Compare commits

...

42 Commits

Author SHA1 Message Date
Sergey M․
0a04e03a02 release 2021.02.22 2021-02-22 02:42:16 +07:00
Sergey M․
44b2d5f5fc [ChangeLog] Actualize
[ci skip]
2021-02-22 02:40:00 +07:00
Sergey M․
aa9118a373 [apa] Improve extraction (closes #27750) 2021-02-22 02:29:50 +07:00
Adrian Heine
36abc16c3c [apa] Fix extraction 2021-02-22 02:28:28 +07:00
Sergey M․
919d764600 [youporn] Skip test 2021-02-21 23:21:38 +07:00
piplongrun
696183e133 [youporn] Extract duration (#28019)
Co-authored-by: Sergey M <dstftw@gmail.com>
2021-02-21 23:19:37 +07:00
SirCipherz
f90d825a6b [peertube] Add support for canard.tube (#28190) 2021-02-21 23:05:33 +07:00
Remita Amine
3037ab00c7 [youtube] fixup m4a_dash formats(closes #28165) 2021-02-21 10:31:27 +01:00
Isaac-the-Man
21e872b19a [samplefocus] Add new extractor(closes #27763) 2021-02-20 10:55:19 +01:00
Remita Amine
cf2dbec630 [vimeo] add support for unlisted video source format extraction 2021-02-19 21:13:56 +01:00
Remita Amine
b92bb0e02a [viki] improve extraction(closes #26522)(closes #28203)
- extract uploader_url and episode_number
- report login required error
- extract 480p formats
- fix API v4 calls
2021-02-19 16:00:22 +01:00
Remita Amine
40edffae3d [ninegag] unscape title(#28201) 2021-02-19 11:55:40 +01:00
Sergey M․
9fc5eafb8e [youtube] Improve _VALID_URL (refs #28193) 2021-02-18 04:59:56 +07:00
bopol
08c2fbb844 [youtube] Add support for redirect.invidious.io (#28193)
Co-authored-by: Sergey M <dstftw@gmail.com>
2021-02-18 04:29:32 +07:00
Remita Amine
3997efb65e [dplay] add support for de.hgtv.com (closes #28182) 2021-02-17 19:50:04 +01:00
Remita Amine
a7356dffe9 [dplay] Add support for discoveryplus.com (closes #24698) 2021-02-17 18:33:33 +01:00
dmsummers
e20ec43094 [simplecast] Add new extractor(closes #24107) 2021-02-17 14:53:23 +01:00
PrinceOfPuppers
70baa7bfae [test_youtube_lists] Actualize youtube flat playlist test (closes #28045) 2021-02-17 04:58:54 +07:00
PrinceOfPuppers
8980f53b42 [youtube] Fix uploader extraction in flat playlist mode (#28045) 2021-02-17 04:21:33 +07:00
Sergey M․
a363fb5d28 [yandexmusic:playlist] Request missing tracks in chunks (closes #27355, closes #28184) 2021-02-17 04:03:54 +07:00
Max
646052e416 [postprocessor/embedthumbnail] Recognize atomicparsley binary in lowercase (#28112) 2021-02-17 03:22:51 +07:00
Stephen Stair
844e4cbc54 [storyfire] Add new extractor(closes #25628)(closes #26349) 2021-02-16 21:14:43 +01:00
Remita Amine
56c63c8c02 [zhihu] Add new extractor(closes #28177) 2021-02-16 10:08:43 +01:00
Sergey M․
07eb8f1916 [youtube] Fix controversial videos when authenticated with cookies (closes #28174) 2021-02-16 05:57:53 +07:00
Remita Amine
4b5410c5c8 [ccma] fix timestamp parsing in python 2 2021-02-15 13:06:54 +01:00
Remita Amine
be2e9b76ee [videopress] add support for video.wordpress.com 2021-02-14 22:10:06 +01:00
Remita Amine
d8085580f6 [kakao] improve info extraction and detect geo restriction(closes #26577) 2021-02-14 19:48:26 +01:00
Remita Amine
6d32c6c6d3 [xboxclips] fix extraction(closes #27151) 2021-02-14 16:22:45 +01:00
Sergey M․
f94d764993 [ard] Improve formats extraction (closes #28155) 2021-02-14 05:03:15 +07:00
Kevin Velghe
f28f1b4d6e [canvas] Add new extractor for Dagelijkse Kost (#28119) 2021-02-11 08:04:16 +00:00
Sergey M․
360d5f0daa release 2021.02.10 2021-02-10 22:34:47 +07:00
Sergey M․
cd493c5adc [ChangeLog] Actualize
[ci skip]
2021-02-10 22:32:25 +07:00
Sergey M․
a4c7ed6b1e [youtube:tab] Improve grid continuation extraction (closes #28130) 2021-02-10 22:28:58 +07:00
Remita Amine
7f8b8bc418 [ign] fix extraction(closes #24771) 2021-02-08 15:58:20 +01:00
Sergey M․
311ebdd9a5 [xhamster] Extract formats from xplayer settings and extract filesizes (closes #28114) 2021-02-08 15:47:12 +07:00
Remita Amine
99c68db0a8 [youtube] add support phone/tablet JS player(closes #26424) 2021-02-08 09:20:28 +01:00
Sergey M․
5fc53690cb [archiveorg] Fix and improve extraction (closes #21330, closes #23586, closes #25277, closes #26780, closes #27109, closes #27236, closes #28063) 2021-02-07 20:34:41 +07:00
Sergey M․
7a9161578e [cda] Detect geo restricted videos (refs #28106) 2021-02-07 19:18:40 +07:00
Adrian Heine né Lang
2405854705 [urplay] Fix extraction (closes #28073) (#28074) 2021-02-07 02:46:05 +07:00
Sergey M․
0cf09c2b41 [youtube] Fix release date extraction (closes #28094) 2021-02-07 02:17:03 +07:00
Sergey M․
0156ce95c5 [youtube] Extract abr and vbr (closes #28100) 2021-02-07 02:03:47 +07:00
Remita Amine
1641b13232 [youtube] skip OTF formats(#28070) 2021-02-04 13:05:35 +01:00
37 changed files with 1493 additions and 486 deletions

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 2021.02.04.1. 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 2021.02.22. 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 **2021.02.04.1**
- [ ] I've verified that I'm running youtube-dl version **2021.02.22**
- [ ] 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 2021.02.04.1
[debug] youtube-dl version 2021.02.22
[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: {}

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 2021.02.04.1. 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 2021.02.22. 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 **2021.02.04.1**
- [ ] I've verified that I'm running youtube-dl version **2021.02.22**
- [ ] 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

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 2021.02.04.1. 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 2021.02.22. 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 **2021.02.04.1**
- [ ] I've verified that I'm running youtube-dl version **2021.02.22**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones

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 2021.02.04.1. 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 2021.02.22. 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 **2021.02.04.1**
- [ ] I've verified that I'm running youtube-dl version **2021.02.22**
- [ ] 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 2021.02.04.1
[debug] youtube-dl version 2021.02.22
[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: {}

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 2021.02.04.1. 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 2021.02.22. 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 **2021.02.04.1**
- [ ] I've verified that I'm running youtube-dl version **2021.02.22**
- [ ] I've searched the bugtracker for similar feature requests including closed ones

View File

@@ -1,3 +1,57 @@
version 2021.02.22
Core
+ [postprocessor/embedthumbnail] Recognize atomicparsley binary in lowercase
(#28112)
Extractors
* [apa] Fix and improve extraction (#27750)
+ [youporn] Extract duration (#28019)
+ [peertube] Add support for canard.tube (#28190)
* [youtube] Fixup m4a_dash formats (#28165)
+ [samplefocus] Add support for samplefocus.com (#27763)
+ [vimeo] Add support for unlisted video source format extraction
* [viki] Improve extraction (#26522, #28203)
* Extract uploader URL and episode number
* Report login required error
+ Extract 480p formats
* Fix API v4 calls
* [ninegag] Unescape title (#28201)
* [youtube] Improve URL regular expression (#28193)
+ [youtube] Add support for redirect.invidious.io (#28193)
+ [dplay] Add support for de.hgtv.com (#28182)
+ [dplay] Add support for discoveryplus.com (#24698)
+ [simplecast] Add support for simplecast.com (#24107)
* [youtube] Fix uploader extraction in flat playlist mode (#28045)
* [yandexmusic:playlist] Request missing tracks in chunks (#27355, #28184)
+ [storyfire] Add support for storyfire.com (#25628, #26349)
+ [zhihu] Add support for zhihu.com (#28177)
* [youtube] Fix controversial videos when authenticated with cookies (#28174)
* [ccma] Fix timestamp parsing in python 2
+ [videopress] Add support for video.wordpress.com
* [kakao] Improve info extraction and detect geo restriction (#26577)
* [xboxclips] Fix extraction (#27151)
* [ard] Improve formats extraction (#28155)
+ [canvas] Add support for dagelijksekost.een.be (#28119)
version 2021.02.10
Extractors
* [youtube:tab] Improve grid continuation extraction (#28130)
* [ign] Fix extraction (#24771)
+ [xhamster] Extract format filesize
+ [xhamster] Extract formats from xplayer settings (#28114)
+ [youtube] Add support phone/tablet JS player (#26424)
* [archiveorg] Fix and improve extraction (#21330, #23586, #25277, #26780,
#27109, #27236, #28063)
+ [cda] Detect geo restricted videos (#28106)
* [urplay] Fix extraction (#28073, #28074)
* [youtube] Fix release date extraction (#28094)
+ [youtube] Extract abr and vbr (#28100)
* [youtube] Skip OTF formats (#28070)
version 2021.02.04.1
Extractors

View File

@@ -1,6 +1,5 @@
# Supported sites
- **1tv**: Первый канал
- **1up.com**
- **20min**
- **220.ro**
- **23video**
@@ -213,6 +212,7 @@
- **curiositystream**
- **curiositystream:collection**
- **CWTV**
- **DagelijkseKost**: dagelijksekost.een.be
- **DailyMail**
- **dailymotion**
- **dailymotion:playlist**
@@ -234,6 +234,7 @@
- **DiscoveryGo**
- **DiscoveryGoPlaylist**
- **DiscoveryNetworksDe**
- **DiscoveryPlus**
- **DiscoveryVR**
- **Disney**
- **dlive:stream**
@@ -354,6 +355,7 @@
- **HentaiStigma**
- **hetklokhuis**
- **hgtv.com:show**
- **HGTVDe**
- **HiDive**
- **HistoricFilms**
- **history:player**
@@ -376,6 +378,8 @@
- **HungamaSong**
- **Hypem**
- **ign.com**
- **IGNArticle**
- **IGNVideo**
- **IHeartRadio**
- **iheartradio:podcast**
- **imdb**: Internet Movie Database trailers
@@ -676,7 +680,6 @@
- **parliamentlive.tv**: UK parliament videos
- **Patreon**
- **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC)
- **pcmag**
- **PearVideo**
- **PeerTube**
- **People**
@@ -803,6 +806,7 @@
- **safari:course**: safaribooksonline.com online courses
- **SAKTV**
- **SaltTV**
- **SampleFocus**
- **Sapo**: SAPO Vídeos
- **savefrom.net**
- **SBS**: sbs.com.au
@@ -825,6 +829,9 @@
- **ShahidShow**
- **Shared**: shared.sx
- **ShowRoomLive**
- **simplecast**
- **simplecast:episode**
- **simplecast:podcast**
- **Sina**
- **sky.it**
- **sky:news**
@@ -877,6 +884,9 @@
- **Steam**
- **Stitcher**
- **StitcherShow**
- **StoryFire**
- **StoryFireSeries**
- **StoryFireUser**
- **Streamable**
- **streamcloud.eu**
- **StreamCZ**
@@ -1198,5 +1208,6 @@
- **ZattooLive**
- **ZDF**
- **ZDFChannel**
- **Zhihu**
- **zingmp3**: mp3.zing.vn
- **Zype**

View File

@@ -12,6 +12,7 @@ from test.helper import FakeYDL
from youtube_dl.extractor import (
YoutubePlaylistIE,
YoutubeTabIE,
YoutubeIE,
)
@@ -57,14 +58,22 @@ class TestYoutubeLists(unittest.TestCase):
entries = result['entries']
self.assertEqual(len(entries), 100)
def test_youtube_flat_playlist_titles(self):
def test_youtube_flat_playlist_extraction(self):
dl = FakeYDL()
dl.params['extract_flat'] = True
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PL-KKIb8rvtMSrAO9YFbeM6UQrAqoFTUWv')
ie = YoutubeTabIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc')
self.assertIsPlaylist(result)
for entry in result['entries']:
self.assertTrue(entry.get('title'))
entries = list(result['entries'])
self.assertTrue(len(entries) == 1)
video = entries[0]
self.assertEqual(video['_type'], 'url_transparent')
self.assertEqual(video['ie_key'], 'Youtube')
self.assertEqual(video['id'], 'BaW_jenozKc')
self.assertEqual(video['url'], 'BaW_jenozKc')
self.assertEqual(video['title'], 'youtube-dl test video "\'/\\ä↭𝕐')
self.assertEqual(video['duration'], 10)
self.assertEqual(video['uploader'], 'Philipp Hagemeister')
if __name__ == '__main__':

View File

@@ -19,55 +19,46 @@ from youtube_dl.compat import compat_str, compat_urlretrieve
_TESTS = [
(
'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js',
'js',
86,
'>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js',
'js',
85,
'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js',
'js',
90,
']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl0Cbn9e.js',
'js',
84,
'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVW@YZ!"#$%&\'()*+,-./:;<=',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js',
'js',
'2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA',
'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
'js',
84,
'123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>'
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl9FYC6l.js',
'js',
83,
'123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F'
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflCGk6yw/html5player.js',
'js',
'4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288',
'82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B'
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js',
'js',
'312AA52209E3623129A412D56A40F11CB0AF14AE.3EE09501CB14E3BCDC3B2AE808BF3F1D14E7FBF12',
'112AA5220913623229A412D56A40F11CB0AF14AE.3EE0950FCB14EEBCDC3B2AE808BF331D14E7FBF3',
)
@@ -78,6 +69,10 @@ class TestPlayerInfo(unittest.TestCase):
def test_youtube_extract_player_info(self):
PLAYER_URLS = (
('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/en_US/base.js', '64dddad9'),
('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/fr_FR/base.js', '64dddad9'),
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-en_US.vflset/base.js', '64dddad9'),
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-de_DE.vflset/base.js', '64dddad9'),
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-tablet-en_US.vflset/base.js', '64dddad9'),
# obsolete
('https://www.youtube.com/yts/jsbin/player_ias-vfle4-e03/en_US/base.js', 'vfle4-e03'),
('https://www.youtube.com/yts/jsbin/player_ias-vfl49f_g4/en_US/base.js', 'vfl49f_g4'),
@@ -100,13 +95,13 @@ class TestSignature(unittest.TestCase):
os.mkdir(self.TESTDATA_DIR)
def make_tfunc(url, stype, sig_input, expected_sig):
def make_tfunc(url, sig_input, expected_sig):
m = re.match(r'.*-([a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.[a-z]+$', url)
assert m, '%r should follow URL format' % url
test_id = m.group(1)
def test_func(self):
basename = 'player-%s.%s' % (test_id, stype)
basename = 'player-%s.js' % test_id
fn = os.path.join(self.TESTDATA_DIR, basename)
if not os.path.exists(fn):
@@ -114,22 +109,16 @@ def make_tfunc(url, stype, sig_input, expected_sig):
ydl = FakeYDL()
ie = YoutubeIE(ydl)
if stype == 'js':
with io.open(fn, encoding='utf-8') as testf:
jscode = testf.read()
func = ie._parse_sig_js(jscode)
else:
assert stype == 'swf'
with open(fn, 'rb') as testf:
swfcode = testf.read()
func = ie._parse_sig_swf(swfcode)
with io.open(fn, encoding='utf-8') as testf:
jscode = testf.read()
func = ie._parse_sig_js(jscode)
src_sig = (
compat_str(string.printable[:sig_input])
if isinstance(sig_input, int) else sig_input)
got_sig = func(src_sig)
self.assertEqual(got_sig, expected_sig)
test_func.__name__ = str('test_signature_' + stype + '_' + test_id)
test_func.__name__ = str('test_signature_js_' + test_id)
setattr(TestSignature, test_func.__name__, test_func)

View File

@@ -6,25 +6,21 @@ import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
js_to_json,
int_or_none,
url_or_none,
)
class APAIE(InfoExtractor):
_VALID_URL = r'https?://[^/]+\.apa\.at/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
_VALID_URL = r'(?P<base_url>https?://[^/]+\.apa\.at)/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
_TESTS = [{
'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
'md5': '2b12292faeb0a7d930c778c7a5b4759b',
'info_dict': {
'id': 'jjv85FdZ',
'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'ext': 'mp4',
'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 254,
'timestamp': 1519211149,
'upload_date': '20180221',
},
}, {
'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
@@ -46,9 +42,11 @@ class APAIE(InfoExtractor):
webpage)]
def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
video_id, base_url = mobj.group('id', 'base_url')
webpage = self._download_webpage(url, video_id)
webpage = self._download_webpage(
'%s/player/%s' % (base_url, video_id), video_id)
jwplatform_id = self._search_regex(
r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
@@ -59,16 +57,18 @@ class APAIE(InfoExtractor):
'jwplatform:' + jwplatform_id, ie='JWPlatform',
video_id=video_id)
sources = self._parse_json(
self._search_regex(
r'sources\s*=\s*(\[.+?\])\s*;', webpage, 'sources'),
video_id, transform_source=js_to_json)
def extract(field, name=None):
return self._search_regex(
r'\b%s["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % field,
webpage, name or field, default=None, group='value')
title = extract('title') or video_id
description = extract('description')
thumbnail = extract('poster', 'thumbnail')
formats = []
for source in sources:
if not isinstance(source, dict):
continue
source_url = url_or_none(source.get('file'))
for format_id in ('hls', 'progressive'):
source_url = url_or_none(extract(format_id))
if not source_url:
continue
ext = determine_ext(source_url)
@@ -77,18 +77,19 @@ class APAIE(InfoExtractor):
source_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
height = int_or_none(self._search_regex(
r'(\d+)\.mp4', source_url, 'height', default=None))
formats.append({
'url': source_url,
'format_id': format_id,
'height': height,
})
self._sort_formats(formats)
thumbnail = self._search_regex(
r'image\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'thumbnail', fatal=False, group='url')
return {
'id': video_id,
'title': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'formats': formats,
}

View File

@@ -2,15 +2,17 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
unified_strdate,
clean_html,
extract_attributes,
unified_strdate,
unified_timestamp,
)
class ArchiveOrgIE(InfoExtractor):
IE_NAME = 'archive.org'
IE_DESC = 'archive.org videos'
_VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$'
_VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'md5': '8af1d4cf447933ed3c7f4871162602db',
@@ -19,8 +21,11 @@ class ArchiveOrgIE(InfoExtractor):
'ext': 'ogg',
'title': '1968 Demo - FJCC Conference Presentation Reel #1',
'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
'upload_date': '19681210',
'uploader': 'SRI International'
'creator': 'SRI International',
'release_date': '19681210',
'uploader': 'SRI International',
'timestamp': 1268695290,
'upload_date': '20100315',
}
}, {
'url': 'https://archive.org/details/Cops1922',
@@ -29,22 +34,43 @@ class ArchiveOrgIE(InfoExtractor):
'id': 'Cops1922',
'ext': 'mp4',
'title': 'Buster Keaton\'s "Cops" (1922)',
'description': 'md5:89e7c77bf5d965dd5c0372cfb49470f6',
'description': 'md5:43a603fd6c5b4b90d12a96b921212b9c',
'timestamp': 1387699629,
'upload_date': '20131222',
}
}, {
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'only_matching': True,
}, {
'url': 'https://archive.org/details/MSNBCW_20131125_040000_To_Catch_a_Predator/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://archive.org/embed/' + video_id, video_id)
jwplayer_playlist = self._parse_json(self._search_regex(
r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
webpage, 'jwplayer playlist'), video_id)
info = self._parse_jwplayer_data(
{'playlist': jwplayer_playlist}, video_id, base_url=url)
playlist = None
play8 = self._search_regex(
r'(<[^>]+\bclass=["\']js-play8-playlist[^>]+>)', webpage,
'playlist', default=None)
if play8:
attrs = extract_attributes(play8)
playlist = attrs.get('value')
if not playlist:
# Old jwplayer fallback
playlist = self._search_regex(
r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
webpage, 'jwplayer playlist', default='[]')
jwplayer_playlist = self._parse_json(playlist, video_id, fatal=False)
if jwplayer_playlist:
info = self._parse_jwplayer_data(
{'playlist': jwplayer_playlist}, video_id, base_url=url)
else:
# HTML5 media fallback
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
info['id'] = video_id
def get_optional(metadata, field):
return metadata.get(field, [None])[0]
@@ -58,8 +84,12 @@ class ArchiveOrgIE(InfoExtractor):
'description': clean_html(get_optional(metadata, 'description')),
})
if info.get('_type') != 'playlist':
creator = get_optional(metadata, 'creator')
info.update({
'uploader': get_optional(metadata, 'creator'),
'upload_date': unified_strdate(get_optional(metadata, 'date')),
'creator': creator,
'release_date': unified_strdate(get_optional(metadata, 'date')),
'uploader': get_optional(metadata, 'publisher') or creator,
'timestamp': unified_timestamp(get_optional(metadata, 'publicdate')),
'language': get_optional(metadata, 'language'),
})
return info

View File

@@ -284,20 +284,42 @@ class ARDIE(InfoExtractor):
formats = []
for a in video_node.findall('.//asset'):
file_name = xpath_text(a, './fileName', default=None)
if not file_name:
continue
format_type = a.attrib.get('type')
format_url = url_or_none(file_name)
if format_url:
ext = determine_ext(file_name)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, display_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=format_type or 'hls', fatal=False))
continue
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(format_url, {'hdcore': '3.7.0'}),
display_id, f4m_id=format_type or 'hds', fatal=False))
continue
f = {
'format_id': a.attrib['type'],
'width': int_or_none(a.find('./frameWidth').text),
'height': int_or_none(a.find('./frameHeight').text),
'vbr': int_or_none(a.find('./bitrateVideo').text),
'abr': int_or_none(a.find('./bitrateAudio').text),
'vcodec': a.find('./codecVideo').text,
'tbr': int_or_none(a.find('./totalBitrate').text),
'format_id': format_type,
'width': int_or_none(xpath_text(a, './frameWidth')),
'height': int_or_none(xpath_text(a, './frameHeight')),
'vbr': int_or_none(xpath_text(a, './bitrateVideo')),
'abr': int_or_none(xpath_text(a, './bitrateAudio')),
'vcodec': xpath_text(a, './codecVideo'),
'tbr': int_or_none(xpath_text(a, './totalBitrate')),
}
if a.find('./serverPrefix').text:
f['url'] = a.find('./serverPrefix').text
f['playpath'] = a.find('./fileName').text
server_prefix = xpath_text(a, './serverPrefix', default=None)
if server_prefix:
f.update({
'url': server_prefix,
'playpath': file_name,
})
else:
f['url'] = a.find('./fileName').text
if not format_url:
continue
f['url'] = format_url
formats.append(f)
self._sort_formats(formats)

View File

@@ -7,19 +7,21 @@ from .common import InfoExtractor
from .gigya import GigyaBaseIE
from ..compat import compat_HTTPError
from ..utils import (
extract_attributes,
ExtractorError,
strip_or_none,
clean_html,
extract_attributes,
float_or_none,
get_element_by_class,
int_or_none,
merge_dicts,
str_or_none,
strip_or_none,
url_or_none,
)
class CanvasIE(InfoExtractor):
_VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza)/assets/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza|dako)/assets/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
'md5': '68993eda72ef62386a15ea2cf3c93107',
@@ -332,3 +334,51 @@ class VrtNUIE(GigyaBaseIE):
'display_id': display_id,
'season_number': int_or_none(page.get('episode_season')),
})
class DagelijkseKostIE(InfoExtractor):
IE_DESC = 'dagelijksekost.een.be'
_VALID_URL = r'https?://dagelijksekost\.een\.be/gerechten/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'https://dagelijksekost.een.be/gerechten/hachis-parmentier-met-witloof',
'md5': '30bfffc323009a3e5f689bef6efa2365',
'info_dict': {
'id': 'md-ast-27a4d1ff-7d7b-425e-b84f-a4d227f592fa',
'display_id': 'hachis-parmentier-met-witloof',
'ext': 'mp4',
'title': 'Hachis parmentier met witloof',
'description': 'md5:9960478392d87f63567b5b117688cdc5',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 283.02,
},
'expected_warnings': ['is not a supported codec'],
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
title = strip_or_none(get_element_by_class(
'dish-metadata__title', webpage
) or self._html_search_meta(
'twitter:title', webpage))
description = clean_html(get_element_by_class(
'dish-description', webpage)
) or self._html_search_meta(
('description', 'twitter:description', 'og:description'),
webpage)
video_id = self._html_search_regex(
r'data-url=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id',
group='id')
return {
'_type': 'url_transparent',
'url': 'https://mediazone.vrt.be/api/v1/dako/assets/%s' % video_id,
'ie_key': CanvasIE.ie_key(),
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
}

View File

@@ -1,12 +1,14 @@
# coding: utf-8
from __future__ import unicode_literals
import calendar
import datetime
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
extract_timezone,
int_or_none,
parse_duration,
parse_resolution,
@@ -97,8 +99,9 @@ class CCMAIE(InfoExtractor):
timestamp = None
data_utc = try_get(informacio, lambda x: x['data_emissio']['utc'])
try:
timestamp = datetime.datetime.strptime(
data_utc, '%Y-%d-%mT%H:%M:%S%z').timestamp()
timezone, data_utc = extract_timezone(data_utc)
timestamp = calendar.timegm((datetime.datetime.strptime(
data_utc, '%Y-%d-%mT%H:%M:%S') - timezone).timetuple())
except TypeError:
pass

View File

@@ -95,6 +95,9 @@ class CDAIE(InfoExtractor):
if 'Ten film jest dostępny dla użytkowników premium' in webpage:
raise ExtractorError('This video is only available for premium users.', expected=True)
if re.search(r'niedostępn[ey] w(?:&nbsp;|\s+)Twoim kraju\s*<', webpage):
self.raise_geo_restricted()
need_confirm_age = False
if self._html_search_regex(r'(<form[^>]+action="[^"]*/a/validatebirth[^"]*")',
webpage, 'birthday validate form', default=None):

View File

@@ -1,6 +1,7 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
@@ -10,11 +11,13 @@ from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
strip_or_none,
unified_timestamp,
)
class DPlayIE(InfoExtractor):
_PATH_REGEX = r'/(?P<id>[^/]+/[^/?#]+)'
_VALID_URL = r'''(?x)https?://
(?P<domain>
(?:www\.)?(?P<host>d
@@ -24,7 +27,7 @@ class DPlayIE(InfoExtractor):
)
)|
(?P<subdomain_country>es|it)\.dplay\.com
)/[^/]+/(?P<id>[^/]+/[^/?#]+)'''
)/[^/]+''' + _PATH_REGEX
_TESTS = [{
# non geo restricted, via secure api, unsigned download hls URL
@@ -151,56 +154,79 @@ class DPlayIE(InfoExtractor):
'only_matching': True,
}]
def _process_errors(self, e, geo_countries):
info = self._parse_json(e.cause.read().decode('utf-8'), None)
error = info['errors'][0]
error_code = error.get('code')
if error_code == 'access.denied.geoblocked':
self.raise_geo_restricted(countries=geo_countries)
elif error_code in ('access.denied.missingpackage', 'invalid.token'):
raise ExtractorError(
'This video is only available for registered users. You may want to use --cookies.', expected=True)
raise ExtractorError(info['errors'][0]['detail'], expected=True)
def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
headers['Authorization'] = 'Bearer ' + self._download_json(
disco_base + 'token', display_id, 'Downloading token',
query={
'realm': realm,
})['data']['attributes']['token']
def _download_video_playback_info(self, disco_base, video_id, headers):
streaming = self._download_json(
disco_base + 'playback/videoPlaybackInfo/' + video_id,
video_id, headers=headers)['data']['attributes']['streaming']
streaming_list = []
for format_id, format_dict in streaming.items():
streaming_list.append({
'type': format_id,
'url': format_dict.get('url'),
})
return streaming_list
def _get_disco_api_info(self, url, display_id, disco_host, realm, country):
geo_countries = [country.upper()]
self._initialize_geo_bypass({
'countries': geo_countries,
})
disco_base = 'https://%s/' % disco_host
token = self._download_json(
disco_base + 'token', display_id, 'Downloading token',
query={
'realm': realm,
})['data']['attributes']['token']
headers = {
'Referer': url,
'Authorization': 'Bearer ' + token,
}
video = self._download_json(
disco_base + 'content/videos/' + display_id, display_id,
headers=headers, query={
'fields[channel]': 'name',
'fields[image]': 'height,src,width',
'fields[show]': 'name',
'fields[tag]': 'name',
'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
'include': 'images,primaryChannel,show,tags'
})
self._update_disco_api_headers(headers, disco_base, display_id, realm)
try:
video = self._download_json(
disco_base + 'content/videos/' + display_id, display_id,
headers=headers, query={
'fields[channel]': 'name',
'fields[image]': 'height,src,width',
'fields[show]': 'name',
'fields[tag]': 'name',
'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
'include': 'images,primaryChannel,show,tags'
})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
self._process_errors(e, geo_countries)
raise
video_id = video['data']['id']
info = video['data']['attributes']
title = info['name'].strip()
formats = []
try:
streaming = self._download_json(
disco_base + 'playback/videoPlaybackInfo/' + video_id,
display_id, headers=headers)['data']['attributes']['streaming']
streaming = self._download_video_playback_info(
disco_base, video_id, headers)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
error = info['errors'][0]
error_code = error.get('code')
if error_code == 'access.denied.geoblocked':
self.raise_geo_restricted(countries=geo_countries)
elif error_code == 'access.denied.missingpackage':
self.raise_login_required()
raise ExtractorError(info['errors'][0]['detail'], expected=True)
self._process_errors(e, geo_countries)
raise
for format_id, format_dict in streaming.items():
for format_dict in streaming:
if not isinstance(format_dict, dict):
continue
format_url = format_dict.get('url')
if not format_url:
continue
format_id = format_dict.get('type')
ext = determine_ext(format_url)
if format_id == 'dash' or ext == 'mpd':
formats.extend(self._extract_mpd_formats(
@@ -248,7 +274,7 @@ class DPlayIE(InfoExtractor):
'id': video_id,
'display_id': display_id,
'title': title,
'description': info.get('description'),
'description': strip_or_none(info.get('description')),
'duration': float_or_none(info.get('videoDuration'), 1000),
'timestamp': unified_timestamp(info.get('publishStart')),
'series': series,
@@ -268,3 +294,75 @@ class DPlayIE(InfoExtractor):
host = 'disco-api.' + domain if domain[0] == 'd' else 'eu2-prod.disco-api.com'
return self._get_disco_api_info(
url, display_id, host, 'dplay' + country, country)
class DiscoveryPlusIE(DPlayIE):
_VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/video' + DPlayIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
'info_dict': {
'id': '1140794',
'display_id': 'property-brothers-forever-home/food-and-family',
'ext': 'mp4',
'title': 'Food and Family',
'description': 'The brothers help a Richmond family expand their single-level home.',
'duration': 2583.113,
'timestamp': 1609304400,
'upload_date': '20201230',
'creator': 'HGTV',
'series': 'Property Brothers: Forever Home',
'season_number': 1,
'episode_number': 1,
},
'skip': 'Available for Premium users',
}]
def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
headers['x-disco-client'] = 'WEB:UNKNOWN:dplus_us:15.0.0'
def _download_video_playback_info(self, disco_base, video_id, headers):
return self._download_json(
disco_base + 'playback/v3/videoPlaybackInfo',
video_id, headers=headers, data=json.dumps({
'deviceInfo': {
'adBlocker': False,
},
'videoId': video_id,
'wisteriaProperties': {
'platform': 'desktop',
},
}).encode('utf-8'))['data']['attributes']['streaming']
def _real_extract(self, url):
display_id = self._match_id(url)
return self._get_disco_api_info(
url, display_id, 'us1-prod-direct.discoveryplus.com', 'go', 'us')
class HGTVDeIE(DPlayIE):
_VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayIE._PATH_REGEX
_TESTS = [{
'url': 'https://de.hgtv.com/sendungen/tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette/',
'info_dict': {
'id': '151205',
'display_id': 'tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette',
'ext': 'mp4',
'title': 'Wer braucht schon eine Toilette',
'description': 'md5:05b40a27e7aed2c9172de34d459134e2',
'duration': 1177.024,
'timestamp': 1595705400,
'upload_date': '20200725',
'creator': 'HGTV',
'series': 'Tiny House - klein, aber oho',
'season_number': 3,
'episode_number': 3,
},
'params': {
'format': 'bestvideo',
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
return self._get_disco_api_info(
url, display_id, 'eu1-prod.disco-api.com', 'hgtv', 'de')

View File

@@ -163,6 +163,7 @@ from .canvas import (
CanvasIE,
CanvasEenIE,
VrtNUIE,
DagelijkseKostIE,
)
from .carambatv import (
CarambaTVIE,
@@ -287,7 +288,11 @@ from .douyutv import (
DouyuShowIE,
DouyuTVIE,
)
from .dplay import DPlayIE
from .dplay import (
DPlayIE,
DiscoveryPlusIE,
HGTVDeIE,
)
from .dreisat import DreiSatIE
from .drbonanza import DRBonanzaIE
from .drtuber import DrTuberIE
@@ -470,8 +475,8 @@ from .hungama import (
from .hypem import HypemIE
from .ign import (
IGNIE,
OneUPIE,
PCMagIE,
IGNVideoIE,
IGNArticleIE,
)
from .iheart import (
IHeartRadioIE,
@@ -1024,6 +1029,7 @@ from .safari import (
SafariApiIE,
SafariCourseIE,
)
from .samplefocus import SampleFocusIE
from .sapo import SapoIE
from .savefrom import SaveFromIE
from .sbs import SBSIE
@@ -1056,6 +1062,11 @@ from .shared import (
VivoIE,
)
from .showroomlive import ShowRoomLiveIE
from .simplecast import (
SimplecastIE,
SimplecastEpisodeIE,
SimplecastPodcastIE,
)
from .sina import SinaIE
from .sixplay import SixPlayIE
from .skyit import (
@@ -1140,6 +1151,11 @@ from .srgssr import (
from .srmediathek import SRMediathekIE
from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE
from .storyfire import (
StoryFireIE,
StoryFireUserIE,
StoryFireSeriesIE,
)
from .streamable import StreamableIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
@@ -1602,5 +1618,6 @@ from .zattoo import (
ZattooLiveIE,
)
from .zdf import ZDFIE, ZDFChannelIE
from .zhihu import ZhihuIE
from .zingmp3 import ZingMp3IE
from .zype import ZypeIE

View File

@@ -129,6 +129,7 @@ from .odnoklassniki import OdnoklassnikiIE
from .kinja import KinjaEmbedIE
from .arcpublishing import ArcPublishingIE
from .medialaan import MedialaanIE
from .simplecast import SimplecastIE
class GenericIE(InfoExtractor):
@@ -2238,6 +2239,15 @@ class GenericIE(InfoExtractor):
'duration': 159,
},
},
{
# Simplecast player embed
'url': 'https://www.bio.org/podcast',
'info_dict': {
'id': 'podcast',
'title': 'I AM BIO Podcast | BIO',
},
'playlist_mincount': 52,
},
]
def report_following_redirect(self, new_url):
@@ -2792,6 +2802,12 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
# Look for Simplecast embeds
simplecast_urls = SimplecastIE._extract_urls(webpage)
if simplecast_urls:
return self.playlist_from_matches(
simplecast_urls, video_id, video_title)
# Look for BBC iPlayer embed
matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
if matches:

View File

@@ -3,230 +3,255 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
HEADRequest,
determine_ext,
int_or_none,
parse_iso8601,
strip_or_none,
try_get,
)
class IGNIE(InfoExtractor):
class IGNBaseIE(InfoExtractor):
def _call_api(self, slug):
return self._download_json(
'http://apis.ign.com/{0}/v3/{0}s/slug/{1}'.format(self._PAGE_TYPE, slug), slug)
class IGNIE(IGNBaseIE):
"""
Extractor for some of the IGN sites, like www.ign.com, es.ign.com de.ign.com.
Some videos of it.ign.com are also supported
"""
_VALID_URL = r'https?://.+?\.ign\.com/(?:[^/]+/)?(?P<type>videos|show_videos|articles|feature|(?:[^/]+/\d+/video))(/.+)?/(?P<name_or_id>.+)'
_VALID_URL = r'https?://(?:.+?\.ign|www\.pcmag)\.com/videos/(?:\d{4}/\d{2}/\d{2}/)?(?P<id>[^/?&#]+)'
IE_NAME = 'ign.com'
_PAGE_TYPE = 'video'
_API_URL_TEMPLATE = 'http://apis.ign.com/video/v3/videos/%s'
_EMBED_RE = r'<iframe[^>]+?["\']((?:https?:)?//.+?\.ign\.com.+?/embed.+?)["\']'
_TESTS = [
{
'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
'md5': 'febda82c4bafecd2d44b6e1a18a595f8',
'info_dict': {
'id': '8f862beef863986b2785559b9e1aa599',
'ext': 'mp4',
'title': 'The Last of Us Review',
'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c',
'timestamp': 1370440800,
'upload_date': '20130605',
'uploader_id': 'cberidon@ign.com',
}
},
{
'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
'info_dict': {
'id': '100-little-things-in-gta-5-that-will-blow-your-mind',
},
'playlist': [
{
'info_dict': {
'id': '5ebbd138523268b93c9141af17bec937',
'ext': 'mp4',
'title': 'GTA 5 Video Review',
'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
'timestamp': 1379339880,
'upload_date': '20130916',
'uploader_id': 'danieljkrupa@gmail.com',
},
},
{
'info_dict': {
'id': '638672ee848ae4ff108df2a296418ee2',
'ext': 'mp4',
'title': '26 Twisted Moments from GTA 5 in Slow Motion',
'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
'timestamp': 1386878820,
'upload_date': '20131212',
'uploader_id': 'togilvie@ign.com',
},
},
],
'params': {
'skip_download': True,
},
},
{
'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
'md5': '618fedb9c901fd086f6f093564ef8558',
'info_dict': {
'id': '078fdd005f6d3c02f63d795faa1b984f',
'ext': 'mp4',
'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
'description': 'Brian and Jared explore Michel Ancel\'s captivating new preview.',
'timestamp': 1408047180,
'upload_date': '20140814',
'uploader_id': 'jamesduggan1990@gmail.com',
},
},
{
'url': 'http://me.ign.com/en/videos/112203/video/how-hitman-aims-to-be-different-than-every-other-s',
'only_matching': True,
},
{
'url': 'http://me.ign.com/ar/angry-birds-2/106533/video/lrd-ldyy-lwl-lfylm-angry-birds',
'only_matching': True,
},
{
# videoId pattern
'url': 'http://www.ign.com/articles/2017/06/08/new-ducktales-short-donalds-birthday-doesnt-go-as-planned',
'only_matching': True,
},
]
def _find_video_id(self, webpage):
res_id = [
r'"video_id"\s*:\s*"(.*?)"',
r'class="hero-poster[^"]*?"[^>]*id="(.+?)"',
r'data-video-id="(.+?)"',
r'<object id="vid_(.+?)"',
r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
r'videoId&quot;\s*:\s*&quot;(.+?)&quot;',
r'videoId["\']\s*:\s*["\']([^"\']+?)["\']',
]
return self._search_regex(res_id, webpage, 'video id', default=None)
_TESTS = [{
'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
'md5': 'd2e1586d9987d40fad7867bf96a018ea',
'info_dict': {
'id': '8f862beef863986b2785559b9e1aa599',
'ext': 'mp4',
'title': 'The Last of Us Review',
'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c',
'timestamp': 1370440800,
'upload_date': '20130605',
'tags': 'count:9',
}
}, {
'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data',
'md5': 'f1581a6fe8c5121be5b807684aeac3f6',
'info_dict': {
'id': 'ee10d774b508c9b8ec07e763b9125b91',
'ext': 'mp4',
'title': 'What\'s New Now: Is GoGo Snooping on Your Data?',
'description': 'md5:817a20299de610bd56f13175386da6fa',
'timestamp': 1420571160,
'upload_date': '20150106',
'tags': 'count:4',
}
}, {
'url': 'https://www.ign.com/videos/is-a-resident-evil-4-remake-on-the-way-ign-daily-fix',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name_or_id = mobj.group('name_or_id')
page_type = mobj.group('type')
webpage = self._download_webpage(url, name_or_id)
if page_type != 'video':
multiple_urls = re.findall(
r'<param name="flashvars"[^>]*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
webpage)
if multiple_urls:
entries = [self.url_result(u, ie='IGN') for u in multiple_urls]
return {
'_type': 'playlist',
'id': name_or_id,
'entries': entries,
}
video_id = self._find_video_id(webpage)
if not video_id:
return self.url_result(self._search_regex(
self._EMBED_RE, webpage, 'embed url'))
return self._get_video_info(video_id)
def _get_video_info(self, video_id):
api_data = self._download_json(
self._API_URL_TEMPLATE % video_id, video_id)
display_id = self._match_id(url)
video = self._call_api(display_id)
video_id = video['videoId']
metadata = video['metadata']
title = metadata.get('longTitle') or metadata.get('title') or metadata['name']
formats = []
m3u8_url = api_data['refs'].get('m3uUrl')
refs = video.get('refs') or {}
m3u8_url = refs.get('m3uUrl')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
f4m_url = api_data['refs'].get('f4mUrl')
f4m_url = refs.get('f4mUrl')
if f4m_url:
formats.extend(self._extract_f4m_formats(
f4m_url, video_id, f4m_id='hds', fatal=False))
for asset in api_data['assets']:
for asset in (video.get('assets') or []):
asset_url = asset.get('url')
if not asset_url:
continue
formats.append({
'url': asset['url'],
'tbr': asset.get('actual_bitrate_kbps'),
'fps': asset.get('frame_rate'),
'url': asset_url,
'tbr': int_or_none(asset.get('bitrate'), 1000),
'fps': int_or_none(asset.get('frame_rate')),
'height': int_or_none(asset.get('height')),
'width': int_or_none(asset.get('width')),
})
mezzanine_url = try_get(video, lambda x: x['system']['mezzanineUrl'])
if mezzanine_url:
formats.append({
'ext': determine_ext(mezzanine_url, 'mp4'),
'format_id': 'mezzanine',
'preference': 1,
'url': mezzanine_url,
})
self._sort_formats(formats)
thumbnails = [{
'url': thumbnail['url']
} for thumbnail in api_data.get('thumbnails', [])]
thumbnails = []
for thumbnail in (video.get('thumbnails') or []):
thumbnail_url = thumbnail.get('url')
if not thumbnail_url:
continue
thumbnails.append({
'url': thumbnail_url,
})
metadata = api_data['metadata']
tags = []
for tag in (video.get('tags') or []):
display_name = tag.get('displayName')
if not display_name:
continue
tags.append(display_name)
return {
'id': api_data.get('videoId') or video_id,
'title': metadata.get('longTitle') or metadata.get('name') or metadata.get['title'],
'description': metadata.get('description'),
'id': video_id,
'title': title,
'description': strip_or_none(metadata.get('description')),
'timestamp': parse_iso8601(metadata.get('publishDate')),
'duration': int_or_none(metadata.get('duration')),
'display_id': metadata.get('slug') or video_id,
'uploader_id': metadata.get('creator'),
'display_id': display_id,
'thumbnails': thumbnails,
'formats': formats,
'tags': tags,
}
class OneUPIE(IGNIE):
_VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)\.html'
IE_NAME = '1up.com'
class IGNVideoIE(InfoExtractor):
_VALID_URL = r'https?://.+?\.ign\.com/(?:[a-z]{2}/)?[^/]+/(?P<id>\d+)/(?:video|trailer)/'
_TESTS = [{
'url': 'http://gamevideos.1up.com/video/id/34976.html',
'md5': 'c9cc69e07acb675c31a16719f909e347',
'url': 'http://me.ign.com/en/videos/112203/video/how-hitman-aims-to-be-different-than-every-other-s',
'md5': 'dd9aca7ed2657c4e118d8b261e5e9de1',
'info_dict': {
'id': '34976',
'id': 'e9be7ea899a9bbfc0674accc22a36cc8',
'ext': 'mp4',
'title': 'Sniper Elite V2 - Trailer',
'description': 'md5:bf0516c5ee32a3217aa703e9b1bc7826',
'timestamp': 1313099220,
'upload_date': '20110811',
'uploader_id': 'IGN',
'title': 'How Hitman Aims to Be Different Than Every Other Stealth Game - NYCC 2015',
'description': 'Taking out assassination targets in Hitman has never been more stylish.',
'timestamp': 1444665600,
'upload_date': '20151012',
}
}, {
'url': 'http://me.ign.com/ar/angry-birds-2/106533/video/lrd-ldyy-lwl-lfylm-angry-birds',
'only_matching': True,
}, {
# Youtube embed
'url': 'https://me.ign.com/ar/ratchet-clank-rift-apart/144327/trailer/embed',
'only_matching': True,
}, {
# Twitter embed
'url': 'http://adria.ign.com/sherlock-season-4/9687/trailer/embed',
'only_matching': True,
}, {
# Vimeo embed
'url': 'https://kr.ign.com/bic-2018/3307/trailer/embed',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
result = super(OneUPIE, self)._real_extract(url)
result['id'] = mobj.group('name_or_id')
return result
video_id = self._match_id(url)
req = HEADRequest(url.rsplit('/', 1)[0] + '/embed')
url = self._request_webpage(req, video_id).geturl()
ign_url = compat_parse_qs(
compat_urllib_parse_urlparse(url).query).get('url', [None])[0]
if ign_url:
return self.url_result(ign_url, IGNIE.ie_key())
return self.url_result(url)
class PCMagIE(IGNIE):
_VALID_URL = r'https?://(?:www\.)?pcmag\.com/(?P<type>videos|article2)(/.+)?/(?P<name_or_id>.+)'
IE_NAME = 'pcmag'
_EMBED_RE = r'iframe\.setAttribute\("src",\s*__util.objToUrlString\("http://widgets\.ign\.com/video/embed/content\.html?[^"]*url=([^"]+)["&]'
class IGNArticleIE(IGNBaseIE):
_VALID_URL = r'https?://.+?\.ign\.com/(?:articles(?:/\d{4}/\d{2}/\d{2})?|(?:[a-z]{2}/)?feature/\d+)/(?P<id>[^/?&#]+)'
_PAGE_TYPE = 'article'
_TESTS = [{
'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data',
'md5': '212d6154fd0361a2781075f1febbe9ad',
'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
'info_dict': {
'id': 'ee10d774b508c9b8ec07e763b9125b91',
'ext': 'mp4',
'title': '010615_What\'s New Now: Is GoGo Snooping on Your Data?',
'description': 'md5:a7071ae64d2f68cc821c729d4ded6bb3',
'timestamp': 1420571160,
'upload_date': '20150106',
'uploader_id': 'cozzipix@gmail.com',
}
'id': '524497489e4e8ff5848ece34',
'title': '100 Little Things in GTA 5 That Will Blow Your Mind',
},
'playlist': [
{
'info_dict': {
'id': '5ebbd138523268b93c9141af17bec937',
'ext': 'mp4',
'title': 'GTA 5 Video Review',
'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
'timestamp': 1379339880,
'upload_date': '20130916',
},
},
{
'info_dict': {
'id': '638672ee848ae4ff108df2a296418ee2',
'ext': 'mp4',
'title': '26 Twisted Moments from GTA 5 in Slow Motion',
'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
'timestamp': 1386878820,
'upload_date': '20131212',
},
},
],
'params': {
'playlist_items': '2-3',
'skip_download': True,
},
}, {
'url': 'http://www.pcmag.com/article2/0,2817,2470156,00.asp',
'md5': '94130c1ca07ba0adb6088350681f16c1',
'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
'info_dict': {
'id': '042e560ba94823d43afcb12ddf7142ca',
'ext': 'mp4',
'title': 'HTC\'s Weird New Re Camera - What\'s New Now',
'description': 'md5:53433c45df96d2ea5d0fda18be2ca908',
'timestamp': 1412953920,
'upload_date': '20141010',
'uploader_id': 'chris_snyder@pcmag.com',
}
'id': '53ee806780a81ec46e0790f8',
'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
},
'playlist_count': 2,
}, {
# videoId pattern
'url': 'http://www.ign.com/articles/2017/06/08/new-ducktales-short-donalds-birthday-doesnt-go-as-planned',
'only_matching': True,
}, {
# Youtube embed
'url': 'https://www.ign.com/articles/2021-mvp-named-in-puppy-bowl-xvii',
'only_matching': True,
}, {
# IMDB embed
'url': 'https://www.ign.com/articles/2014/08/07/sons-of-anarchy-final-season-trailer',
'only_matching': True,
}, {
# Facebook embed
'url': 'https://www.ign.com/articles/2017/09/20/marvels-the-punisher-watch-the-new-trailer-for-the-netflix-series',
'only_matching': True,
}, {
# Brightcove embed
'url': 'https://www.ign.com/articles/2016/01/16/supergirl-goes-flying-with-martian-manhunter-in-new-clip',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
article = self._call_api(display_id)
def entries():
media_url = try_get(article, lambda x: x['mediaRelations'][0]['media']['metadata']['url'])
if media_url:
yield self.url_result(media_url, IGNIE.ie_key())
for content in (article.get('content') or []):
for video_url in re.findall(r'(?:\[(?:ignvideo\s+url|youtube\s+clip_id)|<iframe[^>]+src)="([^"]+)"', content):
yield self.url_result(video_url)
return self.playlist_result(
entries(), article.get('articleId'),
strip_or_none(try_get(article, lambda x: x['metadata']['headline'])))

View File

@@ -3,10 +3,13 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
int_or_none,
str_or_none,
strip_or_none,
try_get,
unified_timestamp,
update_url_query,
)
@@ -23,7 +26,7 @@ class KakaoIE(InfoExtractor):
'id': '301965083',
'ext': 'mp4',
'title': '乃木坂46 バナナマン 「3期生紹介コーナーが始動顔高低差GPも」 『乃木坂工事中』',
'uploader_id': 2671005,
'uploader_id': '2671005',
'uploader': '그랑그랑이',
'timestamp': 1488160199,
'upload_date': '20170227',
@@ -36,11 +39,15 @@ class KakaoIE(InfoExtractor):
'ext': 'mp4',
'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
'uploader_id': 2653210,
'uploader_id': '2653210',
'uploader': '쇼! 음악중심',
'timestamp': 1485684628,
'upload_date': '20170129',
}
}, {
# geo restricted
'url': 'https://tv.kakao.com/channel/3643855/cliplink/412069491',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -68,8 +75,7 @@ class KakaoIE(InfoExtractor):
'fields': ','.join([
'-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title',
'description', 'channelId', 'createTime', 'duration', 'playCount',
'likeCount', 'commentCount', 'tagList', 'channel', 'name',
'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault',
'likeCount', 'commentCount', 'tagList', 'channel', 'name', 'thumbnailUrl',
'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label'])
}
@@ -82,24 +88,28 @@ class KakaoIE(InfoExtractor):
title = clip.get('title') or clip_link.get('displayTitle')
query['tid'] = impress.get('tid', '')
query.update({
'fields': '-*,code,message,url',
'tid': impress.get('tid') or '',
})
formats = []
for fmt in clip.get('videoOutputList', []):
for fmt in (clip.get('videoOutputList') or []):
try:
profile_name = fmt['profile']
if profile_name == 'AUDIO':
continue
query.update({
'profile': profile_name,
'fields': '-*,url',
})
fmt_url_json = self._download_json(
api_base + 'raw/videolocation', display_id,
'Downloading video URL for profile %s' % profile_name,
query=query, headers=player_header, fatal=False)
if fmt_url_json is None:
query['profile'] = profile_name
try:
fmt_url_json = self._download_json(
api_base + 'raw/videolocation', display_id,
'Downloading video URL for profile %s' % profile_name,
query=query, headers=player_header)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
resp = self._parse_json(e.cause.read().decode(), video_id)
if resp.get('code') == 'GeoBlocked':
self.raise_geo_restricted()
continue
fmt_url = fmt_url_json['url']
@@ -116,27 +126,13 @@ class KakaoIE(InfoExtractor):
pass
self._sort_formats(formats)
thumbs = []
for thumb in clip.get('clipChapterThumbnailList', []):
thumbs.append({
'url': thumb.get('thumbnailUrl'),
'id': compat_str(thumb.get('timeInSec')),
'preference': -1 if thumb.get('isDefault') else 0
})
top_thumbnail = clip.get('thumbnailUrl')
if top_thumbnail:
thumbs.append({
'url': top_thumbnail,
'preference': 10,
})
return {
'id': display_id,
'title': title,
'description': strip_or_none(clip.get('description')),
'uploader': clip_link.get('channel', {}).get('name'),
'uploader_id': clip_link.get('channelId'),
'thumbnails': thumbs,
'uploader': try_get(clip_link, lambda x: x['channel']['name']),
'uploader_id': str_or_none(clip_link.get('channelId')),
'thumbnail': clip.get('thumbnailUrl'),
'timestamp': unified_timestamp(clip_link.get('createTime')),
'duration': int_or_none(clip.get('duration')),
'view_count': int_or_none(clip.get('playCount')),

View File

@@ -2,10 +2,11 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
determine_ext,
int_or_none,
try_get,
unescapeHTML,
url_or_none,
)
@@ -14,7 +15,7 @@ class NineGagIE(InfoExtractor):
IE_NAME = '9gag'
_VALID_URL = r'https?://(?:www\.)?9gag\.com/gag/(?P<id>[^/?&#]+)'
_TEST = {
_TESTS = [{
'url': 'https://9gag.com/gag/ae5Ag7B',
'info_dict': {
'id': 'ae5Ag7B',
@@ -29,7 +30,11 @@ class NineGagIE(InfoExtractor):
'dislike_count': int,
'comment_count': int,
}
}
}, {
# HTML escaped title
'url': 'https://9gag.com/gag/av5nvyb',
'only_matching': True,
}]
def _real_extract(self, url):
post_id = self._match_id(url)
@@ -43,7 +48,7 @@ class NineGagIE(InfoExtractor):
'The given url does not contain a video',
expected=True)
title = post['title']
title = unescapeHTML(post['title'])
duration = None
formats = []

View File

@@ -413,7 +413,8 @@ class PeerTubeIE(InfoExtractor):
peertube3\.cpy\.re|
peertube2\.cpy\.re|
videos\.tcit\.fr|
peertube\.cpy\.re
peertube\.cpy\.re|
canard\.tube
)'''
_UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}'
_API_BASE = 'https://%s/api/v1/videos/%s/%s'

View File

@@ -0,0 +1,100 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
extract_attributes,
get_element_by_attribute,
int_or_none,
)
class SampleFocusIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?samplefocus\.com/samples/(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://samplefocus.com/samples/lil-peep-sad-emo-guitar',
'md5': '48c8d62d60be467293912e0e619a5120',
'info_dict': {
'id': '40316',
'display_id': 'lil-peep-sad-emo-guitar',
'ext': 'mp3',
'title': 'Lil Peep Sad Emo Guitar',
'thumbnail': r're:^https?://.+\.png',
'license': 'Standard License',
'uploader': 'CapsCtrl',
'uploader_id': 'capsctrl',
'like_count': int,
'comment_count': int,
'categories': ['Samples', 'Guitar', 'Electric guitar'],
},
}, {
'url': 'https://samplefocus.com/samples/dababy-style-bass-808',
'only_matching': True
}, {
'url': 'https://samplefocus.com/samples/young-chop-kick',
'only_matching': True
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
sample_id = self._search_regex(
r'<input[^>]+id=(["\'])sample_id\1[^>]+value=(?:["\'])(?P<id>\d+)',
webpage, 'sample id', group='id')
title = self._og_search_title(webpage, fatal=False) or self._html_search_regex(
r'<h1>(.+?)</h1>', webpage, 'title')
mp3_url = self._search_regex(
r'<input[^>]+id=(["\'])sample_mp3\1[^>]+value=(["\'])(?P<url>(?:(?!\2).)+)',
webpage, 'mp3', fatal=False, group='url') or extract_attributes(self._search_regex(
r'<meta[^>]+itemprop=(["\'])contentUrl\1[^>]*>',
webpage, 'mp3 url', group=0))['content']
thumbnail = self._og_search_thumbnail(webpage) or self._html_search_regex(
r'<img[^>]+class=(?:["\'])waveform responsive-img[^>]+src=(["\'])(?P<url>(?:(?!\1).)+)',
webpage, 'mp3', fatal=False, group='url')
comments = []
for author_id, author, body in re.findall(r'(?s)<p[^>]+class="comment-author"><a[^>]+href="/users/([^"]+)">([^"]+)</a>.+?<p[^>]+class="comment-body">([^>]+)</p>', webpage):
comments.append({
'author': author,
'author_id': author_id,
'text': body,
})
uploader_id = uploader = None
mobj = re.search(r'>By <a[^>]+href="/users/([^"]+)"[^>]*>([^<]+)', webpage)
if mobj:
uploader_id, uploader = mobj.groups()
breadcrumb = get_element_by_attribute('typeof', 'BreadcrumbList', webpage)
categories = []
if breadcrumb:
for _, name in re.findall(r'<span[^>]+property=(["\'])name\1[^>]*>([^<]+)', breadcrumb):
categories.append(name)
def extract_count(klass):
return int_or_none(self._html_search_regex(
r'<span[^>]+class=(?:["\'])?%s-count[^>]*>(\d+)' % klass,
webpage, klass, fatal=False))
return {
'id': sample_id,
'title': title,
'url': mp3_url,
'display_id': display_id,
'thumbnail': thumbnail,
'uploader': uploader,
'license': self._html_search_regex(
r'<a[^>]+href=(["\'])/license\1[^>]*>(?P<license>[^<]+)<',
webpage, 'license', fatal=False, group='license'),
'uploader_id': uploader_id,
'like_count': extract_count('sample-%s-favorites' % sample_id),
'comment_count': extract_count('comments'),
'comments': comments,
'categories': categories,
}

View File

@@ -0,0 +1,160 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
clean_podcast_url,
int_or_none,
parse_iso8601,
strip_or_none,
try_get,
urlencode_postdata,
)
class SimplecastBaseIE(InfoExtractor):
_UUID_REGEX = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
_API_BASE = 'https://api.simplecast.com/'
def _call_api(self, path_tmpl, video_id):
return self._download_json(
self._API_BASE + path_tmpl % video_id, video_id)
def _call_search_api(self, resource, resource_id, resource_url):
return self._download_json(
'https://api.simplecast.com/%ss/search' % resource, resource_id,
data=urlencode_postdata({'url': resource_url}))
def _parse_episode(self, episode):
episode_id = episode['id']
title = episode['title'].strip()
audio_file = episode.get('audio_file') or {}
audio_file_url = audio_file.get('url') or episode.get('audio_file_url') or episode['enclosure_url']
season = episode.get('season') or {}
season_href = season.get('href')
season_id = None
if season_href:
season_id = self._search_regex(
r'https?://api.simplecast.com/seasons/(%s)' % self._UUID_REGEX,
season_href, 'season id', default=None)
webpage_url = episode.get('episode_url')
channel_url = None
if webpage_url:
channel_url = self._search_regex(
r'(https?://[^/]+\.simplecast\.com)',
webpage_url, 'channel url', default=None)
return {
'id': episode_id,
'display_id': episode.get('slug'),
'title': title,
'url': clean_podcast_url(audio_file_url),
'webpage_url': webpage_url,
'channel_url': channel_url,
'series': try_get(episode, lambda x: x['podcast']['title']),
'season_number': int_or_none(season.get('number')),
'season_id': season_id,
'thumbnail': episode.get('image_url'),
'episode_id': episode_id,
'episode_number': int_or_none(episode.get('number')),
'description': strip_or_none(episode.get('description')),
'timestamp': parse_iso8601(episode.get('published_at')),
'duration': int_or_none(episode.get('duration')),
'filesize': int_or_none(audio_file.get('size') or episode.get('audio_file_size')),
}
class SimplecastIE(SimplecastBaseIE):
IE_NAME = 'simplecast'
_VALID_URL = r'https?://(?:api\.simplecast\.com/episodes|player\.simplecast\.com)/(?P<id>%s)' % SimplecastBaseIE._UUID_REGEX
_COMMON_TEST_INFO = {
'display_id': 'errant-signal-chris-franklin-new-wave-video-essays',
'id': 'b6dc49a2-9404-4853-9aa9-9cfc097be876',
'ext': 'mp3',
'title': 'Errant Signal - Chris Franklin & New Wave Video Essays',
'episode_number': 1,
'episode_id': 'b6dc49a2-9404-4853-9aa9-9cfc097be876',
'description': 'md5:34752789d3d2702e2d2c975fbd14f357',
'season_number': 1,
'season_id': 'e23df0da-bae4-4531-8bbf-71364a88dc13',
'series': 'The RE:BIND.io Podcast',
'duration': 5343,
'timestamp': 1580979475,
'upload_date': '20200206',
'webpage_url': r're:^https?://the-re-bind-io-podcast\.simplecast\.com/episodes/errant-signal-chris-franklin-new-wave-video-essays',
'channel_url': r're:^https?://the-re-bind-io-podcast\.simplecast\.com$',
}
_TESTS = [{
'url': 'https://api.simplecast.com/episodes/b6dc49a2-9404-4853-9aa9-9cfc097be876',
'md5': '8c93be7be54251bf29ee97464eabe61c',
'info_dict': _COMMON_TEST_INFO,
}, {
'url': 'https://player.simplecast.com/b6dc49a2-9404-4853-9aa9-9cfc097be876',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'''(?x)<iframe[^>]+src=["\']
(
https?://(?:embed\.simplecast\.com/[0-9a-f]{8}|
player\.simplecast\.com/%s
))''' % SimplecastBaseIE._UUID_REGEX, webpage)
def _real_extract(self, url):
episode_id = self._match_id(url)
episode = self._call_api('episodes/%s', episode_id)
return self._parse_episode(episode)
class SimplecastEpisodeIE(SimplecastBaseIE):
IE_NAME = 'simplecast:episode'
_VALID_URL = r'https?://(?!api\.)[^/]+\.simplecast\.com/episodes/(?P<id>[^/?&#]+)'
_TEST = {
'url': 'https://the-re-bind-io-podcast.simplecast.com/episodes/errant-signal-chris-franklin-new-wave-video-essays',
'md5': '8c93be7be54251bf29ee97464eabe61c',
'info_dict': SimplecastIE._COMMON_TEST_INFO,
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
episode = self._call_search_api(
'episode', mobj.group(1), mobj.group(0))
return self._parse_episode(episode)
class SimplecastPodcastIE(SimplecastBaseIE):
IE_NAME = 'simplecast:podcast'
_VALID_URL = r'https?://(?!(?:api|cdn|embed|feeds|player)\.)(?P<id>[^/]+)\.simplecast\.com(?!/episodes/[^/?&#]+)'
_TESTS = [{
'url': 'https://the-re-bind-io-podcast.simplecast.com',
'playlist_mincount': 33,
'info_dict': {
'id': '07d28d26-7522-42eb-8c53-2bdcfc81c43c',
'title': 'The RE:BIND.io Podcast',
},
}, {
'url': 'https://the-re-bind-io-podcast.simplecast.com/episodes',
'only_matching': True,
}]
def _real_extract(self, url):
subdomain = self._match_id(url)
site = self._call_search_api('site', subdomain, url)
podcast = site['podcast']
podcast_id = podcast['id']
podcast_title = podcast.get('title')
def entries():
episodes = self._call_api('podcasts/%s/episodes', podcast_id)
for episode in (episodes.get('collection') or []):
info = self._parse_episode(episode)
info['series'] = podcast_title
yield info
return self.playlist_result(entries(), podcast_id, podcast_title)

View File

@@ -0,0 +1,151 @@
# coding: utf-8
from __future__ import unicode_literals
import functools
from .common import InfoExtractor
from ..utils import (
# HEADRequest,
int_or_none,
OnDemandPagedList,
smuggle_url,
)
class StoryFireBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.)?storyfire\.com/'
def _call_api(self, path, video_id, resource, query=None):
return self._download_json(
'https://storyfire.com/app/%s/%s' % (path, video_id), video_id,
'Downloading %s JSON metadata' % resource, query=query)
def _parse_video(self, video):
title = video['title']
vimeo_id = self._search_regex(
r'https?://player\.vimeo\.com/external/(\d+)',
video['vimeoVideoURL'], 'vimeo id')
# video_url = self._request_webpage(
# HEADRequest(video['vimeoVideoURL']), video_id).geturl()
# formats = []
# for v_url, suffix in [(video_url, '_sep'), (video_url.replace('/sep/video/', '/video/'), '')]:
# formats.extend(self._extract_m3u8_formats(
# v_url, video_id, 'mp4', 'm3u8_native',
# m3u8_id='hls' + suffix, fatal=False))
# formats.extend(self._extract_mpd_formats(
# v_url.replace('.m3u8', '.mpd'), video_id,
# mpd_id='dash' + suffix, fatal=False))
# self._sort_formats(formats)
uploader_id = video.get('hostID')
return {
'_type': 'url_transparent',
'id': vimeo_id,
'title': title,
'description': video.get('description'),
'url': smuggle_url(
'https://player.vimeo.com/video/' + vimeo_id, {
'http_headers': {
'Referer': 'https://storyfire.com/',
}
}),
# 'formats': formats,
'thumbnail': video.get('storyImage'),
'view_count': int_or_none(video.get('views')),
'like_count': int_or_none(video.get('likesCount')),
'comment_count': int_or_none(video.get('commentsCount')),
'duration': int_or_none(video.get('videoDuration')),
'timestamp': int_or_none(video.get('publishDate')),
'uploader': video.get('username'),
'uploader_id': uploader_id,
'uploader_url': 'https://storyfire.com/user/%s/video' % uploader_id if uploader_id else None,
'episode_number': int_or_none(video.get('episodeNumber') or video.get('episode_number')),
}
class StoryFireIE(StoryFireBaseIE):
_VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'video-details/(?P<id>[0-9a-f]{24})'
_TEST = {
'url': 'https://storyfire.com/video-details/5df1d132b6378700117f9181',
'md5': 'caec54b9e4621186d6079c7ec100c1eb',
'info_dict': {
'id': '378954662',
'ext': 'mp4',
'title': 'Buzzfeed Teaches You About Memes',
'uploader_id': 'ntZAJFECERSgqHSxzonV5K2E89s1',
'timestamp': 1576129028,
'description': 'md5:0b4e28021548e144bed69bb7539e62ea',
'uploader': 'whang!',
'upload_date': '20191212',
'duration': 418,
'view_count': int,
'like_count': int,
'comment_count': int,
},
'params': {
'skip_download': True,
},
'expected_warnings': ['Unable to download JSON metadata']
}
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._call_api(
'generic/video-detail', video_id, 'video')['video']
return self._parse_video(video)
class StoryFireUserIE(StoryFireBaseIE):
_VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'user/(?P<id>[^/]+)/video'
_TEST = {
'url': 'https://storyfire.com/user/UQ986nFxmAWIgnkZQ0ftVhq4nOk2/video',
'info_dict': {
'id': 'UQ986nFxmAWIgnkZQ0ftVhq4nOk2',
},
'playlist_mincount': 151,
}
_PAGE_SIZE = 20
def _fetch_page(self, user_id, page):
videos = self._call_api(
'publicVideos', user_id, 'page %d' % (page + 1), {
'skip': page * self._PAGE_SIZE,
})['videos']
for video in videos:
yield self._parse_video(video)
def _real_extract(self, url):
user_id = self._match_id(url)
entries = OnDemandPagedList(functools.partial(
self._fetch_page, user_id), self._PAGE_SIZE)
return self.playlist_result(entries, user_id)
class StoryFireSeriesIE(StoryFireBaseIE):
_VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'write/series/stories/(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://storyfire.com/write/series/stories/-Lq6MsuIHLODO6d2dDkr/',
'info_dict': {
'id': '-Lq6MsuIHLODO6d2dDkr',
},
'playlist_mincount': 13,
}, {
'url': 'https://storyfire.com/write/series/stories/the_mortal_one/',
'info_dict': {
'id': 'the_mortal_one',
},
'playlist_count': 0,
}]
def _extract_videos(self, stories):
for story in stories.values():
if story.get('hasVideo'):
yield self._parse_video(story)
def _real_extract(self, url):
series_id = self._match_id(url)
stories = self._call_api(
'seriesStories', series_id, 'series stories')
return self.playlist_result(self._extract_videos(stories), series_id)

View File

@@ -42,8 +42,8 @@ class URPlayIE(InfoExtractor):
url = url.replace('skola.se/Produkter', 'play.se/program')
webpage = self._download_webpage(url, video_id)
urplayer_data = self._parse_json(self._html_search_regex(
r'data-react-class="components/Player/Player"[^>]+data-react-props="({.+?})"',
webpage, 'urplayer data'), video_id)['currentProduct']
r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"',
webpage, 'urplayer data'), video_id)['accessibleEpisodes'][0]
episode = urplayer_data['title']
raw_streaming_info = urplayer_data['streamingInfo']['raw']
host = self._download_json(

View File

@@ -4,21 +4,22 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
float_or_none,
int_or_none,
parse_age_limit,
qualities,
random_birthday,
try_get,
unified_timestamp,
urljoin,
)
class VideoPressIE(InfoExtractor):
_VALID_URL = r'https?://videopress\.com/embed/(?P<id>[\da-zA-Z]+)'
_ID_REGEX = r'[\da-zA-Z]{8}'
_PATH_REGEX = r'video(?:\.word)?press\.com/embed/'
_VALID_URL = r'https?://%s(?P<id>%s)' % (_PATH_REGEX, _ID_REGEX)
_TESTS = [{
'url': 'https://videopress.com/embed/kUJmAcSf',
'md5': '706956a6c875873d51010921310e4bc6',
@@ -36,35 +37,36 @@ class VideoPressIE(InfoExtractor):
# 17+, requires birth_* params
'url': 'https://videopress.com/embed/iH3gstfZ',
'only_matching': True,
}, {
'url': 'https://video.wordpress.com/embed/kUJmAcSf',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+src=["\']((?:https?://)?videopress\.com/embed/[\da-zA-Z]+)',
r'<iframe[^>]+src=["\']((?:https?://)?%s%s)' % (VideoPressIE._PATH_REGEX, VideoPressIE._ID_REGEX),
webpage)
def _real_extract(self, url):
video_id = self._match_id(url)
query = random_birthday('birth_year', 'birth_month', 'birth_day')
query['fields'] = 'description,duration,file_url_base,files,height,original,poster,rating,title,upload_date,width'
video = self._download_json(
'https://public-api.wordpress.com/rest/v1.1/videos/%s' % video_id,
video_id, query=query)
title = video['title']
def base_url(scheme):
return try_get(
video, lambda x: x['file_url_base'][scheme], compat_str)
base_url = base_url('https') or base_url('http')
file_url_base = video.get('file_url_base') or {}
base_url = file_url_base.get('https') or file_url_base.get('http')
QUALITIES = ('std', 'dvd', 'hd')
quality = qualities(QUALITIES)
formats = []
for format_id, f in video['files'].items():
for format_id, f in (video.get('files') or {}).items():
if not isinstance(f, dict):
continue
for ext, path in f.items():
@@ -75,12 +77,14 @@ class VideoPressIE(InfoExtractor):
'ext': determine_ext(path, ext),
'quality': quality(format_id),
})
original_url = try_get(video, lambda x: x['original'], compat_str)
original_url = video.get('original')
if original_url:
formats.append({
'url': original_url,
'format_id': 'original',
'quality': len(QUALITIES),
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
})
self._sort_formats(formats)

View File

@@ -21,6 +21,7 @@ from ..utils import (
parse_iso8601,
sanitized_Request,
std_headers,
try_get,
)
@@ -30,7 +31,7 @@ class VikiBaseIE(InfoExtractor):
_API_URL_TEMPLATE = 'https://api.viki.io%s&sig=%s'
_APP = '100005a'
_APP_VERSION = '2.2.5.1428709186'
_APP_VERSION = '6.0.0'
_APP_SECRET = 'MM_d*yP@`&1@]@!AVrXf_o-HVEnoTnm$O-ti4[G~$JDI/Dc-&piU&z&5.;:}95=Iad'
_GEO_BYPASS = False
@@ -41,7 +42,7 @@ class VikiBaseIE(InfoExtractor):
_ERRORS = {
'geo': 'Sorry, this content is not available in your region.',
'upcoming': 'Sorry, this content is not yet available.',
# 'paywall': 'paywall',
'paywall': 'Sorry, this content is only available to Viki Pass Plus subscribers',
}
def _prepare_call(self, path, timestamp=None, post_data=None):
@@ -62,7 +63,8 @@ class VikiBaseIE(InfoExtractor):
def _call_api(self, path, video_id, note, timestamp=None, post_data=None):
resp = self._download_json(
self._prepare_call(path, timestamp, post_data), video_id, note)
self._prepare_call(path, timestamp, post_data), video_id, note,
headers={'x-viki-app-ver': self._APP_VERSION})
error = resp.get('error')
if error:
@@ -82,11 +84,13 @@ class VikiBaseIE(InfoExtractor):
expected=True)
def _check_errors(self, data):
for reason, status in data.get('blocking', {}).items():
for reason, status in (data.get('blocking') or {}).items():
if status and reason in self._ERRORS:
message = self._ERRORS[reason]
if reason == 'geo':
self.raise_geo_restricted(msg=message)
elif reason == 'paywall':
self.raise_login_required(message)
raise ExtractorError('%s said: %s' % (
self.IE_NAME, message), expected=True)
@@ -131,13 +135,19 @@ class VikiIE(VikiBaseIE):
'info_dict': {
'id': '1023585v',
'ext': 'mp4',
'title': 'Heirs Episode 14',
'uploader': 'SBS',
'description': 'md5:c4b17b9626dd4b143dcc4d855ba3474e',
'title': 'Heirs - Episode 14',
'uploader': 'SBS Contents Hub',
'timestamp': 1385047627,
'upload_date': '20131121',
'age_limit': 13,
'duration': 3570,
'episode_number': 14,
},
'params': {
'format': 'bestvideo',
},
'skip': 'Blocked in the US',
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
}, {
# clip
'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference',
@@ -153,7 +163,8 @@ class VikiIE(VikiBaseIE):
'uploader': 'Arirang TV',
'like_count': int,
'age_limit': 0,
}
},
'skip': 'Sorry. There was an error loading this video',
}, {
'url': 'http://www.viki.com/videos/1048879v-ankhon-dekhi',
'info_dict': {
@@ -171,7 +182,7 @@ class VikiIE(VikiBaseIE):
}, {
# episode
'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1',
'md5': '94e0e34fd58f169f40c184f232356cfe',
'md5': '0a53dc252e6e690feccd756861495a8c',
'info_dict': {
'id': '44699v',
'ext': 'mp4',
@@ -183,6 +194,10 @@ class VikiIE(VikiBaseIE):
'uploader': 'group8',
'like_count': int,
'age_limit': 13,
'episode_number': 1,
},
'params': {
'format': 'bestvideo',
},
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
}, {
@@ -209,7 +224,7 @@ class VikiIE(VikiBaseIE):
}, {
# non-English description
'url': 'http://www.viki.com/videos/158036v-love-in-magic',
'md5': 'adf9e321a0ae5d0aace349efaaff7691',
'md5': '41faaba0de90483fb4848952af7c7d0d',
'info_dict': {
'id': '158036v',
'ext': 'mp4',
@@ -220,6 +235,10 @@ class VikiIE(VikiBaseIE):
'title': 'Love In Magic',
'age_limit': 13,
},
'params': {
'format': 'bestvideo',
},
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
}]
def _real_extract(self, url):
@@ -229,36 +248,33 @@ class VikiIE(VikiBaseIE):
'https://www.viki.com/api/videos/' + video_id,
video_id, 'Downloading video JSON', headers={
'x-client-user-agent': std_headers['User-Agent'],
'x-viki-app-ver': '4.0.57',
'x-viki-app-ver': '3.0.0',
})
video = resp['video']
self._check_errors(video)
title = self.dict_selection(video.get('titles', {}), 'en', allow_fallback=False)
episode_number = int_or_none(video.get('number'))
if not title:
title = 'Episode %d' % video.get('number') if video.get('type') == 'episode' else video.get('id') or video_id
container_titles = video.get('container', {}).get('titles', {})
title = 'Episode %d' % episode_number if video.get('type') == 'episode' else video.get('id') or video_id
container_titles = try_get(video, lambda x: x['container']['titles'], dict) or {}
container_title = self.dict_selection(container_titles, 'en')
title = '%s - %s' % (container_title, title)
description = self.dict_selection(video.get('descriptions', {}), 'en')
duration = int_or_none(video.get('duration'))
timestamp = parse_iso8601(video.get('created_at'))
uploader = video.get('author')
like_count = int_or_none(video.get('likes', {}).get('count'))
age_limit = parse_age_limit(video.get('rating'))
like_count = int_or_none(try_get(video, lambda x: x['likes']['count']))
thumbnails = []
for thumbnail_id, thumbnail in video.get('images', {}).items():
for thumbnail_id, thumbnail in (video.get('images') or {}).items():
thumbnails.append({
'id': thumbnail_id,
'url': thumbnail.get('url'),
})
subtitles = {}
for subtitle_lang, _ in video.get('subtitle_completions', {}).items():
for subtitle_lang, _ in (video.get('subtitle_completions') or {}).items():
subtitles[subtitle_lang] = [{
'ext': subtitles_format,
'url': self._prepare_call(
@@ -269,13 +285,15 @@ class VikiIE(VikiBaseIE):
'id': video_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': timestamp,
'uploader': uploader,
'duration': int_or_none(video.get('duration')),
'timestamp': parse_iso8601(video.get('created_at')),
'uploader': video.get('author'),
'uploader_url': video.get('author_url'),
'like_count': like_count,
'age_limit': age_limit,
'age_limit': parse_age_limit(video.get('rating')),
'thumbnails': thumbnails,
'subtitles': subtitles,
'episode_number': episode_number,
}
formats = []
@@ -360,7 +378,7 @@ class VikiChannelIE(VikiBaseIE):
'info_dict': {
'id': '50c',
'title': 'Boys Over Flowers',
'description': 'md5:ecd3cff47967fe193cff37c0bec52790',
'description': 'md5:804ce6e7837e1fd527ad2f25420f4d59',
},
'playlist_mincount': 71,
}, {
@@ -371,6 +389,7 @@ class VikiChannelIE(VikiBaseIE):
'description': 'md5:05bf5471385aa8b21c18ad450e350525',
},
'playlist_count': 127,
'skip': 'Page not found',
}, {
'url': 'http://www.viki.com/news/24569c-showbiz-korea',
'only_matching': True,

View File

@@ -226,10 +226,12 @@ class VimeoBaseInfoExtractor(InfoExtractor):
'is_live': is_live,
}
def _extract_original_format(self, url, video_id):
def _extract_original_format(self, url, video_id, unlisted_hash=None):
query = {'action': 'load_download_config'}
if unlisted_hash:
query['unlisted_hash'] = unlisted_hash
download_data = self._download_json(
url, video_id, fatal=False,
query={'action': 'load_download_config'},
url, video_id, fatal=False, query=query,
headers={'X-Requested-With': 'XMLHttpRequest'})
if download_data:
source_file = download_data.get('source_file')
@@ -509,6 +511,11 @@ class VimeoIE(VimeoBaseInfoExtractor):
{
'url': 'https://vimeo.com/160743502/abd0e13fb4',
'only_matching': True,
},
{
# requires passing unlisted_hash(a52724358e) to load_download_config request
'url': 'https://vimeo.com/392479337/a52724358e',
'only_matching': True,
}
# https://gettingthingsdone.com/workflowmap/
# vimeo embed with check-password page protected by Referer header
@@ -673,7 +680,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
if config.get('view') == 4:
config = self._verify_player_video_password(redirect_url, video_id, headers)
vod = config.get('video', {}).get('vod', {})
video = config.get('video') or {}
vod = video.get('vod') or {}
def is_rented():
if '>You rented this title.<' in webpage:
@@ -733,7 +741,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
formats = []
source_format = self._extract_original_format(
'https://vimeo.com/' + video_id, video_id)
'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
if source_format:
formats.append(source_format)

View File

@@ -1,40 +1,55 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
int_or_none,
month_by_abbreviation,
parse_filesize,
unified_strdate,
)
class XboxClipsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?xboxclips\.com/(?:video\.php\?.*vid=|[^/]+/)(?P<id>[\w-]{36})'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?(?:xboxclips\.com|gameclips\.io)/(?:video\.php\?.*vid=|[^/]+/)(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
_TESTS = [{
'url': 'http://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325',
'md5': 'fbe1ec805e920aeb8eced3c3e657df5d',
'info_dict': {
'id': '074a69a9-5faf-46aa-b93b-9909c1720325',
'ext': 'mp4',
'title': 'Iabdulelah playing Titanfall',
'title': 'iAbdulElah playing Titanfall',
'filesize_approx': 26800000,
'upload_date': '20140807',
'duration': 56,
}
}
}, {
'url': 'https://gameclips.io/iAbdulElah/074a69a9-5faf-46aa-b93b-9909c1720325',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if '/video.php' in url:
qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
url = 'https://gameclips.io/%s/%s' % (qs['gamertag'][0], qs['vid'][0])
video_url = self._html_search_regex(
r'>(?:Link|Download): <a[^>]+href="([^"]+)"', webpage, 'video URL')
title = self._html_search_regex(
r'<title>XboxClips \| ([^<]+)</title>', webpage, 'title')
upload_date = unified_strdate(self._html_search_regex(
r'>Recorded: ([^<]+)<', webpage, 'upload date', fatal=False))
webpage = self._download_webpage(url, video_id)
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
title = self._html_search_meta(['og:title', 'twitter:title'], webpage)
upload_date = None
mobj = re.search(
r'>Recorded: (\d{2})-(Jan|Feb|Mar|Apr|May|Ju[nl]|Aug|Sep|Oct|Nov|Dec)-(\d{4})',
webpage)
if mobj:
upload_date = '%s%.2d%s' % (mobj.group(3), month_by_abbreviation(mobj.group(2)), mobj.group(1))
filesize = parse_filesize(self._html_search_regex(
r'>Size: ([^<]+)<', webpage, 'file size', fatal=False))
duration = int_or_none(self._html_search_regex(
@@ -42,12 +57,12 @@ class XboxClipsIE(InfoExtractor):
view_count = int_or_none(self._html_search_regex(
r'>Views: (\d+)<', webpage, 'view count', fatal=False))
return {
info.update({
'id': video_id,
'url': video_url,
'title': title,
'upload_date': upload_date,
'filesize_approx': filesize,
'duration': duration,
'view_count': view_count,
}
})
return info

View File

@@ -11,11 +11,14 @@ from ..utils import (
dict_get,
extract_attributes,
ExtractorError,
float_or_none,
int_or_none,
parse_duration,
str_or_none,
try_get,
unified_strdate,
url_or_none,
urljoin,
)
@@ -146,36 +149,89 @@ class XHamsterIE(InfoExtractor):
video = initials['videoModel']
title = video['title']
formats = []
for format_id, formats_dict in video['sources'].items():
format_urls = set()
format_sizes = {}
sources = try_get(video, lambda x: x['sources'], dict) or {}
for format_id, formats_dict in sources.items():
if not isinstance(formats_dict, dict):
continue
download_sources = try_get(sources, lambda x: x['download'], dict) or {}
for quality, format_dict in download_sources.items():
if not isinstance(format_dict, dict):
continue
format_sizes[quality] = float_or_none(format_dict.get('size'))
for quality, format_item in formats_dict.items():
if format_id == 'download':
# Download link takes some time to be generated,
# skipping for now
continue
if not isinstance(format_item, dict):
continue
format_url = format_item.get('link')
filesize = int_or_none(
format_item.get('size'), invscale=1000000)
else:
format_url = format_item
filesize = None
format_url = format_item
format_url = url_or_none(format_url)
if not format_url:
if not format_url or format_url in format_urls:
continue
format_urls.add(format_url)
formats.append({
'format_id': '%s-%s' % (format_id, quality),
'url': format_url,
'ext': determine_ext(format_url, 'mp4'),
'height': get_height(quality),
'filesize': filesize,
'filesize': format_sizes.get(quality),
'http_headers': {
'Referer': urlh.geturl(),
},
})
self._sort_formats(formats)
xplayer_sources = try_get(
initials, lambda x: x['xplayerSettings']['sources'], dict)
if xplayer_sources:
hls_sources = xplayer_sources.get('hls')
if isinstance(hls_sources, dict):
for hls_format_key in ('url', 'fallback'):
hls_url = hls_sources.get(hls_format_key)
if not hls_url:
continue
hls_url = urljoin(url, hls_url)
if not hls_url or hls_url in format_urls:
continue
format_urls.add(hls_url)
formats.extend(self._extract_m3u8_formats(
hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
standard_sources = xplayer_sources.get('standard')
if isinstance(standard_sources, dict):
for format_id, formats_list in standard_sources.items():
if not isinstance(formats_list, list):
continue
for standard_format in formats_list:
if not isinstance(standard_format, dict):
continue
for standard_format_key in ('url', 'fallback'):
standard_url = standard_format.get(standard_format_key)
if not standard_url:
continue
standard_url = urljoin(url, standard_url)
if not standard_url or standard_url in format_urls:
continue
format_urls.add(standard_url)
ext = determine_ext(standard_url, 'mp4')
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
standard_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
continue
quality = (str_or_none(standard_format.get('quality'))
or str_or_none(standard_format.get('label'))
or '')
formats.append({
'format_id': '%s-%s' % (format_id, quality),
'url': standard_url,
'ext': ext,
'height': get_height(quality),
'filesize': format_sizes.get(quality),
'http_headers': {
'Referer': standard_url,
},
})
self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
categories_list = video.get('categories')
if isinstance(categories_list, list):

View File

@@ -1,8 +1,9 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import hashlib
import itertools
import re
from .common import InfoExtractor
from ..compat import compat_str
@@ -209,17 +210,27 @@ class YandexMusicPlaylistBaseIE(YandexMusicBaseIE):
missing_track_ids = [
track_id for track_id in track_ids
if track_id not in present_track_ids]
missing_tracks = self._call_api(
'track-entries', tld, url, item_id,
'Downloading missing tracks JSON', {
'entries': ','.join(missing_track_ids),
'lang': tld,
'external-domain': 'music.yandex.%s' % tld,
'overembed': 'false',
'strict': 'true',
})
if missing_tracks:
tracks.extend(missing_tracks)
# Request missing tracks in chunks to avoid exceeding max HTTP header size,
# see https://github.com/ytdl-org/youtube-dl/issues/27355
_TRACKS_PER_CHUNK = 250
for chunk_num in itertools.count(0):
start = chunk_num * _TRACKS_PER_CHUNK
end = start + _TRACKS_PER_CHUNK
missing_track_ids_req = missing_track_ids[start:end]
assert missing_track_ids_req
missing_tracks = self._call_api(
'track-entries', tld, url, item_id,
'Downloading missing tracks JSON chunk %d' % (chunk_num + 1), {
'entries': ','.join(missing_track_ids_req),
'lang': tld,
'external-domain': 'music.yandex.%s' % tld,
'overembed': 'false',
'strict': 'true',
})
if missing_tracks:
tracks.extend(missing_tracks)
if end >= len(missing_track_ids):
break
return tracks

View File

@@ -25,6 +25,7 @@ class YouPornIE(InfoExtractor):
'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 210,
'uploader': 'Ask Dan And Jennifer',
'upload_date': '20101217',
'average_rating': int,
@@ -54,6 +55,7 @@ class YouPornIE(InfoExtractor):
'params': {
'skip_download': True,
},
'skip': '404',
}, {
'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/',
'only_matching': True,
@@ -153,6 +155,8 @@ class YouPornIE(InfoExtractor):
thumbnail = self._search_regex(
r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
webpage, 'thumbnail', fatal=False, group='thumbnail')
duration = int_or_none(self._html_search_meta(
'video:duration', webpage, 'duration', fatal=False))
uploader = self._html_search_regex(
r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
@@ -194,6 +198,7 @@ class YouPornIE(InfoExtractor):
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'uploader': uploader,
'upload_date': upload_date,
'average_rating': average_rating,

View File

@@ -308,7 +308,9 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
'view count', default=None))
uploader = try_get(
renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
renderer,
(lambda x: x['ownerText']['runs'][0]['text'],
lambda x: x['shortBylineText']['runs'][0]['text']), compat_str)
return {
'_type': 'url_transparent',
'ie_key': YoutubeIE.ie_key(),
@@ -324,52 +326,57 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
class YoutubeIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube.com'
_INVIDIOUS_SITES = (
# invidious-redirect websites
r'(?:www\.)?redirect\.invidious\.io',
r'(?:(?:www|dev)\.)?invidio\.us',
# Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
r'(?:(?:www|no)\.)?invidiou\.sh',
r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
r'(?:www\.)?invidious\.kabi\.tk',
r'(?:www\.)?invidious\.13ad\.de',
r'(?:www\.)?invidious\.mastodon\.host',
r'(?:www\.)?invidious\.zapashcanon\.fr',
r'(?:www\.)?invidious\.kavin\.rocks',
r'(?:www\.)?invidious\.tube',
r'(?:www\.)?invidiou\.site',
r'(?:www\.)?invidious\.site',
r'(?:www\.)?invidious\.xyz',
r'(?:www\.)?invidious\.nixnet\.xyz',
r'(?:www\.)?invidious\.drycat\.fr',
r'(?:www\.)?tube\.poal\.co',
r'(?:www\.)?tube\.connect\.cafe',
r'(?:www\.)?vid\.wxzm\.sx',
r'(?:www\.)?vid\.mint\.lgbt',
r'(?:www\.)?yewtu\.be',
r'(?:www\.)?yt\.elukerio\.org',
r'(?:www\.)?yt\.lelux\.fi',
r'(?:www\.)?invidious\.ggc-project\.de',
r'(?:www\.)?yt\.maisputain\.ovh',
r'(?:www\.)?invidious\.13ad\.de',
r'(?:www\.)?invidious\.toot\.koeln',
r'(?:www\.)?invidious\.fdn\.fr',
r'(?:www\.)?watch\.nettohikari\.com',
r'(?:www\.)?kgg2m7yk5aybusll\.onion',
r'(?:www\.)?qklhadlycap4cnod\.onion',
r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
)
_VALID_URL = r"""(?x)^
(
(?:https?://|//) # http(s):// or protocol-independent URL
(?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/|
(?:www\.)?deturl\.com/www\.youtube\.com/|
(?:www\.)?pwnyoutube\.com/|
(?:www\.)?hooktube\.com/|
(?:www\.)?yourepeat\.com/|
tube\.majestyc\.net/|
# Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
(?:(?:www|dev)\.)?invidio\.us/|
(?:(?:www|no)\.)?invidiou\.sh/|
(?:(?:www|fi)\.)?invidious\.snopyta\.org/|
(?:www\.)?invidious\.kabi\.tk/|
(?:www\.)?invidious\.13ad\.de/|
(?:www\.)?invidious\.mastodon\.host/|
(?:www\.)?invidious\.zapashcanon\.fr/|
(?:www\.)?invidious\.kavin\.rocks/|
(?:www\.)?invidious\.tube/|
(?:www\.)?invidiou\.site/|
(?:www\.)?invidious\.site/|
(?:www\.)?invidious\.xyz/|
(?:www\.)?invidious\.nixnet\.xyz/|
(?:www\.)?invidious\.drycat\.fr/|
(?:www\.)?tube\.poal\.co/|
(?:www\.)?tube\.connect\.cafe/|
(?:www\.)?vid\.wxzm\.sx/|
(?:www\.)?vid\.mint\.lgbt/|
(?:www\.)?yewtu\.be/|
(?:www\.)?yt\.elukerio\.org/|
(?:www\.)?yt\.lelux\.fi/|
(?:www\.)?invidious\.ggc-project\.de/|
(?:www\.)?yt\.maisputain\.ovh/|
(?:www\.)?invidious\.13ad\.de/|
(?:www\.)?invidious\.toot\.koeln/|
(?:www\.)?invidious\.fdn\.fr/|
(?:www\.)?watch\.nettohikari\.com/|
(?:www\.)?kgg2m7yk5aybusll\.onion/|
(?:www\.)?qklhadlycap4cnod\.onion/|
(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/|
youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
(?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
(?:www\.)?deturl\.com/www\.youtube\.com|
(?:www\.)?pwnyoutube\.com|
(?:www\.)?hooktube\.com|
(?:www\.)?yourepeat\.com|
tube\.majestyc\.net|
%(invidious)s|
youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
@@ -384,6 +391,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
youtu\.be| # just youtu.be/xxxx
vid\.plus| # or vid.plus/xxxx
zwearz\.com/watch| # or zwearz.com/watch/xxxx
%(invidious)s
)/
|(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
)
@@ -396,9 +404,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
)
)
(?(1).+)? # if we found the ID, everything can follow
$""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
$""" % {
'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
'invidious': '|'.join(_INVIDIOUS_SITES),
}
_PLAYER_INFO_RE = (
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?/base\.js$',
r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
)
_SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
@@ -500,6 +512,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'uploader': 'AfrojackVEVO',
'uploader_id': 'AfrojackVEVO',
'upload_date': '20131011',
'abr': 129.495,
},
'params': {
'youtube_include_dash_manifest': True,
@@ -902,6 +915,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'url': 'https://invidio.us/watch?v=BaW_jenozKc',
'only_matching': True,
},
{
'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
'only_matching': True,
},
{
# from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
'only_matching': True,
},
{
# DRM protected
'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
@@ -1018,6 +1040,33 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
'only_matching': True,
},
{
# https://github.com/ytdl-org/youtube-dl/pull/28094
'url': 'OtqTfy26tG0',
'info_dict': {
'id': 'OtqTfy26tG0',
'ext': 'mp4',
'title': 'Burn Out',
'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
'upload_date': '20141120',
'uploader': 'The Cinematic Orchestra - Topic',
'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
'artist': 'The Cinematic Orchestra',
'track': 'Burn Out',
'album': 'Every Day',
'release_data': None,
'release_year': None,
},
'params': {
'skip_download': True,
},
},
{
# controversial video, only works with bpctr when authenticated with cookies
'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
'only_matching': True,
},
]
_formats = {
'5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
@@ -1214,6 +1263,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
funcname = self._search_regex(
(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'\bm=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(h\.s\)\)',
r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(c\)\)',
r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\);[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\)',
r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
# Obsolete patterns
@@ -1378,7 +1430,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
video_id = self._match_id(url)
base_url = self.http_scheme() + '//www.youtube.com/'
webpage_url = base_url + 'watch?v=' + video_id
webpage = self._download_webpage(webpage_url, video_id, fatal=False)
webpage = self._download_webpage(
webpage_url + '&bpctr=9999999999', video_id, fatal=False)
player_response = None
if webpage:
@@ -1477,6 +1530,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
formats = []
itags = []
itag_qualities = {}
player_url = None
q = qualities(['tiny', 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'])
streaming_data = player_response.get('streamingData') or {}
@@ -1486,6 +1540,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
continue
itag = str_or_none(fmt.get('itag'))
quality = fmt.get('quality')
if itag and quality:
itag_qualities[itag] = quality
# FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
# (adding `&sq=0` to the URL) and parsing emsg box to determine the
# number of fragment that would subsequently requested with (`&sq=N`)
if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
continue
fmt_url = fmt.get('url')
if not fmt_url:
sc = compat_parse_qs(fmt.get('signatureCipher'))
@@ -1505,10 +1569,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
fmt_url += '&' + sp + '=' + signature
itag = str_or_none(fmt.get('itag'))
if itag:
itags.append(itag)
quality = fmt.get('quality')
tbr = float_or_none(
fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
dct = {
'asr': int_or_none(fmt.get('audioSampleRate')),
'filesize': int_or_none(fmt.get('contentLength')),
@@ -1517,8 +1581,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'fps': int_or_none(fmt.get('fps')),
'height': int_or_none(fmt.get('height')),
'quality': q(quality),
'tbr': float_or_none(fmt.get(
'averageBitrate') or fmt.get('bitrate'), 1000),
'tbr': tbr,
'url': fmt_url,
'width': fmt.get('width'),
}
@@ -1529,11 +1592,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if mobj:
dct['ext'] = mimetype2ext(mobj.group(1))
dct.update(parse_codecs(mobj.group(2)))
if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
no_audio = dct.get('acodec') == 'none'
no_video = dct.get('vcodec') == 'none'
if no_audio:
dct['vbr'] = tbr
if no_video:
dct['abr'] = tbr
if no_audio or no_video:
dct['downloader_options'] = {
# Youtube throttles chunks >~10M
'http_chunk_size': 10485760,
}
if dct.get('ext'):
dct['container'] = dct['ext'] + '_dash'
formats.append(dct)
hls_manifest_url = streaming_data.get('hlsManifestUrl')
@@ -1549,22 +1620,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if self._downloader.params.get('youtube_include_dash_manifest'):
dash_manifest_url = streaming_data.get('dashManifestUrl')
if dash_manifest_url:
dash_formats = []
for f in self._extract_mpd_formats(
dash_manifest_url, video_id, fatal=False):
itag = f['format_id']
if itag in itags:
continue
if itag in itag_qualities:
f['quality'] = q(itag_qualities[itag])
filesize = int_or_none(self._search_regex(
r'/clen/(\d+)', f.get('fragment_base_url')
or f['url'], 'file size', default=None))
if filesize:
f['filesize'] = filesize
dash_formats.append(f)
# Until further investigation prefer DASH formats as non-DASH
# may not be available (see [1])
# 1. https://github.com/ytdl-org/youtube-dl/issues/28070
if dash_formats:
dash_formats_keys = [f['format_id'] for f in dash_formats]
formats = [f for f in formats if f['format_id'] not in dash_formats_keys]
formats.extend(dash_formats)
formats.append(f)
if not formats:
if streaming_data.get('licenseInfos'):
@@ -1729,7 +1797,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
'track': mobj.group('track').strip(),
'release_date': release_date,
'release_year': int(release_year),
'release_year': int_or_none(release_year),
})
initial_data = None
@@ -2334,9 +2402,9 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
next_continuation = cls._extract_next_continuation_data(renderer)
if next_continuation:
return next_continuation
contents = renderer.get('contents')
if not isinstance(contents, list):
return
contents = []
for key in ('contents', 'items'):
contents.extend(try_get(renderer, lambda x: x[key], list) or [])
for content in contents:
if not isinstance(content, dict):
continue
@@ -2469,6 +2537,13 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
continuation_item = continuation_items[0]
if not isinstance(continuation_item, dict):
continue
renderer = continuation_item.get('gridVideoRenderer')
if renderer:
grid_renderer = {'items': continuation_items}
for entry in self._grid_entries(grid_renderer):
yield entry
continuation = self._extract_continuation(grid_renderer)
continue
renderer = continuation_item.get('playlistVideoRenderer') or continuation_item.get('itemSectionRenderer')
if renderer:
video_list_renderer = {'contents': continuation_items}

View File

@@ -0,0 +1,69 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import float_or_none, int_or_none
class ZhihuIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?zhihu\.com/zvideo/(?P<id>[0-9]+)'
_TEST = {
'url': 'https://www.zhihu.com/zvideo/1342930761977176064',
'md5': 'c8d4c9cd72dd58e6f9bc9c2c84266464',
'info_dict': {
'id': '1342930761977176064',
'ext': 'mp4',
'title': '写春联也太难了吧!',
'thumbnail': r're:^https?://.*\.jpg',
'uploader': '桥半舫',
'timestamp': 1612959715,
'upload_date': '20210210',
'uploader_id': '244ecb13b0fd7daf92235288c8ca3365',
'duration': 146.333,
'view_count': int,
'like_count': int,
'comment_count': int,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
zvideo = self._download_json(
'https://www.zhihu.com/api/v4/zvideos/' + video_id, video_id)
title = zvideo['title']
video = zvideo.get('video') or {}
formats = []
for format_id, q in (video.get('playlist') or {}).items():
play_url = q.get('url') or q.get('play_url')
if not play_url:
continue
formats.append({
'asr': int_or_none(q.get('sample_rate')),
'filesize': int_or_none(q.get('size')),
'format_id': format_id,
'fps': int_or_none(q.get('fps')),
'height': int_or_none(q.get('height')),
'tbr': float_or_none(q.get('bitrate')),
'url': play_url,
'width': int_or_none(q.get('width')),
})
self._sort_formats(formats)
author = zvideo.get('author') or {}
url_token = author.get('url_token')
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': video.get('thumbnail') or zvideo.get('image_url'),
'uploader': author.get('name'),
'timestamp': int_or_none(zvideo.get('published_at')),
'uploader_id': author.get('id'),
'uploader_url': 'https://www.zhihu.com/people/' + url_token if url_token else None,
'duration': float_or_none(video.get('duration')),
'view_count': int_or_none(zvideo.get('play_count')),
'like_count': int_or_none(zvideo.get('liked_count')),
'comment_count': int_or_none(zvideo.get('comment_count')),
}

View File

@@ -89,10 +89,14 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
elif info['ext'] in ['m4a', 'mp4']:
if not check_executable('AtomicParsley', ['-v']):
atomicparsley = next((x
for x in ['AtomicParsley', 'atomicparsley']
if check_executable(x, ['-v'])), None)
if atomicparsley is None:
raise EmbedThumbnailPPError('AtomicParsley was not found. Please install.')
cmd = [encodeFilename('AtomicParsley', True),
cmd = [encodeFilename(atomicparsley, True),
encodeFilename(filename, True),
encodeArgument('--artwork'),
encodeFilename(thumbnail_filename, True),

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2021.02.04.1'
__version__ = '2021.02.22'