Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-02 05:07:55 +01:00
Code Issues Releases Wiki Activity

Merge branch 'master' of https://github.com/speakerender/youtube-dl into directvnow-auth-fix

Browse Source
This commit is contained in:
SpeakerEnder 2019-06-28 10:34:34 -04:00
commit f0ea1d96ee
27 changed files with 461 additions and 272 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.github/ISSUE_TEMPLATE/1_broken_site.md vendored
View File

@ -18,7 +18,7 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.06.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.06.27. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support
- [ ] I've verified that I'm running youtube-dl version **2019.06.08**
- [ ] I've verified that I'm running youtube-dl version **2019.06.27**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [ ] I've searched the bugtracker for similar issues including closed ones
@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2019.06.08
[debug] youtube-dl version 2019.06.27
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

4
.github/ISSUE_TEMPLATE/2_site_support_request.md vendored
View File

@ -19,7 +19,7 @@ labels: 'site-support-request'
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.06.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.06.27. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
- Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a new site support request
- [ ] I've verified that I'm running youtube-dl version **2019.06.08**
- [ ] I've verified that I'm running youtube-dl version **2019.06.27**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that none of provided URLs violate any copyrights
- [ ] I've searched the bugtracker for similar site support requests including closed ones

4
.github/ISSUE_TEMPLATE/3_site_feature_request.md vendored
View File

@ -18,13 +18,13 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.06.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.06.27. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Finally, put x into all relevant boxes (like this [x])
-->
- [ ] I'm reporting a site feature request
- [ ] I've verified that I'm running youtube-dl version **2019.06.08**
- [ ] I've verified that I'm running youtube-dl version **2019.06.27**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones

6
.github/ISSUE_TEMPLATE/4_bug_report.md vendored
View File

@ -18,7 +18,7 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.06.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.06.27. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support issue
- [ ] I've verified that I'm running youtube-dl version **2019.06.08**
- [ ] I've verified that I'm running youtube-dl version **2019.06.27**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [ ] I've searched the bugtracker for similar bug reports including closed ones
@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2019.06.08
[debug] youtube-dl version 2019.06.27
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

4
.github/ISSUE_TEMPLATE/5_feature_request.md vendored
View File

@ -19,13 +19,13 @@ labels: 'request'
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.06.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.06.27. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Finally, put x into all relevant boxes (like this [x])
-->
- [ ] I'm reporting a feature request
- [ ] I've verified that I'm running youtube-dl version **2019.06.08**
- [ ] I've verified that I'm running youtube-dl version **2019.06.27**
- [ ] I've searched the bugtracker for similar feature requests including closed ones

38
ChangeLog
View File

@ -1,3 +1,41 @@
version 2019.06.27
Extractors
+ [go] Add support for disneynow.com (#21528)
* [mixer:vod] Relax URL regular expression (#21531, #21536)
* [drtv] Relax URL regular expression
* [fusion] Fix extraction (#17775, #21269)
- [nfb] Remove extractor (#21518)
+ [beeg] Add support for api/v6 v2 URLs (#21511)
+ [brightcove:new] Add support for playlists (#21331)
+ [openload] Add support for oload.life (#21495)
* [vimeo:channel,group] Make title extraction non fatal
* [vimeo:likes] Implement extrator in terms of channel extractor (#21493)
+ [pornhub] Add support for more paged video sources
+ [pornhub] Add support for downloading single pages and search pages (#15570)
* [pornhub] Rework extractors (#11922, #16078, #17454, #17936)
+ [youtube] Add another signature function pattern
* [tf1] Fix extraction (#21365, #21372)
* [crunchyroll] Move Accept-Language workaround to video extractor since
it causes playlists not to list any videos
* [crunchyroll:playlist] Fix and relax title extraction (#21291, #21443)
version 2019.06.21
Core
* [utils] Restrict parse_codecs and add theora as known vcodec (#21381)
Extractors
* [youtube] Update signature function patterns (#21469, #21476)
* [youtube] Make --write-annotations non fatal (#21452)
+ [sixplay] Add support for rtlmost.hu (#21405)
* [youtube] Hardcode codec metadata for av01 video only formats (#21381)
* [toutv] Update client key (#21370)
+ [biqle] Add support for new embed domain
* [cbs] Improve DRM protected videos detection (#21339)
version 2019.06.08
Core

6
docs/supportedsites.md
View File

@ -581,7 +581,6 @@
- **NextTV**: 壹電視
- **Nexx**
- **NexxEmbed**
- **nfb**: National Film Board of Canada
- **nfl.com**
- **NhkVod**
- **nhl.com**
@ -692,8 +691,9 @@
- **PornerBros**
- **PornHd**
- **PornHub**: PornHub and Thumbzilla
- **PornHubPlaylist**
- **PornHubUserVideos**
- **PornHubPagedVideoList**
- **PornHubUser**
- **PornHubUserVideosUpload**
- **Pornotube**
- **PornoVoisines**
- **PornoXO**

9
test/test_utils.py
View File

@ -822,6 +822,15 @@ class TestUtil(unittest.TestCase):
'vcodec': 'av01.0.05M.08',
'acodec': 'none',
})
self.assertEqual(parse_codecs('theora, vorbis'), {
'vcodec': 'theora',
'acodec': 'vorbis',
})
self.assertEqual(parse_codecs('unknownvcodec, unknownacodec'), {
'vcodec': 'unknownvcodec',
'acodec': 'unknownacodec',
})
self.assertEqual(parse_codecs('unknown'), {})
def test_escape_rfc3986(self):
reserved = "!*'();:@&=+$,/?#[]"

9
youtube_dl/extractor/beampro.py
View File

@ -99,8 +99,8 @@ class BeamProLiveIE(BeamProBaseIE):
class BeamProVodIE(BeamProBaseIE):
IE_NAME = 'Mixer:vod'
_VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/[^/?#&]+\?.*?\bvod=(?P<id>\d+)'
_TEST = {
_VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/[^/?#&]+\?.*?\bvod=(?P<id>\w+)'
_TESTS = [{
'url': 'https://mixer.com/willow8714?vod=2259830',
'md5': 'b2431e6e8347dc92ebafb565d368b76b',
'info_dict': {
@ -119,7 +119,10 @@ class BeamProVodIE(BeamProBaseIE):
'params': {
'skip_download': True,
},
}
}, {
'url': 'https://mixer.com/streamer?vod=IxFno1rqC0S_XJ1a2yGgNw',
'only_matching': True,
}]
@staticmethod
def _extract_format(vod, vod_type):

23
youtube_dl/extractor/beeg.py
View File

@ -1,7 +1,10 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..compat import (
compat_str,
compat_urlparse,
)
from ..utils import (
int_or_none,
unified_timestamp,
@ -11,6 +14,7 @@ from ..utils import (
class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P<id>\d+)'
_TESTS = [{
# api/v6 v1
'url': 'http://beeg.com/5416503',
'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
'info_dict': {
@ -24,6 +28,10 @@ class BeegIE(InfoExtractor):
'tags': list,
'age_limit': 18,
}
}, {
# api/v6 v2
'url': 'https://beeg.com/1941093077?t=911-1391',
'only_matching': True,
}, {
'url': 'https://beeg.porn/video/5416503',
'only_matching': True,
@ -41,11 +49,22 @@ class BeegIE(InfoExtractor):
r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
default='1546225636701')
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
t = qs.get('t', [''])[0].split('-')
if len(t) > 1:
query = {
'v': 2,
's': t[0],
'e': t[1],
}
else:
query = {'v': 1}
for api_path in ('', 'api.'):
video = self._download_json(
'https://%sbeeg.com/api/v6/%s/video/%s'
% (api_path, beeg_version, video_id), video_id,
fatal=api_path == 'api.')
fatal=api_path == 'api.', query=query)
if video:
break

2
youtube_dl/extractor/biqle.py
View File

@ -42,7 +42,7 @@ class BIQLEIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
embed_url = self._proto_relative_url(self._search_regex(
r'<iframe.+?src="((?:https?:)?//daxab\.com/[^"]+)".*?></iframe>',
r'<iframe.+?src="((?:https?:)?//(?:daxab\.com|dxb\.to|[^/]+/player)/[^"]+)".*?></iframe>',
webpage, 'embed url'))
if VKIE.suitable(embed_url):
return self.url_result(embed_url, VKIE.ie_key(), video_id)

28
youtube_dl/extractor/brightcove.py
View File

@ -483,7 +483,7 @@ class BrightcoveLegacyIE(InfoExtractor):
class BrightcoveNewIE(AdobePassIE):
IE_NAME = 'brightcove:new'
_VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>\d+|ref:[^&]+)'
_VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*(?P<content_type>video|playlist)Id=(?P<video_id>\d+|ref:[^&]+)'
_TESTS = [{
'url': 'http://players.brightcove.net/929656772001/e41d32dc-ec74-459e-a845-6c69f7b724ea_default/index.html?videoId=4463358922001',
'md5': 'c8100925723840d4b0d243f7025703be',
@ -516,6 +516,21 @@ class BrightcoveNewIE(AdobePassIE):
# m3u8 download
'skip_download': True,
}
}, {
# playlist stream
'url': 'https://players.brightcove.net/1752604059001/S13cJdUBz_default/index.html?playlistId=5718313430001',
'info_dict': {
'id': '5718313430001',
'title': 'No Audio Playlist',
},
'playlist_count': 7,
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'http://players.brightcove.net/5690807595001/HyZNerRl7_default/index.html?playlistId=5743160747001',
'only_matching': True,
}, {
# ref: prefixed video id
'url': 'http://players.brightcove.net/3910869709001/21519b5c-4b3b-4363-accb-bdc8f358f823_default/index.html?videoId=ref:7069442',
@ -715,7 +730,7 @@ class BrightcoveNewIE(AdobePassIE):
'ip_blocks': smuggled_data.get('geo_ip_blocks'),
})
account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups()
account_id, player_id, embed, content_type, video_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(
'http://players.brightcove.net/%s/%s_%s/index.min.js'
@ -736,7 +751,7 @@ class BrightcoveNewIE(AdobePassIE):
r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
webpage, 'policy key', group='pk')
api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id)
api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/%ss/%s' % (account_id, content_type, video_id)
headers = {
'Accept': 'application/json;pk=%s' % policy_key,
}
@ -771,5 +786,12 @@ class BrightcoveNewIE(AdobePassIE):
'tveToken': tve_token,
})
if content_type == 'playlist':
return self.playlist_result(
[self._parse_brightcove_metadata(vid, vid.get('id'), headers)
for vid in json_data.get('videos', []) if vid.get('id')],
json_data.get('id'), json_data.get('name'),
json_data.get('description'))
return self._parse_brightcove_metadata(
json_data, video_id, headers=headers)

31
youtube_dl/extractor/crunchyroll.py
View File

@ -103,19 +103,6 @@ class CrunchyrollBaseIE(InfoExtractor):
def _real_initialize(self):
self._login()
def _download_webpage(self, url_or_request, *args, **kwargs):
request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
else sanitized_Request(url_or_request))
# Accept-Language must be set explicitly to accept any language to avoid issues
# similar to https://github.com/ytdl-org/youtube-dl/issues/6797.
# Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
# should be imposed or not (from what I can see it just takes the first language
# ignoring the priority and requires it to correspond the IP). By the way this causes
# Crunchyroll to not work in georestriction cases in some browsers that don't place
# the locale lang first in header. However allowing any language seems to workaround the issue.
request.add_header('Accept-Language', '*')
return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)
@staticmethod
def _add_skip_wall(url):
parsed_url = compat_urlparse.urlparse(url)
@ -269,6 +256,19 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE):
'1080': ('80', '108'),
}
def _download_webpage(self, url_or_request, *args, **kwargs):
request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
else sanitized_Request(url_or_request))
# Accept-Language must be set explicitly to accept any language to avoid issues
# similar to https://github.com/ytdl-org/youtube-dl/issues/6797.
# Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
# should be imposed or not (from what I can see it just takes the first language
# ignoring the priority and requires it to correspond the IP). By the way this causes
# Crunchyroll to not work in georestriction cases in some browsers that don't place
# the locale lang first in header. However allowing any language seems to workaround the issue.
request.add_header('Accept-Language', '*')
return super(CrunchyrollBaseIE, self)._download_webpage(request, *args, **kwargs)
def _decrypt_subtitles(self, data, iv, id):
data = bytes_to_intlist(compat_b64decode(data))
iv = bytes_to_intlist(compat_b64decode(iv))
@ -661,9 +661,8 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
webpage = self._download_webpage(
self._add_skip_wall(url), show_id,
headers=self.geo_verification_headers())
title = self._html_search_regex(
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
webpage, 'title')
title = self._html_search_meta('name', webpage, default=None)
episode_paths = re.findall(
r'(?s)<li id="showview_videos_media_(\d+)"[^>]+>.*?<a href="([^"]+)"',
webpage)

5
youtube_dl/extractor/drtv.py
View File

@ -24,7 +24,7 @@ from ..utils import (
class DRTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio/ondemand)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio(?:/ondemand)?)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_GEO_BYPASS = False
_GEO_COUNTRIES = ['DK']
IE_NAME = 'drtv'
@ -80,6 +80,9 @@ class DRTVIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.dr.dk/radio/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9',
'only_matching': True,
}]
def _real_extract(self, url):

6
youtube_dl/extractor/extractors.py
View File

@ -745,7 +745,6 @@ from .nexx import (
NexxIE,
NexxEmbedIE,
)
from .nfb import NFBIE
from .nfl import NFLIE
from .nhk import NhkVodIE
from .nhl import NHLIE
@ -892,8 +891,9 @@ from .porncom import PornComIE
from .pornhd import PornHdIE
from .pornhub import (
PornHubIE,
PornHubPlaylistIE,
PornHubUserVideosIE,
PornHubUserIE,
PornHubPagedVideoListIE,
PornHubUserVideosUploadIE,
)
from .pornotube import PornotubeIE
from .pornovoisines import PornoVoisinesIE

69
youtube_dl/extractor/fusion.py
View File

@ -1,35 +1,84 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from .ooyala import OoyalaIE
from ..utils import (
determine_ext,
int_or_none,
mimetype2ext,
parse_iso8601,
)
class FusionIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?fusion\.(?:net|tv)/video/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?fusion\.(?:net|tv)/(?:video/|show/.+?\bvideo=)(?P<id>\d+)'
_TESTS = [{
'url': 'http://fusion.tv/video/201781/u-s-and-panamanian-forces-work-together-to-stop-a-vessel-smuggling-drugs/',
'info_dict': {
'id': 'ZpcWNoMTE6x6uVIIWYpHh0qQDjxBuq5P',
'id': '3145868',
'ext': 'mp4',
'title': 'U.S. and Panamanian forces work together to stop a vessel smuggling drugs',
'description': 'md5:0cc84a9943c064c0f46b128b41b1b0d7',
'duration': 140.0,
'timestamp': 1442589635,
'uploader': 'UNIVISON',
'upload_date': '20150918',
},
'params': {
'skip_download': True,
},
'add_ie': ['Ooyala'],
'add_ie': ['Anvato'],
}, {
'url': 'http://fusion.tv/video/201781',
'only_matching': True,
}, {
'url': 'https://fusion.tv/show/food-exposed-with-nelufar-hedayat/?ancla=full-episodes&video=588644',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._match_id(url)
video = self._download_json(
'https://platform.fusion.net/wp-json/fusiondotnet/v1/video/' + video_id, video_id)
ooyala_code = self._search_regex(
r'data-ooyala-id=(["\'])(?P<code>(?:(?!\1).)+)\1',
webpage, 'ooyala code', group='code')
info = {
'id': video_id,
'title': video['title'],
'description': video.get('excerpt'),
'timestamp': parse_iso8601(video.get('published')),
'series': video.get('show'),
}
return OoyalaIE._build_url_result(ooyala_code)
formats = []
src = video.get('src') or {}
for f_id, f in src.items():
for q_id, q in f.items():
q_url = q.get('url')
if not q_url:
continue
ext = determine_ext(q_url, mimetype2ext(q.get('type')))
if ext == 'smil':
formats.extend(self._extract_smil_formats(q_url, video_id, fatal=False))
elif f_id == 'm3u8-variant' or (ext == 'm3u8' and q_id == 'Variant'):
formats.extend(self._extract_m3u8_formats(
q_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
else:
formats.append({
'format_id': '-'.join([f_id, q_id]),
'url': q_url,
'width': int_or_none(q.get('width')),
'height': int_or_none(q.get('height')),
'tbr': int_or_none(self._search_regex(r'_(\d+)\.m(?:p4|3u8)', q_url, 'bitrate')),
'ext': 'mp4' if ext == 'm3u8' else ext,
'protocol': 'm3u8_native' if ext == 'm3u8' else 'https',
})
if formats:
self._sort_formats(formats)
info['formats'] = formats
else:
info.update({
'_type': 'url',
'url': 'anvato:uni:' + video['video_ids']['anvato'],
'ie_key': 'Anvato',
})
return info

7
youtube_dl/extractor/go.py
View File

@ -36,7 +36,7 @@ class GoIE(AdobePassIE):
'resource_id': 'DisneyXD',
}
}
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\
_VALID_URL = r'https?://(?:(?:(?P<sub_domain>%s)\.)?go|disneynow)\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\
% '|'.join(list(_SITE_INFO.keys()) + ['disneynow'])
_TESTS = [{
'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
@ -71,6 +71,9 @@ class GoIE(AdobePassIE):
# brand 008
'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
}, {
'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
}]
def _extract_videos(self, brand, video_id='-1', show_id='-1'):
@ -89,7 +92,7 @@ class GoIE(AdobePassIE):
# There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
# from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id',
default=None)
default=video_id)
if not site_info:
brand = self._search_regex(
(r'data-brand=\s*["\']\s*(\d+)',

112
youtube_dl/extractor/nfb.py
View File

@ -1,112 +0,0 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
determine_ext,
int_or_none,
qualities,
urlencode_postdata,
xpath_text,
)
class NFBIE(InfoExtractor):
IE_NAME = 'nfb'
IE_DESC = 'National Film Board of Canada'
_VALID_URL = r'https?://(?:www\.)?(?:nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)'
_TEST = {
'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny',
'info_dict': {
'id': 'qallunaat_why_white_people_are_funny',
'ext': 'flv',
'title': 'Qallunaat! Why White People Are Funny ',
'description': 'md5:6b8e32dde3abf91e58857b174916620c',
'duration': 3128,
'creator': 'Mark Sandiford',
'uploader': 'Mark Sandiford',
},
'params': {
# rtmp download
'skip_download': True,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
config = self._download_xml(
'https://www.nfb.ca/film/%s/player_config' % video_id,
video_id, 'Downloading player config XML',
data=urlencode_postdata({'getConfig': 'true'}),
headers={
'Content-Type': 'application/x-www-form-urlencoded',
'X-NFB-Referer': 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf'
})
title, description, thumbnail, duration, uploader, author = [None] * 6
thumbnails, formats = [[]] * 2
subtitles = {}
for media in config.findall('./player/stream/media'):
if media.get('type') == 'posterImage':
quality_key = qualities(('low', 'high'))
thumbnails = []
for asset in media.findall('assets/asset'):
asset_url = xpath_text(asset, 'default/url', default=None)
if not asset_url:
continue
quality = asset.get('quality')
thumbnails.append({
'url': asset_url,
'id': quality,
'preference': quality_key(quality),
})
elif media.get('type') == 'video':
title = xpath_text(media, 'title', fatal=True)
for asset in media.findall('assets/asset'):
quality = asset.get('quality')
height = int_or_none(self._search_regex(
r'^(\d+)[pP]$', quality or '', 'height', default=None))
for node in asset:
streamer = xpath_text(node, 'streamerURI', default=None)
if not streamer:
continue
play_path = xpath_text(node, 'url', default=None)
if not play_path:
continue
formats.append({
'url': streamer,
'app': streamer.split('/', 3)[3],
'play_path': play_path,
'rtmp_live': False,
'ext': 'flv',
'format_id': '%s-%s' % (node.tag, quality) if quality else node.tag,
'height': height,
})
self._sort_formats(formats)
description = clean_html(xpath_text(media, 'description'))
uploader = xpath_text(media, 'author')
duration = int_or_none(media.get('duration'))
for subtitle in media.findall('./subtitles/subtitle'):
subtitle_url = xpath_text(subtitle, 'url', default=None)
if not subtitle_url:
continue
lang = xpath_text(subtitle, 'lang', default='en')
subtitles.setdefault(lang, []).append({
'url': subtitle_url,
'ext': (subtitle.get('format') or determine_ext(subtitle_url)).lower(),
})
return {
'id': video_id,
'title': title,
'description': description,
'thumbnails': thumbnails,
'duration': duration,
'creator': uploader,
'uploader': uploader,
'formats': formats,
'subtitles': subtitles,
}

5
youtube_dl/extractor/openload.py
View File

@ -244,7 +244,7 @@ class PhantomJSwrapper(object):
class OpenloadIE(InfoExtractor):
_DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|live|space|services|website)|oladblock\.(?:services|xyz|me)|openloed\.co)'
_DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website)|oladblock\.(?:services|xyz|me)|openloed\.co)'
_VALID_URL = r'''(?x)
https?://
(?P<host>
@ -363,6 +363,9 @@ class OpenloadIE(InfoExtractor):
}, {
'url': 'https://oload.website/embed/drTBl1aOTvk/',
'only_matching': True,
}, {
'url': 'https://oload.life/embed/oOzZjNPw9Dc/',
'only_matching': True,
}, {
'url': 'https://oladblock.services/f/b8NWEgkqNLI/',
'only_matching': True,

207
youtube_dl/extractor/pornhub.py
View File

@ -372,37 +372,92 @@ class PornHubPlaylistBaseIE(PornHubBaseIE):
entries, playlist_id, title, playlist.get('description'))
class PornHubPlaylistIE(PornHubPlaylistBaseIE):
_VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/playlist/(?P<id>\d+)'
class PornHubUserIE(PornHubPlaylistBaseIE):
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
_TESTS = [{
'url': 'http://www.pornhub.com/playlist/4667351',
'info_dict': {
'id': '4667351',
'title': 'Nataly Hot',
},
'playlist_mincount': 2,
'url': 'https://www.pornhub.com/model/zoe_ph',
'playlist_mincount': 118,
}, {
'url': 'https://de.pornhub.com/playlist/4667351',
'url': 'https://www.pornhub.com/pornstar/liz-vicious',
'info_dict': {
'id': 'liz-vicious',
},
'playlist_mincount': 118,
}, {
'url': 'https://www.pornhub.com/users/russianveet69',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/channels/povd',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('id')
return self.url_result(
'%s/videos' % mobj.group('url'), ie=PornHubPagedVideoListIE.ie_key(),
video_id=user_id)
class PornHubUserVideosIE(PornHubPlaylistBaseIE):
_VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos'
class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
item_id = mobj.group('id')
page = int_or_none(self._search_regex(
r'\bpage=(\d+)', url, 'page', default=None))
page_url = self._make_page_url(url)
entries = []
for page_num in (page, ) if page is not None else itertools.count(1):
try:
webpage = self._download_webpage(
page_url, item_id, 'Downloading page %d' % page_num,
query={'page': page_num})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
break
raise
page_entries = self._extract_entries(webpage, host)
if not page_entries:
break
entries.extend(page_entries)
if not self._has_more(webpage):
break
return self.playlist_result(orderedSet(entries), item_id)
class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
_VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
_TESTS = [{
'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
'info_dict': {
'id': 'zoe_ph',
},
'playlist_mincount': 171,
'url': 'https://www.pornhub.com/model/zoe_ph/videos',
'only_matching': True,
}, {
'url': 'http://www.pornhub.com/users/rushandlia/videos',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
'info_dict': {
'id': 'pornstar/jenny-blighe/videos',
},
'playlist_mincount': 149,
}, {
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
'info_dict': {
'id': 'pornstar/jenny-blighe/videos',
},
'playlist_mincount': 40,
}, {
# default sorting as Top Rated Videos
'url': 'https://www.pornhub.com/channels/povd/videos',
'info_dict': {
'id': 'povd',
'id': 'channels/povd/videos',
},
'playlist_mincount': 293,
}, {
@ -421,31 +476,107 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/model/jayndrea/videos/upload',
# Most Viewed Videos
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
# Top Rated Videos
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr',
'only_matching': True,
}, {
# Longest Videos
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg',
'only_matching': True,
}, {
# Newest Videos
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/video',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/video?page=3',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/video/search?search=123',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/categories/teen',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/categories/teen?page=3',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/hd',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/hd?page=3',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/described-video',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/described-video?page=2',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/playlist/44121572',
'info_dict': {
'id': 'playlist/44121572',
},
'playlist_mincount': 132,
}, {
'url': 'https://www.pornhub.com/playlist/4667351',
'only_matching': True,
}, {
'url': 'https://de.pornhub.com/playlist/4667351',
'only_matching': True,
}]
def _real_extract(self, url):
@classmethod
def suitable(cls, url):
return (False
if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
else super(PornHubPagedVideoListIE, cls).suitable(url))
def _make_page_url(self, url):
return url
@staticmethod
def _has_more(webpage):
return re.search(
r'''(?x)
<li[^>]+\bclass=["\']page_next|
<link[^>]+\brel=["\']next|
<button[^>]+\bid=["\']moreDataBtn
''', webpage) is not None
class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
_TESTS = [{
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
'info_dict': {
'id': 'jenny-blighe',
},
'playlist_mincount': 129,
}, {
'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
'only_matching': True,
}]
def _make_page_url(self, url):
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
user_id = mobj.group('id')
return '%s/ajax' % mobj.group('url')
entries = []
for page_num in itertools.count(1):
try:
webpage = self._download_webpage(
url, user_id, 'Downloading page %d' % page_num,
query={'page': page_num})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
break
raise
page_entries = self._extract_entries(webpage, host)
if not page_entries:
break
entries.extend(page_entries)
return self.playlist_result(entries, user_id)
@staticmethod
def _has_more(webpage):
return True

6
youtube_dl/extractor/sixplay.py
View File

@ -19,7 +19,7 @@ from ..utils import (
class SixPlayIE(InfoExtractor):
IE_NAME = '6play'
_VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay\.be|play\.rtl\.hr)/.+?-c_)(?P<id>[0-9]+)'
_VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay\.be|play\.rtl\.hr|rtlmost\.hu)/.+?-c_)(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051',
'md5': '31fcd112637baa0c2ab92c4fcd8baf27',
@ -35,6 +35,9 @@ class SixPlayIE(InfoExtractor):
}, {
'url': 'https://play.rtl.hr/pj-masks-p_9455/epizoda-34-sezona-1-catboyevo-cudo-na-dva-kotaca-c_11984989',
'only_matching': True,
}, {
'url': 'https://www.rtlmost.hu/megtorve-p_14167/megtorve-6-resz-c_12397787',
'only_matching': True,
}]
def _real_extract(self, url):
@ -43,6 +46,7 @@ class SixPlayIE(InfoExtractor):
'6play.fr': ('6play', 'm6web'),
'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'),
'play.rtl.hr': ('rtlhr_rtl_play', 'rtlhr'),
'rtlmost.hu': ('rtlhu_rtl_most', 'rtlhu'),
}.get(domain, ('6play', 'm6web'))
data = self._download_json(

40
youtube_dl/extractor/tf1.py
View File

@ -2,6 +2,7 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
class TF1IE(InfoExtractor):
@ -43,12 +44,49 @@ class TF1IE(InfoExtractor):
}, {
'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html',
'only_matching': True,
}, {
'url': 'https://www.tf1.fr/tmc/quotidien-avec-yann-barthes/videos/quotidien-premiere-partie-11-juin-2019.html',
'info_dict': {
'id': '13641379',
'ext': 'mp4',
'title': 'md5:f392bc52245dc5ad43771650c96fb620',
'description': 'md5:44bc54f0a21322f5b91d68e76a544eae',
'upload_date': '20190611',
},
'params': {
# Sometimes wat serves the whole file with the --test option
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
wat_id = None
data = self._parse_json(
self._search_regex(
r'__APOLLO_STATE__\s*=\s*({.+?})\s*(?:;|</script>)', webpage,
'data', default='{}'), video_id, fatal=False)
if data:
try:
wat_id = next(
video.get('streamId')
for key, video in data.items()
if isinstance(video, dict)
and video.get('slug') == video_id)
if not isinstance(wat_id, compat_str) or not wat_id.isdigit():
wat_id = None
except StopIteration:
pass
if not wat_id:
wat_id = self._html_search_regex(
r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
(r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
r'(["\']?)streamId\1\s*:\s*(["\']?)(?P<id>\d+)\2'),
webpage, 'wat id', group='id')
return self.url_result('wat:%s' % wat_id, 'Wat')

2
youtube_dl/extractor/toutv.py
View File

@ -38,7 +38,7 @@ class TouTvIE(RadioCanadaIE):
'url': 'https://ici.tou.tv/l-age-adulte/S01C501',
'only_matching': True,
}]
_CLIENT_KEY = '4dd36440-09d5-4468-8923-b6d91174ad36'
_CLIENT_KEY = '90505c8d-9c34-4f34-8da1-3a85bdc6d4f4'
def _real_initialize(self):
email, password = self._get_login_info()

55
youtube_dl/extractor/vimeo.py
View File

@ -16,7 +16,6 @@ from ..utils import (
determine_ext,
ExtractorError,
js_to_json,
InAdvancePagedList,
int_or_none,
merge_dicts,
NO_DEFAULT,
@ -814,7 +813,8 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
return '%s/videos/page:%d/' % (base_url, pagenum)
def _extract_list_title(self, webpage):
return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
return self._TITLE or self._html_search_regex(
self._TITLE_RE, webpage, 'list title', fatal=False)
def _login_list_password(self, page_url, list_id, webpage):
login_form = self._search_regex(
@ -955,7 +955,7 @@ class VimeoGroupsIE(VimeoAlbumIE):
}]
def _extract_list_title(self, webpage):
return self._og_search_title(webpage)
return self._og_search_title(webpage, fatal=False)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@ -1065,7 +1065,7 @@ class VimeoWatchLaterIE(VimeoChannelIE):
return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
class VimeoLikesIE(InfoExtractor):
class VimeoLikesIE(VimeoChannelIE):
_VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
IE_NAME = 'vimeo:likes'
IE_DESC = 'Vimeo user likes'
@ -1073,55 +1073,20 @@ class VimeoLikesIE(InfoExtractor):
'url': 'https://vimeo.com/user755559/likes/',
'playlist_mincount': 293,
'info_dict': {
'id': 'user755559_likes',
'description': 'See all the videos urza likes',
'title': 'Videos urza likes',
'id': 'user755559',
'title': 'urza’s Likes',
},
}, {
'url': 'https://vimeo.com/stormlapse/likes',
'only_matching': True,
}]
def _page_url(self, base_url, pagenum):
return '%s/page:%d/' % (base_url, pagenum)
def _real_extract(self, url):
user_id = self._match_id(url)
webpage = self._download_webpage(url, user_id)
page_count = self._int(
self._search_regex(
r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
.*?</a></li>\s*<li\s+class="pagination_next">
''', webpage, 'page count', default=1),
'page count', fatal=True)
PAGE_SIZE = 12
title = self._html_search_regex(
r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
description = self._html_search_meta('description', webpage)
def _get_page(idx):
page_url = 'https://vimeo.com/%s/likes/page:%d/sort:date' % (
user_id, idx + 1)
webpage = self._download_webpage(
page_url, user_id,
note='Downloading page %d/%d' % (idx + 1, page_count))
video_list = self._search_regex(
r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
webpage, 'video content')
paths = re.findall(
r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
for path in paths:
yield {
'_type': 'url',
'url': compat_urlparse.urljoin(page_url, path),
}
pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
return {
'_type': 'playlist',
'id': '%s_likes' % user_id,
'title': title,
'description': description,
'entries': pl,
}
return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
class VHXEmbedIE(InfoExtractor):

32
youtube_dl/extractor/youtube.py
View File

@ -500,6 +500,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# RTMP (unnamed)
'_rtmp': {'protocol': 'rtmp'},
# av01 video only formats sometimes served with "unknown" codecs
'394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
'395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
'396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
'397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
}
_SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
@ -1306,11 +1312,18 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _parse_sig_js(self, jscode):
funcname = self._search_regex(
(r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
(r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
# Obsolete patterns
r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
jscode, 'Initial JS player signature function name', group='sig')
jsi = JSInterpreter(jscode)
@ -1575,8 +1588,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return video_id
def _extract_annotations(self, video_id):
url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
return self._download_webpage(
'https://www.youtube.com/annotations_invideo', video_id,
note='Downloading annotations',
errnote='Unable to download video annotations', fatal=False,
query={
'features': 1,
'legacy': 1,
'video_id': video_id,
})
@staticmethod
def _extract_chapters(description, duration):

11
youtube_dl/utils.py
View File

@ -2529,7 +2529,7 @@ def parse_codecs(codecs_str):
vcodec, acodec = None, None
for full_codec in splited_codecs:
codec = full_codec.split('.')[0]
if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1', 'av01'):
if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1', 'av01', 'theora'):
if not vcodec:
vcodec = full_codec
elif codec in ('mp4a', 'opus', 'vorbis', 'mp3', 'aac', 'ac-3', 'ec-3', 'eac3', 'dtsc', 'dtse', 'dtsh', 'dtsl'):
@ -2540,13 +2540,8 @@ def parse_codecs(codecs_str):
if not vcodec and not acodec:
if len(splited_codecs) == 2:
return {
'vcodec': vcodec,
'acodec': acodec,
}
elif len(splited_codecs) == 1:
return {
'vcodec': 'none',
'acodec': vcodec,
'vcodec': splited_codecs[0],
'acodec': splited_codecs[1],
}
else:
return {

2
youtube_dl/version.py
View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2019.06.08'
__version__ = '2019.06.27'