import HowcastIE
from .hypem import HypemIE
from .ign import IGNIE, OneUPIE
+from .imdb import ImdbIE
from .ina import InaIE
from .infoq import InfoQIE
from .instagram import InstagramIE
from .internetvideoarchive import InternetVideoArchiveIE
+from .ivi import (
+ IviIE,
+ IviCompilationIE
+)
from .jeuxvideo import JeuxVideoIE
from .jukebox import JukeboxIE
from .justintv import JustinTVIE
from .kickstarter import KickStarterIE
from .keek import KeekIE
from .liveleak import LiveLeakIE
-from .livestream import LivestreamIE
+from .livestream import LivestreamIE, LivestreamOriginalIE
+from .mdr import MDRIE
from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
from .mit import TechTVMITIE, MITIE
from .mixcloud import MixcloudIE
+from .mofosex import MofosexIE
from .mtv import MTVIE
from .muzu import MuzuTVIE
from .myspace import MySpaceIE
from .naver import NaverIE
from .nba import NBAIE
from .nbc import NBCNewsIE
+from .ndtv import NDTVIE
from .newgrounds import NewgroundsIE
from .nhl import NHLIE, NHLVideocenterIE
+from .niconico import NiconicoIE
+from .ninegag import NineGagIE
from .nowvideo import NowVideoIE
from .ooyala import OoyalaIE
from .orf import ORFIE
from .pbs import PBSIE
from .photobucket import PhotobucketIE
+from .podomatic import PodomaticIE
+from .pornhd import PornHdIE
from .pornhub import PornHubIE
from .pornotube import PornotubeIE
+from .pyvideo import PyvideoIE
+from .radiofrance import RadioFranceIE
from .rbmaradio import RBMARadioIE
from .redtube import RedTubeIE
from .ringtv import RingTVIE
from .sina import SinaIE
from .slashdot import SlashdotIE
from .slideshare import SlideshareIE
+from .smotri import (
+ SmotriIE,
+ SmotriCommunityIE,
+ SmotriUserIE,
+ SmotriBroadcastIE,
+)
from .sohu import SohuIE
from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
-from .southparkstudios import SouthParkStudiosIE
+from .southparkstudios import (
+ SouthParkStudiosIE,
+ SouthparkDeIE,
+)
+from .space import SpaceIE
from .spankwire import SpankwireIE
from .spiegel import SpiegelIE
from .stanfordoc import StanfordOpenClassroomIE
from .statigram import StatigramIE
from .steam import SteamIE
+from .streamcloud import StreamcloudIE
from .sztvhu import SztvHuIE
from .teamcoco import TeamcocoIE
from .techtalks import TechTalksIE
from .ted import TEDIE
from .tf1 import TF1IE
+from .theplatform import ThePlatformIE
from .thisav import ThisAVIE
+from .toutv import TouTvIE
from .traileraddict import TrailerAddictIE
from .trilulilu import TriluliluIE
from .tube8 import Tube8IE
from .tudou import TudouIE
from .tumblr import TumblrIE
from .tutv import TutvIE
+from .tvp import TvpIE
from .unistra import UnistraIE
from .ustream import UstreamIE, UstreamChannelIE
from .vbox7 import Vbox7IE
from .videodetective import VideoDetectiveIE
from .videofyme import VideofyMeIE
from .videopremium import VideoPremiumIE
-from .vimeo import VimeoIE, VimeoChannelIE
+from .vimeo import (
+ VimeoIE,
+ VimeoChannelIE,
+ VimeoUserIE,
+ VimeoAlbumIE,
+ VimeoGroupsIE,
+)
from .vine import VineIE
+from .viki import VikiIE
from .vk import VKIE
from .wat import WatIE
from .websurg import WeBSurgIE
from .weibo import WeiboIE
from .wimp import WimpIE
+from .wistia import WistiaIE
from .worldstarhiphop import WorldStarHipHopIE
from .xhamster import XHamsterIE
from .xnxx import XNXXIE
from .xvideos import XVideosIE
-from .yahoo import YahooIE, YahooSearchIE
+from .xtube import XTubeIE
+from .yahoo import (
+ YahooIE,
+ YahooNewsIE,
+ YahooSearchIE,
+)
from .youjizz import YouJizzIE
from .youku import YoukuIE
from .youporn import YouPornIE
YoutubeIE,
YoutubePlaylistIE,
YoutubeSearchIE,
+ YoutubeSearchDateIE,
YoutubeUserIE,
YoutubeChannelIE,
YoutubeShowIE,
YoutubeTruncatedURLIE,
YoutubeWatchLaterIE,
YoutubeFavouritesIE,
+ YoutubeHistoryIE,
+ YoutubeTopListIE,
)
from .zdf import ZDFIE
--- /dev/null
+import re
+
+from .common import InfoExtractor
+
+
+class AcademicEarthCourseIE(InfoExtractor):
+ _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P<id>[^?#/]+)'
+ IE_NAME = u'AcademicEarth:Course'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ playlist_id = m.group('id')
+
+ webpage = self._download_webpage(url, playlist_id)
+ title = self._html_search_regex(
+ r'<h1 class="playlist-name">(.*?)</h1>', webpage, u'title')
+ description = self._html_search_regex(
+ r'<p class="excerpt">(.*?)</p>',
+ webpage, u'description', fatal=False)
+ urls = re.findall(
+ r'<h3 class="lecture-title"><a target="_blank" href="([^"]+)">',
+ webpage)
+ entries = [self.url_result(u) for u in urls]
+
+ return {
+ '_type': 'playlist',
+ 'id': playlist_id,
+ 'title': title,
+ 'description': description,
+ 'entries': entries,
+ }
class AddAnimeIE(InfoExtractor):
- _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
+ _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
IE_NAME = u'AddAnime'
_TEST = {
u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
--- /dev/null
+import re
+
+from .common import InfoExtractor
+
+
+class AnitubeIE(InfoExtractor):
+ IE_NAME = u'anitube.se'
+ _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
+
+ _TEST = {
+ u'url': u'http://www.anitube.se/video/36621',
+ u'md5': u'59d0eeae28ea0bc8c05e7af429998d43',
+ u'file': u'36621.mp4',
+ u'info_dict': {
+ u'id': u'36621',
+ u'ext': u'mp4',
+ u'title': u'Recorder to Randoseru 01',
+ },
+ u'skip': u'Blocked in the US',
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ 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, u'key')
+
+ config_xml = self._download_xml('http://www.anitube.se/nuevo/econfig.php?key=%s' % key,
+ key)
+
+ video_title = config_xml.find('title').text
+
+ formats = []
+ video_url = config_xml.find('file')
+ if video_url is not None:
+ formats.append({
+ 'format_id': 'sd',
+ 'url': video_url.text,
+ })
+ video_url = config_xml.find('filehd')
+ if video_url is not None:
+ formats.append({
+ 'format_id': 'hd',
+ 'url': video_url.text,
+ })
+
+ return {
+ 'id': video_id,
+ 'title': video_title,
+ 'formats': formats
+ }
--- /dev/null
+#coding: utf-8
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+ HEADRequest,
+)
+
+
+class AparatIE(InfoExtractor):
+ _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
+
+ _TEST = {
+ u'url': u'http://www.aparat.com/v/wP8On',
+ u'file': u'wP8On.mp4',
+ u'md5': u'6714e0af7e0d875c5a39c4dc4ab46ad1',
+ u'info_dict': {
+ u"title": u"تیم گلکسی 11 - زومیت",
+ },
+ #u'skip': u'Extremely unreliable',
+ }
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('id')
+
+ # Note: There is an easier-to-parse configuration at
+ # http://www.aparat.com/video/video/config/videohash/%video_id
+ # but the URL in there does not work
+ embed_url = (u'http://www.aparat.com/video/video/embed/videohash/' +
+ video_id + u'/vt/frame')
+ webpage = self._download_webpage(embed_url, video_id)
+
+ video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)
+ for i, video_url in enumerate(video_urls):
+ req = HEADRequest(video_url)
+ res = self._request_webpage(
+ req, video_id, note=u'Testing video URL %d' % i, errnote=False)
+ if res:
+ break
+ else:
+ raise ExtractorError(u'No working video URLs found')
+
+ title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, u'title')
+ thumbnail = self._search_regex(
+ r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'thumbnail': thumbnail,
+ }
import re
-import xml.etree.ElementTree
import json
from .common import InfoExtractor
class AppleTrailersIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?trailers.apple.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
+ _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
_TEST = {
u"url": u"http://trailers.apple.com/trailers/wb/manofsteel/",
u"playlist": [
uploader_id = mobj.group('company')
playlist_url = compat_urlparse.urljoin(url, u'includes/playlists/itunes.inc')
- playlist_snippet = self._download_webpage(playlist_url, movie)
- playlist_cleaned = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', playlist_snippet)
- playlist_cleaned = re.sub(r'<img ([^<]*?)>', r'<img \1/>', playlist_cleaned)
- # The ' in the onClick attributes are not escaped, it couldn't be parsed
- # with xml.etree.ElementTree.fromstring
- # like: http://trailers.apple.com/trailers/wb/gravity/
- def _clean_json(m):
- return u'iTunes.playURL(%s);' % m.group(1).replace('\'', ''')
- playlist_cleaned = re.sub(self._JSON_RE, _clean_json, playlist_cleaned)
- playlist_html = u'<html>' + playlist_cleaned + u'</html>'
+ def fix_html(s):
+ s = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', s)
+ s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
+ # The ' in the onClick attributes are not escaped, it couldn't be parsed
+ # like: http://trailers.apple.com/trailers/wb/gravity/
+ def _clean_json(m):
+ return u'iTunes.playURL(%s);' % m.group(1).replace('\'', ''')
+ s = re.sub(self._JSON_RE, _clean_json, s)
+ s = u'<html>' + s + u'</html>'
+ return s
+ doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
- doc = xml.etree.ElementTree.fromstring(playlist_html)
playlist = []
for li in doc.findall('./div/ul/li'):
on_click = li.find('.//a').attrib['onClick']
})
formats = sorted(formats, key=lambda f: (f['height'], f['width']))
- info = {
+ playlist.append({
'_type': 'video',
'id': video_id,
'title': title,
'upload_date': upload_date,
'uploader_id': uploader_id,
'user_agent': 'QuickTime compatible (youtube-dl)',
- }
- # TODO: Remove when #980 has been merged
- info['url'] = formats[-1]['url']
- info['ext'] = formats[-1]['ext']
-
- playlist.append(info)
+ })
return {
'_type': 'playlist',
class ArchiveOrgIE(InfoExtractor):
IE_NAME = 'archive.org'
IE_DESC = 'archive.org videos'
- _VALID_URL = r'(?:https?://)?(?:www\.)?archive.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
+ _VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
_TEST = {
u"url": u"http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
u'file': u'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',
for f in formats:
f['ext'] = determine_ext(f['url'])
- info = {
+ return {
'_type': 'video',
'id': video_id,
'title': title,
'description': description,
'uploader': uploader,
'upload_date': upload_date,
+ 'thumbnail': data.get('misc', {}).get('image'),
}
- thumbnail = data.get('misc', {}).get('image')
- if thumbnail:
- info['thumbnail'] = thumbnail
-
- # TODO: Remove when #980 has been merged
- info.update(formats[-1])
-
- return info
# encoding: utf-8
import re
import json
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
unified_strdate,
determine_ext,
get_element_by_id,
+ compat_str,
+ get_element_by_attribute,
)
# There are different sources of video in arte.tv, the extraction process
# add tests.
class ArteTvIE(InfoExtractor):
- _VIDEOS_URL = r'(?:http://)?videos.arte.tv/(?P<lang>fr|de)/.*-(?P<id>.*?).html'
- _LIVEWEB_URL = r'(?:http://)?liveweb.arte.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)'
+ _VIDEOS_URL = r'(?:http://)?videos\.arte\.tv/(?P<lang>fr|de)/.*-(?P<id>.*?)\.html'
+ _LIVEWEB_URL = r'(?:http://)?liveweb\.arte\.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)'
_LIVE_URL = r'index-[0-9]+\.html$'
IE_NAME = u'arte.tv'
lang = mobj.group('lang')
return self._extract_liveweb(url, name, lang)
- if re.search(self._LIVE_URL, video_id) is not None:
+ if re.search(self._LIVE_URL, url) is not None:
raise ExtractorError(u'Arte live streams are not yet supported, sorry')
# self.extractLiveStream(url)
# return
"""Extract from videos.arte.tv"""
ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
- ref_xml = self._download_webpage(ref_xml_url, video_id, note=u'Downloading metadata')
- ref_xml_doc = xml.etree.ElementTree.fromstring(ref_xml)
+ ref_xml_doc = self._download_xml(ref_xml_url, video_id, note=u'Downloading metadata')
config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
config_xml_url = config_node.attrib['ref']
config_xml = self._download_webpage(config_xml_url, video_id, note=u'Downloading configuration')
"""Extract form http://liveweb.arte.tv/"""
webpage = self._download_webpage(url, name)
video_id = self._search_regex(r'eventId=(\d+?)("|&)', webpage, u'event id')
- config_xml = self._download_webpage('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id,
+ config_doc = self._download_xml('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id,
video_id, u'Downloading information')
- config_doc = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
event_doc = config_doc.find('event')
url_node = event_doc.find('video').find('urlHd')
if url_node is None:
- url_node = video_doc.find('urlSd')
+ url_node = event_doc.find('urlSd')
return {'id': video_id,
'title': event_doc.find('name%s' % lang.capitalize()).text,
def _extract_from_webpage(self, webpage, video_id, lang):
json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
+ return self._extract_from_json_url(json_url, video_id, lang)
+ def _extract_from_json_url(self, json_url, video_id, lang):
json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
self.report_extraction(video_id)
info = json.loads(json_info)
formats = all_formats
else:
raise ExtractorError(u'The formats list is empty')
- # We order the formats by quality
+
if re.match(r'[A-Z]Q', formats[0]['quality']) is not None:
- sort_key = lambda f: ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality'])
+ def sort_key(f):
+ return ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality'])
else:
- sort_key = lambda f: int(f.get('height',-1))
+ def sort_key(f):
+ return (
+ # Sort first by quality
+ int(f.get('height',-1)),
+ int(f.get('bitrate',-1)),
+ # The original version with subtitles has lower relevance
+ re.match(r'VO-ST(F|A)', f.get('versionCode', '')) is None,
+ # The version with sourds/mal subtitles has also lower relevance
+ re.match(r'VO?(F|A)-STM\1', f.get('versionCode', '')) is None,
+ )
formats = sorted(formats, key=sort_key)
- # Prefer videos without subtitles in the same language
- formats = sorted(formats, key=lambda f: re.match(r'VO(F|A)-STM\1', f.get('versionCode', '')) is None)
- # Pick the best quality
def _format(format_info):
- quality = format_info['quality']
- m_quality = re.match(r'\w*? - (\d*)p', quality)
- if m_quality is not None:
- quality = m_quality.group(1)
+ quality = ''
+ height = format_info.get('height')
+ if height is not None:
+ quality = compat_str(height)
+ bitrate = format_info.get('bitrate')
+ if bitrate is not None:
+ quality += '-%d' % bitrate
if format_info.get('versionCode') is not None:
format_id = u'%s-%s' % (quality, format_info['versionCode'])
else:
'format_id': format_id,
'format_note': format_info.get('versionLibelle'),
'width': format_info.get('width'),
- 'height': format_info.get('height'),
+ 'height': height,
}
if format_info['mediaType'] == u'rtmp':
info['url'] = format_info['streamer']
webpage = self._download_webpage(url, anchor_id)
row = get_element_by_id(anchor_id, webpage)
return self._extract_from_webpage(row, anchor_id, lang)
+
+
+class ArteTVDDCIE(ArteTVPlus7IE):
+ IE_NAME = u'arte.tv:ddc'
+ _VALID_URL = r'http?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)'
+
+ def _real_extract(self, url):
+ video_id, lang = self._extract_url_info(url)
+ if lang == 'folge':
+ lang = 'de'
+ elif lang == 'emission':
+ lang = 'fr'
+ webpage = self._download_webpage(url, video_id)
+ scriptElement = get_element_by_attribute('class', 'visu_video_block', webpage)
+ script_url = self._html_search_regex(r'src="(.*?)"', scriptElement, 'script url')
+ javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator')
+ json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url')
+ return self._extract_from_json_url(json_url, video_id, lang)
-import os.path
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
- compat_urllib_parse_urlparse,
+ determine_ext,
+ ExtractorError,
)
class AUEngineIE(InfoExtractor):
u"title": u"[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]"
}
}
- _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?'
+ _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
webpage, u'title')
title = title.strip()
- links = re.findall(r'[^A-Za-z0-9]?(?:file|url):\s*["\'](http[^\'"&]*)', webpage)
- links = [compat_urllib_parse.unquote(l) for l in links]
+ links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
+ links = map(compat_urllib_parse.unquote, links)
+
+ thumbnail = None
+ video_url = None
for link in links:
- root, pathext = os.path.splitext(compat_urllib_parse_urlparse(link).path)
- if pathext == '.png':
+ if link.endswith('.png'):
thumbnail = link
- elif pathext == '.mp4':
- url = link
- ext = pathext
+ elif '/videos/' in link:
+ video_url = link
+ if not video_url:
+ raise ExtractorError(u'Could not find video URL')
+ ext = u'.' + determine_ext(video_url)
if ext == title[-len(ext):]:
title = title[:-len(ext)]
- ext = ext[1:]
- return [{
+
+ return {
'id': video_id,
- 'url': url,
- 'ext': ext,
+ 'url': video_url,
'title': title,
'thumbnail': thumbnail,
- }]
+ }
--- /dev/null
+import re
+import json
+import itertools
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_request,
+)
+
+
+class BambuserIE(InfoExtractor):
+ IE_NAME = u'bambuser'
+ _VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)'
+ _API_KEY = '005f64509e19a868399060af746a00aa'
+
+ _TEST = {
+ u'url': u'http://bambuser.com/v/4050584',
+ # MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388
+ #u'md5': u'fba8f7693e48fd4e8641b3fd5539a641',
+ u'info_dict': {
+ u'id': u'4050584',
+ u'ext': u'flv',
+ u'title': u'Education engineering days - lightning talks',
+ u'duration': 3741,
+ u'uploader': u'pixelversity',
+ u'uploader_id': u'344706',
+ },
+ u'params': {
+ # It doesn't respect the 'Range' header, it would download the whole video
+ # caused the travis builds to fail: https://travis-ci.org/rg3/youtube-dl/jobs/14493845#L59
+ u'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ info_url = ('http://player-c.api.bambuser.com/getVideo.json?'
+ '&api_key=%s&vid=%s' % (self._API_KEY, video_id))
+ info_json = self._download_webpage(info_url, video_id)
+ info = json.loads(info_json)['result']
+
+ return {
+ 'id': video_id,
+ 'title': info['title'],
+ 'url': info['url'],
+ 'thumbnail': info.get('preview'),
+ 'duration': int(info['length']),
+ 'view_count': int(info['views_total']),
+ 'uploader': info['username'],
+ 'uploader_id': info['uid'],
+ }
+
+
+class BambuserChannelIE(InfoExtractor):
+ IE_NAME = u'bambuser:channel'
+ _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
+ # The maximum number we can get with each request
+ _STEP = 50
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ user = mobj.group('user')
+ urls = []
+ last_id = ''
+ for i in itertools.count(1):
+ req_url = ('http://bambuser.com/xhr-api/index.php?username={user}'
+ '&sort=created&access_mode=0%2C1%2C2&limit={count}'
+ '&method=broadcast&format=json&vid_older_than={last}'
+ ).format(user=user, count=self._STEP, last=last_id)
+ req = compat_urllib_request.Request(req_url)
+ # Without setting this header, we wouldn't get any result
+ req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
+ info_json = self._download_webpage(req, user,
+ u'Downloading page %d' % i)
+ results = json.loads(info_json)['result']
+ if len(results) == 0:
+ break
+ last_id = results[-1]['vid']
+ urls.extend(self.url_result(v['page'], 'Bambuser') for v in results)
+
+ return {
+ '_type': 'playlist',
+ 'title': user,
+ 'entries': urls,
+ }
from .common import InfoExtractor
from ..utils import (
+ compat_str,
+ compat_urlparse,
ExtractorError,
)
class BandcampIE(InfoExtractor):
+ IE_NAME = u'Bandcamp'
_VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
- _TEST = {
+ _TESTS = [{
u'url': u'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
u'file': u'1812978515.mp3',
u'md5': u'cdeb30cdae1921719a3cbcab696ef53c',
u"title": u"youtube-dl test song \"'/\\\u00e4\u21ad"
},
u'skip': u'There is a limit of 200 free downloads / month for the test song'
- }
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
# We get the link to the free download page
m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
if m_download is None:
+ m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
+ if m_trackinfo:
+ json_code = m_trackinfo.group(1)
+ data = json.loads(json_code)
+
+ for d in data:
+ formats = [{
+ 'format_id': 'format_id',
+ 'url': format_url,
+ 'ext': format_id.partition('-')[0]
+ } for format_id, format_url in sorted(d['file'].items())]
+ return {
+ 'id': compat_str(d['id']),
+ 'title': d['title'],
+ 'formats': formats,
+ }
+ else:
raise ExtractorError(u'No free songs found')
download_link = m_download.group(1)
}
return [track_info]
+
+
+class BandcampAlbumIE(InfoExtractor):
+ IE_NAME = u'Bandcamp:album'
+ _VALID_URL = r'http://.*?\.bandcamp\.com/album/(?P<title>.*)'
+
+ _TEST = {
+ u'url': u'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
+ u'playlist': [
+ {
+ u'file': u'1353101989.mp3',
+ u'md5': u'39bc1eded3476e927c724321ddf116cf',
+ u'info_dict': {
+ u'title': u'Intro',
+ }
+ },
+ {
+ u'file': u'38097443.mp3',
+ u'md5': u'1a2c32e2691474643e912cc6cd4bffaa',
+ u'info_dict': {
+ u'title': u'Kero One - Keep It Alive (Blazo remix)',
+ }
+ },
+ ],
+ u'params': {
+ u'playlistend': 2
+ },
+ u'skip': u'Bancamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ title = mobj.group('title')
+ webpage = self._download_webpage(url, title)
+ tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
+ if not tracks_paths:
+ raise ExtractorError(u'The page doesn\'t contain any track')
+ entries = [
+ self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
+ for t_path in tracks_paths]
+ title = self._search_regex(r'album_title : "(.*?)"', webpage, u'title')
+ return {
+ '_type': 'playlist',
+ 'title': title,
+ 'entries': entries,
+ }
--- /dev/null
+import datetime
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ remove_start,
+)
+
+
+class BlinkxIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://(?:www\.)blinkx\.com/ce/|blinkx:)(?P<id>[^?]+)'
+ _IE_NAME = u'blinkx'
+
+ _TEST = {
+ u'url': u'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB',
+ u'file': u'8aQUy7GV.mp4',
+ u'md5': u'2e9a07364af40163a908edbf10bb2492',
+ u'info_dict': {
+ u"title": u"Police Car Rolls Away",
+ u"uploader": u"stupidvideos.com",
+ u"upload_date": u"20131215",
+ u"description": u"A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!",
+ u"duration": 14.886,
+ u"thumbnails": [{
+ "width": 100,
+ "height": 76,
+ "url": "http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg",
+ }],
+ },
+ }
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('id')
+ display_id = video_id[:8]
+
+ api_url = (u'https://apib4.blinkx.com/api.php?action=play_video&' +
+ u'video=%s' % video_id)
+ data_json = self._download_webpage(api_url, display_id)
+ data = json.loads(data_json)['api']['results'][0]
+ dt = datetime.datetime.fromtimestamp(data['pubdate_epoch'])
+ upload_date = dt.strftime('%Y%m%d')
+
+ duration = None
+ thumbnails = []
+ formats = []
+ for m in data['media']:
+ if m['type'] == 'jpg':
+ thumbnails.append({
+ 'url': m['link'],
+ 'width': int(m['w']),
+ 'height': int(m['h']),
+ })
+ elif m['type'] == 'original':
+ duration = m['d']
+ elif m['type'] == 'youtube':
+ yt_id = m['link']
+ self.to_screen(u'Youtube video detected: %s' % yt_id)
+ return self.url_result(yt_id, 'Youtube', video_id=yt_id)
+ elif m['type'] in ('flv', 'mp4'):
+ vcodec = remove_start(m['vcodec'], 'ff')
+ acodec = remove_start(m['acodec'], 'ff')
+ format_id = (u'%s-%sk-%s' %
+ (vcodec,
+ (int(m['vbr']) + int(m['abr'])) // 1000,
+ m['w']))
+ formats.append({
+ 'format_id': format_id,
+ 'url': m['link'],
+ 'vcodec': vcodec,
+ 'acodec': acodec,
+ 'abr': int(m['abr']) // 1000,
+ 'vbr': int(m['vbr']) // 1000,
+ 'width': int(m['w']),
+ 'height': int(m['h']),
+ })
+ formats.sort(key=lambda f: (f['width'], f['vbr'], f['abr']))
+
+ return {
+ 'id': display_id,
+ 'fullid': video_id,
+ 'title': data['title'],
+ 'formats': formats,
+ 'uploader': data['channel_name'],
+ 'upload_date': upload_date,
+ 'description': data.get('description'),
+ 'thumbnails': thumbnails,
+ 'duration': duration,
+ }
url = 'http://blip.tv/play/g_%s' % api_mobj.group('video_id')
urlp = compat_urllib_parse_urlparse(url)
if urlp.path.startswith('/play/'):
- request = compat_urllib_request.Request(url)
- response = compat_urllib_request.urlopen(request)
+ response = self._request_webpage(url, None, False)
redirecturl = response.geturl()
rurlp = compat_urllib_parse_urlparse(redirecturl)
file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2]
request.add_header('User-Agent', 'iTunes/10.6.1')
self.report_extraction(mobj.group(1))
info = None
- try:
- urlh = compat_urllib_request.urlopen(request)
- if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
- basename = url.split('/')[-1]
- title,ext = os.path.splitext(basename)
- title = title.decode('UTF-8')
- ext = ext.replace('.', '')
- self.report_direct_download(title)
- info = {
- 'id': title,
- 'url': url,
- 'uploader': None,
- 'upload_date': None,
- 'title': title,
- 'ext': ext,
- 'urlhandle': urlh
- }
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
+ urlh = self._request_webpage(request, None, False,
+ u'unable to download video info webpage')
+ if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
+ basename = url.split('/')[-1]
+ title,ext = os.path.splitext(basename)
+ title = title.decode('UTF-8')
+ ext = ext.replace('.', '')
+ self.report_direct_download(title)
+ info = {
+ 'id': title,
+ 'url': url,
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': title,
+ 'ext': ext,
+ 'urlhandle': urlh
+ }
if info is None: # Regular URL
try:
json_code_bytes = urlh.read()
class BloombergIE(InfoExtractor):
- _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?).html'
+ _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html'
_TEST = {
u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
compat_urllib_parse,
find_xpath_attr,
compat_urlparse,
+ compat_str,
+ compat_urllib_request,
ExtractorError,
)
+
class BrightcoveIE(InfoExtractor):
_VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)'
_FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
# From http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/
u'url': u'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001',
u'file': u'2371591881001.mp4',
- u'md5': u'9e80619e0a94663f0bdc849b4566af19',
+ u'md5': u'8eccab865181d29ec2958f32a6a754f5',
u'note': u'Test Brightcove downloads and detection in GenericIE',
u'info_dict': {
u'title': u'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
u'uploader': u'Oracle',
},
},
+ {
+ # From http://mashable.com/2013/10/26/thermoelectric-bracelet-lets-you-control-your-body-temperature/
+ u'url': u'http://c.brightcove.com/services/viewer/federated_f9?&playerID=1265504713001&publisherID=AQ%7E%7E%2CAAABBzUwv1E%7E%2CxP-xFHVUstiMFlNYfvF4G9yFnNaqCw_9&videoID=2750934548001',
+ u'info_dict': {
+ u'id': u'2750934548001',
+ u'ext': u'mp4',
+ u'title': u'This Bracelet Acts as a Personal Thermostat',
+ u'description': u'md5:547b78c64f4112766ccf4e151c20b6a0',
+ u'uploader': u'Mashable',
+ },
+ },
+ {
+ # test that the default referer works
+ # from http://national.ballet.ca/interact/video/Lost_in_Motion_II/
+ u'url': u'http://link.brightcove.com/services/player/bcpid756015033001?bckey=AQ~~,AAAApYJi_Ck~,GxhXCegT1Dp39ilhXuxMJxasUhVNZiil&bctid=2878862109001',
+ u'info_dict': {
+ u'id': u'2878862109001',
+ u'ext': u'mp4',
+ u'title': u'Lost in Motion II',
+ u'description': u'md5:363109c02998fee92ec02211bd8000df',
+ u'uploader': u'National Ballet of Canada',
+ },
+ },
]
@classmethod
params = {'flashID': object_doc.attrib['id'],
'playerID': find_xpath_attr(object_doc, './param', 'name', 'playerID').attrib['value'],
}
- playerKey = find_xpath_attr(object_doc, './param', 'name', 'playerKey')
+ def find_param(name):
+ node = find_xpath_attr(object_doc, './param', 'name', name)
+ if node is not None:
+ return node.attrib['value']
+ return None
+ playerKey = find_param('playerKey')
# Not all pages define this value
if playerKey is not None:
- params['playerKey'] = playerKey.attrib['value']
- videoPlayer = find_xpath_attr(object_doc, './param', 'name', '@videoPlayer')
+ params['playerKey'] = playerKey
+ # The three fields hold the id of the video
+ videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID')
if videoPlayer is not None:
- params['@videoPlayer'] = videoPlayer.attrib['value']
+ params['@videoPlayer'] = videoPlayer
+ linkBase = find_param('linkBaseURL')
+ if linkBase is not None:
+ params['linkBaseURL'] = linkBase
data = compat_urllib_parse.urlencode(params)
return cls._FEDERATED_URL_TEMPLATE % data
+ @classmethod
+ def _extract_brightcove_url(cls, webpage):
+ """Try to extract the brightcove url from the wepbage, returns None
+ if it can't be found
+ """
+ m_brightcove = re.search(
+ r'<object[^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1.+?</object>',
+ webpage, re.DOTALL)
+ if m_brightcove is not None:
+ return cls._build_brighcove_url(m_brightcove.group())
+ else:
+ return None
+
def _real_extract(self, url):
+ # Change the 'videoId' and others field to '@videoPlayer'
+ url = re.sub(r'(?<=[?&])(videoI(d|D)|bctid)', '%40videoPlayer', url)
+ # Change bckey (used by bcove.me urls) to playerKey
+ url = re.sub(r'(?<=[?&])bckey', 'playerKey', url)
mobj = re.match(self._VALID_URL, url)
query_str = mobj.group('query')
query = compat_urlparse.parse_qs(query_str)
videoPlayer = query.get('@videoPlayer')
if videoPlayer:
- return self._get_video_info(videoPlayer[0], query_str)
+ return self._get_video_info(videoPlayer[0], query_str, query,
+ # We set the original url as the default 'Referer' header
+ referer=url)
else:
player_key = query['playerKey']
return self._get_playlist_info(player_key[0])
- def _get_video_info(self, video_id, query):
- request_url = self._FEDERATED_URL_TEMPLATE % query
- webpage = self._download_webpage(request_url, video_id)
+ def _get_video_info(self, video_id, query_str, query, referer=None):
+ request_url = self._FEDERATED_URL_TEMPLATE % query_str
+ req = compat_urllib_request.Request(request_url)
+ linkBase = query.get('linkBaseURL')
+ if linkBase is not None:
+ referer = linkBase[0]
+ if referer is not None:
+ req.add_header('Referer', referer)
+ webpage = self._download_webpage(req, video_id)
self.report_extraction(video_id)
info = self._search_regex(r'var experienceJSON = ({.*?});', webpage, 'json')
def _extract_video_info(self, video_info):
info = {
- 'id': video_info['id'],
+ 'id': compat_str(video_info['id']),
'title': video_info['displayName'],
'description': video_info.get('shortDescription'),
'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
renditions = video_info.get('renditions')
if renditions:
renditions = sorted(renditions, key=lambda r: r['size'])
- best_format = renditions[-1]
- info.update({
- 'url': best_format['defaultURL'],
- 'ext': 'mp4',
- })
+ info['formats'] = [{
+ 'url': rend['defaultURL'],
+ 'height': rend.get('frameHeight'),
+ 'width': rend.get('frameWidth'),
+ } for rend in renditions]
elif video_info.get('FLVFullLengthURL') is not None:
info.update({
'url': video_info['FLVFullLengthURL'],
- 'ext': 'flv',
})
else:
raise ExtractorError(u'Unable to extract video url for %s' % info['id'])
class Canalc2IE(InfoExtractor):
IE_NAME = 'canalc2.tv'
- _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui'
+ _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
_TEST = {
u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
}
def _real_extract(self, url):
- video_id = re.match(self._VALID_URL, url).group(1)
+ 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
webpage = self._download_webpage(url, video_id)
file_name = self._search_regex(
r"so\.addVariable\('file','(.*?)'\);",
# encoding: utf-8
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import unified_strdate
+
class CanalplusIE(InfoExtractor):
_VALID_URL = r'https?://(www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>\d+))'
_VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = mobj.groupdict().get('id')
if video_id is None:
webpage = self._download_webpage(url, mobj.group('path'))
video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id')
info_url = self._VIDEO_INFO_TEMPLATE % video_id
- info_page = self._download_webpage(info_url,video_id,
+ doc = self._download_xml(info_url,video_id,
u'Downloading video info')
self.report_extraction(video_id)
- doc = xml.etree.ElementTree.fromstring(info_page.encode('utf-8'))
video_info = [video for video in doc if video.find('ID').text == video_id][0]
infos = video_info.find('INFOS')
media = video_info.find('MEDIA')
--- /dev/null
+import re
+
+from .common import InfoExtractor
+
+
+class CBSIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/video/(?P<id>[^/]+)/.*'
+
+ _TEST = {
+ u'url': u'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
+ u'file': u'4JUVEwq3wUT7.flv',
+ u'info_dict': {
+ u'title': u'Connect Chat feat. Garth Brooks',
+ u'description': u'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
+ u'duration': 1495,
+ },
+ u'params': {
+ # rtmp download
+ u'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+ real_id = self._search_regex(
+ r"video\.settings\.pid\s*=\s*'([^']+)';",
+ webpage, u'real video ID')
+ return self.url_result(u'theplatform:%s' % real_id)
--- /dev/null
+# encoding: utf-8
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+class Channel9IE(InfoExtractor):
+ '''
+ Common extractor for channel9.msdn.com.
+
+ The type of provided URL (video or playlist) is determined according to
+ meta Search.PageType from web page HTML rather than URL itself, as it is
+ not always possible to do.
+ '''
+ IE_DESC = u'Channel 9'
+ IE_NAME = u'channel9'
+ _VALID_URL = r'^https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
+
+ _TESTS = [
+ {
+ u'url': u'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
+ u'file': u'Events_TechEd_Australia_2013_KOS002.mp4',
+ u'md5': u'bbd75296ba47916b754e73c3a4bbdf10',
+ u'info_dict': {
+ u'title': u'Developer Kick-Off Session: Stuff We Love',
+ u'description': u'md5:c08d72240b7c87fcecafe2692f80e35f',
+ u'duration': 4576,
+ u'thumbnail': u'http://media.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
+ u'session_code': u'KOS002',
+ u'session_day': u'Day 1',
+ u'session_room': u'Arena 1A',
+ u'session_speakers': [ u'Ed Blankenship', u'Andrew Coates', u'Brady Gaster', u'Patrick Klug', u'Mads Kristensen' ],
+ },
+ },
+ {
+ u'url': u'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
+ u'file': u'posts_Self-service-BI-with-Power-BI-nuclear-testing.mp4',
+ u'md5': u'b43ee4529d111bc37ba7ee4f34813e68',
+ u'info_dict': {
+ u'title': u'Self-service BI with Power BI - nuclear testing',
+ u'description': u'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
+ u'duration': 1540,
+ u'thumbnail': u'http://media.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
+ u'authors': [ u'Mike Wilmot' ],
+ },
+ }
+ ]
+
+ _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<size>\d+(?:\.\d+)?)\s+(?P<units>[a-zA-Z]+)', formatted_size)
+ if not m:
+ return 0
+ units = m.group('units')
+ try:
+ exponent = [u'B', u'KB', u'MB', u'GB', u'TB', u'PB', u'EB', u'ZB', u'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)
+ <a\s+href="(?P<url>[^"]+)">(?P<quality>[^<]+)</a>\s*
+ <span\s+class="usage">\((?P<note>[^\)]+)\)</span>\s*
+ (?:<div\s+class="popup\s+rounded">\s*
+ <h3>File\s+size</h3>\s*(?P<filesize>.*?)\s*
+ </div>)? # File size part may be missing
+ '''
+ # Extract known formats
+ 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
+ } for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats]
+ # Sort according to known formats list
+ formats.sort(key=lambda fmt: self._known_formats.index(fmt['format_id']))
+ return formats
+
+ def _extract_title(self, html):
+ title = self._html_search_meta(u'title', html, u'title')
+ if title is None:
+ title = self._og_search_title(html)
+ TITLE_SUFFIX = u' (Channel 9)'
+ if title is not None and title.endswith(TITLE_SUFFIX):
+ title = title[:-len(TITLE_SUFFIX)]
+ return title
+
+ def _extract_description(self, html):
+ DESCRIPTION_REGEX = r'''(?sx)
+ <div\s+class="entry-content">\s*
+ <div\s+id="entry-body">\s*
+ (?P<description>.+?)\s*
+ </div>\s*
+ </div>
+ '''
+ m = re.search(DESCRIPTION_REGEX, html)
+ if m is not None:
+ return m.group('description')
+ return self._html_search_meta(u'description', html, u'description')
+
+ def _extract_duration(self, html):
+ m = re.search(r'data-video_duration="(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
+ return ((int(m.group('hours')) * 60 * 60) + (int(m.group('minutes')) * 60) + int(m.group('seconds'))) if m else None
+
+ def _extract_slides(self, html):
+ m = re.search(r'<a href="(?P<slidesurl>[^"]+)" class="slides">Slides</a>', html)
+ return m.group('slidesurl') if m is not None else None
+
+ def _extract_zip(self, html):
+ m = re.search(r'<a href="(?P<zipurl>[^"]+)" class="zip">Zip</a>', html)
+ return m.group('zipurl') if m is not None else None
+
+ def _extract_avg_rating(self, html):
+ m = re.search(r'<p class="avg-rating">Avg Rating: <span>(?P<avgrating>[^<]+)</span></p>', html)
+ return float(m.group('avgrating')) if m is not None else 0
+
+ def _extract_rating_count(self, html):
+ m = re.search(r'<div class="rating-count">\((?P<ratingcount>[^<]+)\)</div>', html)
+ return int(self._fix_count(m.group('ratingcount'))) if m is not None else 0
+
+ def _extract_view_count(self, html):
+ m = re.search(r'<li class="views">\s*<span class="count">(?P<viewcount>[^<]+)</span> Views\s*</li>', html)
+ return int(self._fix_count(m.group('viewcount'))) if m is not None else 0
+
+ def _extract_comment_count(self, html):
+ m = re.search(r'<li class="comments">\s*<a href="#comments">\s*<span class="count">(?P<commentcount>[^<]+)</span> Comments\s*</a>\s*</li>', html)
+ return int(self._fix_count(m.group('commentcount'))) if m is not None else 0
+
+ def _fix_count(self, count):
+ return int(str(count).replace(',', '')) if count is not None else None
+
+ def _extract_authors(self, html):
+ m = re.search(r'(?s)<li class="author">(.*?)</li>', html)
+ if m is None:
+ return None
+ return re.findall(r'<a href="/Niners/[^"]+">([^<]+)</a>', m.group(1))
+
+ def _extract_session_code(self, html):
+ m = re.search(r'<li class="code">\s*(?P<code>.+?)\s*</li>', html)
+ return m.group('code') if m is not None else None
+
+ def _extract_session_day(self, html):
+ m = re.search(r'<li class="day">\s*<a href="/Events/[^"]+">(?P<day>[^<]+)</a>\s*</li>', html)
+ return m.group('day') if m is not None else None
+
+ def _extract_session_room(self, html):
+ m = re.search(r'<li class="room">\s*(?P<room>.+?)\s*</li>', html)
+ return m.group('room') if m is not None else None
+
+ def _extract_session_speakers(self, html):
+ return re.findall(r'<a href="/Events/Speakers/[^"]+">([^<]+)</a>', html)
+
+ def _extract_content(self, html, content_path):
+ # Look for downloadable content
+ formats = self._formats_from_html(html)
+ slides = self._extract_slides(html)
+ zip_ = self._extract_zip(html)
+
+ # Nothing to download
+ if len(formats) == 0 and slides is None and zip_ is None:
+ self._downloader.report_warning(u'None of recording, slides or zip are available for %s' % content_path)
+ return
+
+ # Extract meta
+ title = self._extract_title(html)
+ description = self._extract_description(html)
+ thumbnail = self._og_search_thumbnail(html)
+ duration = self._extract_duration(html)
+ avg_rating = self._extract_avg_rating(html)
+ rating_count = self._extract_rating_count(html)
+ view_count = self._extract_view_count(html)
+ comment_count = self._extract_comment_count(html)
+
+ common = {'_type': 'video',
+ 'id': content_path,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'avg_rating': avg_rating,
+ 'rating_count': rating_count,
+ 'view_count': view_count,
+ 'comment_count': comment_count,
+ }
+
+ result = []
+
+ if slides is not None:
+ d = common.copy()
+ d.update({ 'title': title + '-Slides', 'url': slides })
+ result.append(d)
+
+ if zip_ is not None:
+ d = common.copy()
+ d.update({ 'title': title + '-Zip', 'url': zip_ })
+ result.append(d)
+
+ if len(formats) > 0:
+ d = common.copy()
+ d.update({ 'title': title, 'formats': formats })
+ result.append(d)
+
+ return result
+
+ def _extract_entry_item(self, html, content_path):
+ contents = self._extract_content(html, content_path)
+ if contents is None:
+ return contents
+
+ authors = self._extract_authors(html)
+
+ for content in contents:
+ content['authors'] = authors
+
+ return contents
+
+ def _extract_session(self, html, content_path):
+ contents = self._extract_content(html, content_path)
+ if contents is None:
+ return contents
+
+ session_meta = {'session_code': self._extract_session_code(html),
+ 'session_day': self._extract_session_day(html),
+ 'session_room': self._extract_session_room(html),
+ 'session_speakers': self._extract_session_speakers(html),
+ }
+
+ for content in contents:
+ content.update(session_meta)
+
+ return contents
+
+ def _extract_list(self, content_path):
+ rss = self._download_xml(self._RSS_URL % content_path, content_path, u'Downloading RSS')
+ entries = [self.url_result(session_url.text, 'Channel9')
+ for session_url in rss.findall('./channel/item/link')]
+ title_text = rss.find('./channel/title').text
+ return self.playlist_result(entries, content_path, title_text)
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ content_path = mobj.group('contentpath')
+
+ webpage = self._download_webpage(url, content_path, u'Downloading web page')
+
+ page_type_m = re.search(r'<meta name="Search.PageType" content="(?P<pagetype>[^"]+)"/>', webpage)
+ if page_type_m is None:
+ raise ExtractorError(u'Search.PageType not found, don\'t know how to process this page', expected=True)
+
+ page_type = page_type_m.group('pagetype')
+ if page_type == 'List': # List page, may contain list of 'item'-like objects
+ return self._extract_list(content_path)
+ elif page_type == 'Entry.Item': # Any 'item'-like page, may contain downloadable content
+ return self._extract_entry_item(webpage, content_path)
+ elif page_type == 'Session': # Event session page, may contain downloadable content
+ return self._extract_session(webpage, content_path)
+ else:
+ raise ExtractorError(u'Unexpected Search.PageType %s' % page_type, expected=True)
\ No newline at end of file
webpage_url = u'http://' + mobj.group('url')
webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
- mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/(?:embed|player)\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
+ mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
if not mobj:
raise ExtractorError(u'Can\'t extract embed url and video id')
playerdata_url = mobj.group(u'embed_url')
{
'url': url,
'play_path': 'mp4:' + sd_file,
+ 'rtmp_live': True, # workaround
'ext': 'flv',
'format': 'sd',
'format_id': 'sd',
{
'url': url,
'play_path': 'mp4:' + hd_file,
+ 'rtmp_live': True, # workaround
'ext': 'flv',
'format': 'hd',
'format_id': 'hd',
--- /dev/null
+import re
+import time
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class ClipfishIE(InfoExtractor):
+ IE_NAME = u'clipfish'
+
+ _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
+ _TEST = {
+ u'url': u'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
+ u'file': u'3966754.mp4',
+ u'md5': u'2521cd644e862936cf2e698206e47385',
+ u'info_dict': {
+ u'title': u'FIFA 14 - E3 2013 Trailer',
+ u'duration': 82,
+ },
+ u'skip': 'Blocked in the US'
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group(1)
+
+ info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
+ (video_id, int(time.time())))
+ doc = self._download_xml(
+ info_url, video_id, note=u'Downloading info page')
+ title = doc.find('title').text
+ video_url = doc.find('filename').text
+ if video_url is None:
+ xml_bytes = xml.etree.ElementTree.tostring(doc)
+ raise ExtractorError(u'Cannot find video URL in document %r' %
+ xml_bytes)
+ thumbnail = doc.find('imageurl').text
+ duration_str = doc.find('duration').text
+ m = re.match(
+ r'^(?P<hours>[0-9]+):(?P<minutes>[0-9]{2}):(?P<seconds>[0-9]{2}):(?P<ms>[0-9]*)$',
+ duration_str)
+ if m:
+ duration = (
+ (int(m.group('hours')) * 60 * 60) +
+ (int(m.group('minutes')) * 60) +
+ (int(m.group('seconds')))
+ )
+ else:
+ duration = None
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'url': video_url,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ }
--- /dev/null
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ find_xpath_attr,
+ fix_xml_all_ampersand,
+)
+
+
+class ClipsyndicateIE(InfoExtractor):
+ _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
+
+ _TEST = {
+ u'url': u'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
+ u'md5': u'4d7d549451bad625e0ff3d7bd56d776c',
+ u'info_dict': {
+ u'id': u'4629301',
+ u'ext': u'mp4',
+ u'title': u'Brick Briscoe',
+ u'duration': 612,
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ js_player = self._download_webpage(
+ 'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
+ video_id, u'Downlaoding player')
+ # it includes a required token
+ flvars = self._search_regex(r'flvars: "(.*?)"', js_player, u'flvars')
+
+ pdoc = self._download_xml(
+ 'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars,
+ video_id, u'Downloading video info',
+ transform_source=fix_xml_all_ampersand)
+
+ track_doc = pdoc.find('trackList/track')
+ def find_param(name):
+ node = find_xpath_attr(track_doc, './/param', 'name', name)
+ if node is not None:
+ return node.attrib['value']
+
+ return {
+ 'id': video_id,
+ 'title': find_param('title'),
+ 'url': track_doc.find('location').text,
+ 'thumbnail': find_param('thumbnail'),
+ 'duration': int(find_param('duration')),
+ }
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import determine_ext
class CNNIE(InfoExtractor):
- _VALID_URL = r'''(?x)https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/
+ _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/
(?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))'''
_TESTS = [{
path = mobj.group('path')
page_title = mobj.group('title')
info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path
- info_xml = self._download_webpage(info_url, page_title)
- info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+ info = self._download_xml(info_url, page_title)
formats = []
for f in info.findall('files/file'):
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
self.report_extraction(video_id)
xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
- metaXml = self._download_webpage(xmlUrl, video_id,
+ mdoc = self._download_xml(xmlUrl, video_id,
u'Downloading info XML',
u'Unable to download video info XML')
- mdoc = xml.etree.ElementTree.fromstring(metaXml)
try:
videoNode = mdoc.findall('./video')[0]
youtubeIdNode = videoNode.find('./youtubeID')
if next_url.endswith(u'manifest.f4m'):
manifest_url = next_url + '?hdcore=2.10.3'
- manifestXml = self._download_webpage(manifest_url, video_id,
+ adoc = self._download_xml(manifest_url, video_id,
u'Downloading XML manifest',
u'Unable to download video info XML')
- adoc = xml.etree.ElementTree.fromstring(manifestXml)
try:
- media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
- node_id = media_node.attrib['url']
video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
- except IndexError as err:
+ except IndexError:
raise ExtractorError(u'Invalid manifest file')
url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
+from .mtv import MTVServicesInfoExtractor
from ..utils import (
compat_str,
compat_urllib_parse,
)
-class ComedyCentralIE(InfoExtractor):
+class ComedyCentralIE(MTVServicesInfoExtractor):
+ _VALID_URL = r'https?://(?:www.)?comedycentral.com/(video-clips|episodes|cc-studios)/(?P<title>.*)'
+ _FEED_URL = u'http://comedycentral.com/feeds/mrss/'
+
+ _TEST = {
+ u'url': u'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
+ u'md5': u'4167875aae411f903b751a21f357f1ee',
+ u'info_dict': {
+ u'id': u'cef0cbb3-e776-4bc9-b62e-8016deccb354',
+ u'ext': u'mp4',
+ u'title': u'Uncensored - Greg Fitzsimmons - Too Good of a Mother',
+ u'description': u'After a certain point, breastfeeding becomes c**kblocking.',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ title = mobj.group('title')
+ webpage = self._download_webpage(url, title)
+ mgid = self._search_regex(r'data-mgid="(?P<mgid>mgid:.*?)"',
+ webpage, u'mgid')
+ return self._get_videos_info(mgid)
+
+
+class ComedyCentralShowsIE(InfoExtractor):
IE_DESC = u'The Daily Show / Colbert Report'
# urls can be abbreviations like :thedailyshow or :colbert
# urls for episodes like:
uri = mMovieParams[0][1]
indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
- indexXml = self._download_webpage(indexUrl, epTitle,
+ idoc = self._download_xml(indexUrl, epTitle,
u'Downloading show index',
u'unable to download episode index')
results = []
- idoc = xml.etree.ElementTree.fromstring(indexXml)
itemEls = idoc.findall('.//item')
for partNum,itemEl in enumerate(itemEls):
mediaId = itemEl.findall('./guid')[0].text
configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
compat_urllib_parse.urlencode({'uri': mediaId}))
- configXml = self._download_webpage(configUrl, epTitle,
+ cdoc = self._download_xml(configUrl, epTitle,
u'Downloading configuration for %s' % shortMediaId)
- cdoc = xml.etree.ElementTree.fromstring(configXml)
turls = []
for rendition in cdoc.findall('.//rendition'):
finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
})
effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
- info = {
+ results.append({
'id': shortMediaId,
'formats': formats,
'uploader': showId,
'title': effTitle,
'thumbnail': None,
'description': compat_str(officialTitle),
- }
-
- # TODO: Remove when #980 has been merged
- info.update(info['formats'][-1])
-
- results.append(info)
+ })
return results
import socket
import sys
import netrc
+import xml.etree.ElementTree
from ..utils import (
compat_http_client,
compat_urllib_error,
- compat_urllib_request,
compat_str,
clean_html,
sanitize_filename,
unescapeHTML,
)
+_NO_DEFAULT = object()
+
class InfoExtractor(object):
"""Information Extractor class.
The dictionaries must include the following fields:
id: Video identifier.
- url: Final video URL.
title: Video title, unescaped.
- ext: Video filename extension.
- Instead of url and ext, formats can also specified.
+ Additionally, it must contain either a formats entry or url and ext:
+
+ formats: A list of dictionaries for each format available, it must
+ be ordered from worst to best quality. Potential fields:
+ * url Mandatory. The URL of the video file
+ * ext Will be calculated from url if missing
+ * format A human-readable description of the format
+ ("mp4 container with h264/opus").
+ Calculated from the format_id, width, height.
+ and format_note fields if missing.
+ * format_id A short description of the format
+ ("mp4_h264_opus" or "19")
+ * format_note Additional info about the format
+ ("3D" or "DASH video")
+ * width Width of the video, if known
+ * height Height of the video, if known
+ * abr Average audio bitrate in KBit/s
+ * acodec Name of the audio codec in use
+ * vbr Average video bitrate in KBit/s
+ * vcodec Name of the video codec in use
+ * filesize The number of bytes, if known in advance
+ * player_url SWF Player URL (used for rtmpdump).
+ url: Final video URL.
+ ext: Video filename extension.
+ format: The video format, defaults to ext (used for --get-format)
+ player_url: SWF Player URL (used for rtmpdump).
+ urlhandle: [internal] The urlHandle to be used to download the file,
+ like returned by urllib.request.urlopen
The following fields are optional:
- format: The video format, defaults to ext (used for --get-format)
thumbnails: A list of dictionaries (with the entries "resolution" and
"url") for the varying thumbnails
thumbnail: Full URL to a video thumbnail image.
upload_date: Video upload date (YYYYMMDD).
uploader_id: Nickname or id of the video uploader.
location: Physical location of the video.
- player_url: SWF Player URL (used for rtmpdump).
subtitles: The subtitle file contents as a dictionary in the format
{language: subtitles}.
+ duration: Length of the video in seconds, as an integer.
view_count: How many users have watched the video on the platform.
- urlhandle: [internal] The urlHandle to be used to download the file,
- like returned by urllib.request.urlopen
+ like_count: Number of positive ratings of the video
+ dislike_count: Number of negative ratings of the video
+ comment_count: Number of comments on the video
age_limit: Age restriction for the video, as an integer (years)
- formats: A list of dictionaries for each format available, it must
- be ordered from worst to best quality. Potential fields:
- * url Mandatory. The URL of the video file
- * ext Will be calculated from url if missing
- * format A human-readable description of the format
- ("mp4 container with h264/opus").
- Calculated from the format_id, width, height.
- and format_note fields if missing.
- * format_id A short description of the format
- ("mp4_h264_opus" or "19")
- * format_note Additional info about the format
- ("3D" or "DASH video")
- * width Width of the video, if known
- * height Height of the video, if known
+ webpage_url: The url to the video webpage, if given to youtube-dl it
+ should allow to get the same result again. (It will be set
+ by YoutubeDL if it's missing)
Unless mentioned otherwise, the fields should be Unicode strings.
def IE_NAME(self):
return type(self).__name__[:-2]
- def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
+ def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
""" Returns the response handle """
if note is None:
self.report_download_webpage(video_id)
elif note is not False:
- self.to_screen(u'%s: %s' % (video_id, note))
+ if video_id is None:
+ self.to_screen(u'%s' % (note,))
+ else:
+ self.to_screen(u'%s: %s' % (video_id, note))
try:
- return compat_urllib_request.urlopen(url_or_request)
+ return self._downloader.urlopen(url_or_request)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ if errnote is False:
+ return False
if errnote is None:
errnote = u'Unable to download webpage'
- raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err)
+ errmsg = u'%s: %s' % (errnote, compat_str(err))
+ if fatal:
+ raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
+ else:
+ self._downloader.report_warning(errmsg)
+ return False
- def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
+ def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
""" Returns a tuple (page content as string, URL handle) """
# Strip hashes from the URL (#1038)
if isinstance(url_or_request, (compat_str, str)):
url_or_request = url_or_request.partition('#')[0]
- urlh = self._request_webpage(url_or_request, video_id, note, errnote)
+ urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal)
+ if urlh is False:
+ assert not fatal
+ return False
content_type = urlh.headers.get('Content-Type', '')
webpage_bytes = urlh.read()
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
content = webpage_bytes.decode(encoding, 'replace')
return (content, urlh)
- def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
+ def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
""" Returns the data of the page as a string """
- return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0]
+ res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
+ if res is False:
+ return res
+ else:
+ content, _ = res
+ return content
+
+ def _download_xml(self, url_or_request, video_id,
+ note=u'Downloading XML', errnote=u'Unable to download XML',
+ transform_source=None):
+ """Return the xml as an xml.etree.ElementTree.Element"""
+ xml_string = self._download_webpage(url_or_request, video_id, note, errnote)
+ if transform_source:
+ xml_string = transform_source(xml_string)
+ return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
def to_screen(self, msg):
"""Print msg to screen, prefixing it with '[ie_name]'"""
self.to_screen(u'Logging in')
#Methods for following #608
- def url_result(self, url, ie=None):
+ @staticmethod
+ def url_result(url, ie=None, video_id=None):
"""Returns a url that points to a page that should be processed"""
#TODO: ie should be the class used for getting the info
video_info = {'_type': 'url',
'url': url,
'ie_key': ie}
+ if video_id is not None:
+ video_info['id'] = video_id
return video_info
- def playlist_result(self, entries, playlist_id=None, playlist_title=None):
+ @staticmethod
+ def playlist_result(entries, playlist_id=None, playlist_title=None):
"""Returns a playlist"""
video_info = {'_type': 'playlist',
'entries': entries}
video_info['title'] = playlist_title
return video_info
- def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+ def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
"""
Perform a regex search on the given string, using a single or a list of
patterns returning the first matching group.
mobj = re.search(p, string, flags)
if mobj: break
- if sys.stderr.isatty() and os.name != 'nt':
+ if os.name != 'nt' and sys.stderr.isatty():
_name = u'\033[0;34m%s\033[0m' % name
else:
_name = name
if mobj:
# return the first matching group
return next(g for g in mobj.groups() if g is not None)
- elif default is not None:
+ elif default is not _NO_DEFAULT:
return default
elif fatal:
raise RegexNotFoundError(u'Unable to extract %s' % _name)
u'please report this issue on http://yt-dl.org/bug' % _name)
return None
- def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+ def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
"""
Like _search_regex, but strips HTML tags and unescapes entities.
"""
# Helper functions for extracting OpenGraph info
@staticmethod
- def _og_regex(prop):
- return r'<meta.+?property=[\'"]og:%s[\'"].+?content=(?:"(.+?)"|\'(.+?)\')' % re.escape(prop)
+ def _og_regexes(prop):
+ content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')'
+ property_re = r'property=[\'"]og:%s[\'"]' % re.escape(prop)
+ template = r'<meta[^>]+?%s[^>]+?%s'
+ return [
+ template % (property_re, content_re),
+ template % (content_re, property_re),
+ ]
def _og_search_property(self, prop, html, name=None, **kargs):
if name is None:
name = 'OpenGraph %s' % prop
- escaped = self._search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs)
+ escaped = self._search_regex(self._og_regexes(prop), html, name, flags=re.DOTALL, **kargs)
+ if escaped is None:
+ return None
return unescapeHTML(escaped)
def _og_search_thumbnail(self, html, **kargs):
return self._og_search_property('title', html, **kargs)
def _og_search_video_url(self, html, name='video url', secure=True, **kargs):
- regexes = [self._og_regex('video')]
- if secure: regexes.insert(0, self._og_regex('video:secure_url'))
+ regexes = self._og_regexes('video')
+ if secure: regexes = self._og_regexes('video:secure_url') + regexes
return self._html_search_regex(regexes, html, name, **kargs)
+ def _html_search_meta(self, name, html, display_name=None):
+ if display_name is None:
+ display_name = name
+ return self._html_search_regex(
+ r'''(?ix)<meta
+ (?=[^>]+(?:itemprop|name|property)=["\']%s["\'])
+ [^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
+ html, display_name, fatal=False)
+
+ def _dc_search_uploader(self, html):
+ return self._html_search_meta('dc.creator', html, 'uploader')
+
def _rta_search(self, html):
# See http://www.rtalabel.org/index.php?content=howtofaq#single
if re.search(r'(?ix)<meta\s+name="rating"\s+'
return 18
return 0
+ def _media_rating_search(self, html):
+ # See http://www.tjg-designs.com/WP/metadata-code-examples-adding-metadata-to-your-web-pages/
+ rating = self._html_search_meta('rating', html)
+
+ if not rating:
+ return None
+
+ RATING_TABLE = {
+ 'safe for kids': 0,
+ 'general': 8,
+ '14 years': 14,
+ 'mature': 17,
+ 'restricted': 19,
+ }
+ return RATING_TABLE.get(rating.lower(), None)
+
+
class SearchInfoExtractor(InfoExtractor):
"""
)
class CSpanIE(InfoExtractor):
- _VALID_URL = r'http://www.c-spanvideo.org/program/(.*)'
+ _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)'
_TEST = {
u'url': u'http://www.c-spanvideo.org/program/HolderonV',
u'file': u'315139.flv',
--- /dev/null
+# encoding: utf-8
+from .canalplus import CanalplusIE
+
+
+class D8IE(CanalplusIE):
+ _VALID_URL = r'https?://www\.d8\.tv/.*?/(?P<path>.*)'
+ _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/d8/%s'
+ IE_NAME = u'd8.tv'
+
+ _TEST = {
+ u'url': u'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
+ u'file': u'966289.flv',
+ u'info_dict': {
+ u'title': u'Campagne intime - Documentaire exceptionnel',
+ u'description': u'md5:d2643b799fb190846ae09c61e59a859f',
+ u'upload_date': u'20131108',
+ },
+ u'params': {
+ # rtmp
+ u'skip_download': True,
+ },
+ }
get_element_by_attribute,
get_element_by_id,
orderedSet,
+ str_to_int,
ExtractorError,
)
class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
"""Information Extractor for Dailymotion"""
- _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
+ _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P<id>[^/?_]+)'
IE_NAME = u'dailymotion'
_FORMATS = [
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group(1).split('_')[0].split('?')[0]
+ video_id = mobj.group('id')
url = 'http://www.dailymotion.com/video/%s' % video_id
self.to_screen(u'Vevo video detected: %s' % vevo_id)
return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo')
- video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
- # Looking for official user
- r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
- webpage, 'video uploader', fatal=False)
age_limit = self._rta_search(webpage)
video_upload_date = None
raise ExtractorError(u'Unable to extract video URL')
# subtitles
- video_subtitles = self.extract_subtitles(video_id)
+ video_subtitles = self.extract_subtitles(video_id, webpage)
if self._downloader.params.get('listsubtitles', False):
- self._list_available_subtitles(video_id)
+ self._list_available_subtitles(video_id, webpage)
return
+ view_count = self._search_regex(
+ r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, u'view count', fatal=False)
+ if view_count is not None:
+ view_count = str_to_int(view_count)
+
return {
'id': video_id,
'formats': formats,
- 'uploader': video_uploader,
+ 'uploader': info['owner_screenname'],
'upload_date': video_upload_date,
'title': self._og_search_title(webpage),
'subtitles': video_subtitles,
'thumbnail': info['thumbnail_url'],
'age_limit': age_limit,
+ 'view_count': view_count,
}
- def _get_available_subtitles(self, video_id):
+ def _get_available_subtitles(self, video_id, webpage):
try:
sub_list = self._download_webpage(
'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
webpage = self._download_webpage(request,
id, u'Downloading page %s' % pagenum)
- playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)
+ playlist_el = get_element_by_attribute(u'class', u'row video_list', webpage)
video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el))
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
# encoding: utf-8
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
class DaumIE(InfoExtractor):
- _VALID_URL = r'https?://tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
IE_NAME = u'daum.net'
_TEST = {
video_id = mobj.group(1)
canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
webpage = self._download_webpage(canonical_url, video_id)
- full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"',
+ full_id = self._search_regex(
+ r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
webpage, u'full id')
query = compat_urllib_parse.urlencode({'vid': full_id})
- info_xml = self._download_webpage(
+ info = self._download_xml(
'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
u'Downloading video info')
- urls_xml = self._download_webpage(
+ urls = self._download_xml(
'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
video_id, u'Downloading video formats info')
- info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
- urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8'))
self.to_screen(u'%s: Getting video urls' % video_id)
formats = []
'vid': full_id,
'profile': profile,
})
- url_xml = self._download_webpage(
+ url_doc = self._download_xml(
'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
video_id, note=False)
- url_doc = xml.etree.ElementTree.fromstring(url_xml.encode('utf-8'))
format_url = url_doc.find('result/url').text
formats.append({
'url': format_url,
'format_id': profile,
})
- info = {
+ return {
'id': video_id,
'title': info.find('TITLE').text,
'formats': formats,
'duration': int(info.find('DURATION').text),
'upload_date': info.find('REGDTTM').text[:8],
}
- # TODO: Remove when #980 has been merged
- info.update(formats[-1])
- return info
url = 'http://depositfiles.com/en/files/' + file_id
# Retrieve file webpage with 'Free download' button pressed
- free_download_indication = { 'gateway_result' : '1' }
+ free_download_indication = {'gateway_result' : '1'}
request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication))
try:
self.report_download_webpage(file_id)
# coding: utf-8
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
class DreiSatIE(InfoExtractor):
IE_NAME = '3sat'
- _VALID_URL = r'(?:http://)?(?:www\.)?3sat.de/mediathek/index.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
+ _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/index\.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
_TEST = {
u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983",
u'file': u'36983.webm',
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
- details_xml = self._download_webpage(details_url, video_id, note=u'Downloading video details')
- details_doc = xml.etree.ElementTree.fromstring(details_xml.encode('utf-8'))
+ details_doc = self._download_xml(details_url, video_id, note=u'Downloading video details')
thumbnail_els = details_doc.findall('.//teaserimage')
thumbnails = [{
return (qidx, prefer_http, format['video_bitrate'])
formats.sort(key=_sortkey)
- info = {
+ return {
'_type': 'video',
'id': video_id,
'title': video_title,
'uploader': video_uploader,
'upload_date': upload_date,
}
-
- # TODO: Remove when #980 has been merged
- info.update(formats[-1])
-
- return info
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import determine_ext
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
- config_xml = self._download_webpage(
+ config = self._download_xml(
'http://www.ebaumsworld.com/video/player/%s' % video_id, video_id)
- config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
video_url = config.find('file').text
return {
-import itertools
import json
import random
import re
class EightTracksIE(InfoExtractor):
IE_NAME = '8tracks'
- _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
+ _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
_TEST = {
u"name": u"EightTracks",
u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
--- /dev/null
+# encoding: utf-8
+import re
+
+from .common import InfoExtractor
+from .brightcove import BrightcoveIE
+from ..utils import ExtractorError
+
+
+class EitbIE(InfoExtractor):
+ IE_NAME = u'eitb.tv'
+ _VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)'
+
+ _TEST = {
+ u'add_ie': ['Brightcove'],
+ u'url': u'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/',
+ u'md5': u'edf4436247185adee3ea18ce64c47998',
+ u'info_dict': {
+ u'id': u'2743577154001',
+ u'ext': u'mp4',
+ u'title': u'60 minutos (Lasa y Zabala, 30 años)',
+ # All videos from eitb has this description in the brightcove info
+ u'description': u'.',
+ u'uploader': u'Euskal Telebista',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ chapter_id = mobj.group('chapter_id')
+ webpage = self._download_webpage(url, chapter_id)
+ bc_url = BrightcoveIE._extract_brightcove_url(webpage)
+ if bc_url is None:
+ raise ExtractorError(u'Could not extract the Brightcove url')
+ # The BrightcoveExperience object doesn't contain the video id, we set
+ # it manually
+ bc_url += '&%40videoPlayer={0}'.format(chapter_id)
+ return self.url_result(bc_url, BrightcoveIE.ie_key())
class EscapistIE(InfoExtractor):
- _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+ _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
_TEST = {
u'url': u'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
u'file': u'6618-Breaking-Down-Baldurs-Gate.mp4',
- u'md5': u'c6793dbda81388f4264c1ba18684a74d',
+ u'md5': u'ab3a706c681efca53f0a35f1415cf0d1',
u'info_dict': {
u"description": u"Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
u"uploader": u"the-escapist-presents",
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
showName = mobj.group('showname')
videoId = mobj.group('episode')
self.report_extraction(videoId)
webpage = self._download_webpage(url, videoId)
- videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
+ videoDesc = self._html_search_regex(
+ r'<meta name="description" content="([^"]*)"',
webpage, u'description', fatal=False)
- playerUrl = self._og_search_video_url(webpage, name='player url')
+ playerUrl = self._og_search_video_url(webpage, name=u'player URL')
- title = self._html_search_regex('<meta name="title" content="([^"]*)"',
- webpage, u'player url').split(' : ')[-1]
+ title = self._html_search_regex(
+ r'<meta name="title" content="([^"]*)"',
+ webpage, u'title').split(' : ')[-1]
- configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
+ configUrl = self._search_regex('config=(.*)$', playerUrl, u'config URL')
configUrl = compat_urllib_parse.unquote(configUrl)
- configJSON = self._download_webpage(configUrl, videoId,
- u'Downloading configuration',
- u'unable to download configuration')
-
- # Technically, it's JavaScript, not JSON
- configJSON = configJSON.replace("'", '"')
-
+ formats = []
+
+ def _add_format(name, cfgurl):
+ configJSON = self._download_webpage(
+ cfgurl, videoId,
+ u'Downloading ' + name + ' configuration',
+ u'Unable to download ' + name + ' configuration')
+
+ # Technically, it's JavaScript, not JSON
+ configJSON = configJSON.replace("'", '"')
+
+ try:
+ config = json.loads(configJSON)
+ except (ValueError,) as err:
+ raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
+ playlist = config['playlist']
+ formats.append({
+ 'url': playlist[1]['url'],
+ 'format_id': name,
+ })
+
+ _add_format(u'normal', configUrl)
+ hq_url = (configUrl +
+ ('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))
try:
- config = json.loads(configJSON)
- except (ValueError,) as err:
- raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
+ _add_format(u'hq', hq_url)
+ except ExtractorError:
+ pass # That's fine, we'll just use normal quality
- playlist = config['playlist']
- videoUrl = playlist[1]['url']
-
- info = {
+ return {
'id': videoId,
- 'url': videoUrl,
+ 'formats': formats,
'uploader': showName,
- 'upload_date': None,
'title': title,
- 'ext': 'mp4',
'thumbnail': self._og_search_thumbnail(webpage),
'description': videoDesc,
'player_url': playerUrl,
}
-
- return [info]
IE_NAME = u'exfm'
IE_DESC = u'ex.fm'
_VALID_URL = r'(?:http://)?(?:www\.)?ex\.fm/song/([^/]+)'
- _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud.com/tracks/([^/]+)/stream'
+ _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
_TESTS = [
{
u'url': u'http://ex.fm/song/eh359',
u'description': u'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
},
u'note': u'Soundcloud song',
+ u'skip': u'The site is down too often',
},
{
u'url': u'http://ex.fm/song/wddt8',
u'title': u'Safe and Sound',
u'uploader': u'Capital Cities',
},
+ u'skip': u'The site is down too often',
},
]
--- /dev/null
+import os
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse_urlparse,
+ compat_urllib_request,
+ compat_urllib_parse,
+)
+
+class ExtremeTubeIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
+ _TEST = {
+ u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
+ u'file': u'652431.mp4',
+ u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0',
+ u'info_dict': {
+ u"title": u"Music Video 14 british euro brit european cumshots swallow",
+ u"uploader": u"unknown",
+ u"age_limit": 18,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('videoid')
+ url = 'http://www.' + mobj.group('url')
+
+ req = compat_urllib_request.Request(url)
+ req.add_header('Cookie', 'age_verified=1')
+ webpage = self._download_webpage(req, video_id)
+
+ video_title = self._html_search_regex(r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, u'title')
+ uploader = self._html_search_regex(r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, u'uploader', fatal=False)
+ video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&', webpage, u'video_url'))
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
+ format = path.split('/')[5].split('_')[:2]
+ format = "-".join(format)
+
+ return {
+ 'id': video_id,
+ 'title': video_title,
+ 'uploader': uploader,
+ 'url': video_url,
+ 'ext': extension,
+ 'format': format,
+ 'format_id': format,
+ 'age_limit': 18,
+ }
import json
-import netrc
import re
import socket
class FacebookIE(InfoExtractor):
"""Information Extractor for Facebook"""
- _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:[^#?]*#!/)?(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
_LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
_CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
_NETRC_MACHINE = 'facebook'
u'file': u'120708114770723.mp4',
u'md5': u'48975a41ccc4b7a581abd68651c1a5a8',
u'info_dict': {
- u"duration": 279,
+ u"duration": 279,
u"title": u"PEOPLE ARE AWESOME 2013"
}
}
# encoding: utf-8
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
class FazIE(InfoExtractor):
IE_NAME = u'faz.net'
- _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+).html'
+ _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html'
_TEST = {
u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
webpage = self._download_webpage(url, video_id)
config_xml_url = self._search_regex(r'writeFLV\(\'(.+?)\',', webpage,
u'config xml url')
- config_xml = self._download_webpage(config_xml_url, video_id,
+ config = self._download_xml(config_xml_url, video_id,
u'Downloading config xml')
- config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
encodings = config.find('ENCODINGS')
formats = []
})
descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description')
- info = {
+ return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'description': descr,
'thumbnail': config.find('STILL/STILL_BIG').text,
}
- # TODO: Remove when #980 has been merged
- info.update(formats[-1])
- return info
class FKTVIE(InfoExtractor):
IE_NAME = u'fernsehkritik.tv'
- _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
+ _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
_TEST = {
u'url': u'http://fernsehkritik.tv/folge-1',
for i, _ in enumerate(files, 1):
video_id = '%04d%d' % (episode, i)
video_url = 'http://dl%d.fernsehkritik.tv/fernsehkritik%d%s.flv' % (server, episode, '' if i == 1 else '-%d' % i)
- video_title = 'Fernsehkritik %d.%d' % (episode, i)
videos.append({
'id': video_id,
'url': video_url,
class FKTVPosteckeIE(InfoExtractor):
IE_NAME = u'fernsehkritik.tv:postecke'
- _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/inline-video/postecke.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
+ _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
_TEST = {
u'url': u'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120',
u'file': u'0120.flv',
# encoding: utf-8
import re
-import xml.etree.ElementTree
import json
from .common import InfoExtractor
class FranceTVBaseInfoExtractor(InfoExtractor):
def _extract_video(self, video_id):
- xml_desc = self._download_webpage(
+ info = self._download_xml(
'http://www.francetvinfo.fr/appftv/webservices/video/'
'getInfosOeuvre.php?id-diffusion='
+ video_id, video_id, 'Downloading XML config')
- info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8'))
manifest_url = info.find('videos/video/url').text
video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8')
thumbnail_path = info.find('image').text
return {'id': video_id,
- 'ext': 'mp4',
+ 'ext': 'flv' if video_url.startswith('rtmp') else 'mp4',
'url': video_url,
'title': info.find('titre').text,
'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
class FranceTvInfoIE(FranceTVBaseInfoExtractor):
IE_NAME = u'francetvinfo.fr'
- _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+).html'
+ _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+)\.html'
_TEST = {
u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
return self._extract_video(video_id)
-class France2IE(FranceTVBaseInfoExtractor):
- IE_NAME = u'france2.fr'
- _VALID_URL = r'''(?x)https?://www\.france2\.fr/
+class FranceTVIE(FranceTVBaseInfoExtractor):
+ IE_NAME = u'francetv'
+ IE_DESC = u'France 2, 3, 4, 5 and Ô'
+ _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
(?:
- emissions/.*?/videos/(?P<id>\d+)
- | emission/(?P<key>[^/?]+)
+ emissions/.*?/(videos|emissions)/(?P<id>[^/?]+)
+ | (emissions?|jt)/(?P<key>[^/?]+)
)'''
- _TEST = {
- u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
- u'file': u'75540104.mp4',
- u'info_dict': {
- u'title': u'13h15, le samedi...',
- u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d',
+ _TESTS = [
+ # france2
+ {
+ u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
+ u'file': u'75540104.mp4',
+ u'info_dict': {
+ u'title': u'13h15, le samedi...',
+ u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d',
+ },
+ u'params': {
+ # m3u8 download
+ u'skip_download': True,
+ },
},
- u'params': {
- u'skip_download': True,
+ # france3
+ {
+ u'url': u'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
+ u'info_dict': {
+ u'id': u'000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
+ u'ext': u'flv',
+ u'title': u'Le scandale du prix des médicaments',
+ u'description': u'md5:1384089fbee2f04fc6c9de025ee2e9ce',
+ },
+ u'params': {
+ # rtmp download
+ u'skip_download': True,
+ },
},
- }
+ # france4
+ {
+ u'url': u'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+ u'info_dict': {
+ u'id': u'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+ u'ext': u'flv',
+ u'title': u'Hero Corp Making of - Extrait 1',
+ u'description': u'md5:c87d54871b1790679aec1197e73d650a',
+ },
+ u'params': {
+ # rtmp download
+ u'skip_download': True,
+ },
+ },
+ # france5
+ {
+ u'url': u'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
+ u'info_dict': {
+ u'id': u'92837968',
+ u'ext': u'mp4',
+ u'title': u'C à dire ?!',
+ u'description': u'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
+ },
+ u'params': {
+ # m3u8 download
+ u'skip_download': True,
+ },
+ },
+ # franceo
+ {
+ u'url': u'http://www.franceo.fr/jt/info-afrique/04-12-2013',
+ u'info_dict': {
+ u'id': u'92327925',
+ u'ext': u'mp4',
+ u'title': u'Infô-Afrique',
+ u'description': u'md5:ebf346da789428841bee0fd2a935ea55',
+ },
+ u'params': {
+ # m3u8 download
+ u'skip_download': True,
+ },
+ u'skip': u'The id changes frequently',
+ },
+ ]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj.group('key'):
webpage = self._download_webpage(url, mobj.group('key'))
- video_id = self._html_search_regex(
- r'''(?x)<div\s+class="video-player">\s*
+ id_res = [
+
(r'''(?x)<div\s+class="video-player">\s*
<a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+
- class="francetv-video-player">''',
- webpage, u'video ID')
+ class="francetv-video-player">'''),
+ (r'<a id="player_direct" href="http://info\.francetelevisions'
+ '\.fr/\?id-video=([^"/&]+)'),
+ (r'<a class="video" id="ftv_player_(.+?)"'),
+ ]
+ video_id = self._html_search_regex(id_res, webpage, u'video ID')
else:
video_id = mobj.group('id')
return self._extract_video(video_id)
--- /dev/null
+import re
+
+from .common import InfoExtractor
+
+
+class GamekingsIE(InfoExtractor):
+ _VALID_URL = r'http://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)'
+ _TEST = {
+ u"url": u"http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/",
+ u'file': u'20130811.mp4',
+ # MD5 is flaky, seems to change regularly
+ #u'md5': u'2f32b1f7b80fdc5cb616efb4f387f8a3',
+ u'info_dict': {
+ u"title": u"Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review",
+ u"description": u"Melle en Steven hebben voor de review een week in de rechtbank doorbracht met Phoenix Wright: Ace Attorney - Dual Destinies.",
+ }
+ }
+
+ def _real_extract(self, url):
+
+ mobj = re.match(self._VALID_URL, url)
+ name = mobj.group('name')
+ webpage = self._download_webpage(url, name)
+ video_url = self._og_search_video_url(webpage)
+
+ video = re.search(r'[0-9]+', video_url)
+ video_id = video.group(0)
+
+ # Todo: add medium format
+ video_url = video_url.replace(video_id, 'large/' + video_id)
+
+ return {
+ 'id': video_id,
+ 'ext': 'mp4',
+ 'url': video_url,
+ 'title': self._og_search_title(webpage),
+ 'description': self._og_search_description(webpage),
+ }
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- page_id = video_id = mobj.group('page_id')
+ page_id = mobj.group('page_id')
webpage = self._download_webpage(url, page_id)
data_video_json = self._search_regex(r'data-video=\'(.*?)\'', webpage, u'data video')
data_video = json.loads(unescapeHTML(data_video_json))
'format_id': q,
})
- info = {
+ return {
'id': data_video['guid'],
'title': compat_urllib_parse.unquote(data_video['title']),
'formats': formats,
'description': get_meta_content('description', webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}
- # TODO: Remove when #980 has been merged
- info.update(formats[-1])
- return info
import re
-from .mtv import MTVIE, _media_xml_tag
+from .mtv import MTVServicesInfoExtractor
-class GametrailersIE(MTVIE):
- """
- Gametrailers use the same videos system as MTVIE, it just changes the feed
- url, where the uri is and the method to get the thumbnails.
- """
- _VALID_URL = r'http://www.gametrailers.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
+
+class GametrailersIE(MTVServicesInfoExtractor):
+ _VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
_TEST = {
u'url': u'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
u'file': u'70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.mp4',
u'description': u'Faith is back! Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!',
},
}
- # Overwrite MTVIE properties we don't want
- _TESTS = []
_FEED_URL = 'http://www.gametrailers.com/feeds/mrss'
- def _get_thumbnail_url(self, uri, itemdoc):
- search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
- return itemdoc.find(search_path).attrib['url']
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
compat_urlparse,
ExtractorError,
+ HEADRequest,
smuggle_url,
unescapeHTML,
+ unified_strdate,
+ url_basename,
)
from .brightcove import BrightcoveIE
+from .ooyala import OoyalaIE
class GenericIE(InfoExtractor):
},
# embedded vimeo video
{
+ u'add_ie': ['Vimeo'],
u'url': u'http://skillsmatter.com/podcast/home/move-semanticsperfect-forwarding-and-rvalue-references',
u'file': u'22444065.mp4',
u'md5': u'2903896e23df39722c33f015af0666e2',
},
# bandcamp page with custom domain
{
+ u'add_ie': ['Bandcamp'],
u'url': u'http://bronyrock.com/track/the-pony-mash',
u'file': u'3235767654.mp3',
u'info_dict': {
},
u'skip': u'There is a limit of 200 free downloads / month for the test song',
},
+ # embedded brightcove video
+ # it also tests brightcove videos that need to set the 'Referer' in the
+ # http requests
+ {
+ u'add_ie': ['Brightcove'],
+ u'url': u'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
+ u'info_dict': {
+ u'id': u'2765128793001',
+ u'ext': u'mp4',
+ u'title': u'Le cours de bourse : l’analyse technique',
+ u'description': u'md5:7e9ad046e968cb2d1114004aba466fd9',
+ u'uploader': u'BFM BUSINESS',
+ },
+ u'params': {
+ u'skip_download': True,
+ },
+ },
+ # Direct link to a video
+ {
+ u'url': u'http://media.w3.org/2010/05/sintel/trailer.mp4',
+ u'file': u'trailer.mp4',
+ u'md5': u'67d406c2bcb6af27fa886f31aa934bbe',
+ u'info_dict': {
+ u'id': u'trailer',
+ u'title': u'trailer',
+ u'upload_date': u'20100513',
+ }
+ },
+ # ooyala video
+ {
+ u'url': u'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
+ u'md5': u'5644c6ca5d5782c1d0d350dad9bd840c',
+ u'info_dict': {
+ u'id': u'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
+ u'ext': u'mp4',
+ u'title': u'2cc213299525360.mov', #that's what we get
+ },
+ },
]
def report_download_webpage(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url)
- def _test_redirect(self, url):
+ def _send_head(self, url):
"""Check if it is a redirect, like url shorteners, in case return the new url."""
- class HeadRequest(compat_urllib_request.Request):
- def get_method(self):
- return "HEAD"
class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
"""
Subclass the HTTPRedirectHandler to make it use our
- HeadRequest also on the redirected URL
+ HEADRequest also on the redirected URL
"""
def redirect_request(self, req, fp, code, msg, headers, newurl):
if code in (301, 302, 303, 307):
newurl = newurl.replace(' ', '%20')
newheaders = dict((k,v) for k,v in req.headers.items()
if k.lower() not in ("content-length", "content-type"))
- return HeadRequest(newurl,
+ return HEADRequest(newurl,
headers=newheaders,
origin_req_host=req.get_origin_req_host(),
unverifiable=True)
compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
opener.add_handler(handler())
- response = opener.open(HeadRequest(url))
+ response = opener.open(HEADRequest(url))
if response is None:
raise ExtractorError(u'Invalid URL protocol')
- new_url = response.geturl()
-
- if url == new_url:
- return False
-
- self.report_following_redirect(new_url)
- return new_url
+ return response
def _real_extract(self, url):
parsed_url = compat_urlparse.urlparse(url)
if not parsed_url.scheme:
self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
return self.url_result('http://' + url)
+ video_id = os.path.splitext(url.split('/')[-1])[0]
try:
- new_url = self._test_redirect(url)
- if new_url:
- return [self.url_result(new_url)]
+ response = self._send_head(url)
+
+ # Check for redirect
+ new_url = response.geturl()
+ if url != new_url:
+ self.report_following_redirect(new_url)
+ return self.url_result(new_url)
+
+ # Check for direct link to a video
+ content_type = response.headers.get('Content-Type', '')
+ m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
+ if m:
+ upload_date = response.headers.get('Last-Modified')
+ if upload_date:
+ upload_date = unified_strdate(upload_date)
+ return {
+ 'id': video_id,
+ 'title': os.path.splitext(url_basename(url))[0],
+ 'formats': [{
+ 'format_id': m.group('format_id'),
+ 'url': url,
+ 'vcodec': u'none' if m.group('type') == 'audio' else None
+ }],
+ 'upload_date': upload_date,
+ }
+
except compat_urllib_error.HTTPError:
# This may be a stupid server that doesn't like HEAD, our UA, or so
pass
- video_id = url.split('/')[-1]
try:
webpage = self._download_webpage(url, video_id)
except ValueError:
raise ExtractorError(u'Failed to download URL: %s' % url)
self.report_extraction(video_id)
+
+ # it's tempting to parse this further, but you would
+ # have to take into account all the variations like
+ # Video Title - Site Name
+ # Site Name | Video Title
+ # Video Title - Tagline | Site Name
+ # and so on and so forth; it's just not practical
+ video_title = self._html_search_regex(
+ r'(?s)<title>(.*?)</title>', webpage, u'video title',
+ default=u'video')
+
+ # video uploader is domain name
+ video_uploader = self._search_regex(
+ r'^(?:https?://)?([^/]*)/.*', url, u'video uploader')
+
# Look for BrightCove:
- m_brightcove = re.search(r'<object[^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1.+?</object>', webpage, re.DOTALL)
- if m_brightcove is not None:
+ bc_url = BrightcoveIE._extract_brightcove_url(webpage)
+ if bc_url is not None:
self.to_screen(u'Brightcove video detected.')
- bc_url = BrightcoveIE._build_brighcove_url(m_brightcove.group())
return self.url_result(bc_url, 'Brightcove')
# Look for embedded Vimeo player
return self.url_result(surl, 'Vimeo')
# Look for embedded YouTube player
- mobj = re.search(
- r'<iframe[^>]+?src="(https?://(?:www\.)?youtube.com/embed/.+?)"', webpage)
+ matches = re.findall(r'''(?x)
+ (?:<iframe[^>]+?src=|embedSWF\(\s*)
+ (["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
+ (?:embed|v)/.+?)
+ \1''', webpage)
+ if matches:
+ urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube')
+ for tuppl in matches]
+ return self.playlist_result(
+ urlrs, playlist_id=video_id, playlist_title=video_title)
+
+ # Look for embedded Dailymotion player
+ matches = re.findall(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
+ if matches:
+ urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Dailymotion')
+ for tuppl in matches]
+ return self.playlist_result(
+ urlrs, playlist_id=video_id, playlist_title=video_title)
+
+ # Look for embedded Wistia player
+ match = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
+ if match:
+ return {
+ '_type': 'url_transparent',
+ 'url': unescapeHTML(match.group('url')),
+ 'ie_key': 'Wistia',
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'id': video_id,
+ }
+
+ # Look for embedded blip.tv player
+ mobj = re.search(r'<meta\s[^>]*https?://api.blip.tv/\w+/redirect/\w+/(\d+)', webpage)
+ if mobj:
+ return self.url_result('http://blip.tv/seo/-'+mobj.group(1), 'BlipTV')
+ mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*https?://(?:\w+\.)?blip.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', webpage)
if mobj:
- surl = unescapeHTML(mobj.group(1))
- return self.url_result(surl, 'Youtube')
+ player_url = 'http://blip.tv/play/%s.x?p=1' % mobj.group(1)
+ player_page = self._download_webpage(player_url, mobj.group(1))
+ blip_video_id = self._search_regex(r'data-episode-id="(\d+)', player_page, u'blip_video_id', fatal=False)
+ if blip_video_id:
+ return self.url_result('http://blip.tv/seo/-'+blip_video_id, 'BlipTV')
# Look for Bandcamp pages with custom domain
mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
if mobj is not None:
burl = unescapeHTML(mobj.group(1))
- return self.url_result(burl, 'Bandcamp')
+ # Don't set the extractor because it can be a track url or an album
+ return self.url_result(burl)
+
+ # Look for embedded Vevo player
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
+ # Look for Ooyala videos
+ mobj = re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=([^"&]+)', webpage)
+ if mobj is not None:
+ return OoyalaIE._build_url_result(mobj.group(1))
+
+ # Look for Aparat videos
+ mobj = re.search(r'<iframe src="(http://www.aparat.com/video/[^"]+)"', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group(1), 'Aparat')
# Start with something easy: JW Player in SWFObject
mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
if mobj is None:
# Broaden the search a little bit: JWPlayer JS loader
- mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http[^\'"&]*)', webpage)
+ mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http[^\'"]*)', webpage)
if mobj is None:
# Try to find twitter cards info
mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
# here's a fun little line of code for you:
- video_extension = os.path.splitext(video_id)[1][1:]
video_id = os.path.splitext(video_id)[0]
- # it's tempting to parse this further, but you would
- # have to take into account all the variations like
- # Video Title - Site Name
- # Site Name | Video Title
- # Video Title - Tagline | Site Name
- # and so on and so forth; it's just not practical
- video_title = self._html_search_regex(r'<title>(.*)</title>',
- webpage, u'video title', default=u'video', flags=re.DOTALL)
-
- # video uploader is domain name
- video_uploader = self._search_regex(r'(?:https?://)?([^/]*)/.*',
- url, u'video uploader')
-
- return [{
+ return {
'id': video_id,
'url': video_url,
'uploader': video_uploader,
- 'upload_date': None,
'title': video_title,
- 'ext': video_extension,
- }]
+ }
u'file': u'1435540.mp3',
u'md5': u'2c2cd2f76ef11a9b3b581e8b232f3d96',
u'info_dict': {
- u"title": u"Freddie Gibbs - Lay It Down"
+ u"title": u'Freddie Gibbs "Lay It Down"'
}
}
_TEST = {
u'url': u'http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly',
u'file': u'390161.mp4',
- u'md5': u'1d7ba54e2c9d7dc6935ef39e00529138',
+ u'md5': u'8b743df908c42f60cf6496586c7f12c3',
u'info_dict': {
u"description": u"The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here's the proper way to tie a square knot.",
u"title": u"How to Tie a Square Knot Properly"
raise ExtractorError(u'Invalid URL: %s' % url)
track_id = mobj.group(1)
- data = { 'ax': 1, 'ts': time.time() }
+ data = {'ax': 1, 'ts': time.time()}
data_encoded = compat_urllib_parse.urlencode(data)
complete_url = url + "?" + data_encoded
request = compat_urllib_request.Request(complete_url)
'ext': "mp3",
'title': title,
'artist': artist,
- }]
\ No newline at end of file
+ }]
{
u'file': u'638672ee848ae4ff108df2a296418ee2.mp4',
u'info_dict': {
- u'title': u'GTA 5\'s Twisted Beauty in Super Slow Motion',
+ u'title': u'26 Twisted Moments from GTA 5 in Slow Motion',
u'description': u'The twisted beauty of GTA 5 in stunning slow motion.',
},
},
class OneUPIE(IGNIE):
"""Extractor for 1up.com, it uses the ign videos system."""
- _VALID_URL = r'https?://gamevideos.1up.com/(?P<type>video)/id/(?P<name_or_id>.+)'
+ _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)'
IE_NAME = '1up.com'
_DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'
--- /dev/null
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urlparse,
+ get_element_by_attribute,
+)
+
+
+class ImdbIE(InfoExtractor):
+ IE_NAME = u'imdb'
+ IE_DESC = u'Internet Movie Database trailers'
+ _VALID_URL = r'http://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
+
+ _TEST = {
+ u'url': u'http://www.imdb.com/video/imdb/vi2524815897',
+ u'md5': u'9f34fa777ade3a6e57a054fdbcb3a068',
+ u'info_dict': {
+ u'id': u'2524815897',
+ u'ext': u'mp4',
+ u'title': u'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
+ u'description': u'md5:9061c2219254e5d14e03c25c98e96a81',
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
+ descr = get_element_by_attribute('itemprop', 'description', webpage)
+ available_formats = re.findall(
+ r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
+ flags=re.MULTILINE)
+ formats = []
+ for f_id, f_path in available_formats:
+ f_path = f_path.strip()
+ format_page = self._download_webpage(
+ compat_urlparse.urljoin(url, f_path),
+ u'Downloading info for %s format' % f_id)
+ json_data = self._search_regex(
+ r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
+ format_page, u'json data', flags=re.DOTALL)
+ info = json.loads(json_data)
+ format_info = info['videoPlayerObject']['video']
+ formats.append({
+ 'format_id': f_id,
+ 'url': format_info['url'],
+ })
+
+ return {
+ 'id': video_id,
+ 'title': self._og_search_title(webpage),
+ 'formats': formats,
+ 'description': descr,
+ 'thumbnail': format_info['slate'],
+ }
from .common import InfoExtractor
class InstagramIE(InfoExtractor):
- _VALID_URL = r'(?:http://)?instagram.com/p/(.*?)/'
+ _VALID_URL = r'(?:http://)?instagram\.com/p/(.*?)/'
_TEST = {
u'url': u'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
u'file': u'aye83DjauH.mp4',
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
video_id = query_dic['publishedid'][0]
url = self._build_url(query)
- flashconfiguration_xml = self._download_webpage(url, video_id,
+ flashconfiguration = self._download_xml(url, video_id,
u'Downloading flash configuration')
- flashconfiguration = xml.etree.ElementTree.fromstring(flashconfiguration_xml.encode('utf-8'))
file_url = flashconfiguration.find('file').text
file_url = file_url.replace('/playlist.aspx', '/mrssplaylist.aspx')
# Replace some of the parameters in the query to get the best quality
file_url = re.sub(r'(?<=\?)(.+)$',
lambda m: self._clean_query(m.group()),
file_url)
- info_xml = self._download_webpage(file_url, video_id,
+ info = self._download_xml(file_url, video_id,
u'Downloading video info')
- info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
item = info.find('channel/item')
def _bp(p):
--- /dev/null
+# encoding: utf-8
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_request,
+ ExtractorError,
+)
+
+
+class IviIE(InfoExtractor):
+ IE_DESC = u'ivi.ru'
+ IE_NAME = u'ivi'
+ _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch(?:/(?P<compilationid>[^/]+))?/(?P<videoid>\d+)'
+
+ _TESTS = [
+ # Single movie
+ {
+ u'url': u'http://www.ivi.ru/watch/53141',
+ u'file': u'53141.mp4',
+ u'md5': u'6ff5be2254e796ed346251d117196cf4',
+ u'info_dict': {
+ u'title': u'Иван Васильевич меняет профессию',
+ u'description': u'md5:14d8eda24e9d93d29b5857012c6d6346',
+ u'duration': 5498,
+ u'thumbnail': u'http://thumbs.ivi.ru/f20.vcp.digitalaccess.ru/contents/d/1/c3c885163a082c29bceeb7b5a267a6.jpg',
+ },
+ u'skip': u'Only works from Russia',
+ },
+ # Serial's serie
+ {
+ u'url': u'http://www.ivi.ru/watch/dezhurnyi_angel/74791',
+ u'file': u'74791.mp4',
+ u'md5': u'3e6cc9a848c1d2ebcc6476444967baa9',
+ u'info_dict': {
+ u'title': u'Дежурный ангел - 1 серия',
+ u'duration': 2490,
+ u'thumbnail': u'http://thumbs.ivi.ru/f7.vcp.digitalaccess.ru/contents/8/e/bc2f6c2b6e5d291152fdd32c059141.jpg',
+ },
+ u'skip': u'Only works from Russia',
+ }
+ ]
+
+ # Sorted by quality
+ _known_formats = ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ']
+
+ # Sorted by size
+ _known_thumbnails = ['Thumb-120x90', 'Thumb-160', 'Thumb-640x480']
+
+ def _extract_description(self, html):
+ m = re.search(r'<meta name="description" content="(?P<description>[^"]+)"/>', html)
+ return m.group('description') if m is not None else None
+
+ def _extract_comment_count(self, html):
+ m = re.search(u'(?s)<a href="#" id="view-comments" class="action-button dim gradient">\s*Комментарии:\s*(?P<commentcount>\d+)\s*</a>', html)
+ return int(m.group('commentcount')) if m is not None else 0
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('videoid')
+
+ api_url = 'http://api.digitalaccess.ru/api/json/'
+
+ data = {u'method': u'da.content.get',
+ u'params': [video_id, {u'site': u's183',
+ u'referrer': u'http://www.ivi.ru/watch/%s' % video_id,
+ u'contentid': video_id
+ }
+ ]
+ }
+
+ request = compat_urllib_request.Request(api_url, json.dumps(data))
+
+ video_json_page = self._download_webpage(request, video_id, u'Downloading video JSON')
+ video_json = json.loads(video_json_page)
+
+ if u'error' in video_json:
+ error = video_json[u'error']
+ if error[u'origin'] == u'NoRedisValidData':
+ raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
+ raise ExtractorError(u'Unable to download video %s: %s' % (video_id, error[u'message']), expected=True)
+
+ result = video_json[u'result']
+
+ formats = [{'url': x[u'url'],
+ 'format_id': x[u'content_format']
+ } for x in result[u'files'] if x[u'content_format'] in self._known_formats]
+ formats.sort(key=lambda fmt: self._known_formats.index(fmt['format_id']))
+
+ if len(formats) == 0:
+ self._downloader.report_warning(u'No media links available for %s' % video_id)
+ return
+
+ duration = result[u'duration']
+ compilation = result[u'compilation']
+ title = result[u'title']
+
+ title = '%s - %s' % (compilation, title) if compilation is not None else title
+
+ previews = result[u'preview']
+ previews.sort(key=lambda fmt: self._known_thumbnails.index(fmt['content_format']))
+ thumbnail = previews[-1][u'url'] if len(previews) > 0 else None
+
+ video_page = self._download_webpage(url, video_id, u'Downloading video page')
+ description = self._extract_description(video_page)
+ comment_count = self._extract_comment_count(video_page)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'description': description,
+ 'duration': duration,
+ 'comment_count': comment_count,
+ 'formats': formats,
+ }
+
+
+class IviCompilationIE(InfoExtractor):
+ IE_DESC = u'ivi.ru compilations'
+ IE_NAME = u'ivi:compilation'
+ _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
+
+ def _extract_entries(self, html, compilation_id):
+ return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi')
+ for serie in re.findall(r'<strong><a href="/watch/%s/(\d+)">(?:[^<]+)</a></strong>' % compilation_id, html)]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ compilation_id = mobj.group('compilationid')
+ season_id = mobj.group('seasonid')
+
+ if season_id is not None: # Season link
+ season_page = self._download_webpage(url, compilation_id, u'Downloading season %s web page' % season_id)
+ playlist_id = '%s/season%s' % (compilation_id, season_id)
+ playlist_title = self._html_search_meta(u'title', season_page, u'title')
+ entries = self._extract_entries(season_page, compilation_id)
+ else: # Compilation link
+ compilation_page = self._download_webpage(url, compilation_id, u'Downloading compilation web page')
+ playlist_id = compilation_id
+ playlist_title = self._html_search_meta(u'title', compilation_page, u'title')
+ seasons = re.findall(r'<a href="/watch/%s/season(\d+)">[^<]+</a>' % compilation_id, compilation_page)
+ if len(seasons) == 0: # No seasons in this compilation
+ entries = self._extract_entries(compilation_page, compilation_id)
+ else:
+ entries = []
+ for season_id in seasons:
+ season_page = self._download_webpage('http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id),
+ compilation_id, u'Downloading season %s web page' % season_id)
+ entries.extend(self._extract_entries(season_page, compilation_id))
+
+ return self.playlist_result(entries, playlist_id, playlist_title)
\ No newline at end of file
import json
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- title = re.match(self._VALID_URL, url).group(1)
+ title = mobj.group(1)
webpage = self._download_webpage(url, title)
xml_link = self._html_search_regex(
r'<param name="flashvars" value="config=(.*?)" />',
r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',
xml_link, u'video ID')
- xml_config = self._download_webpage(
+ config = self._download_xml(
xml_link, title, u'Downloading XML config')
- config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
- info_json = self._search_regex(
- r'(?sm)<format\.json>(.*?)</format\.json>',
- xml_config, u'JSON information')
+ info_json = config.find('format.json').text
info = json.loads(info_json)['versions'][0]
video_url = 'http://video720.jeuxvideo.com/' + info['file']
)
class JukeboxIE(InfoExtractor):
- _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+).html'
+ _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+)\.html'
_IFRAME = r'<iframe .*src="(?P<iframe>[^"]*)".*>'
_VIDEO_URL = r'"config":{"file":"(?P<video_url>http:[^"]+[.](?P<video_ext>[^.?]+)[?]mdtk=[0-9]+)"'
_TITLE = r'<h1 class="inline">(?P<title>[^<]+)</h1>.*<span id="infos_article_artist">(?P<artist>[^<]+)</span>'
import json
import os
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
archive_id = m.group(1)
api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id
- chapter_info_xml = self._download_webpage(api, chapter_id,
+ doc = self._download_xml(api, chapter_id,
note=u'Downloading chapter information',
errnote=u'Chapter information download failed')
- doc = xml.etree.ElementTree.fromstring(chapter_info_xml)
for a in doc.findall('.//archive'):
if archive_id == a.find('./id').text:
break
import re
+import hashlib
from .common import InfoExtractor
from ..utils import determine_ext
+_md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
class KankanIE(InfoExtractor):
_VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml'
video_id, u'Downloading video url info')
ip = self._search_regex(r'ip:"(.+?)"', video_info_page, u'video url ip')
path = self._search_regex(r'path:"(.+?)"', video_info_page, u'video url path')
- video_url = 'http://%s%s' % (ip, path)
+ param1 = self._search_regex(r'param1:(\d+)', video_info_page, u'param1')
+ param2 = self._search_regex(r'param2:(\d+)', video_info_page, u'param2')
+ key = _md5('xl_mp43651' + param1 + param2)
+ video_url = 'http://%s%s?key=%s&key1=%s' % (ip, path, key, param2)
return {'id': video_id,
'title': title,
)
class KeezMoviesIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[0-9]+))'
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
_TEST = {
u'url': u'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
u'file': u'1214711.mp4',
if webpage.find('encrypted=true')!=-1:
password = self._html_search_regex(r'video_title=(.+?)&', webpage, u'password')
video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
- path = compat_urllib_parse_urlparse( video_url ).path
- extension = os.path.splitext( path )[1][1:]
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
format = path.split('/')[4].split('_')[:2]
- format = "-".join( format )
+ format = "-".join(format)
age_limit = self._rta_search(webpage)
class LiveLeakIE(InfoExtractor):
- _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
+ _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
IE_NAME = u'liveleak'
_TEST = {
u'url': u'http://www.liveleak.com/view?i=757_1364311680',
from ..utils import (
compat_urllib_parse_urlparse,
compat_urlparse,
- get_meta_content,
- ExtractorError,
+ xpath_with_ns,
)
class LivestreamIE(InfoExtractor):
- _VALID_URL = r'http://new.livestream.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
+ IE_NAME = u'livestream'
+ _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
_TEST = {
u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
u'file': u'4719370.mp4',
info = json.loads(self._download_webpage(api_url, video_id,
u'Downloading video info'))
return self._extract_video_info(info)
+
+
+# The original version of Livestream uses a different system
+class LivestreamOriginalIE(InfoExtractor):
+ IE_NAME = u'livestream:original'
+ _VALID_URL = r'https?://www\.livestream\.com/(?P<user>[^/]+)/video\?.*?clipId=(?P<id>.*?)(&|$)'
+ _TEST = {
+ u'url': u'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
+ u'info_dict': {
+ u'id': u'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
+ u'ext': u'flv',
+ u'title': u'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
+ },
+ u'params': {
+ # rtmp
+ u'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ user = mobj.group('user')
+ api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id)
+
+ info = self._download_xml(api_url, video_id)
+ item = info.find('channel').find('item')
+ ns = {'media': 'http://search.yahoo.com/mrss'}
+ thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url']
+ # Remove the extension and number from the path (like 1.jpg)
+ path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, u'path')
+
+ return {
+ 'id': video_id,
+ 'title': item.find('title').text,
+ 'url': 'rtmp://extondemand.livestream.com/ondemand',
+ 'play_path': 'mp4:trans/dv15/mogulus-{0}.mp4'.format(path),
+ 'ext': 'flv',
+ 'thumbnail': thumbnail_url,
+ }
--- /dev/null
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+)
+
+
+class MDRIE(InfoExtractor):
+ _VALID_URL = r'^(?P<domain>(?:https?://)?(?:www\.)?mdr\.de)/mediathek/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)_.*'
+
+ _TESTS = [{
+ u'url': u'http://www.mdr.de/mediathek/themen/nachrichten/video165624_zc-c5c7de76_zs-3795826d.html',
+ u'file': u'165624.mp4',
+ u'md5': u'ae785f36ecbf2f19b42edf1bc9c85815',
+ u'info_dict': {
+ u"title": u"MDR aktuell Eins30 09.12.2013, 22:48 Uhr"
+ },
+ },
+ {
+ u'url': u'http://www.mdr.de/mediathek/radio/mdr1-radio-sachsen/audio718370_zc-67b21197_zs-1b9b2483.html',
+ u'file': u'718370.mp3',
+ u'md5': u'a9d21345a234c7b45dee612f290fd8d7',
+ u'info_dict': {
+ u"title": u"MDR 1 RADIO SACHSEN 10.12.2013, 05:00 Uhr"
+ },
+ }]
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('video_id')
+ domain = m.group('domain')
+
+ # determine title and media streams from webpage
+ html = self._download_webpage(url, video_id)
+
+ title = self._html_search_regex(r'<h2>(.*?)</h2>', html, u'title')
+ xmlurl = self._search_regex(
+ r'(/mediathek/(?:.+)/(?:video|audio)[0-9]+-avCustom.xml)', html, u'XML URL')
+
+ doc = self._download_xml(domain + xmlurl, video_id)
+ formats = []
+ for a in doc.findall('./assets/asset'):
+ url_el = a.find('.//progressiveDownloadUrl')
+ if url_el is None:
+ continue
+ abr = int(a.find('bitrateAudio').text) // 1000
+ media_type = a.find('mediaType').text
+ format = {
+ 'abr': abr,
+ 'filesize': int(a.find('fileSize').text),
+ 'url': url_el.text,
+ }
+
+ vbr_el = a.find('bitrateVideo')
+ if vbr_el is None:
+ format.update({
+ 'vcodec': 'none',
+ 'format_id': u'%s-%d' % (media_type, abr),
+ })
+ else:
+ vbr = int(vbr_el.text) // 1000
+ format.update({
+ 'vbr': vbr,
+ 'width': int(a.find('frameWidth').text),
+ 'height': int(a.find('frameHeight').text),
+ 'format_id': u'%s-%d' % (media_type, vbr),
+ })
+ formats.append(format)
+ formats.sort(key=lambda f: (f.get('vbr'), f['abr']))
+ if not formats:
+ raise ExtractorError(u'Could not find any valid formats')
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'formats': formats,
+ }
import re
-import socket
from .common import InfoExtractor
from ..utils import (
- compat_http_client,
compat_parse_qs,
- compat_urllib_error,
compat_urllib_parse,
compat_urllib_request,
- compat_str,
determine_ext,
ExtractorError,
)
u'age_limit': 18,
},
},
+ # cbs video
+ {
+ u'url': u'http://www.metacafe.com/watch/cb-0rOxMBabDXN6/samsung_galaxy_note_2_samsungs_next_generation_phablet/',
+ u'info_dict': {
+ u'id': u'0rOxMBabDXN6',
+ u'ext': u'flv',
+ u'title': u'Samsung Galaxy Note 2: Samsung\'s next-generation phablet',
+ u'description': u'md5:54d49fac53d26d5a0aaeccd061ada09d',
+ u'duration': 129,
+ },
+ u'params': {
+ # rtmp download
+ u'skip_download': True,
+ },
+ },
]
def _real_initialize(self):
# Retrieve disclaimer
- request = compat_urllib_request.Request(self._DISCLAIMER)
- try:
- self.report_disclaimer()
- compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err))
+ self.report_disclaimer()
+ self._download_webpage(self._DISCLAIMER, None, False, u'Unable to retrieve disclaimer')
# Confirm age
disclaimer_form = {
}
request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
- try:
- self.report_age_confirmation()
- compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
+ self.report_age_confirmation()
+ self._download_webpage(request, None, False, u'Unable to confirm age')
def _real_extract(self, url):
# Extract id and simplified title from URL
video_id = mobj.group(1)
- # Check if video comes from YouTube
- mobj2 = re.match(r'^yt-(.*)$', video_id)
- if mobj2 is not None:
- return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
+ # the video may come from an external site
+ m_external = re.match('^(\w{2})-(.*)$', video_id)
+ if m_external is not None:
+ prefix, ext_id = m_external.groups()
+ # Check if video comes from YouTube
+ if prefix == 'yt':
+ return self.url_result('http://www.youtube.com/watch?v=%s' % ext_id, 'Youtube')
+ # CBS videos use theplatform.com
+ if prefix == 'cb':
+ return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
# Retrieve video webpage to extract further information
req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
import re
-import xml.etree.ElementTree
import operator
from .common import InfoExtractor
+from ..utils import (
+ fix_xml_all_ampersand,
+)
class MetacriticIE(InfoExtractor):
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
# The xml is not well formatted, there are raw '&'
- info_xml = self._download_webpage('http://www.metacritic.com/video_data?video=' + video_id,
- video_id, u'Downloading info xml').replace('&', '&')
- info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
+ info = self._download_xml('http://www.metacritic.com/video_data?video=' + video_id,
+ video_id, u'Downloading info xml', transform_source=fix_xml_all_ampersand)
clip = next(c for c in info.findall('playList/clip') if c.find('id').text == video_id)
formats = []
description = self._html_search_regex(r'<b>Description:</b>(.*?)</p>',
webpage, u'description', flags=re.DOTALL)
- info = {
+ return {
'id': video_id,
'title': clip.find('title').text,
'formats': formats,
'description': description,
'duration': int(clip.find('duration').text),
}
- # TODO: Remove when #980 has been merged
- info.update(formats[-1])
- return info
import json
import re
-import socket
from .common import InfoExtractor
from ..utils import (
- compat_http_client,
- compat_urllib_error,
- compat_urllib_request,
unified_strdate,
+ ExtractorError,
)
"""Returns 1st active url from list"""
for url in url_list:
try:
- compat_urllib_request.urlopen(url)
+ # We only want to know if the request succeed
+ # don't download the whole file
+ self._request_webpage(url, None, False)
return url
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error):
+ except ExtractorError:
url = None
return None
+ def _get_url(self, template_url):
+ return self.check_urls(template_url % i for i in range(30))
+
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
preview_url = self._search_regex(r'data-preview-url="(.+?)"', webpage, u'preview url')
song_url = preview_url.replace('/previews/', '/cloudcasts/originals/')
template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
- final_song_url = self.check_urls(template_url % i for i in range(30))
+ final_song_url = self._get_url(template_url)
+ if final_song_url is None:
+ self.to_screen('Trying with m4a extension')
+ template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
+ final_song_url = self._get_url(template_url)
+ if final_song_url is None:
+ raise ExtractorError(u'Unable to extract track url')
return {
'id': track_id,
'title': info['name'],
'url': final_song_url,
- 'ext': 'mp3',
- 'description': info['description'],
+ 'description': info.get('description'),
'thumbnail': info['pictures'].get('extra_large'),
'uploader': info['user']['name'],
'uploader_id': info['user']['username'],
--- /dev/null
+import os
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse_urlparse,
+ compat_urllib_request,
+ compat_urllib_parse,
+)
+
+class MofosexIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)'
+ _TEST = {
+ u'url': u'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
+ u'file': u'5018.mp4',
+ u'md5': u'1b2eb47ac33cc75d4a80e3026b613c5a',
+ u'info_dict': {
+ u"title": u"Japanese Teen Music Video",
+ u"age_limit": 18,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('videoid')
+ url = 'http://www.' + mobj.group('url')
+
+ req = compat_urllib_request.Request(url)
+ req.add_header('Cookie', 'age_verified=1')
+ webpage = self._download_webpage(req, video_id)
+
+ video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, u'title')
+ video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, u'video_url'))
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
+ format = path.split('/')[5].split('_')[:2]
+ format = "-".join(format)
+
+ age_limit = self._rta_search(webpage)
+
+ return {
+ 'id': video_id,
+ 'title': video_title,
+ 'url': video_url,
+ 'ext': extension,
+ 'format': format,
+ 'format_id': format,
+ 'age_limit': age_limit,
+ }
def _media_xml_tag(tag):
return '{http://search.yahoo.com/mrss/}%s' % tag
-class MTVIE(InfoExtractor):
- _VALID_URL = r'^https?://(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$'
-
- _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'
-
- _TESTS = [
- {
- u'url': u'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
- u'file': u'853555.mp4',
- u'md5': u'850f3f143316b1e71fa56a4edfd6e0f8',
- u'info_dict': {
- u'title': u'Taylor Swift - "Ours (VH1 Storytellers)"',
- u'description': u'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
- },
- },
- {
- u'url': u'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
- u'file': u'USCJY1331283.mp4',
- u'md5': u'73b4e7fcadd88929292fe52c3ced8caf',
- u'info_dict': {
- u'title': u'Everything Has Changed',
- u'upload_date': u'20130606',
- u'uploader': u'Taylor Swift',
- },
- u'skip': u'VEVO is only available in some countries',
- },
- ]
+class MTVServicesInfoExtractor(InfoExtractor):
@staticmethod
def _id_from_uri(uri):
return uri.split(':')[-1]
def _transform_rtmp_url(rtmp_video_url):
m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
if not m:
- raise ExtractorError(u'Cannot transform RTMP url')
+ return rtmp_video_url
base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
return base + m.group('finalid')
def _get_thumbnail_url(self, uri, itemdoc):
- return 'http://mtv.mtvnimages.com/uri/' + uri
+ search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
+ thumb_node = itemdoc.find(search_path)
+ if thumb_node is None:
+ return None
+ else:
+ return thumb_node.attrib['url']
def _extract_video_formats(self, metadataXml):
if '/error_country_block.swf' in metadataXml:
raise ExtractorError(u'This video is not available from your country.', expected=True)
mdoc = xml.etree.ElementTree.fromstring(metadataXml.encode('utf-8'))
- renditions = mdoc.findall('.//rendition')
formats = []
for rendition in mdoc.findall('.//rendition'):
else:
description = None
- info = {
+ return {
'title': itemdoc.find('title').text,
'formats': self._extract_video_formats(mediagen_page),
'id': video_id,
'description': description,
}
- # TODO: Remove when #980 has been merged
- info.update(info['formats'][-1])
-
- return info
-
def _get_videos_info(self, uri):
video_id = self._id_from_uri(uri)
data = compat_urllib_parse.urlencode({'uri': uri})
- infoXml = self._download_webpage(self._FEED_URL +'?' + data, video_id,
- u'Downloading info')
- idoc = xml.etree.ElementTree.fromstring(infoXml.encode('utf-8'))
+
+ def fix_ampersand(s):
+ """ Fix unencoded ampersand in XML """
+ return s.replace(u'& ', '& ')
+ idoc = self._download_xml(
+ self._FEED_URL + '?' + data, video_id,
+ u'Downloading info', transform_source=fix_ampersand)
return [self._get_video_info(item) for item in idoc.findall('.//item')]
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('videoid')
- webpage = self._download_webpage(url, video_id)
+class MTVIE(MTVServicesInfoExtractor):
+ _VALID_URL = r'''(?x)^https?://
+ (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$|
+ m\.mtv\.com/videos/video\.rbml\?.*?id=(?P<mgid>[^&]+))'''
- # Some videos come from Vevo.com
- m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
- webpage, re.DOTALL)
- if m_vevo:
- vevo_id = m_vevo.group(1);
- self.to_screen(u'Vevo video detected: %s' % vevo_id)
- return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
+ _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'
- uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, u'uri')
+ _TESTS = [
+ {
+ u'url': u'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
+ u'file': u'853555.mp4',
+ u'md5': u'850f3f143316b1e71fa56a4edfd6e0f8',
+ u'info_dict': {
+ u'title': u'Taylor Swift - "Ours (VH1 Storytellers)"',
+ u'description': u'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
+ },
+ },
+ {
+ u'add_ie': ['Vevo'],
+ u'url': u'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
+ u'file': u'USCJY1331283.mp4',
+ u'md5': u'73b4e7fcadd88929292fe52c3ced8caf',
+ u'info_dict': {
+ u'title': u'Everything Has Changed',
+ u'upload_date': u'20130606',
+ u'uploader': u'Taylor Swift',
+ },
+ u'skip': u'VEVO is only available in some countries',
+ },
+ ]
+
+ def _get_thumbnail_url(self, uri, itemdoc):
+ return 'http://mtv.mtvnimages.com/uri/' + uri
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('videoid')
+ uri = mobj.group('mgid')
+ if uri is None:
+ webpage = self._download_webpage(url, video_id)
+
+ # Some videos come from Vevo.com
+ m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
+ webpage, re.DOTALL)
+ if m_vevo:
+ vevo_id = m_vevo.group(1);
+ self.to_screen(u'Vevo video detected: %s' % vevo_id)
+ return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
+
+ uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, u'uri')
return self._get_videos_info(uri)
class MuzuTVIE(InfoExtractor):
- _VALID_URL = r'https?://www.muzu.tv/(.+?)/(.+?)/(?P<id>\d+)'
+ _VALID_URL = r'https?://www\.muzu\.tv/(.+?)/(.+?)/(?P<id>\d+)'
IE_NAME = u'muzu.tv'
_TEST = {
import os.path
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
class MySpassIE(InfoExtractor):
- _VALID_URL = r'http://www.myspass.de/.*'
+ _VALID_URL = r'http://www\.myspass\.de/.*'
_TEST = {
u'url': u'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
u'file': u'11741.mp4',
# get metadata
metadata_url = META_DATA_URL_TEMPLATE % video_id
- metadata_text = self._download_webpage(metadata_url, video_id)
- metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8'))
+ metadata = self._download_xml(metadata_url, video_id)
# extract values from metadata
url_flv_el = metadata.find('url_flv')
# encoding: utf-8
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
class NaverIE(InfoExtractor):
- _VALID_URL = r'https?://tvcast\.naver\.com/v/(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)'
_TEST = {
u'url': u'http://tvcast.naver.com/v/81652',
'protocol': 'p2p',
'inKey': key,
})
- info_xml = self._download_webpage(
+ info = self._download_xml(
'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query,
video_id, u'Downloading video info')
- urls_xml = self._download_webpage(
+ urls = self._download_xml(
'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls,
video_id, u'Downloading video formats info')
- info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
- urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8'))
formats = []
for format_el in urls.findall('EncodingOptions/EncodingOption'):
'height': int(format_el.find('height').text),
})
- info = {
+ return {
'id': video_id,
'title': info.find('Subject').text,
'formats': formats,
'upload_date': info.find('WriteDate').text.replace('.', ''),
'view_count': int(info.find('PlayCount').text),
}
- # TODO: Remove when #980 has been merged
- info.update(formats[-1])
- return info
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import find_xpath_attr, compat_str
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
- info_xml = self._download_webpage('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
- info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')).find('video')
+ all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
+ info = all_info.find('video')
return {'id': video_id,
'title': info.find('headline').text,
--- /dev/null
+import re
+
+from .common import InfoExtractor
+from ..utils import month_by_name
+
+
+class NDTVIE(InfoExtractor):
+ _VALID_URL = r'^https?://(?:www\.)?ndtv\.com/video/player/[^/]*/[^/]*/(?P<id>[a-z0-9]+)'
+
+ _TEST = {
+ u"url": u"http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710",
+ u"file": u"300710.mp4",
+ u"md5": u"39f992dbe5fb531c395d8bbedb1e5e88",
+ u"info_dict": {
+ u"title": u"NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal",
+ u"description": u"In an exclusive interview to NDTV, Aam Aadmi Party's Arvind Kejriwal says it makes no difference to him that Rahul Gandhi said the Congress needs to learn from his party.",
+ u"upload_date": u"20131208",
+ u"duration": 1327,
+ u"thumbnail": u"http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg",
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ filename = self._search_regex(
+ r"__filename='([^']+)'", webpage, u'video filename')
+ video_url = (u'http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' %
+ filename)
+
+ duration_str = filename = self._search_regex(
+ r"__duration='([^']+)'", webpage, u'duration', fatal=False)
+ duration = None if duration_str is None else int(duration_str)
+
+ date_m = re.search(r'''(?x)
+ <p\s+class="vod_dateline">\s*
+ Published\s+On:\s*
+ (?P<monthname>[A-Za-z]+)\s+(?P<day>[0-9]+),\s*(?P<year>[0-9]+)
+ ''', webpage)
+ upload_date = None
+ assert date_m
+ if date_m is not None:
+ month = month_by_name(date_m.group('monthname'))
+ if month is not None:
+ upload_date = '%s%02d%02d' % (
+ date_m.group('year'), month, int(date_m.group('day')))
+
+ description = self._og_search_description(webpage)
+ READ_MORE = u' (Read more)'
+ if description.endswith(READ_MORE):
+ description = description[:-len(READ_MORE)]
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': self._og_search_title(webpage),
+ 'description': description,
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ 'duration': duration,
+ 'upload_date': upload_date,
+ }
import re
import json
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
'path': initial_video_url.replace('.mp4', '_sd.mp4'),
})
path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
- path_response = self._download_webpage(path_url, video_id,
+ path_doc = self._download_xml(path_url, video_id,
u'Downloading final video url')
- path_doc = xml.etree.ElementTree.fromstring(path_response)
video_url = path_doc.find('path').text
join = compat_urlparse.urljoin
class NHLVideocenterIE(NHLBaseInfoExtractor):
IE_NAME = u'nhl.com:videocenter'
- IE_DESC = u'Download the first 12 videos from a videocenter category'
+ IE_DESC = u'NHL videocenter category'
_VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[^&]+))?'
@classmethod
--- /dev/null
+# encoding: utf-8
+
+import re
+import socket
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_http_client,
+ compat_urllib_error,
+ compat_urllib_parse,
+ compat_urllib_request,
+ compat_urlparse,
+ compat_str,
+
+ ExtractorError,
+ unified_strdate,
+)
+
+
+class NiconicoIE(InfoExtractor):
+ IE_NAME = u'niconico'
+ IE_DESC = u'ニコニコ動画'
+
+ _TEST = {
+ u'url': u'http://www.nicovideo.jp/watch/sm22312215',
+ u'file': u'sm22312215.mp4',
+ u'md5': u'd1a75c0823e2f629128c43e1212760f9',
+ u'info_dict': {
+ u'title': u'Big Buck Bunny',
+ u'uploader': u'takuya0301',
+ u'uploader_id': u'2698420',
+ u'upload_date': u'20131123',
+ u'description': u'(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
+ },
+ u'params': {
+ u'username': u'ydl.niconico@gmail.com',
+ u'password': u'youtube-dl',
+ },
+ }
+
+ _VALID_URL = r'^https?://(?:www\.|secure\.)?nicovideo\.jp/watch/([a-z][a-z][0-9]+)(?:.*)$'
+ _NETRC_MACHINE = 'niconico'
+ # If True it will raise an error if no login info is provided
+ _LOGIN_REQUIRED = True
+
+ def _real_initialize(self):
+ self._login()
+
+ def _login(self):
+ (username, password) = self._get_login_info()
+ # No authentication to be performed
+ if username is None:
+ if self._LOGIN_REQUIRED:
+ raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True)
+ return False
+
+ # Log in
+ login_form_strs = {
+ u'mail': username,
+ u'password': password,
+ }
+ # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
+ # chokes on unicode
+ login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
+ login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
+ request = compat_urllib_request.Request(
+ u'https://secure.nicovideo.jp/secure/login', login_data)
+ login_results = self._download_webpage(
+ request, u'', note=u'Logging in', errnote=u'Unable to log in')
+ if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
+ self._downloader.report_warning(u'unable to log in: bad username or password')
+ return False
+ return True
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group(1)
+
+ # Get video webpage. We are not actually interested in it, but need
+ # the cookies in order to be able to download the info webpage
+ self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id)
+
+ video_info = self._download_xml(
+ 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
+ note=u'Downloading video info page')
+
+ # Get flv info
+ flv_info_webpage = self._download_webpage(
+ u'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
+ video_id, u'Downloading flv info')
+ video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
+
+ # Start extracting information
+ video_title = video_info.find('.//title').text
+ video_extension = video_info.find('.//movie_type').text
+ video_format = video_extension.upper()
+ video_thumbnail = video_info.find('.//thumbnail_url').text
+ video_description = video_info.find('.//description').text
+ video_uploader_id = video_info.find('.//user_id').text
+ video_upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0])
+ video_view_count = video_info.find('.//view_counter').text
+ video_webpage_url = video_info.find('.//watch_url').text
+
+ # uploader
+ video_uploader = video_uploader_id
+ url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id
+ try:
+ user_info = self._download_xml(
+ url, video_id, note=u'Downloading user information')
+ video_uploader = user_info.find('.//nickname').text
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.report_warning(u'Unable to download user info webpage: %s' % compat_str(err))
+
+ return {
+ 'id': video_id,
+ 'url': video_real_url,
+ 'title': video_title,
+ 'ext': video_extension,
+ 'format': video_format,
+ 'thumbnail': video_thumbnail,
+ 'description': video_description,
+ 'uploader': video_uploader,
+ 'upload_date': video_upload_date,
+ 'uploader_id': video_uploader_id,
+ 'view_count': video_view_count,
+ 'webpage_url': video_webpage_url,
+ }
--- /dev/null
+import json
+import re
+
+from .common import InfoExtractor
+
+
+class NineGagIE(InfoExtractor):
+ IE_NAME = '9gag'
+ _VALID_URL = r'^https?://(?:www\.)?9gag\.tv/v/(?P<id>[0-9]+)'
+
+ _TEST = {
+ u"url": u"http://9gag.tv/v/1912",
+ u"file": u"1912.mp4",
+ u"info_dict": {
+ u"description": u"This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)",
+ u"title": u"\"People Are Awesome 2013\" Is Absolutely Awesome"
+ },
+ u'add_ie': [u'Youtube']
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+ data_json = self._html_search_regex(r'''(?x)
+ <div\s*id="tv-video"\s*data-video-source="youtube"\s*
+ data-video-meta="([^"]+)"''', webpage, u'video metadata')
+
+ data = json.loads(data_json)
+
+ return {
+ '_type': 'url_transparent',
+ 'url': data['youtubeVideoId'],
+ 'ie_key': 'Youtube',
+ 'id': video_id,
+ 'title': data['title'],
+ 'description': data['description'],
+ 'view_count': int(data['view_count']),
+ 'like_count': int(data['statistic']['like']),
+ 'dislike_count': int(data['statistic']['dislike']),
+ 'thumbnail': data['thumbnail_url'],
+ }
def _url_for_embed_code(embed_code):
return 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code
+ @classmethod
+ def _build_url_result(cls, embed_code):
+ return cls.url_result(cls._url_for_embed_code(embed_code),
+ ie=cls.ie_key())
+
def _extract_result(self, info, more_info):
return {'id': info['embedCode'],
'ext': 'mp4',
)
class ORFIE(InfoExtractor):
- _VALID_URL = r'https?://tvthek.orf.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)'
+ _VALID_URL = r'https?://tvthek\.orf\.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
class PBSIE(InfoExtractor):
- _VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?'
+ _VALID_URL = r'https?://video\.pbs\.org/video/(?P<id>\d+)/?'
_TEST = {
u'url': u'http://video.pbs.org/video/2365006249/',
--- /dev/null
+import json
+import re
+
+from .common import InfoExtractor
+
+
+class PodomaticIE(InfoExtractor):
+ IE_NAME = 'podomatic'
+ _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)'
+
+ _TEST = {
+ u"url": u"http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00",
+ u"file": u"2009-01-02T16_03_35-08_00.mp3",
+ u"md5": u"84bb855fcf3429e6bf72460e1eed782d",
+ u"info_dict": {
+ u"uploader": u"Science Teaching Tips",
+ u"uploader_id": u"scienceteachingtips",
+ u"title": u"64. When the Moon Hits Your Eye",
+ u"duration": 446,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ channel = mobj.group('channel')
+
+ json_url = (('%s://%s.podomatic.com/entry/embed_params/%s' +
+ '?permalink=true&rtmp=0') %
+ (mobj.group('proto'), channel, video_id))
+ data_json = self._download_webpage(
+ json_url, video_id, note=u'Downloading video info')
+ data = json.loads(data_json)
+
+ video_url = data['downloadLink']
+ uploader = data['podcast']
+ title = data['title']
+ thumbnail = data['imageLocation']
+ duration = int(data['length'] / 1000.0)
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'uploader': uploader,
+ 'uploader_id': channel,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ }
--- /dev/null
+import re
+
+from .common import InfoExtractor
+from ..utils import compat_urllib_parse
+
+
+class PornHdIE(InfoExtractor):
+ _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
+ _TEST = {
+ u'url': u'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
+ u'file': u'1962.flv',
+ u'md5': u'35272469887dca97abd30abecc6cdf75',
+ u'info_dict': {
+ u"title": u"sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
+ u"age_limit": 18,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+
+ video_id = mobj.group('video_id')
+ video_title = mobj.group('video_title')
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = self._html_search_regex(
+ r'&hd=(http.+?)&', webpage, u'video URL')
+ video_url = compat_urllib_parse.unquote(video_url)
+ age_limit = 18
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'flv',
+ 'title': video_title,
+ 'age_limit': age_limit,
+ }
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
- unescapeHTML,
)
from ..aes import (
aes_decrypt_text
)
class PornHubIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9]+))'
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9a-f]+))'
_TEST = {
u'url': u'http://www.pornhub.com/view_video.php?viewkey=648719015',
u'file': u'648719015.mp4',
formats = []
for video_url in video_urls:
- path = compat_urllib_parse_urlparse( video_url ).path
- extension = os.path.splitext( path )[1][1:]
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
format = path.split('/')[5].split('_')[:2]
- format = "-".join( format )
+ format = "-".join(format)
formats.append({
'url': video_url,
'ext': extension,
--- /dev/null
+import re
+import os
+
+from .common import InfoExtractor
+
+
+class PyvideoIE(InfoExtractor):
+ _VALID_URL = r'(?:http://)?(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
+ _TESTS = [{
+ u'url': u'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes',
+ u'file': u'24_4WWkSmNo.mp4',
+ u'md5': u'de317418c8bc76b1fd8633e4f32acbc6',
+ u'info_dict': {
+ u"title": u"Become a logging expert in 30 minutes",
+ u"description": u"md5:9665350d466c67fb5b1598de379021f7",
+ u"upload_date": u"20130320",
+ u"uploader": u"NextDayVideo",
+ u"uploader_id": u"NextDayVideo",
+ },
+ u'add_ie': ['Youtube'],
+ },
+ {
+ u'url': u'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v',
+ u'md5': u'5fe1c7e0a8aa5570330784c847ff6d12',
+ u'info_dict': {
+ u'id': u'2542',
+ u'ext': u'm4v',
+ u'title': u'Gloriajw-SpotifyWithErikBernhardsson182',
+ },
+ },
+ ]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+ m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage)
+
+ if m_youtube is not None:
+ return self.url_result(m_youtube.group(1), 'Youtube')
+
+ title = self._html_search_regex(r'<div class="section">.*?<h3>([^>]+?)</h3>',
+ webpage, u'title', flags=re.DOTALL)
+ video_url = self._search_regex([r'<source src="(.*?)"',
+ r'<dt>Download</dt>.*?<a href="(.+?)"'],
+ webpage, u'video url', flags=re.DOTALL)
+ return {
+ 'id': video_id,
+ 'title': os.path.splitext(title)[0],
+ 'url': video_url,
+ }
--- /dev/null
+# coding: utf-8
+import re
+
+from .common import InfoExtractor
+
+
+class RadioFranceIE(InfoExtractor):
+ _VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'
+ IE_NAME = u'radiofrance'
+
+ _TEST = {
+ u'url': u'http://maison.radiofrance.fr/radiovisions/one-one',
+ u'file': u'one-one.ogg',
+ u'md5': u'bdbb28ace95ed0e04faab32ba3160daf',
+ u'info_dict': {
+ u"title": u"One to one",
+ u"description": u"Plutôt que d'imaginer la radio de demain comme technologie ou comme création de contenu, je veux montrer que quelles que soient ses évolutions, j'ai l'intime conviction que la radio continuera d'être un grand média de proximité pour les auditeurs.",
+ u"uploader": u"Thomas Hercouët",
+ },
+ }
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+ title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, u'title')
+ description = self._html_search_regex(
+ r'<div class="bloc_page_wrapper"><div class="text">(.*?)</div>',
+ webpage, u'description', fatal=False)
+ uploader = self._html_search_regex(
+ r'<div class="credit"> © (.*?)</div>',
+ webpage, u'uploader', fatal=False)
+
+ formats_str = self._html_search_regex(
+ r'class="jp-jplayer[^"]*" data-source="([^"]+)">',
+ webpage, u'audio URLs')
+ formats = [
+ {
+ 'format_id': fm[0],
+ 'url': fm[1],
+ 'vcodec': 'none',
+ }
+ for fm in
+ re.findall(r"([a-z0-9]+)\s*:\s*'([^']+)'", formats_str)
+ ]
+ # No sorting, we don't know any more about these formats
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'formats': formats,
+ 'description': description,
+ 'uploader': uploader,
+ }
_TEST = {
u'url': u'http://www.redtube.com/66418',
u'file': u'66418.mp4',
- u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
+ # md5 varies from time to time, as in
+ # https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295
+ #u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
u'info_dict': {
u"title": u"Sucked on a toilet",
u"age_limit": 18,
r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL')
video_title = self._html_search_regex(
- r'<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
+ r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
webpage, u'title')
# No self-labeling, but they describe themselves as
ExtractorError,
)
+
class RTLnowIE(InfoExtractor):
"""Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW"""
- _VALID_URL = r'(?:http://)?(?P<url>(?P<base_url>rtl-now\.rtl\.de/|rtl2now\.rtl2\.de/|(?:www\.)?voxnow\.de/|(?:www\.)?rtlnitronow\.de/|(?:www\.)?superrtlnow\.de/|(?:www\.)?n-tvnow\.de/)[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
+ _VALID_URL = r'(?:http://)?(?P<url>(?P<domain>rtl-now\.rtl\.de|rtl2now\.rtl2\.de|(?:www\.)?voxnow\.de|(?:www\.)?rtlnitronow\.de|(?:www\.)?superrtlnow\.de|(?:www\.)?n-tvnow\.de)/+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
_TESTS = [{
u'url': u'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
u'file': u'90419.flv',
u'info_dict': {
- u'upload_date': u'20070416',
+ u'upload_date': u'20070416',
u'title': u'Ahornallee - Folge 1 - Der Einzug',
u'description': u'Folge 1 - Der Einzug',
},
u'skip_download': True,
},
},
- {
- u'url': u'http://www.rtlnitronow.de/recht-ordnung/stadtpolizei-frankfurt-gerichtsvollzieher-leipzig.php?film_id=129679&player=1&season=1',
- u'file': u'129679.flv',
- u'info_dict': {
- u'upload_date': u'20131016',
- u'title': u'Recht & Ordnung - Stadtpolizei Frankfurt/ Gerichtsvollzieher...',
- u'description': u'Stadtpolizei Frankfurt/ Gerichtsvollzieher Leipzig',
- },
- u'params': {
- u'skip_download': True,
- },
- },
{
u'url': u'http://www.n-tvnow.de/top-gear/episode-1-2013-01-01-00-00-00.php?film_id=124903&player=1&season=10',
u'file': u'124903.flv',
mobj = re.match(self._VALID_URL, url)
webpage_url = u'http://' + mobj.group('url')
- video_page_url = u'http://' + mobj.group('base_url')
+ video_page_url = u'http://' + mobj.group('domain') + u'/'
video_id = mobj.group(u'video_id')
webpage = self._download_webpage(webpage_url, video_id)
class RutubeIE(InfoExtractor):
- _VALID_URL = r'https?://rutube.ru/video/(?P<long_id>\w+)'
+ _VALID_URL = r'https?://rutube\.ru/video/(?P<long_id>\w+)'
_TEST = {
u'url': u'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
# coding: utf-8
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
def _extract_video(self, video_id):
data = compat_urllib_parse.urlencode({'vid': video_id})
- url_page = self._download_webpage('http://v.iask.com/v_play.php?%s' % data,
+ url_doc = self._download_xml('http://v.iask.com/v_play.php?%s' % data,
video_id, u'Downloading video url')
image_page = self._download_webpage(
'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data,
video_id, u'Downloading thumbnail info')
- url_doc = xml.etree.ElementTree.fromstring(url_page.encode('utf-8'))
return {'id': video_id,
'url': url_doc.find('./durl/url').text,
class SlashdotIE(InfoExtractor):
- _VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)'
+ _VALID_URL = r'https?://tv\.slashdot\.org/video/\?embed=(?P<id>.*?)(&|$)'
_TEST = {
+ u'add_ie': ['Ooyala'],
u'url': u'http://tv.slashdot.org/video/?embed=JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz',
u'file': u'JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz.mp4',
u'md5': u'd2222e7a4a4c1541b3e0cf732fb26735',
--- /dev/null
+# encoding: utf-8
+
+import re
+import json
+import hashlib
+import uuid
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse,
+ compat_urllib_request,
+ ExtractorError,
+)
+
+
+class SmotriIE(InfoExtractor):
+ IE_DESC = u'Smotri.com'
+ IE_NAME = u'smotri'
+ _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/video/view/\?id=(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4}))'
+
+ _TESTS = [
+ # real video id 2610366
+ {
+ u'url': u'http://smotri.com/video/view/?id=v261036632ab',
+ u'file': u'v261036632ab.mp4',
+ u'md5': u'2a7b08249e6f5636557579c368040eb9',
+ u'info_dict': {
+ u'title': u'катастрофа с камер видеонаблюдения',
+ u'uploader': u'rbc2008',
+ u'uploader_id': u'rbc08',
+ u'upload_date': u'20131118',
+ u'description': u'катастрофа с камер видеонаблюдения, видео катастрофа с камер видеонаблюдения',
+ u'thumbnail': u'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
+ },
+ },
+ # real video id 57591
+ {
+ u'url': u'http://smotri.com/video/view/?id=v57591cb20',
+ u'file': u'v57591cb20.flv',
+ u'md5': u'830266dfc21f077eac5afd1883091bcd',
+ u'info_dict': {
+ u'title': u'test',
+ u'uploader': u'Support Photofile@photofile',
+ u'uploader_id': u'support-photofile',
+ u'upload_date': u'20070704',
+ u'description': u'test, видео test',
+ u'thumbnail': u'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
+ },
+ },
+ # video-password
+ {
+ u'url': u'http://smotri.com/video/view/?id=v1390466a13c',
+ u'file': u'v1390466a13c.mp4',
+ u'md5': u'f6331cef33cad65a0815ee482a54440b',
+ u'info_dict': {
+ u'title': u'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
+ u'uploader': u'timoxa40',
+ u'uploader_id': u'timoxa40',
+ u'upload_date': u'20100404',
+ u'thumbnail': u'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
+ u'description': u'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1, видео TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
+ },
+ u'params': {
+ u'videopassword': u'qwerty',
+ },
+ },
+ # age limit + video-password
+ {
+ u'url': u'http://smotri.com/video/view/?id=v15408898bcf',
+ u'file': u'v15408898bcf.flv',
+ u'md5': u'91e909c9f0521adf5ee86fbe073aad70',
+ u'info_dict': {
+ u'title': u'этот ролик не покажут по ТВ',
+ u'uploader': u'zzxxx',
+ u'uploader_id': u'ueggb',
+ u'upload_date': u'20101001',
+ u'thumbnail': u'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
+ u'age_limit': 18,
+ u'description': u'этот ролик не покажут по ТВ, видео этот ролик не покажут по ТВ',
+ },
+ u'params': {
+ u'videopassword': u'333'
+ }
+ }
+ ]
+
+ _SUCCESS = 0
+ _PASSWORD_NOT_VERIFIED = 1
+ _PASSWORD_DETECTED = 2
+ _VIDEO_NOT_FOUND = 3
+
+ def _search_meta(self, name, html, display_name=None):
+ if display_name is None:
+ display_name = name
+ return self._html_search_regex(
+ r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name),
+ html, display_name, fatal=False)
+ return self._html_search_meta(name, html, display_name)
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('videoid')
+ real_video_id = mobj.group('realvideoid')
+
+ # Download video JSON data
+ video_json_url = 'http://smotri.com/vt.php?id=%s' % real_video_id
+ video_json_page = self._download_webpage(video_json_url, video_id, u'Downloading video JSON')
+ video_json = json.loads(video_json_page)
+
+ status = video_json['status']
+ if status == self._VIDEO_NOT_FOUND:
+ raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
+ elif status == self._PASSWORD_DETECTED: # The video is protected by a password, retry with
+ # video-password set
+ video_password = self._downloader.params.get('videopassword', None)
+ if not video_password:
+ raise ExtractorError(u'This video is protected by a password, use the --video-password option', expected=True)
+ video_json_url += '&md5pass=%s' % hashlib.md5(video_password.encode('utf-8')).hexdigest()
+ video_json_page = self._download_webpage(video_json_url, video_id, u'Downloading video JSON (video-password set)')
+ video_json = json.loads(video_json_page)
+ status = video_json['status']
+ if status == self._PASSWORD_NOT_VERIFIED:
+ raise ExtractorError(u'Video password is invalid', expected=True)
+
+ if status != self._SUCCESS:
+ raise ExtractorError(u'Unexpected status value %s' % status)
+
+ # Extract the URL of the video
+ video_url = video_json['file_data']
+
+ # Video JSON does not provide enough meta data
+ # We will extract some from the video web page instead
+ video_page_url = 'http://' + mobj.group('url')
+ video_page = self._download_webpage(video_page_url, video_id, u'Downloading video page')
+
+ # Adult content
+ if re.search(u'EroConfirmText">', video_page) is not None:
+ self.report_age_confirmation()
+ confirm_string = self._html_search_regex(
+ r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
+ video_page, u'confirm string')
+ confirm_url = video_page_url + '&confirm=%s' % confirm_string
+ video_page = self._download_webpage(confirm_url, video_id, u'Downloading video page (age confirmed)')
+ adult_content = True
+ else:
+ adult_content = False
+
+ # Extract the rest of meta data
+ video_title = self._search_meta(u'name', video_page, u'title')
+ if not video_title:
+ video_title = video_url.rsplit('/', 1)[-1]
+
+ video_description = self._search_meta(u'description', video_page)
+ END_TEXT = u' на сайте Smotri.com'
+ if video_description.endswith(END_TEXT):
+ video_description = video_description[:-len(END_TEXT)]
+ START_TEXT = u'Смотреть онлайн ролик '
+ if video_description.startswith(START_TEXT):
+ video_description = video_description[len(START_TEXT):]
+ video_thumbnail = self._search_meta(u'thumbnail', video_page)
+
+ upload_date_str = self._search_meta(u'uploadDate', video_page, u'upload date')
+ upload_date_m = re.search(r'(?P<year>\d{4})\.(?P<month>\d{2})\.(?P<day>\d{2})T', upload_date_str)
+ video_upload_date = (
+ (
+ upload_date_m.group('year') +
+ upload_date_m.group('month') +
+ upload_date_m.group('day')
+ )
+ if upload_date_m else None
+ )
+
+ duration_str = self._search_meta(u'duration', video_page)
+ duration_m = re.search(r'T(?P<hours>[0-9]{2})H(?P<minutes>[0-9]{2})M(?P<seconds>[0-9]{2})S', duration_str)
+ video_duration = (
+ (
+ (int(duration_m.group('hours')) * 60 * 60) +
+ (int(duration_m.group('minutes')) * 60) +
+ int(duration_m.group('seconds'))
+ )
+ if duration_m else None
+ )
+
+ video_uploader = self._html_search_regex(
+ u'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info[^"]+">(.*?)</a>',
+ video_page, u'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL)
+
+ video_uploader_id = self._html_search_regex(
+ u'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info\\(.*?\'([^\']+)\'\\);">',
+ video_page, u'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL)
+
+ video_view_count = self._html_search_regex(
+ u'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
+ video_page, u'view count', fatal=False, flags=re.MULTILINE|re.DOTALL)
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': video_title,
+ 'thumbnail': video_thumbnail,
+ 'description': video_description,
+ 'uploader': video_uploader,
+ 'upload_date': video_upload_date,
+ 'uploader_id': video_uploader_id,
+ 'duration': video_duration,
+ 'view_count': video_view_count,
+ 'age_limit': 18 if adult_content else 0,
+ 'video_page_url': video_page_url
+ }
+
+
+class SmotriCommunityIE(InfoExtractor):
+ IE_DESC = u'Smotri.com community videos'
+ IE_NAME = u'smotri:community'
+ _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ community_id = mobj.group('communityid')
+
+ url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
+ rss = self._download_xml(url, community_id, u'Downloading community RSS')
+
+ entries = [self.url_result(video_url.text, 'Smotri')
+ for video_url in rss.findall('./channel/item/link')]
+
+ description_text = rss.find('./channel/description').text
+ community_title = self._html_search_regex(
+ u'^Видео сообщества "([^"]+)"$', description_text, u'community title')
+
+ return self.playlist_result(entries, community_id, community_title)
+
+
+class SmotriUserIE(InfoExtractor):
+ IE_DESC = u'Smotri.com user videos'
+ IE_NAME = u'smotri:user'
+ _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ user_id = mobj.group('userid')
+
+ url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
+ rss = self._download_xml(url, user_id, u'Downloading user RSS')
+
+ entries = [self.url_result(video_url.text, 'Smotri')
+ for video_url in rss.findall('./channel/item/link')]
+
+ description_text = rss.find('./channel/description').text
+ user_nickname = self._html_search_regex(
+ u'^Видео режиссера (.*)$', description_text,
+ u'user nickname')
+
+ return self.playlist_result(entries, user_id, user_nickname)
+
+
+class SmotriBroadcastIE(InfoExtractor):
+ IE_DESC = u'Smotri.com broadcasts'
+ IE_NAME = u'smotri:broadcast'
+ _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ broadcast_id = mobj.group('broadcastid')
+
+ broadcast_url = 'http://' + mobj.group('url')
+ broadcast_page = self._download_webpage(broadcast_url, broadcast_id, u'Downloading broadcast page')
+
+ if re.search(u'>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
+ raise ExtractorError(u'Broadcast %s does not exist' % broadcast_id, expected=True)
+
+ # Adult content
+ if re.search(u'EroConfirmText">', broadcast_page) is not None:
+
+ (username, password) = self._get_login_info()
+ if username is None:
+ raise ExtractorError(u'Erotic broadcasts allowed only for registered users, '
+ u'use --username and --password options to provide account credentials.', expected=True)
+
+ # Log in
+ login_form_strs = {
+ u'login-hint53': '1',
+ u'confirm_erotic': '1',
+ u'login': username,
+ u'password': password,
+ }
+ # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
+ # chokes on unicode
+ login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
+ login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
+ login_url = broadcast_url + '/?no_redirect=1'
+ request = compat_urllib_request.Request(login_url, login_data)
+ request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+ broadcast_page = self._download_webpage(
+ request, broadcast_id, note=u'Logging in and confirming age')
+
+ if re.search(u'>Неверный логин или пароль<', broadcast_page) is not None:
+ raise ExtractorError(u'Unable to log in: bad username or password', expected=True)
+
+ adult_content = True
+ else:
+ adult_content = False
+
+ ticket = self._html_search_regex(
+ u'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);',
+ broadcast_page, u'broadcast ticket')
+
+ url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
+
+ broadcast_password = self._downloader.params.get('videopassword', None)
+ if broadcast_password:
+ url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
+
+ broadcast_json_page = self._download_webpage(url, broadcast_id, u'Downloading broadcast JSON')
+
+ try:
+ broadcast_json = json.loads(broadcast_json_page)
+
+ protected_broadcast = broadcast_json['_pass_protected'] == 1
+ if protected_broadcast and not broadcast_password:
+ raise ExtractorError(u'This broadcast is protected by a password, use the --video-password option', expected=True)
+
+ broadcast_offline = broadcast_json['is_play'] == 0
+ if broadcast_offline:
+ raise ExtractorError(u'Broadcast %s is offline' % broadcast_id, expected=True)
+
+ rtmp_url = broadcast_json['_server']
+ if not rtmp_url.startswith('rtmp://'):
+ raise ExtractorError(u'Unexpected broadcast rtmp URL')
+
+ broadcast_playpath = broadcast_json['_streamName']
+ broadcast_thumbnail = broadcast_json['_imgURL']
+ broadcast_title = broadcast_json['title']
+ broadcast_description = broadcast_json['description']
+ broadcaster_nick = broadcast_json['nick']
+ broadcaster_login = broadcast_json['login']
+ rtmp_conn = 'S:%s' % uuid.uuid4().hex
+ except KeyError:
+ if protected_broadcast:
+ raise ExtractorError(u'Bad broadcast password', expected=True)
+ raise ExtractorError(u'Unexpected broadcast JSON')
+
+ return {
+ 'id': broadcast_id,
+ 'url': rtmp_url,
+ 'title': broadcast_title,
+ 'thumbnail': broadcast_thumbnail,
+ 'description': broadcast_description,
+ 'uploader': broadcaster_nick,
+ 'uploader_id': broadcaster_login,
+ 'age_limit': 18 if adult_content else 0,
+ 'ext': 'flv',
+ 'play_path': broadcast_playpath,
+ 'rtmp_live': True,
+ 'rtmp_conn': rtmp_conn
+ }
+# encoding: utf-8
import json
import re
import itertools
"""
_VALID_URL = r'''^(?:https?://)?
- (?:(?:(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)/?(?:[?].*)?$)
+ (?:(?:(?:www\.|m\.)?soundcloud\.com/
+ (?P<uploader>[\w\d-]+)/
+ (?!sets/)(?P<title>[\w\d-]+)/?
+ (?P<token>[^?]+?)?(?:[?].*)?$)
|(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
- |(?P<widget>w.soundcloud.com/player/?.*?url=.*)
+ |(?P<widget>w\.soundcloud\.com/player/?.*?url=.*)
)
'''
IE_NAME = u'soundcloud'
- _TEST = {
- u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
- u'file': u'62986583.mp3',
- u'md5': u'ebef0a451b909710ed1d7787dddbf0d7',
- u'info_dict': {
- u"upload_date": u"20121011",
- u"description": u"No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
- u"uploader": u"E.T. ExTerrestrial Music",
- u"title": u"Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
- }
- }
+ _TESTS = [
+ {
+ u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
+ u'file': u'62986583.mp3',
+ u'md5': u'ebef0a451b909710ed1d7787dddbf0d7',
+ u'info_dict': {
+ u"upload_date": u"20121011",
+ u"description": u"No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
+ u"uploader": u"E.T. ExTerrestrial Music",
+ u"title": u"Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
+ }
+ },
+ # not streamable song
+ {
+ u'url': u'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep',
+ u'info_dict': {
+ u'id': u'47127627',
+ u'ext': u'mp3',
+ u'title': u'Goldrushed',
+ u'uploader': u'The Royal Concept',
+ u'upload_date': u'20120521',
+ },
+ u'params': {
+ # rtmp
+ u'skip_download': True,
+ },
+ },
+ # private link
+ {
+ u'url': u'https://soundcloud.com/jaimemf/youtube-dl-test-video-a-y-baw/s-8Pjrp',
+ u'md5': u'aa0dd32bfea9b0c5ef4f02aacd080604',
+ u'info_dict': {
+ u'id': u'123998367',
+ u'ext': u'mp3',
+ u'title': u'Youtube - Dl Test Video \'\' Ä↭',
+ u'uploader': u'jaimeMF',
+ u'description': u'test chars: \"\'/\\ä↭',
+ u'upload_date': u'20131209',
+ },
+ },
+ # downloadable song
+ {
+ u'url': u'https://soundcloud.com/simgretina/just-your-problem-baby-1',
+ u'md5': u'56a8b69568acaa967b4c49f9d1d52d19',
+ u'info_dict': {
+ u'id': u'105614606',
+ u'ext': u'wav',
+ u'title': u'Just Your Problem Baby (Acapella)',
+ u'description': u'Vocals',
+ u'uploader': u'Sim Gretina',
+ u'upload_date': u'20130815',
+ },
+ },
+ ]
_CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28'
+ _IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
@classmethod
def suitable(cls, url):
def _resolv_url(cls, url):
return 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID
- def _extract_info_dict(self, info, full_title=None, quiet=False):
- video_id = info['id']
- name = full_title or video_id
- if quiet == False:
+ def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None):
+ track_id = compat_str(info['id'])
+ name = full_title or track_id
+ if quiet:
self.report_extraction(name)
thumbnail = info['artwork_url']
if thumbnail is not None:
thumbnail = thumbnail.replace('-large', '-t500x500')
- return {
- 'id': info['id'],
- 'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
+ ext = u'mp3'
+ result = {
+ 'id': track_id,
'uploader': info['user']['username'],
'upload_date': unified_strdate(info['created_at']),
- 'title': info['title'],
- 'ext': u'mp3',
+ 'title': info['title'],
'description': info['description'],
'thumbnail': thumbnail,
}
+ if info.get('downloadable', False):
+ # We can build a direct link to the song
+ format_url = (
+ u'https://api.soundcloud.com/tracks/{0}/download?client_id={1}'.format(
+ track_id, self._CLIENT_ID))
+ result['formats'] = [{
+ 'format_id': 'download',
+ 'ext': info.get('original_format', u'mp3'),
+ 'url': format_url,
+ 'vcodec': 'none',
+ }]
+ else:
+ # We have to retrieve the url
+ streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?'
+ 'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token))
+ stream_json = self._download_webpage(
+ streams_url,
+ track_id, u'Downloading track url')
+
+ formats = []
+ format_dict = json.loads(stream_json)
+ for key, stream_url in format_dict.items():
+ if key.startswith(u'http'):
+ formats.append({
+ 'format_id': key,
+ 'ext': ext,
+ 'url': stream_url,
+ 'vcodec': 'none',
+ })
+ elif key.startswith(u'rtmp'):
+ # The url doesn't have an rtmp app, we have to extract the playpath
+ url, path = stream_url.split('mp3:', 1)
+ formats.append({
+ 'format_id': key,
+ 'url': url,
+ 'play_path': 'mp3:' + path,
+ 'ext': ext,
+ 'vcodec': 'none',
+ })
+
+ if not formats:
+ # We fallback to the stream_url in the original info, this
+ # cannot be always used, sometimes it can give an HTTP 404 error
+ formats.append({
+ 'format_id': u'fallback',
+ 'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID,
+ 'ext': ext,
+ 'vcodec': 'none',
+ })
+
+ def format_pref(f):
+ if f['format_id'].startswith('http'):
+ return 2
+ if f['format_id'].startswith('rtmp'):
+ return 1
+ return 0
+
+ formats.sort(key=format_pref)
+ result['formats'] = formats
+
+ return result
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
raise ExtractorError(u'Invalid URL: %s' % url)
track_id = mobj.group('track_id')
+ token = None
if track_id is not None:
info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
full_title = track_id
return self.url_result(query['url'][0], ie='Soundcloud')
else:
# extract uploader (which is in the url)
- uploader = mobj.group(1)
+ uploader = mobj.group('uploader')
# extract simple title (uploader + slug of song title)
- slug_title = mobj.group(2)
- full_title = '%s/%s' % (uploader, slug_title)
+ slug_title = mobj.group('title')
+ token = mobj.group('token')
+ full_title = resolve_title = '%s/%s' % (uploader, slug_title)
+ if token:
+ resolve_title += '/%s' % token
self.report_resolve(full_title)
- url = 'http://soundcloud.com/%s/%s' % (uploader, slug_title)
+ url = 'http://soundcloud.com/%s' % resolve_title
info_json_url = self._resolv_url(url)
info_json = self._download_webpage(info_json_url, full_title, u'Downloading info JSON')
info = json.loads(info_json)
- return self._extract_info_dict(info, full_title)
+ return self._extract_info_dict(info, full_title, secret_token=token)
class SoundcloudSetIE(SoundcloudIE):
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)(?:[?].*)?$'
IE_NAME = u'soundcloud:set'
- _TEST = {
- u"url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
- u"playlist": [
- {
- u"file":"30510138.mp3",
- u"md5":"f9136bf103901728f29e419d2c70f55d",
- u"info_dict": {
- u"upload_date": u"20111213",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"D-D-Dance"
- }
- },
- {
- u"file":"47127625.mp3",
- u"md5":"09b6758a018470570f8fd423c9453dd8",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"The Royal Concept - Gimme Twice"
- }
- },
- {
- u"file":"47127627.mp3",
- u"md5":"154abd4e418cea19c3b901f1e1306d9c",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"uploader": u"The Royal Concept",
- u"title": u"Goldrushed"
- }
- },
- {
- u"file":"47127629.mp3",
- u"md5":"2f5471edc79ad3f33a683153e96a79c1",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"In the End"
- }
- },
- {
- u"file":"47127631.mp3",
- u"md5":"f9ba87aa940af7213f98949254f1c6e2",
- u"info_dict": {
- u"upload_date": u"20120521",
- u"description": u"The Royal Concept from Stockholm\r\nFilip / David / Povel / Magnus\r\nwww.theroyalconceptband.com",
- u"uploader": u"The Royal Concept",
- u"title": u"Knocked Up"
- }
- },
- {
- u"file":"75206121.mp3",
- u"md5":"f9d1fe9406717e302980c30de4af9353",
- u"info_dict": {
- u"upload_date": u"20130116",
- u"description": u"The unreleased track World on Fire premiered on the CW's hit show Arrow (8pm/7pm central). \r\nAs a gift to our fans we would like to offer you a free download of the track! ",
- u"uploader": u"The Royal Concept",
- u"title": u"World On Fire"
- }
- }
- ]
- }
+ # it's in tests/test_playlists.py
+ _TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
resolv_url = self._resolv_url(url)
info_json = self._download_webpage(resolv_url, full_title)
- videos = []
info = json.loads(info_json)
if 'errors' in info:
for err in info['errors']:
class SoundcloudUserIE(SoundcloudIE):
- _VALID_URL = r'https?://(www\.)?soundcloud.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
+ _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$'
IE_NAME = u'soundcloud:user'
# it's in tests/test_playlists.py
- _TEST = None
+ _TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
import re
-from .mtv import MTVIE, _media_xml_tag
+from .mtv import MTVServicesInfoExtractor
-class SouthParkStudiosIE(MTVIE):
+class SouthParkStudiosIE(MTVServicesInfoExtractor):
IE_NAME = u'southparkstudios.com'
- _VALID_URL = r'https?://www\.southparkstudios\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$)'
+ _VALID_URL = r'(https?://)?(www\.)?(?P<url>southparkstudios\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
_FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
- _TEST = {
+ _TESTS = [{
u'url': u'http://www.southparkstudios.com/clips/104437/bat-daded#tab=featured',
u'file': u'a7bff6c2-ed00-11e0-aca6-0026b9414f30.mp4',
u'info_dict': {
u'title': u'Bat Daded',
u'description': u'Randy disqualifies South Park by getting into a fight with Bat Dad.',
},
- }
-
- # Overwrite MTVIE properties we don't want
- _TESTS = []
-
- def _get_thumbnail_url(self, uri, itemdoc):
- search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
- thumb_node = itemdoc.find(search_path)
- if thumb_node is None:
- return None
- else:
- return thumb_node.attrib['url']
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
+ url = u'http://www.' + mobj.group(u'url')
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
mgid = self._search_regex(r'swfobject.embedSWF\(".*?(mgid:.*?)"',
webpage, u'mgid')
return self._get_videos_info(mgid)
+
+class SouthparkDeIE(SouthParkStudiosIE):
+ IE_NAME = u'southpark.de'
+ _VALID_URL = r'(https?://)?(www\.)?(?P<url>southpark\.de/(clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
+ _FEED_URL = 'http://www.southpark.de/feeds/video-player/mrss/'
+
+ _TESTS = [{
+ u'url': u'http://www.southpark.de/clips/uygssh/the-government-wont-respect-my-privacy#tab=featured',
+ u'file': u'85487c96-b3b9-4e39-9127-ad88583d9bf2.mp4',
+ u'info_dict': {
+ u'title': u'The Government Won\'t Respect My Privacy',
+ u'description': u'Cartman explains the benefits of "Shitter" to Stan, Kyle and Craig.',
+ },
+ }]
--- /dev/null
+import re
+
+from .common import InfoExtractor
+from .brightcove import BrightcoveIE
+from ..utils import RegexNotFoundError, ExtractorError
+
+
+class SpaceIE(InfoExtractor):
+ _VALID_URL = r'https?://www\.space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html'
+ _TEST = {
+ u'add_ie': ['Brightcove'],
+ u'url': u'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html',
+ u'info_dict': {
+ u'id': u'2780937028001',
+ u'ext': u'mp4',
+ u'title': u'Huge Martian Landforms\' Detail Revealed By European Probe | Video',
+ u'description': u'md5:db81cf7f3122f95ed234b631a6ea1e61',
+ u'uploader': u'TechMedia Networks',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ title = mobj.group('title')
+ webpage = self._download_webpage(url, title)
+ try:
+ # Some videos require the playerKey field, which isn't define in
+ # the BrightcoveExperience object
+ brightcove_url = self._og_search_video_url(webpage)
+ except RegexNotFoundError:
+ # Other videos works fine with the info from the object
+ brightcove_url = BrightcoveIE._extract_brightcove_url(webpage)
+ if brightcove_url is None:
+ raise ExtractorError(u'The webpage does not contain a video', expected=True)
+ return self.url_result(brightcove_url, BrightcoveIE.ie_key())
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
- unescapeHTML,
)
from ..aes import (
aes_decrypt_text
webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, u'title')
- video_uploader = self._html_search_regex(r'by:\s*<a [^>]*>(.+?)</a>', webpage, u'uploader', fatal=False)
- thumbnail = self._html_search_regex(r'flashvars\.image_url = "([^"]+)', webpage, u'thumbnail', fatal=False)
- description = self._html_search_regex(r'>\s*Description:</div>\s*<[^>]*>([^<]+)', webpage, u'description', fatal=False)
- if len(description) == 0:
- description = None
+ video_uploader = self._html_search_regex(
+ r'by:\s*<a [^>]*>(.+?)</a>', webpage, u'uploader', fatal=False)
+ thumbnail = self._html_search_regex(
+ r'flashvars\.image_url = "([^"]+)', webpage, u'thumbnail', fatal=False)
+ description = self._html_search_regex(
+ r'<div\s+id="descriptionContent">([^<]+)<', webpage, u'description', fatal=False)
video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage)))
if webpage.find('flashvars\.encrypted = "true"') != -1:
formats = []
for video_url in video_urls:
- path = compat_urllib_parse_urlparse( video_url ).path
- extension = os.path.splitext( path )[1][1:]
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
format = path.split('/')[4].split('_')[:2]
- format = "-".join( format )
+ format = "-".join(format)
formats.append({
'url': video_url,
'ext': extension,
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
class SpiegelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
- _TEST = {
+ _TESTS = [{
u'url': u'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
u'file': u'1259285.mp4',
u'md5': u'2c2754212136f35fb4b19767d242f66e',
u'info_dict': {
u"title": u"Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv"
}
- }
+ },
+ {
+ u'url': u'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
+ u'file': u'1309159.mp4',
+ u'md5': u'f2cdf638d7aa47654e251e1aee360af1',
+ u'info_dict': {
+ u'title': u'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers'
+ }
+ }]
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
webpage = self._download_webpage(url, video_id)
- video_title = self._html_search_regex(r'<div class="module-title">(.*?)</div>',
- webpage, u'title')
+ video_title = self._html_search_regex(
+ r'<div class="module-title">(.*?)</div>', webpage, u'title')
xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
- xml_code = self._download_webpage(xml_url, video_id,
- note=u'Downloading XML', errnote=u'Failed to download XML')
-
- idoc = xml.etree.ElementTree.fromstring(xml_code)
- last_type = idoc[-1]
- filename = last_type.findall('./filename')[0].text
- duration = float(last_type.findall('./duration')[0].text)
+ idoc = self._download_xml(
+ xml_url, video_id,
+ note=u'Downloading XML', errnote=u'Failed to download XML')
+
+ formats = [
+ {
+ 'format_id': n.tag.rpartition('type')[2],
+ 'url': u'http://video2.spiegel.de/flash/' + n.find('./filename').text,
+ 'width': int(n.find('./width').text),
+ 'height': int(n.find('./height').text),
+ 'abr': int(n.find('./audiobitrate').text),
+ 'vbr': int(n.find('./videobitrate').text),
+ 'vcodec': n.find('./codec').text,
+ 'acodec': 'MP4A',
+ }
+ for n in list(idoc)
+ # Blacklist type 6, it's extremely LQ and not available on the same server
+ if n.tag.startswith('type') and n.tag != 'type6'
+ ]
+ formats.sort(key=lambda f: f['vbr'])
+ duration = float(idoc[0].findall('./duration')[0].text)
- video_url = 'http://video2.spiegel.de/flash/' + filename
- video_ext = filename.rpartition('.')[2]
info = {
'id': video_id,
- 'url': video_url,
- 'ext': video_ext,
'title': video_title,
'duration': duration,
+ 'formats': formats,
}
- return [info]
+ return info
import re
-import socket
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
- compat_http_client,
- compat_str,
- compat_urllib_error,
- compat_urllib_request,
-
ExtractorError,
orderedSet,
unescapeHTML,
class StanfordOpenClassroomIE(InfoExtractor):
IE_NAME = u'stanfordoc'
IE_DESC = u'Stanford Open ClassRoom'
- _VALID_URL = r'^(?:https?://)?openclassroom
.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
+ _VALID_URL = r'^(?:https?://)?openclassroom
\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
_TEST = {
u'url': u'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100',
u'file': u'PracticalUnix_intro-environment.mp4',
self.report_extraction(info['id'])
baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
xmlUrl = baseUrl + video + '.xml'
- try:
- metaXml = compat_urllib_request.urlopen(xmlUrl).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
- mdoc = xml.etree.ElementTree.fromstring(metaXml)
+ mdoc = self._download_xml(xmlUrl, info['id'])
try:
info['title'] = mdoc.findall('./title')[0].text
info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
'upload_date': None,
}
- self.report_download_webpage(info['id'])
rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
- try:
- rootpage = compat_urllib_request.urlopen(rootURL).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to download course info page: ' + compat_str(err))
+ rootpage = self._download_webpage(rootURL, info['id'],
+ errnote=u'Unable to download course info page')
info['title'] = info['id']
--- /dev/null
+# coding: utf-8
+import re
+import time
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse,
+ compat_urllib_request,
+)
+
+
+class StreamcloudIE(InfoExtractor):
+ IE_NAME = u'streamcloud.eu'
+ _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)/(?P<fname>[^#?]*)\.html'
+
+ _TEST = {
+ u'url': u'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html',
+ u'file': u'skp9j99s4bpz.mp4',
+ u'md5': u'6bea4c7fa5daaacc2a946b7146286686',
+ u'info_dict': {
+ u'title': u'youtube-dl test video \'/\\ ä ↭',
+ u'duration': 9,
+ },
+ u'skip': u'Only available from the EU'
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ orig_webpage = self._download_webpage(url, video_id)
+
+ fields = re.findall(r'''(?x)<input\s+
+ type="(?:hidden|submit)"\s+
+ name="([^"]+)"\s+
+ (?:id="[^"]+"\s+)?
+ value="([^"]*)"
+ ''', orig_webpage)
+ post = compat_urllib_parse.urlencode(fields)
+
+ self.to_screen('%s: Waiting for timeout' % video_id)
+ time.sleep(12)
+ headers = {
+ b'Content-Type': b'application/x-www-form-urlencoded',
+ }
+ req = compat_urllib_request.Request(url, post, headers)
+
+ webpage = self._download_webpage(
+ req, video_id, note=u'Downloading video page ...')
+ title = self._html_search_regex(
+ r'<h1[^>]*>([^<]+)<', webpage, u'title')
+ video_url = self._search_regex(
+ r'file:\s*"([^"]+)"', webpage, u'video URL')
+ duration_str = self._search_regex(
+ r'duration:\s*"?([0-9]+)"?', webpage, u'duration', fatal=False)
+ duration = None if duration_str is None else int(duration_str)
+ thumbnail = self._search_regex(
+ r'image:\s*"([^"]+)"', webpage, u'thumbnail URL', fatal=False)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'url': video_url,
+ 'duration': duration,
+ 'thumbnail': thumbnail,
+ }
return any([self._downloader.params.get('writesubtitles', False),
self._downloader.params.get('writeautomaticsub')])
- def _list_available_subtitles(self, video_id, webpage=None):
+ def _list_available_subtitles(self, video_id, webpage):
""" outputs the available subtitles for the video """
- sub_lang_list = self._get_available_subtitles(video_id)
+ sub_lang_list = self._get_available_subtitles(video_id, webpage)
auto_captions_list = self._get_available_automatic_caption(video_id, webpage)
sub_lang = ",".join(list(sub_lang_list.keys()))
self.to_screen(u'%s: Available subtitles for video: %s' %
self.to_screen(u'%s: Available automatic captions for video: %s' %
(video_id, auto_lang))
- def extract_subtitles(self, video_id, video_webpage=None):
+ def extract_subtitles(self, video_id, webpage):
"""
returns {sub_lang: sub} ,{} if subtitles not found or None if the
subtitles aren't requested.
return None
available_subs_list = {}
if self._downloader.params.get('writeautomaticsub', False):
- available_subs_list.update(self._get_available_automatic_caption(video_id, video_webpage))
+ available_subs_list.update(self._get_available_automatic_caption(video_id, webpage))
if self._downloader.params.get('writesubtitles', False):
- available_subs_list.update(self._get_available_subtitles(video_id))
+ available_subs_list.update(self._get_available_subtitles(video_id, webpage))
if not available_subs_list: # error, it didn't get the available subtitles
return {}
return
return sub
- def _get_available_subtitles(self, video_id):
+ def _get_available_subtitles(self, video_id, webpage):
"""
returns {sub_lang: url} or {} if not available
Must be redefined by the subclasses
u'info_dict': {
u"title": u"Cserkészek népszerűsítették a környezettudatos életmódot a Savaria téren",
u"description": u'A zöld nap játékos ismeretterjesztő programjait a Magyar Cserkész Szövetség szervezte, akik az ország nyolc városában adják át tudásukat az érdeklődőknek. A PET...',
- }
+ },
+ u'skip': u'Service temporarily disabled as of 2013-11-20'
}
def _real_extract(self, url):
_TEST = {
u'url': u'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
u'file': u'19705.mp4',
- u'md5': u'27b6f7527da5acf534b15f21b032656e',
+ u'md5': u'cde9ba0fa3506f5f017ce11ead928f9a',
u'info_dict': {
u"description": u"Louis C.K. got starstruck by George W. Bush, so what? Part one.",
u"title": u"Louis C.K. Interview Pt. 1 11/3/11"
self.report_extraction(video_id)
data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
- data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
+ data = self._download_xml(data_url, video_id, 'Downloading data webpage')
- video_url = self._html_search_regex(r'<file [^>]*type="high".*?>(.*?)</file>',
- data, u'video URL')
- return [{
+ qualities = ['500k', '480p', '1000k', '720p', '1080p']
+ formats = []
+ for file in data.findall('files/file'):
+ if file.attrib.get('playmode') == 'all':
+ # it just duplicates one of the entries
+ break
+ file_url = file.text
+ m_format = re.search(r'(\d+(k|p))\.mp4', file_url)
+ if m_format is not None:
+ format_id = m_format.group(1)
+ else:
+ format_id = file.attrib['bitrate']
+ formats.append({
+ 'url': file_url,
+ 'ext': 'mp4',
+ 'format_id': format_id,
+ })
+ def sort_key(f):
+ try:
+ return qualities.index(f['format_id'])
+ except ValueError:
+ return -1
+ formats.sort(key=sort_key)
+ if not formats:
+ raise ExtractorError(u'Unable to extract video URL')
+
+ return {
'id': video_id,
- 'url': video_url,
- 'ext': 'mp4',
+ 'formats': formats,
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
- }]
+ }
import json
import re
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
+from ..utils import (
+ RegexNotFoundError,
+)
-class TEDIE(InfoExtractor):
+class TEDIE(SubtitlesInfoExtractor):
_VALID_URL=r'''http://www\.ted\.com/
(
((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
def _real_extract(self, url):
m=re.match(self._VALID_URL, url, re.VERBOSE)
if m.group('type_talk'):
- return [self._talk_info(url)]
+ return self._talk_info(url)
else :
playlist_id=m.group('playlist_id')
name=m.group('name')
self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name))
return [self._playlist_videos_info(url,name,playlist_id)]
- def _playlist_videos_info(self,url,name,playlist_id=0):
+
+ def _playlist_videos_info(self, url, name, playlist_id):
'''Returns the videos of the playlist'''
- video_RE=r'''
- <li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)"
- ([.\s]*?)data-playlist_item_id="(\d+)"
- ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)"
- '''
- video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>'
- webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage')
- m_videos=re.finditer(video_RE,webpage,re.VERBOSE)
- m_names=re.finditer(video_name_RE,webpage)
+
+ webpage = self._download_webpage(
+ url, playlist_id, u'Downloading playlist webpage')
+ matches = re.finditer(
+ r'<p\s+class="talk-title[^"]*"><a\s+href="(?P<talk_url>/talks/[^"]+\.html)">[^<]*</a></p>',
+ webpage)
playlist_title = self._html_search_regex(r'div class="headline">\s*?<h1>\s*?<span>(.*?)</span>',
webpage, 'playlist title')
- playlist_entries = []
- for m_video, m_name in zip(m_videos,m_names):
- talk_url='http://www.ted.com%s' % m_name.group('talk_url')
- playlist_entries.append(self.url_result(talk_url, 'TED'))
- return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title)
+ playlist_entries = [
+ self.url_result(u'http://www.ted.com' + m.group('talk_url'), 'TED')
+ for m in matches
+ ]
+ return self.playlist_result(
+ playlist_entries, playlist_id=playlist_id, playlist_title=playlist_title)
def _talk_info(self, url, video_id=0):
"""Return the video for the talk in the url"""
'ext': 'mp4',
'url': stream['file'],
'format': stream['id']
- } for stream in info['htmlStreams']]
- info = {
- 'id': info['id'],
+ } for stream in info['htmlStreams']]
+
+ video_id = info['id']
+
+ # subtitles
+ video_subtitles = self.extract_subtitles(video_id, webpage)
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(video_id, webpage)
+ return
+
+ return {
+ 'id': video_id,
'title': title,
'thumbnail': thumbnail,
'description': desc,
+ 'subtitles': video_subtitles,
'formats': formats,
}
- # TODO: Remove when #980 has been merged
- info.update(info['formats'][-1])
-
- return info
+ def _get_available_subtitles(self, video_id, webpage):
+ try:
+ options = self._search_regex(r'(?:<select name="subtitles_language_select" id="subtitles_language_select">)(.*?)(?:</select>)', webpage, 'subtitles_language_select', flags=re.DOTALL)
+ languages = re.findall(r'(?:<option value=")(\S+)"', options)
+ if languages:
+ sub_lang_list = {}
+ for l in languages:
+ url = 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/srt' % (video_id, l)
+ sub_lang_list[l] = url
+ return sub_lang_list
+ except RegexNotFoundError:
+ self._downloader.report_warning(u'video doesn\'t have subtitles')
+ return {}
class TF1IE(InfoExtractor):
"""TF1 uses the wat.tv player."""
- _VALID_URL = r'http://videos.tf1.fr/.*-(.*?).html'
+ _VALID_URL = r'http://videos\.tf1\.fr/.*-(.*?)\.html'
_TEST = {
u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
u'file': u'10635995.mp4',
--- /dev/null
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+ xpath_with_ns,
+)
+
+_x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language'})
+
+
+class ThePlatformIE(InfoExtractor):
+ _VALID_URL = r'(?:https?://link\.theplatform\.com/s/[^/]+/|theplatform:)(?P<id>[^/\?]+)'
+
+ _TEST = {
+ # from http://www.metacafe.com/watch/cb-e9I_cZgTgIPd/blackberrys_big_bold_z30/
+ u'url': u'http://link.theplatform.com/s/dJ5BDC/e9I_cZgTgIPd/meta.smil?format=smil&Tracking=true&mbr=true',
+ u'info_dict': {
+ u'id': u'e9I_cZgTgIPd',
+ u'ext': u'flv',
+ u'title': u'Blackberry\'s big, bold Z30',
+ u'description': u'The Z30 is Blackberry\'s biggest, baddest mobile messaging device yet.',
+ u'duration': 247,
+ },
+ u'params': {
+ # rtmp download
+ u'skip_download': True,
+ },
+ }
+
+ def _get_info(self, video_id):
+ smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'
+ 'format=smil&mbr=true'.format(video_id))
+ meta = self._download_xml(smil_url, video_id)
+
+ try:
+ error_msg = next(
+ n.attrib['abstract']
+ for n in meta.findall(_x('.//smil:ref'))
+ if n.attrib.get('title') == u'Geographic Restriction')
+ except StopIteration:
+ pass
+ else:
+ raise ExtractorError(error_msg, expected=True)
+
+ info_url = 'http://link.theplatform.com/s/dJ5BDC/{0}?format=preview'.format(video_id)
+ info_json = self._download_webpage(info_url, video_id)
+ info = json.loads(info_json)
+
+ head = meta.find(_x('smil:head'))
+ body = meta.find(_x('smil:body'))
+ base_url = head.find(_x('smil:meta')).attrib['base']
+ switch = body.find(_x('smil:switch'))
+ formats = []
+ for f in switch.findall(_x('smil:video')):
+ attr = f.attrib
+ formats.append({
+ 'url': base_url,
+ 'play_path': 'mp4:' + attr['src'],
+ 'ext': 'flv',
+ 'width': int(attr['width']),
+ 'height': int(attr['height']),
+ 'vbr': int(attr['system-bitrate']),
+ })
+ formats.sort(key=lambda f: (f['height'], f['width'], f['vbr']))
+
+ return {
+ 'id': video_id,
+ 'title': info['title'],
+ 'formats': formats,
+ 'description': info['description'],
+ 'thumbnail': info['defaultThumbnailUrl'],
+ 'duration': info['duration']//1000,
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ return self._get_info(video_id)
--- /dev/null
+# coding: utf-8
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+ unified_strdate,
+)
+
+
+class TouTvIE(InfoExtractor):
+ IE_NAME = u'tou.tv'
+ _VALID_URL = r'https?://www\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/(?P<episode>S[0-9]+E[0-9]+)))'
+
+ _TEST = {
+ u'url': u'http://www.tou.tv/30-vies/S04E41',
+ u'file': u'30-vies_S04E41.mp4',
+ u'info_dict': {
+ u'title': u'30 vies Saison 4 / Épisode 41',
+ u'description': u'md5:da363002db82ccbe4dafeb9cab039b09',
+ u'age_limit': 8,
+ u'uploader': u'Groupe des Nouveaux Médias',
+ u'duration': 1296,
+ u'upload_date': u'20131118',
+ u'thumbnail': u'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg',
+ },
+ u'params': {
+ u'skip_download': True, # Requires rtmpdump
+ },
+ u'skip': 'Only available in Canada'
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+
+ mediaId = self._search_regex(
+ r'"idMedia":\s*"([^"]+)"', webpage, u'media ID')
+
+ streams_url = u'http://release.theplatform.com/content.select?pid=' + mediaId
+ streams_doc = self._download_xml(
+ streams_url, video_id, note=u'Downloading stream list')
+
+ video_url = next(n.text
+ for n in streams_doc.findall('.//choice/url')
+ if u'//ad.doubleclick' not in n.text)
+ if video_url.endswith('/Unavailable.flv'):
+ raise ExtractorError(
+ u'Access to this video is blocked from outside of Canada',
+ expected=True)
+
+ duration_str = self._html_search_meta(
+ 'video:duration', webpage, u'duration')
+ duration = int(duration_str) if duration_str else None
+ upload_date_str = self._html_search_meta(
+ 'video:release_date', webpage, u'upload date')
+ upload_date = unified_strdate(upload_date_str) if upload_date_str else None
+
+ return {
+ 'id': video_id,
+ 'title': self._og_search_title(webpage),
+ 'url': video_url,
+ 'description': self._og_search_description(webpage),
+ 'uploader': self._dc_search_uploader(webpage),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ 'age_limit': self._media_rating_search(webpage),
+ 'duration': duration,
+ 'upload_date': upload_date,
+ 'ext': 'mp4',
+ }
import json
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
format_url = (u'http://fs%(server)s.trilulilu.ro/%(hash)s/'
u'video-formats2' % log)
- format_str = self._download_webpage(
+ format_doc = self._download_xml(
format_url, video_id,
note=u'Downloading formats',
errnote=u'Error while downloading formats')
-
- format_doc = xml.etree.ElementTree.fromstring(format_str)
video_url_template = (
u'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
for fnode in format_doc.findall('./formats/format')
]
- info = {
+ return {
'_type': 'video',
'id': video_id,
'formats': formats,
'thumbnail': thumbnail,
}
- # TODO: Remove when #980 has been merged
- info.update(formats[-1])
-
- return info
from ..utils import (
compat_urllib_parse_urlparse,
compat_urllib_request,
- compat_urllib_parse,
- unescapeHTML,
)
from ..aes import (
aes_decrypt_text
if webpage.find('"encrypted":true')!=-1:
password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password')
video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
- path = compat_urllib_parse_urlparse( video_url ).path
- extension = os.path.splitext( path )[1][1:]
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
format = path.split('/')[4].split('_')[:2]
- format = "-".join( format )
+ format = "-".join(format)
return {
'id': video_id,
--- /dev/null
+import json
+import re
+
+from .common import InfoExtractor
+
+
+class TvpIE(InfoExtractor):
+ IE_NAME = u'tvp.pl'
+ _VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)'
+
+ _TEST = {
+ u'url': u'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238',
+ u'md5': u'148408967a6a468953c0a75cbdaf0d7a',
+ u'file': u'12878238.wmv',
+ u'info_dict': {
+ u'title': u'31.10.2013 - Odcinek 2',
+ u'description': u'31.10.2013 - Odcinek 2',
+ },
+ u'skip': u'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.'
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+ json_url = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id
+ json_params = self._download_webpage(
+ json_url, video_id, u"Downloading video metadata")
+
+ params = json.loads(json_params)
+ self.report_extraction(video_id)
+ video_url = params['video_url']
+
+ title = self._og_search_title(webpage, fatal=True)
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'ext': 'wmv',
+ 'url': video_url,
+ 'description': self._og_search_description(webpage),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ }
from .common import InfoExtractor
class UnistraIE(InfoExtractor):
- _VALID_URL = r'http://utv.unistra.fr/(?:index|video).php\?id_video\=(\d+)'
+ _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(\d+)'
_TEST = {
u'url': u'http://utv.unistra.fr/video.php?id_video=154',
)
class VeeHDIE(InfoExtractor):
- _VALID_URL = r'https?://veehd.com/video/(?P<id>\d+)'
+ _VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)'
_TEST = {
u'url': u'http://veehd.com/video/4686958',
Accepts urls from vevo.com or in the format 'vevo:{id}'
(currently used by MTVIE)
"""
- _VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*?)(\?|$)'
+ _VALID_URL = r'''(?x)
+ (?:https?://www\.vevo\.com/watch/(?:[^/]+/[^/]+/)?|
+ https?://cache\.vevo\.com/m/html/embed\.html\?video=|
+ https?://videoplayer\.vevo\.com/embed/embedded\?videoId=|
+ vevo:)
+ (?P<id>[^&?#]+)'''
_TESTS = [{
u'url': u'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
u'file': u'GB1101300280.mp4',
u"upload_date": u"20130624",
u"uploader": u"Hurts",
u"title": u"Somebody to Die For",
- u"duration": 230,
+ u"duration": 230.12,
u"width": 1920,
u"height": 1080,
}
continue
format_url = self._SMIL_BASE_URL + m.group('path')
- format_note = ('%(vcodec)s@%(vbr)4sk, %(acodec)s@%(abr)3sk' %
- m.groupdict())
formats.append({
'url': format_url,
'format_id': u'SMIL_' + m.group('cbr'),
- 'format_note': format_note,
+ 'vcodec': m.group('vcodec'),
+ 'acodec': m.group('acodec'),
+ 'vbr': int(m.group('vbr')),
+ 'abr': int(m.group('abr')),
'ext': m.group('ext'),
'width': int(m.group('width')),
'height': int(m.group('height')),
class ViceIE(InfoExtractor):
- _VALID_URL = r'http://www.vice.com/.*?/(?P<name>.+)'
+ _VALID_URL = r'http://www\.vice\.com/.*?/(?P<name>.+)'
_TEST = {
u'url': u'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
import re
from .common import InfoExtractor
-from ..utils import (
- determine_ext,
-)
class ViddlerIE(InfoExtractor):
- _VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P<id>[0-9]+)'
+ _VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler\.com)/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
_TEST = {
u"url": u"http://www.viddler.com/v/43903784",
u'file': u'43903784.mp4',
r"thumbnail\s*:\s*'([^']*)'",
webpage, u'thumbnail', fatal=False)
- info = {
+ return {
'_type': 'video',
'id': video_id,
'title': title,
'duration': duration,
'formats': formats,
}
-
- # TODO: Remove when #980 has been merged
- info['formats'][-1]['ext'] = determine_ext(info['formats'][-1]['url'])
- info.update(info['formats'][-1])
-
- return info
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
)
class VideofyMeIE(InfoExtractor):
- _VALID_URL = r'https?://(www.videofy.me/.+?|p.videofy.me/v)/(?P<id>\d+)(&|#|$)'
+ _VALID_URL = r'https?://(www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)'
IE_NAME = u'videofy.me'
_TEST = {
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
- config_xml = self._download_webpage('http://sunshine.videofy.me/?videoId=%s' % video_id,
+ config = self._download_xml('http://sunshine.videofy.me/?videoId=%s' % video_id,
video_id)
- config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
video = config.find('video')
sources = video.find('sources')
url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key)
class VideoPremiumIE(InfoExtractor):
- _VALID_URL = r'(?:https?://)?(?:www\.)?videopremium\.tv/(?P<id>\w+)(?:/.*)?'
+ _VALID_URL = r'(?:https?://)?(?:www\.)?videopremium\.(?:tv|me)/(?P<id>\w+)(?:/.*)?'
_TEST = {
u'url': u'http://videopremium.tv/4w7oadjsf156',
u'file': u'4w7oadjsf156.f4v',
u'params': {
u'skip_download': True,
},
+ u'skip': u'Test file has been deleted.',
}
def _real_extract(self, url):
webpage_url = 'http://videopremium.tv/' + video_id
webpage = self._download_webpage(webpage_url, video_id)
- self.report_extraction(video_id)
+ if re.match(r"^<html><head><script[^>]*>window.location\s*=", webpage):
+ # Download again, we need a cookie
+ webpage = self._download_webpage(
+ webpage_url, video_id,
+ note=u'Downloading webpage again (with cookie)')
- video_title = self._html_search_regex(r'<h2(?:.*?)>\s*(.+?)\s*<',
- webpage, u'video title')
+ video_title = self._html_search_regex(
+ r'<h2(?:.*?)>\s*(.+?)\s*<', webpage, u'video title')
- return [{
+ return {
'id': video_id,
'url': "rtmp://e%d.md.iplay.md/play" % random.randint(1, 16),
'play_path': "mp4:%s.f4v" % video_id,
'player_url': "http://videopremium.tv/uplayer/uppod.swf",
'ext': 'f4v',
'title': video_title,
- }]
+ }
--- /dev/null
+import re
+
+from ..utils import (
+ ExtractorError,
+ unescapeHTML,
+ unified_strdate,
+)
+from .subtitles import SubtitlesInfoExtractor
+
+
+class VikiIE(SubtitlesInfoExtractor):
+ IE_NAME = u'viki'
+
+ _VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P<id>[0-9]+v)'
+ _TEST = {
+ u'url': u'http://www.viki.com/videos/1023585v-heirs-episode-14',
+ u'file': u'1023585v.mp4',
+ u'md5': u'a21454021c2646f5433514177e2caa5f',
+ u'info_dict': {
+ u'title': u'Heirs Episode 14',
+ u'uploader': u'SBS',
+ u'description': u'md5:c4b17b9626dd4b143dcc4d855ba3474e',
+ u'upload_date': u'20131121',
+ u'age_limit': 13,
+ },
+ u'skip': u'Blocked in the US',
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group(1)
+
+ webpage = self._download_webpage(url, video_id)
+ title = self._og_search_title(webpage)
+ description = self._og_search_description(webpage)
+ thumbnail = self._og_search_thumbnail(webpage)
+
+ uploader_m = re.search(
+ r'<strong>Broadcast Network: </strong>\s*([^<]*)<', webpage)
+ if uploader_m is None:
+ uploader = None
+ else:
+ uploader = uploader_m.group(1).strip()
+
+ rating_str = self._html_search_regex(
+ r'<strong>Rating: </strong>\s*([^<]*)<', webpage,
+ u'rating information', default='').strip()
+ RATINGS = {
+ 'G': 0,
+ 'PG': 10,
+ 'PG-13': 13,
+ 'R': 16,
+ 'NC': 18,
+ }
+ age_limit = RATINGS.get(rating_str)
+
+ info_url = 'http://www.viki.com/player5_fragment/%s?action=show&controller=videos' % video_id
+ info_webpage = self._download_webpage(
+ info_url, video_id, note=u'Downloading info page')
+ if re.match(r'\s*<div\s+class="video-error', info_webpage):
+ raise ExtractorError(
+ u'Video %s is blocked from your location.' % video_id,
+ expected=True)
+ video_url = self._html_search_regex(
+ r'<source[^>]+src="([^"]+)"', info_webpage, u'video URL')
+
+ upload_date_str = self._html_search_regex(
+ r'"created_at":"([^"]+)"', info_webpage, u'upload date')
+ upload_date = (
+ unified_strdate(upload_date_str)
+ if upload_date_str is not None
+ else None
+ )
+
+ # subtitles
+ video_subtitles = self.extract_subtitles(video_id, info_webpage)
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(video_id, info_webpage)
+ return
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'url': video_url,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'age_limit': age_limit,
+ 'uploader': uploader,
+ 'subtitles': video_subtitles,
+ 'upload_date': upload_date,
+ }
+
+ def _get_available_subtitles(self, video_id, info_webpage):
+ res = {}
+ for sturl_html in re.findall(r'<track src="([^"]+)"/>', info_webpage):
+ sturl = unescapeHTML(sturl_html)
+ m = re.search(r'/(?P<lang>[a-z]+)\.vtt', sturl)
+ if not m:
+ continue
+ res[m.group('lang')] = sturl
+ return res
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$'
+ _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|(?P<player>player))\.)?vimeo(?P<pro>pro)?\.com/(?:.*?/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$'
_NETRC_MACHINE = 'vimeo'
IE_NAME = u'vimeo'
_TESTS = [
def _real_initialize(self):
self._login()
- def _real_extract(self, url, new_video=True):
+ def _real_extract(self, url):
url, data = unsmuggle_url(url)
headers = std_headers
if data is not None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('id')
- if not mobj.group('proto'):
- url = 'https://' + url
- elif mobj.group('pro'):
+ if mobj.group('pro') or mobj.group('player'):
url = 'http://player.vimeo.com/video/' + video_id
- elif mobj.group('direct_link'):
+ else:
url = 'https://vimeo.com/' + video_id
# Retrieve video webpage to extract further information
config = json.loads(config_json)
except RegexNotFoundError:
# For pro videos or player.vimeo.com urls
- config = self._search_regex([r' = {config:({.+?}),assets:', r'c=({.+?);'],
- webpage, u'info section', flags=re.DOTALL)
+ # We try to find out to which variable is assigned the config dic
+ m_variable_name = re.search('(\w)\.video\.id', webpage)
+ if m_variable_name is not None:
+ config_re = r'%s=({.+?});' % re.escape(m_variable_name.group(1))
+ else:
+ config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
+ config = self._search_regex(config_re, webpage, u'info section',
+ flags=re.DOTALL)
config = json.loads(config)
except Exception as e:
if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
if mobj is not None:
video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
+ try:
+ view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, u'view count'))
+ like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, u'like count'))
+ comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, u'comment count'))
+ except RegexNotFoundError:
+ # This info is only available in vimeo.com/{id} urls
+ view_count = None
+ 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': []}
+ 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, []):
if len(formats) == 0:
raise ExtractorError(u'No known codec found')
- return [{
+ return {
'id': video_id,
'uploader': video_uploader,
'uploader_id': video_uploader_id,
'thumbnail': video_thumbnail,
'description': video_description,
'formats': formats,
- }]
+ 'webpage_url': url,
+ 'view_count': view_count,
+ 'like_count': like_count,
+ 'comment_count': comment_count,
+ }
class VimeoChannelIE(InfoExtractor):
IE_NAME = u'vimeo:channel'
_VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P<id>[^/]+)'
_MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
+ _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- channel_id = mobj.group('id')
- video_ids = []
+ def _page_url(self, base_url, pagenum):
+ return '%s/videos/page:%d/' % (base_url, pagenum)
+ def _extract_list_title(self, webpage):
+ return self._html_search_regex(self._TITLE_RE, webpage, u'list title')
+
+ def _extract_videos(self, list_id, base_url):
+ video_ids = []
for pagenum in itertools.count(1):
- webpage = self._download_webpage('http://vimeo.com/channels/%s/videos/page:%d' % (channel_id, pagenum),
- channel_id, u'Downloading page %s' % pagenum)
+ webpage = self._download_webpage(
+ self._page_url(base_url, pagenum) ,list_id,
+ u'Downloading page %s' % pagenum)
video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
break
entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
for video_id in video_ids]
- channel_title = self._html_search_regex(r'<a href="/channels/%s">(.*?)</a>' % channel_id,
- webpage, u'channel title')
return {'_type': 'playlist',
- 'id': channel_id,
- 'title': channel_title,
+ 'id': list_id,
+ 'title': self._extract_list_title(webpage),
'entries': entries,
}
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ channel_id = mobj.group('id')
+ return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
+
+
+class VimeoUserIE(VimeoChannelIE):
+ IE_NAME = u'vimeo:user'
+ _VALID_URL = r'(?:https?://)?vimeo.\com/(?P<name>[^/]+)'
+ _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
+
+ @classmethod
+ def suitable(cls, url):
+ if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url) or VimeoAlbumIE.suitable(url) or VimeoGroupsIE.suitable(url):
+ return False
+ return super(VimeoUserIE, cls).suitable(url)
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ name = mobj.group('name')
+ return self._extract_videos(name, 'http://vimeo.com/%s' % name)
+
+
+class VimeoAlbumIE(VimeoChannelIE):
+ IE_NAME = u'vimeo:album'
+ _VALID_URL = r'(?:https?://)?vimeo.\com/album/(?P<id>\d+)'
+ _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
+
+ def _page_url(self, base_url, pagenum):
+ return '%s/page:%d/' % (base_url, pagenum)
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ album_id = mobj.group('id')
+ return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id)
+
+
+class VimeoGroupsIE(VimeoAlbumIE):
+ IE_NAME = u'vimeo:group'
+ _VALID_URL = r'(?:https?://)?vimeo.\com/groups/(?P<name>[^/]+)'
+
+ def _extract_list_title(self, webpage):
+ return self._og_search_title(webpage)
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ name = mobj.group('name')
+ return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name)
video_url = self._html_search_regex(r'<meta property="twitter:player:stream" content="(.+?)"',
webpage, u'video URL')
- uploader = self._html_search_regex(r'<div class="user">.*?<h2>(.+?)</h2>',
+ uploader = self._html_search_regex(r'<p class="username">(.*?)</p>',
webpage, u'uploader', fatal=False, flags=re.DOTALL)
return [{
class WatIE(InfoExtractor):
- _VALID_URL=r'http://www.wat.tv/.*-(?P<shortID>.*?)_.*?.html'
+ _VALID_URL=r'http://www\.wat\.tv/.*-(?P<shortID>.*?)_.*?\.html'
IE_NAME = 'wat.tv'
_TEST = {
u'url': u'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html',
_VALID_URL = r'https?://video\.weibo\.com/v/weishipin/t_(?P<id>.+?)\.htm'
_TEST = {
+ u'add_ie': ['Sina'],
u'url': u'http://video.weibo.com/v/weishipin/t_zjUw2kZ.htm',
u'file': u'98322879.flv',
u'info_dict': {
u'file': u'deerfence.flv',
u'md5': u'8b215e2e0168c6081a1cf84b2846a2b5',
u'info_dict': {
- u"title": u"Watch Till End: Herd of deer jump over a fence."
+ u"title": u"Watch Till End: Herd of deer jump over a fence.",
+ u"description": u"These deer look as fluid as running water when they jump over this fence as a herd. This video is one that needs to be watched until the very end for the true majesty to be witnessed, but once it comes, it's sure to take your breath away.",
}
}
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
webpage = self._download_webpage(url, video_id)
- title = self._search_regex(r'<meta name="description" content="(.+?)" />',webpage, 'video title')
- thumbnail_url = self._search_regex(r'<meta property="og\:image" content="(.+?)" />', webpage,'video thumbnail')
googleString = self._search_regex("googleCode = '(.*?)'", webpage, 'file url')
googleString = base64.b64decode(googleString).decode('ascii')
- final_url = self._search_regex('","(.*?)"', googleString,'final video url')
- ext = final_url.rpartition(u'.')[2]
-
- return [{
- 'id': video_id,
- 'url': final_url,
- 'ext': ext,
- 'title': title,
- 'thumbnail': thumbnail_url,
- }]
+ final_url = self._search_regex('","(.*?)"', googleString, u'final video url')
+ return {
+ 'id': video_id,
+ 'url': final_url,
+ 'title': self._og_search_title(webpage),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ 'description': self._og_search_description(webpage),
+ }
--- /dev/null
+import json
+import re
+
+from .common import InfoExtractor
+
+
+class WistiaIE(InfoExtractor):
+ _VALID_URL = r'^https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)'
+
+ _TEST = {
+ u"url": u"http://fast.wistia.net/embed/iframe/sh7fpupwlt",
+ u"file": u"sh7fpupwlt.mov",
+ u"md5": u"cafeb56ec0c53c18c97405eecb3133df",
+ u"info_dict": {
+ u"title": u"cfh_resourceful_zdkh_final_1"
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+ data_json = self._html_search_regex(
+ r'Wistia.iframeInit\((.*?), {}\);', webpage, u'video data')
+
+ data = json.loads(data_json)
+
+ formats = []
+ thumbnails = []
+ for atype, a in data['assets'].items():
+ if atype == 'still':
+ thumbnails.append({
+ 'url': a['url'],
+ 'resolution': '%dx%d' % (a['width'], a['height']),
+ })
+ continue
+ if atype == 'preview':
+ continue
+ formats.append({
+ 'format_id': atype,
+ 'url': a['url'],
+ 'width': a['width'],
+ 'height': a['height'],
+ 'filesize': a['size'],
+ 'ext': a['ext'],
+ })
+ formats.sort(key=lambda a: a['filesize'])
+
+ return {
+ 'id': video_id,
+ 'title': data['name'],
+ 'formats': formats,
+ 'thumbnails': thumbnails,
+ }
return mobj.group('server')+'/key='+mobj.group('file')
def is_hd(webpage):
- return webpage.find('<div class=\'icon iconHD\'>') != -1
+ return webpage.find('<div class=\'icon iconHD\'') != -1
mobj = re.match(self._VALID_URL, url)
class XNXXIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)'
+ _VALID_URL = r'^(?:https?://)?(?:video|www)\.xnxx\.com/video([0-9]+)/(.*)'
VIDEO_URL_RE = r'flv_url=(.*?)&'
VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&'
--- /dev/null
+import os
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse_urlparse,
+ compat_urllib_request,
+)
+
+class XTubeIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))'
+ _TEST = {
+ u'url': u'http://www.xtube.com/watch.php?v=kVTUy_G222_',
+ u'file': u'kVTUy_G222_.mp4',
+ u'md5': u'092fbdd3cbe292c920ef6fc6a8a9cdab',
+ u'info_dict': {
+ u"title": u"strange erotica",
+ u"description": u"surreal gay themed erotica...almost an ET kind of thing",
+ u"uploader": u"greenshowers",
+ u"age_limit": 18,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('videoid')
+ url = 'http://www.' + mobj.group('url')
+
+ req = compat_urllib_request.Request(url)
+ req.add_header('Cookie', 'age_verified=1')
+ webpage = self._download_webpage(req, video_id)
+
+ video_title = self._html_search_regex(r'<div class="p_5px[^>]*>([^<]+)', webpage, u'title')
+ video_uploader = self._html_search_regex(r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, u'uploader', fatal=False)
+ video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, u'description', fatal=False)
+ video_url= self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, u'video_url').replace('\\/', '/')
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
+ format = path.split('/')[5].split('_')[:2]
+ format[0] += 'p'
+ format[1] += 'k'
+ format = "-".join(format)
+
+ return {
+ 'id': video_id,
+ 'title': video_title,
+ 'uploader': video_uploader,
+ 'description': video_description,
+ 'url': video_url,
+ 'ext': extension,
+ 'format': format,
+ 'format_id': format,
+ 'age_limit': 18,
+ }
_TESTS = [
{
u'url': u'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
- u'file': u'214727115.flv',
+ u'file': u'214727115.mp4',
+ u'md5': u'4962b075c08be8690a922ee026d05e69',
u'info_dict': {
u'title': u'Julian Smith & Travis Legg Watch Julian Smith',
u'description': u'Julian and Travis watch Julian Smith',
},
- u'params': {
- # Requires rtmpdump
- u'skip_download': True,
- },
},
{
u'url': u'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html',
- u'file': u'103000935.flv',
+ u'file': u'103000935.mp4',
+ u'md5': u'd6e6fc6e1313c608f316ddad7b82b306',
u'info_dict': {
u'title': u'Codefellas - The Cougar Lies with Spanish Moss',
u'description': u'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?',
},
- u'params': {
- # Requires rtmpdump
- u'skip_download': True,
- },
},
]
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
- items_json = self._search_regex(r'YVIDEO_INIT_ITEMS = ({.*?});$',
+ items_json = self._search_regex(r'mediaItems: ({.*?})$',
webpage, u'items', flags=re.MULTILINE)
items = json.loads(items_json)
info = items['mediaItems']['query']['results']['mediaObj'][0]
# The 'meta' field is not always in the video webpage, we request it
# from another page
long_id = info['id']
+ return self._get_info(long_id, video_id)
+
+ def _get_info(self, long_id, video_id):
query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"'
- ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2"' % long_id)
+ ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="US"'
+ ' AND protocol="http"' % long_id)
data = compat_urllib_parse.urlencode({
'q': query,
'env': 'prod',
formats.append(format_info)
formats = sorted(formats, key=lambda f:(f['height'], f['width']))
- info = {
+ return {
'id': video_id,
'title': meta['title'],
'formats': formats,
'description': clean_html(meta['description']),
'thumbnail': meta['thumbnail'],
}
- # TODO: Remove when #980 has been merged
- info.update(formats[-1])
- return info
+
+class YahooNewsIE(YahooIE):
+ IE_NAME = 'yahoo:news'
+ _VALID_URL = r'http://news\.yahoo\.com/video/.*?-(?P<id>\d*?)\.html'
+
+ _TEST = {
+ u'url': u'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
+ u'md5': u'67010fdf3a08d290e060a4dd96baa07b',
+ u'info_dict': {
+ u'id': u'104538833',
+ u'ext': u'mp4',
+ u'title': u'China Moses Is Crazy About the Blues',
+ u'description': u'md5:9900ab8cd5808175c7b3fe55b979bed0',
+ },
+ }
+
+ # Overwrite YahooIE properties we don't want
+ _TESTS = []
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+ long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, u'long id')
+ return self._get_info(long_id, video_id)
class YahooSearchIE(SearchInfoExtractor):
mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
res['entries'].append(e)
- if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )):
+ if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1)):
break
return res
class YouJizzIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
_TEST = {
u'url': u'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
u'file': u'2189178.flv',
u"url": u"http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
u"file": u"XNDgyMDQ2NTQw_part00.flv",
u"md5": u"ffe3f2e435663dc2d1eea34faeff5b5b",
- u"params": { u"test": False },
+ u"params": {u"test": False},
u"info_dict": {
u"title": u"youtube-dl test video \"'/\\ä↭𝕐"
}
source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
seed = float(seed)
for i in range(len(source)):
- seed = (seed * 211 + 30031 ) % 65536
- index = math.floor(seed / 65536 * len(source) )
+ seed = (seed * 211 + 30031) % 65536
+ index = math.floor(seed / 65536 * len(source))
mixed.append(source[int(index)])
source.remove(source[int(index)])
#return ''.join(mixed)
# 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
- extension = os.path.splitext( path )[1][1:]
+ video_url = unescapeHTML(link)
+ path = compat_urllib_parse_urlparse(video_url).path
+ extension = os.path.splitext(path)[1][1:]
format = path.split('/')[4].split('_')[:2]
# size = format[0]
# bitrate = format[1]
- format = "-".join( format )
+ format = "-".join(format)
# title = u'%s-%s-%s' % (video_title, size, bitrate)
formats.append({
import json
import os.path
import re
-import socket
import string
import struct
import traceback
-import xml.etree.ElementTree
import zlib
from .common import InfoExtractor, SearchInfoExtractor
from .subtitles import SubtitlesInfoExtractor
from ..utils import (
compat_chr,
- compat_http_client,
compat_parse_qs,
- compat_urllib_error,
compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
clean_html,
get_cachedir,
get_element_by_id,
+ get_element_by_attribute,
ExtractorError,
unescapeHTML,
unified_strdate,
# If True it will raise an error if no login info is provided
_LOGIN_REQUIRED = False
- def report_lang(self):
- """Report attempt to set language."""
- self.to_screen(u'Setting language')
-
def _set_language(self):
- request = compat_urllib_request.Request(self._LANG_URL)
- try:
- self.report_lang()
- compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_warning(u'unable to set language: %s' % compat_str(err))
- return False
- return True
+ return bool(self._download_webpage(
+ self._LANG_URL, None,
+ note=u'Setting language', errnote='unable to set language',
+ fatal=False))
def _login(self):
(username, password) = self._get_login_info()
raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True)
return False
- request = compat_urllib_request.Request(self._LOGIN_URL)
- try:
- login_page = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err))
- return False
+ login_page = self._download_webpage(
+ self._LOGIN_URL, None,
+ note=u'Downloading login page',
+ errnote=u'unable to fetch login page', fatal=False)
+ if login_page is False:
+ return
galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"',
login_page, u'Login GALX parameter')
# chokes on unicode
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
login_data = compat_urllib_parse.urlencode(login_form).encode('ascii')
- request = compat_urllib_request.Request(self._LOGIN_URL, login_data)
- try:
- self.report_login()
- login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
- if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
- self._downloader.report_warning(u'unable to log in: bad username or password')
- return False
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
+
+ req = compat_urllib_request.Request(self._LOGIN_URL, login_data)
+ login_results = self._download_webpage(
+ req, None,
+ note=u'Logging in', errnote=u'unable to log in', fatal=False)
+ if login_results is False:
+ return False
+ if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
+ self._downloader.report_warning(u'unable to log in: bad username or password')
return False
return True
def _confirm_age(self):
age_form = {
- 'next_url': '/',
- 'action_confirm': 'Confirm',
- }
- request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form))
- try:
- self.report_age_confirmation()
- compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
+ 'next_url': '/',
+ 'action_confirm': 'Confirm',
+ }
+ req = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form))
+
+ self._download_webpage(
+ req, None,
+ note=u'Confirming age', errnote=u'Unable to confirm age')
return True
def _real_initialize(self):
class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
IE_DESC = u'YouTube.com'
- _VALID_URL = r"""^
+ _VALID_URL = r"""(?x)^
(
- (?:https?://)? # http(s):// (optional)
- (?:(?:(?:(?:\w+\.)?youtube(?:-nocookie)?\.com/|
+ (?:https?://|//)? # http(s):// or protocol-independent URL (optional)
+ (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
tube\.majestyc\.net/|
youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
'248': 'webm',
}
_video_dimensions = {
- '5': '240x400',
+ '5': '400x240',
'6': '???',
'13': '???',
- '17': '144x176',
- '18': '360x640',
- '22': '720x1280',
- '34': '360x640',
- '35': '480x854',
- '36': '240x320',
- '37': '1080x1920',
- '38': '3072x4096',
- '43': '360x640',
- '44': '480x854',
- '45': '720x1280',
- '46': '1080x1920',
+ '17': '176x144',
+ '18': '640x360',
+ '22': '1280x720',
+ '34': '640x360',
+ '35': '854x480',
+ '36': '320x240',
+ '37': '1920x1080',
+ '38': '4096x3072',
+ '43': '640x360',
+ '44': '854x480',
+ '45': '1280x720',
+ '46': '1920x1080',
'82': '360p',
'83': '480p',
'84': '720p',
u"uploader": u"Philipp Hagemeister",
u"uploader_id": u"phihag",
u"upload_date": u"20121002",
- u"description": u"test chars: \"'/\\ä↭𝕐\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ."
- }
- },
- {
- u"url": u"http://www.youtube.com/watch?v=1ltcDfZMA3U",
- u"file": u"1ltcDfZMA3U.mp4",
- u"note": u"Test VEVO video (#897)",
- u"info_dict": {
- u"upload_date": u"20070518",
- u"title": u"Maps - It Will Find You",
- u"description": u"Music video by Maps performing It Will Find You.",
- u"uploader": u"MuteUSA",
- u"uploader_id": u"MuteUSA"
+ u"description": u"test chars: \"'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ."
}
},
{
u"uploader_id": u"justintimberlakeVEVO"
}
},
+ {
+ u"url": u"//www.YouTube.com/watch?v=yZIXLfi8CZQ",
+ u"file": u"yZIXLfi8CZQ.mp4",
+ u"note": u"Embed-only video (#1746)",
+ u"info_dict": {
+ u"upload_date": u"20120608",
+ u"title": u"Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012",
+ u"description": u"md5:09b78bd971f1e3e289601dfba15ca4f7",
+ u"uploader": u"SET India",
+ u"uploader_id": u"setindia"
+ }
+ },
]
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
if YoutubePlaylistIE.suitable(url): return False
- return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
+ return re.match(cls._VALID_URL, url) is not None
def __init__(self, *args, **kwargs):
super(YoutubeIE, self).__init__(*args, **kwargs)
self._player_cache = {}
- def report_video_webpage_download(self, video_id):
- """Report attempt to download video webpage."""
- self.to_screen(u'%s: Downloading video webpage' % video_id)
-
def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage."""
self.to_screen(u'%s: Downloading video info webpage' % video_id)
"""Turn the encrypted s field into a working signature"""
if player_url is not None:
+ if player_url.startswith(u'//'):
+ player_url = u'https:' + player_url
try:
player_id = (player_url, len(s))
if player_id not in self._player_cache:
else:
raise ExtractorError(u'Unable to decrypt signature, key length %d not supported; retrying might work' % (len(s)))
- def _get_available_subtitles(self, video_id):
+ def _get_available_subtitles(self, video_id, webpage):
try:
sub_list = self._download_webpage(
'http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
params = compat_urllib_parse.urlencode({
'lang': lang,
'v': video_id,
- 'fmt': self._downloader.params.get('subtitlesformat'),
+ 'fmt': self._downloader.params.get('subtitlesformat', 'srt'),
'name': l[0].encode('utf-8'),
})
url = u'http://www.youtube.com/api/timedtext?' + params
def _get_available_automatic_caption(self, video_id, webpage):
"""We need the webpage for getting the captions url, pass it as an
argument to speed up the process."""
- sub_format = self._downloader.params.get('subtitlesformat')
+ sub_format = self._downloader.params.get('subtitlesformat', 'srt')
self.to_screen(u'%s: Looking for automatic captions' % video_id)
mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
err_msg = u'Couldn\'t find automatic captions for %s' % video_id
'asrs': 1,
})
list_url = caption_url + '&' + list_params
- list_page = self._download_webpage(list_url, video_id)
- caption_list = xml.etree.ElementTree.fromstring(list_page.encode('utf-8'))
+ caption_list = self._download_xml(list_url, video_id)
original_lang_node = caption_list.find('track')
if original_lang_node is None or original_lang_node.attrib.get('kind') != 'asr' :
self._downloader.report_warning(u'Video doesn\'t have automatic captions')
video_id = self._extract_id(url)
# Get video webpage
- self.report_video_webpage_download(video_id)
url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
- request = compat_urllib_request.Request(url)
- try:
- video_webpage_bytes = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to download video webpage: %s' % compat_str(err))
-
- video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
+ video_webpage = self._download_webpage(url, video_id)
# Attempt to extract SWF player URL
mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
# We simulate the access to the video from www.youtube.com/v/{video_id}
# this can be viewed without login into Youtube
data = compat_urllib_parse.urlencode({'video_id': video_id,
- 'el': 'embedded',
+ 'el': 'player_embedded',
'gl': 'US',
'hl': 'en',
'eurl': 'https://youtube.googleapis.com/v/' + video_id,
else:
raise ExtractorError(u'"token" parameter not in video info for unknown reason')
+ if 'view_count' in video_info:
+ view_count = int(video_info['view_count'][0])
+ else:
+ view_count = None
+
# Check for "rental" videos
if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
raise ExtractorError(u'"rental" videos not supported')
# description
video_description = get_element_by_id("eow-description", video_webpage)
if video_description:
+ video_description = re.sub(r'''(?x)
+ <a\s+
+ (?:[a-zA-Z-]+="[^"]+"\s+)*?
+ title="([^"]+)"\s+
+ (?:[a-zA-Z-]+="[^"]+"\s+)*?
+ class="yt-uix-redirect-link"\s*>
+ [^<]+
+ </a>
+ ''', r'\1', video_description)
video_description = clean_html(video_description)
else:
fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
else:
video_description = u''
+ def _extract_count(klass):
+ count = self._search_regex(
+ r'class="%s">([\d,]+)</span>' % re.escape(klass),
+ video_webpage, klass, default=None)
+ if count is not None:
+ return int(count.replace(',', ''))
+ return None
+ like_count = _extract_count(u'likes-count')
+ dislike_count = _extract_count(u'dislikes-count')
+
# subtitles
video_subtitles = self.extract_subtitles(video_id, video_webpage)
if 'length_seconds' not in video_info:
self._downloader.report_warning(u'unable to extract video duration')
- video_duration = ''
+ video_duration = None
else:
- video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
+ video_duration = int(compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]))
# annotations
video_annotations = None
'subtitles': video_subtitles,
'duration': video_duration,
'age_limit': 18 if age_gate else 0,
- 'annotations': video_annotations
+ 'annotations': video_annotations,
+ 'webpage_url': 'https://www.youtube.com/watch?v=%s' % video_id,
+ 'view_count': view_count,
+ 'like_count': like_count,
+ 'dislike_count': dislike_count,
})
return results
-class YoutubePlaylistIE(InfoExtractor):
+class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
IE_DESC = u'YouTube.com playlists'
_VALID_URL = r"""(?:
(?:https?://)?
\? (?:.*?&)*? (?:p|a|list)=
| p/
)
- ((?:PL|EC|UU|FL)?[0-9A-Za-z-_]{10,})
+ ((?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,})
.*
|
- ((?:PL|EC|UU|FL)[0-9A-Za-z-_]{10,})
+ ((?:PL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,})
)"""
- _TEMPLATE_URL = 'https://gdata.youtube.com/feeds/api/playlists/%s?max-results=%i&start-index=%i&v=2&alt=json&safeSearch=none'
- _MAX_RESULTS = 50
+ _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&page=%s'
+ _MORE_PAGES_INDICATOR = r'data-link-type="next"'
+ _VIDEO_RE = r'href="/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)'
IE_NAME = u'youtube:playlist'
@classmethod
"""Receives a URL and returns True if suitable for this IE."""
return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
+ def _real_initialize(self):
+ self._login()
+
+ def _ids_to_results(self, ids):
+ return [self.url_result(vid_id, 'Youtube', video_id=vid_id)
+ for vid_id in ids]
+
+ def _extract_mix(self, playlist_id):
+ # The mixes are generated from a a single video
+ # the id of the playlist is just 'RD' + video_id
+ url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id)
+ webpage = self._download_webpage(url, playlist_id, u'Downloading Youtube mix')
+ title_span = (get_element_by_attribute('class', 'title long-title', webpage) or
+ get_element_by_attribute('class', 'title ', webpage))
+ title = clean_html(title_span)
+ video_re = r'data-index="\d+".*?href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s' % re.escape(playlist_id)
+ ids = orderedSet(re.findall(video_re, webpage))
+ url_results = self._ids_to_results(ids)
+
+ return self.playlist_result(url_results, playlist_id, title)
+
def _real_extract(self, url):
# Extract playlist id
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
video_id = query_dict['v'][0]
if self._downloader.params.get('noplaylist'):
self.to_screen(u'Downloading just video %s because of --no-playlist' % video_id)
- return self.url_result('https://www.youtube.com/watch?v=' + video_id, 'Youtube')
+ return self.url_result(video_id, 'Youtube', video_id=video_id)
else:
self.to_screen(u'Downloading playlist PL%s - add --no-playlist to just download video %s' % (playlist_id, video_id))
- # Download playlist videos from API
- videos = []
+ if playlist_id.startswith('RD'):
+ # Mixes require a custom extraction process
+ return self._extract_mix(playlist_id)
+ if playlist_id.startswith('TL'):
+ raise ExtractorError(u'For downloading YouTube.com top lists, use '
+ u'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True)
+
+ # Extract the video ids from the playlist pages
+ ids = []
for page_num in itertools.count(1):
- start_index = self._MAX_RESULTS * (page_num - 1) + 1
- if start_index >= 1000:
- self._downloader.report_warning(u'Max number of results reached')
- break
- url = self._TEMPLATE_URL % (playlist_id, self._MAX_RESULTS, start_index)
+ url = self._TEMPLATE_URL % (playlist_id, page_num)
page = self._download_webpage(url, playlist_id, u'Downloading page #%s' % page_num)
+ matches = re.finditer(self._VIDEO_RE, page)
+ # 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')
+ ids.extend(new_ids)
- try:
- response = json.loads(page)
- except ValueError as err:
- raise ExtractorError(u'Invalid JSON in API response: ' + compat_str(err))
-
- if 'feed' not in response:
- raise ExtractorError(u'Got a malformed response from YouTube API')
- playlist_title = response['feed']['title']['$t']
- if 'entry' not in response['feed']:
- # Number of videos is a multiple of self._MAX_RESULTS
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
break
- for entry in response['feed']['entry']:
- index = entry['yt$position']['$t']
- if 'media$group' in entry and 'yt$videoid' in entry['media$group']:
- videos.append((
- index,
- 'https://www.youtube.com/watch?v=' + entry['media$group']['yt$videoid']['$t']
- ))
+ playlist_title = self._og_search_title(page)
- videos = [v[1] for v in sorted(videos)]
+ url_results = self._ids_to_results(ids)
+ return self.playlist_result(url_results, playlist_id, playlist_title)
- url_results = [self.url_result(vurl, 'Youtube') for vurl in videos]
- return [self.playlist_result(url_results, playlist_id, playlist_title)]
+
+class YoutubeTopListIE(YoutubePlaylistIE):
+ IE_NAME = u'youtube:toplist'
+ IE_DESC = (u'YouTube.com top lists, "yttoplist:{channel}:{list title}"'
+ u' (Example: "yttoplist:music:Top Tracks")')
+ _VALID_URL = r'yttoplist:(?P<chann>.*?):(?P<title>.*?)$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ channel = mobj.group('chann')
+ title = mobj.group('title')
+ query = compat_urllib_parse.urlencode({'title': title})
+ playlist_re = 'href="([^"]+?%s[^"]+?)"' % re.escape(query)
+ channel_page = self._download_webpage('https://www.youtube.com/%s' % channel, title)
+ link = self._html_search_regex(playlist_re, channel_page, u'list')
+ url = compat_urlparse.urljoin('https://www.youtube.com/', link)
+
+ video_re = r'data-index="\d+".*?data-video-id="([0-9A-Za-z_-]{11})"'
+ ids = []
+ # sometimes the webpage doesn't contain the videos
+ # retry until we get them
+ for i in itertools.count(0):
+ msg = u'Downloading Youtube mix'
+ if i > 0:
+ msg += ', retry #%d' % i
+ webpage = self._download_webpage(url, title, msg)
+ ids = orderedSet(re.findall(video_re, webpage))
+ if ids:
+ break
+ url_results = self._ids_to_results(ids)
+ return self.playlist_result(url_results, playlist_title=title)
class YoutubeChannelIE(InfoExtractor):
IE_DESC = u'YouTube.com channels'
_VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)"
- _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
_MORE_PAGES_INDICATOR = 'yt-uix-load-more'
_MORE_PAGES_URL = 'http://www.youtube.com/c4_browse_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s'
IE_NAME = u'youtube:channel'
# Download channel page
channel_id = mobj.group(1)
video_ids = []
- pagenum = 1
-
- url = self._TEMPLATE_URL % (channel_id, pagenum)
- page = self._download_webpage(url, channel_id,
- u'Downloading page #%s' % pagenum)
-
- # Extract video identifiers
- ids_in_page = self.extract_videos_from_page(page)
- video_ids.extend(ids_in_page)
-
- # Download any subsequent channel pages using the json-based channel_ajax query
- if self._MORE_PAGES_INDICATOR in page:
+ url = 'https://www.youtube.com/channel/%s/videos' % channel_id
+ channel_page = self._download_webpage(url, channel_id)
+ autogenerated = re.search(r'''(?x)
+ class="[^"]*?(?:
+ channel-header-autogenerated-label|
+ yt-channel-title-autogenerated
+ )[^"]*"''', channel_page) is not None
+
+ if autogenerated:
+ # The videos are contained in a single page
+ # the ajax pages can't be used, they are empty
+ video_ids = self.extract_videos_from_page(channel_page)
+ else:
+ # Download all channel pages using the json-based channel_ajax query
for pagenum in itertools.count(1):
url = self._MORE_PAGES_URL % (pagenum, channel_id)
page = self._download_webpage(url, channel_id,
u'Downloading page #%s' % pagenum)
-
+
page = json.loads(page)
-
+
ids_in_page = self.extract_videos_from_page(page['content_html'])
video_ids.extend(ids_in_page)
-
- if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']:
+
+ if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']:
break
self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids)))
- urls = ['http://www.youtube.com/watch?v=%s' % id for id in video_ids]
- url_entries = [self.url_result(eurl, 'Youtube') for eurl in urls]
- return [self.playlist_result(url_entries, channel_id)]
+ url_entries = [self.url_result(video_id, 'Youtube', video_id=video_id)
+ for video_id in video_ids]
+ return self.playlist_result(url_entries, channel_id)
class YoutubeUserIE(InfoExtractor):
if len(ids_in_page) < self._GDATA_PAGE_SIZE:
break
- urls = ['http://www.youtube.com/watch?v=%s' % video_id for video_id in video_ids]
- url_results = [self.url_result(rurl, 'Youtube') for rurl in urls]
- return [self.playlist_result(url_results, playlist_title = username)]
+ url_results = [
+ self.url_result(video_id, 'Youtube', video_id=video_id)
+ for video_id in video_ids]
+ return self.playlist_result(url_results, playlist_title=username)
+
class YoutubeSearchIE(SearchInfoExtractor):
IE_DESC = u'YouTube.com searches'
IE_NAME = u'youtube:search'
_SEARCH_KEY = 'ytsearch'
- def report_download_page(self, query, pagenum):
- """Report attempt to download search page with given number."""
- self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
-
def _get_n_results(self, query, n):
"""Get a specified number of results for a query"""
limit = n
while (50 * pagenum) < limit:
- self.report_download_page(query, pagenum+1)
result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1)
- request = compat_urllib_request.Request(result_url)
- try:
- data = compat_urllib_request.urlopen(request).read().decode('utf-8')
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to download API page: %s' % compat_str(err))
- api_response = json.loads(data)['data']
-
- if not 'items' in api_response:
+ data_json = self._download_webpage(
+ result_url, video_id=u'query "%s"' % query,
+ note=u'Downloading page %s' % (pagenum + 1),
+ errnote=u'Unable to download API page')
+ data = json.loads(data_json)
+ api_response = data['data']
+
+ if 'items' not in api_response:
raise ExtractorError(u'[youtube] No video results')
new_ids = list(video['id'] for video in api_response['items'])
if len(video_ids) > n:
video_ids = video_ids[:n]
- videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids]
+ videos = [self.url_result(video_id, 'Youtube', video_id=video_id)
+ for video_id in video_ids]
return self.playlist_result(videos, query)
+class YoutubeSearchDateIE(YoutubeSearchIE):
+ IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
+ _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc&orderby=published'
+ _SEARCH_KEY = 'ytsearchdate'
+ IE_DESC = u'YouTube.com searches, newest videos first'
class YoutubeShowIE(InfoExtractor):
IE_DESC = u'YouTube.com (multi-season) shows'
Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
"""
_LOGIN_REQUIRED = True
- _PAGING_STEP = 30
# use action_load_personal_feed instead of action_load_system_feed
_PERSONAL_FEED = False
def _real_extract(self, url):
feed_entries = []
- # The step argument is available only in 2.7 or higher
- for i in itertools.count(0):
- paging = i*self._PAGING_STEP
+ paging = 0
+ for i in itertools.count(1):
info = self._download_webpage(self._FEED_TEMPLATE % paging,
u'%s feed' % self._FEED_NAME,
u'Downloading page %s' % i)
feed_html = info['feed_html']
m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html)
ids = orderedSet(m.group(1) for m in m_ids)
- feed_entries.extend(self.url_result(id, 'Youtube') for id in ids)
+ feed_entries.extend(
+ self.url_result(video_id, 'Youtube', video_id=video_id)
+ for video_id in ids)
if info['paging'] is None:
break
+ paging = info['paging']
return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE)
class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
_VALID_URL = r'https?://www\.youtube\.com/feed/watch_later|:ytwatchlater'
_FEED_NAME = 'watch_later'
_PLAYLIST_TITLE = u'Youtube Watch Later'
- _PAGING_STEP = 100
_PERSONAL_FEED = True
+class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
+ IE_DESC = u'Youtube watch history, "ythistory" keyword (requires authentication)'
+ _VALID_URL = u'https?://www\.youtube\.com/feed/history|:ythistory'
+ _FEED_NAME = 'history'
+ _PERSONAL_FEED = True
+ _PLAYLIST_TITLE = u'Youtube Watch History'
+
class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
IE_NAME = u'youtube:favorites'
IE_DESC = u'YouTube.com favourite videos, "ytfav" keyword (requires authentication)'
+# coding: utf-8
+
+import operator
import re
from .common import InfoExtractor
from ..utils import (
- determine_ext,
- ExtractorError,
+ unified_strdate,
)
class ZDFIE(InfoExtractor):
- _VALID_URL = r'^http://www\.zdf\.de\/ZDFmediathek(?P<hash>#)?\/(.*beitrag\/video\/)(?P<video_id>[^/\?]+)(?:\?.*)?'
- _MEDIA_STREAM = r'<a href="(?P<video_url>.+(?P<media_type>.streaming).+/zdf/(?P<quality>[^\/]+)/[^"]*)".+class="play".+>'
+ _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<video_id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
+
+ _TEST = {
+ u"url": u"http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt",
+ u"file": u"2037704.webm",
+ u"info_dict": {
+ u"upload_date": u"20131127",
+ u"description": u"Union und SPD haben sich auf einen Koalitionsvertrag geeinigt. Aber was bedeutet das für die Bürger? Sehen Sie hierzu das ZDFspezial \"Ende des Machtpokers - Große Koalition für Deutschland\".",
+ u"uploader": u"spezial",
+ u"title": u"ZDFspezial - Ende des Machtpokers"
+ },
+ u"skip": u"Videos on ZDF.de are depublicised in short order",
+ }
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('video_id')
- if mobj.group('hash'):
- url = url.replace(u'#', u'', 1)
+ xml_url = u'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
+ doc = self._download_xml(
+ xml_url, video_id,
+ note=u'Downloading video info',
+ errnote=u'Failed to download video info')
+
+ title = doc.find('.//information/title').text
+ description = doc.find('.//information/detail').text
+ uploader_node = doc.find('.//details/originChannelTitle')
+ uploader = None if uploader_node is None else uploader_node.text
+ duration_str = doc.find('.//details/length').text
+ duration_m = re.match(r'''(?x)^
+ (?P<hours>[0-9]{2})
+ :(?P<minutes>[0-9]{2})
+ :(?P<seconds>[0-9]{2})
+ (?:\.(?P<ms>[0-9]+)?)
+ ''', duration_str)
+ duration = (
+ (
+ (int(duration_m.group('hours')) * 60 * 60) +
+ (int(duration_m.group('minutes')) * 60) +
+ int(duration_m.group('seconds'))
+ )
+ if duration_m
+ else None
+ )
+ upload_date = unified_strdate(doc.find('.//details/airtime').text)
+
+ def xml_to_format(fnode):
+ video_url = fnode.find('url').text
+ is_available = u'http://www.metafilegenerator' not in video_url
- html = self._download_webpage(url, video_id)
- streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
- if streams is None:
- raise ExtractorError(u'No media url found.')
+ format_id = fnode.attrib['basetype']
+ format_m = re.match(r'''(?x)
+ (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
+ (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
+ ''', format_id)
- # s['media_type'] == 'wstreaming' -> use 'Windows Media Player' and mms url
- # s['media_type'] == 'hstreaming' -> use 'Quicktime' and rtsp url
- # choose first/default media type and highest quality for now
- def stream_pref(s):
- TYPE_ORDER = ['ostreaming', 'hstreaming', 'wstreaming']
+ ext = format_m.group('container')
+ is_supported = ext != 'f4f'
+
+ PROTO_ORDER = ['http', 'rtmp', 'rtsp']
try:
- type_pref = TYPE_ORDER.index(s['media_type'])
+ proto_pref = -PROTO_ORDER.index(format_m.group('proto'))
except ValueError:
- type_pref = 999
+ proto_pref = -999
- QUALITY_ORDER = ['veryhigh', '300']
+ quality = fnode.find('./quality').text
+ QUALITY_ORDER = ['veryhigh', '300', 'high', 'med', 'low']
try:
- quality_pref = QUALITY_ORDER.index(s['quality'])
+ quality_pref = -QUALITY_ORDER.index(quality)
except ValueError:
- quality_pref = 999
-
- return (type_pref, quality_pref)
-
- sorted_streams = sorted(streams, key=stream_pref)
- if not sorted_streams:
- raise ExtractorError(u'No stream found.')
- stream = sorted_streams[0]
+ quality_pref = -999
- media_link = self._download_webpage(
- stream['video_url'],
- video_id,
- u'Get stream URL')
+ abr = int(fnode.find('./audioBitrate').text) // 1000
+ vbr = int(fnode.find('./videoBitrate').text) // 1000
+ pref = (is_available, is_supported,
+ proto_pref, quality_pref, vbr, abr)
- MMS_STREAM = r'href="(?P<video_url>mms://[^"]*)"'
- RTSP_STREAM = r'(?P<video_url>rtsp://[^"]*.mp4)'
+ format_note = u''
+ if not is_supported:
+ format_note += u'(unsupported)'
+ if not format_note:
+ format_note = None
- mobj = re.search(self._MEDIA_STREAM, media_link)
- if mobj is None:
- mobj = re.search(RTSP_STREAM, media_link)
- if mobj is None:
- raise ExtractorError(u'Cannot extract mms:// or rtsp:// URL')
- video_url = mobj.group('video_url')
+ return {
+ 'format_id': format_id + u'-' + quality,
+ 'url': video_url,
+ 'ext': ext,
+ 'acodec': format_m.group('acodec'),
+ 'vcodec': format_m.group('vcodec'),
+ 'abr': abr,
+ 'vbr': vbr,
+ 'width': int(fnode.find('./width').text),
+ 'height': int(fnode.find('./height').text),
+ 'filesize': int(fnode.find('./filesize').text),
+ 'format_note': format_note,
+ '_pref': pref,
+ '_available': is_available,
+ }
- title = self._html_search_regex(
- r'<h1(?: class="beitragHeadline")?>(.*?)</h1>',
- html, u'title')
+ format_nodes = doc.findall('.//formitaeten/formitaet')
+ formats = sorted(filter(lambda f: f['_available'],
+ map(xml_to_format, format_nodes)),
+ key=operator.itemgetter('_pref'))
return {
'id': video_id,
- 'url': video_url,
'title': title,
- 'ext': determine_ext(video_url)
+ 'formats': formats,
+ 'description': description,
+ 'uploader': uploader,
+ 'duration': duration,
+ 'upload_date': upload_date,
}
import json
import traceback
import hashlib
+import os
import subprocess
import sys
from zipimport import zipimporter
-from .utils import *
+from .utils import (
+ compat_str,
+ compat_urllib_request,
+)
from .version import __version__
def rsa_verify(message, signature, key):
if signature != sha256(message).digest(): return False
return True
+
def update_self(to_screen, verbose):
"""Update the program file with the latest version from the repository"""
return
version_id = versions_info['latest']
+
+ def version_tuple(version_str):
+ return tuple(map(int, version_str.split('.')))
+ if version_tuple(__version__) >= version_tuple(version_id):
+ to_screen(u'youtube-dl is up to date (%s)' % __version__)
+ return
+
to_screen(u'Updating to version ' + version_id + '...')
version = versions_info['versions'][version_id]
urlh = compat_urllib_request.urlopen(version['exe'][0])
newcontent = urlh.read()
urlh.close()
- except (IOError, OSError) as err:
+ except (IOError, OSError):
if verbose: to_screen(compat_str(traceback.format_exc()))
to_screen(u'ERROR: unable to download latest version')
return
try:
with open(exe + '.new', 'wb') as outf:
outf.write(newcontent)
- except (IOError, OSError) as err:
+ except (IOError, OSError):
if verbose: to_screen(compat_str(traceback.format_exc()))
to_screen(u'ERROR: unable to write the new version')
return
subprocess.Popen([bat]) # Continues to run in the background
return # Do not show premature success messages
- except (IOError, OSError) as err:
+ except (IOError, OSError):
if verbose: to_screen(compat_str(traceback.format_exc()))
to_screen(u'ERROR: unable to overwrite current version')
return
urlh = compat_urllib_request.urlopen(version['bin'][0])
newcontent = urlh.read()
urlh.close()
- except (IOError, OSError) as err:
+ except (IOError, OSError):
if verbose: to_screen(compat_str(traceback.format_exc()))
to_screen(u'ERROR: unable to download latest version')
return
try:
with open(filename, 'wb') as outf:
outf.write(newcontent)
- except (IOError, OSError) as err:
+ except (IOError, OSError):
if verbose: to_screen(compat_str(traceback.format_exc()))
to_screen(u'ERROR: unable to overwrite current version')
return
#!/usr/bin/env python
# -*- coding: utf-8 -*-
+import ctypes
import datetime
import email.utils
import errno
import io
import json
import locale
+import math
import os
import pipes
import platform
import re
+import ssl
import socket
+import subprocess
import sys
import traceback
import zlib
else:
return '%d' % secs
-def make_HTTPS_handler(opts):
- if sys.version_info < (3,2):
- # Python's 2.x handler is very simplistic
- return compat_urllib_request.HTTPSHandler()
+def make_HTTPS_handler(opts_no_check_certificate):
+ if sys.version_info < (3, 2):
+ import httplib
+
+ class HTTPSConnectionV3(httplib.HTTPSConnection):
+ def __init__(self, *args, **kwargs):
+ httplib.HTTPSConnection.__init__(self, *args, **kwargs)
+
+ def connect(self):
+ sock = socket.create_connection((self.host, self.port), self.timeout)
+ if getattr(self, '_tunnel_host', False):
+ self.sock = sock
+ self._tunnel()
+ try:
+ self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv3)
+ except ssl.SSLError:
+ self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv23)
+
+ class HTTPSHandlerV3(compat_urllib_request.HTTPSHandler):
+ def https_open(self, req):
+ return self.do_open(HTTPSConnectionV3, req)
+ return HTTPSHandlerV3()
else:
- import ssl
- context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
- context.set_default_verify_paths()
-
+ context = ssl.SSLContext(ssl.PROTOCOL_SSLv3)
context.verify_mode = (ssl.CERT_NONE
- if opts.no_check_certificate
+ if opts_no_check_certificate
else ssl.CERT_REQUIRED)
+ context.set_default_verify_paths()
+ try:
+ context.load_default_certs()
+ except AttributeError:
+ pass # Python < 3.4
return compat_urllib_request.HTTPSHandler(context=context)
class ExtractorError(Exception):
'%Y/%m/%d %H:%M:%S',
'%d.%m.%Y %H:%M',
'%Y-%m-%dT%H:%M:%SZ',
+ '%Y-%m-%dT%H:%M:%S.%fZ',
+ '%Y-%m-%dT%H:%M:%S.%f0Z',
'%Y-%m-%dT%H:%M:%S',
]
for expression in format_expressions:
upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
except:
pass
+ if upload_date is None:
+ timetuple = email.utils.parsedate_tz(date_str)
+ if timetuple:
+ upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
return upload_date
def determine_ext(url, default_ext=u'unknown_video'):
def shell_quote(args):
- return ' '.join(map(pipes.quote, args))
+ quoted_args = []
+ encoding = sys.getfilesystemencoding()
+ if encoding is None:
+ encoding = 'utf-8'
+ for a in args:
+ if isinstance(a, bytes):
+ # We may get a filename encoded with 'encodeFilename'
+ a = a.decode(encoding)
+ quoted_args.append(pipes.quote(a))
+ return u' '.join(quoted_args)
def takewhile_inclusive(pred, seq):
jsond = compat_parse_qs(sdata)[u'__youtubedl_smuggle'][0]
data = json.loads(jsond)
return url, data
+
+
+def format_bytes(bytes):
+ if bytes is None:
+ return u'N/A'
+ if type(bytes) is str:
+ bytes = float(bytes)
+ if bytes == 0.0:
+ exponent = 0
+ else:
+ exponent = int(math.log(bytes, 1024.0))
+ suffix = [u'B', u'KiB', u'MiB', u'GiB', u'TiB', u'PiB', u'EiB', u'ZiB', u'YiB'][exponent]
+ converted = float(bytes) / float(1024 ** exponent)
+ return u'%.2f%s' % (converted, suffix)
+
+
+def str_to_int(int_str):
+ int_str = re.sub(r'[,\.]', u'', int_str)
+ return int(int_str)
+
+
+def get_term_width():
+ columns = os.environ.get('COLUMNS', None)
+ if columns:
+ return int(columns)
+
+ try:
+ sp = subprocess.Popen(
+ ['stty', 'size'],
+ stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ out, err = sp.communicate()
+ return int(out.split()[1])
+ except:
+ pass
+ return None
+
+
+def month_by_name(name):
+ """ Return the number of a month by (locale-independently) English name """
+
+ ENGLISH_NAMES = [
+ u'January', u'February', u'March', u'April', u'May', u'June',
+ u'July', u'August', u'September', u'October', u'November', u'December']
+ try:
+ return ENGLISH_NAMES.index(name) + 1
+ except ValueError:
+ return None
+
+
+def fix_xml_all_ampersand(xml_str):
+ """Replace all the '&' by '&' in XML"""
+ return xml_str.replace(u'&', u'&')
+
+
+def setproctitle(title):
+ assert isinstance(title, type(u''))
+ try:
+ libc = ctypes.cdll.LoadLibrary("libc.so.6")
+ except OSError:
+ return
+ title = title
+ buf = ctypes.create_string_buffer(len(title) + 1)
+ buf.value = title.encode('utf-8')
+ try:
+ libc.prctl(15, ctypes.byref(buf), 0, 0, 0)
+ except AttributeError:
+ return # Strange libc, just skip this
+
+
+def remove_start(s, start):
+ if s.startswith(start):
+ return s[len(start):]
+ return s
+
+
+def url_basename(url):
+ path = compat_urlparse.urlparse(url).path
+ return path.strip(u'/').split(u'/')[-1]
+
+
+class HEADRequest(compat_urllib_request.Request):
+ def get_method(self):
+ return "HEAD"
-__version__ = '2013.11.02'
+__version__ = '2013.12.20'
projects / youtube-dl / commitdiff