3 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .youtube import YoutubeIE
10 from ..compat import (
12 compat_urllib_parse_unquote,
13 compat_urllib_request,
15 compat_xml_parse_error,
33 from .brightcove import BrightcoveIE
34 from .nbc import NBCSportsVPlayerIE
35 from .ooyala import OoyalaIE
36 from .rutv import RUTVIE
37 from .tvc import TVCIE
38 from .sportbox import SportBoxEmbedIE
39 from .smotri import SmotriIE
40 from .myvi import MyviIE
41 from .condenast import CondeNastIE
42 from .udn import UDNEmbedIE
43 from .senateisvp import SenateISVPIE
44 from .bliptv import BlipTVIE
45 from .svt import SVTIE
46 from .pornhub import PornHubIE
47 from .xhamster import XHamsterEmbedIE
48 from .vimeo import VimeoIE
49 from .dailymotion import DailymotionCloudIE
50 from .onionstudios import OnionStudiosIE
51 from .snagfilms import SnagFilmsEmbedIE
54 class GenericIE(InfoExtractor):
55 IE_DESC = 'Generic downloader that works on some sites'
59 # Direct link to a video
61 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
62 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
67 'upload_date': '20100513',
70 # Direct link to media delivered compressed (until Accept-Encoding is *)
72 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
73 'md5': '128c42e68b13950268b648275386fc74',
75 'id': 'FictionJunction-Parallel_Hearts',
77 'title': 'FictionJunction-Parallel_Hearts',
78 'upload_date': '20140522',
80 'expected_warnings': [
81 'URL could be a direct video link, returning it as such.'
84 # Direct download with broken HEAD
86 'url': 'http://ai-radio.org:8000/radio.opus',
93 'skip_download': True, # infinite live stream
95 'expected_warnings': [
96 r'501.*Not Implemented'
99 # Direct link with incorrect MIME type
101 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
102 'md5': '4ccbebe5f36706d85221f204d7eb5913',
104 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
105 'id': '5_Lennart_Poettering_-_Systemd',
107 'title': '5_Lennart_Poettering_-_Systemd',
108 'upload_date': '20141120',
110 'expected_warnings': [
111 'URL could be a direct video link, returning it as such.'
116 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
118 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
119 'title': 'Zero Punctuation',
120 'description': 're:.*groundbreaking video review series.*'
122 'playlist_mincount': 11,
124 # RSS feed with enclosure
126 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
128 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
130 'upload_date': '20150228',
131 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
136 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
140 'upload_date': '20130224',
141 'uploader_id': 'TheVerge',
142 'description': 're:^Chris Ziegler takes a look at the\.*',
143 'uploader': 'The Verge',
144 'title': 'First Firefox OS phones side-by-side',
147 'skip_download': False,
151 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
152 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
154 'id': '13601338388002',
156 'uploader': 'www.hodiho.fr',
157 'title': 'R\u00e9gis plante sa Jeep',
160 # bandcamp page with custom domain
162 'add_ie': ['Bandcamp'],
163 'url': 'http://bronyrock.com/track/the-pony-mash',
167 'title': 'The Pony Mash',
168 'uploader': 'M_Pallante',
170 'skip': 'There is a limit of 200 free downloads / month for the test song',
172 # embedded brightcove video
173 # it also tests brightcove videos that need to set the 'Referer' in the
176 'add_ie': ['Brightcove'],
177 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
179 'id': '2765128793001',
181 'title': 'Le cours de bourse : l’analyse technique',
182 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
183 'uploader': 'BFM BUSINESS',
186 'skip_download': True,
190 # https://github.com/rg3/youtube-dl/issues/2253
191 'url': 'http://bcove.me/i6nfkrc3',
192 'md5': '0ba9446db037002366bab3b3eb30c88c',
194 'id': '3101154703001',
196 'title': 'Still no power',
197 'uploader': 'thestar.com',
198 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
200 'add_ie': ['Brightcove'],
203 'url': 'http://www.championat.com/video/football/v/87/87499.html',
204 'md5': 'fb973ecf6e4a78a67453647444222983',
206 'id': '3414141473001',
208 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
209 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
210 'uploader': 'Championat',
214 # https://github.com/rg3/youtube-dl/issues/3541
215 'add_ie': ['Brightcove'],
216 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
218 'id': '3866516442001',
220 'title': 'Leer mij vrouwen kennen: Aflevering 1',
221 'description': 'Leer mij vrouwen kennen: Aflevering 1',
222 'uploader': 'SBS Broadcasting',
224 'skip': 'Restricted to Netherlands',
226 'skip_download': True, # m3u8 download
231 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
232 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
234 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
236 'title': '2cc213299525360.mov', # that's what we get
238 'add_ie': ['Ooyala'],
240 # multiple ooyala embeds on SBN network websites
242 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
244 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
245 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
247 'playlist_mincount': 3,
249 'skip_download': True,
251 'add_ie': ['Ooyala'],
255 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
259 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
260 'upload_date': '20140225',
261 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
262 'uploader': 'Tested',
263 'uploader_id': 'testedcom',
265 # No need to test YoutubeIE here
267 'skip_download': True,
272 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
276 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
277 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
282 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
284 'title': 'BBC - Blogs - Adam Curtis - BUGGER',
286 'playlist_mincount': 18,
290 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
294 'title': 'Охотское море стало целиком российским',
295 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
299 'skip_download': True,
304 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
308 'title': 'Дошкольное воспитание',
313 'url': 'http://www.vestifinance.ru/articles/25753',
316 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
321 'title': 'Госзаказ. День 3',
327 'title': 'Госзаказ. День 2',
333 'title': 'Госзаказ. День 1',
339 'skip_download': True,
344 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
346 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
348 'title': 'Ужастики, русский трейлер (2015)',
349 'thumbnail': 're:^https?://.*\.jpg$',
355 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
358 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
360 'playlist_mincount': 7,
364 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
365 'md5': '65fdff94098e4a607385a60c5177c638',
369 'title': 'Hidden miracles of the natural world',
370 'uploader': 'Louie Schwartzberg',
371 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
374 # Embeded Ustream video
376 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
377 'md5': '27b99cdb639c9b12a79bca876a073417',
381 'uploader': 'AU SPA: The NSA and Privacy',
382 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
385 # nowvideo embed hidden behind percent encoding
387 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
388 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
390 'id': '06e53103ca9aa',
392 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
393 'description': 'No description',
398 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
399 'md5': '7653032cbb25bf6c80d80f217055fa43',
401 'id': '048195-004_PLUS7-F',
404 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
405 'upload_date': '20140320',
408 'skip_download': 'Requires rtmpdump'
413 'url': 'http://www.wired.com/2014/04/honda-asimo/',
414 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
416 'id': '53501be369702d3275860000',
418 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
423 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
424 'md5': '441aeeb82eb72c422c7f14ec533999cd',
426 'id': 'k2mm4bCdJ6CQ2i7c8o2',
428 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
431 'add_ie': ['Dailymotion'],
435 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
439 'title': 'The NBL Auction 2014',
440 'uploader': 'BADMINTON England',
441 'uploader_id': 'BADMINTONEvents',
442 'upload_date': '20140603',
443 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
445 'add_ie': ['Youtube'],
447 'skip_download': True,
452 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
453 'md5': '35727f82f58c76d996fc188f9755b0d5',
455 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
458 'description': 'Mario\'s life in the fast lane has never looked so good.',
461 # YouTube embed via <data-embed-url="">
463 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
467 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
468 'uploader': 'Gameloft',
469 'uploader_id': 'gameloft',
470 'upload_date': '20140828',
471 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
474 'skip_download': True,
479 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
481 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
483 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
484 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
489 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
491 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
492 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
498 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
503 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
504 'md5': '9d65602bf31c6e20014319c7d07fba27',
506 'id': '5123ea6d5e5a7',
509 'uploader': 'www.handjobhub.com',
510 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
513 # Multiple brightcove videos
514 # https://github.com/rg3/youtube-dl/issues/2283
516 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
518 'id': 'always-never',
519 'title': 'Always / Never - The New Yorker',
523 'extract_flat': False,
524 'skip_download': True,
529 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
530 'md5': '96f09a37e44da40dd083e12d9a683327',
534 'title': 'Ump changes call to ball',
535 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
537 'timestamp': 1401537900,
538 'upload_date': '20140531',
539 'thumbnail': 're:^https?://.*\.jpg$',
544 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
545 'md5': '8788b683c777a5cf25621eaf286d0c23',
549 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
551 'filesize': 182808282,
552 'uploader': 'education-portal.com',
556 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
557 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
561 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
563 'uploader': 'thoughtworks.wistia.com',
568 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
572 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
573 'uploader': 'Sophos Security',
574 'title': 'Chet Chat 171 - Oct 29, 2014',
575 'upload_date': '20141029',
580 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
584 'upload_date': '20141112',
585 'title': 'Rosetta #CometLanding webcast HL 10',
590 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
593 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
595 'playlist_mincount': 2,
599 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
603 'upload_date': '20141126',
604 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
609 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
611 'id': '730m_DandD_1901_512k',
613 'uploader': 'www.abc.net.au',
614 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
617 # embedded viddler video
619 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
623 'uploader': 'deadspin',
624 'title': 'WALL-TO-GORTAT',
625 'timestamp': 1422285291,
626 'upload_date': '20150126',
628 'add_ie': ['Viddler'],
632 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
636 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
637 'description': 'md5:601cb790edd05908957dae8aaa866465',
638 'upload_date': '20150220',
643 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
647 'upload_date': '20150212',
648 'uploader': 'The National Archives UK',
649 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
650 'uploader_id': 'NationalArchives08',
651 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
656 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
657 'playlist_mincount': 5,
659 'id': 'aanslagen-kopenhagen',
660 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
665 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
669 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
674 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
678 'upload_date': '20150226',
679 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
681 'title': 'John Carlson Postgame 2/25/15',
684 # Kaltura embed (different embed code)
686 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
690 'upload_date': '20150127',
691 'uploader_id': 'PremierMedia',
693 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
696 # Eagle.Platform embed (generic URL)
698 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
702 'title': 'Навальный вышел на свободу',
703 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
704 'thumbnail': 're:^https?://.*\.jpg$',
710 # ClipYou (Eagle.Platform) embed (custom URL)
712 'url': 'http://muz-tv.ru/play/7129/',
716 'title': "'O Sole Mio",
717 'thumbnail': 're:^https?://.*\.jpg$',
724 'url': 'http://muz-tv.ru/kinozal/view/7400/',
728 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
729 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
730 'thumbnail': 're:^https?://.*\.jpg$',
737 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
741 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
742 'thumbnail': 're:^https?://.*\.png$',
748 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
749 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
753 'title': 'Facebook Creates "On This Day" | Crunch Report',
758 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
762 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
767 # Crooks and Liars embed
769 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
773 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
774 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
775 'timestamp': 1428207000,
776 'upload_date': '20150405',
777 'uploader': 'Heather',
780 # Crooks and Liars external embed
782 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
784 'id': 'MTE3MjUtMzQ2MzA',
786 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
787 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
788 'timestamp': 1265032391,
789 'upload_date': '20100201',
790 'uploader': 'Heather',
793 # NBC Sports vplayer embed
795 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
797 'id': 'ln7x1qSThw4k',
799 'title': "PFT Live: New leader in the 'new-look' defense",
800 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
805 'url': 'http://www.udn.com/news/story/7314/822787',
806 'md5': 'fd2060e988c326991037b9aff9df21a6',
810 'title': '中一中男師變性 全校師生力挺',
811 'thumbnail': 're:^https?://.*\.jpg$',
816 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
818 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
820 'description': 'VIDEO: Index/Match versus VLOOKUP.',
821 'title': 'This is what separates the Excel masters from the wannabes',
825 'skip_download': True,
828 # Contains a SMIL manifest
830 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
834 'title': '+ Football: Lottery Champions League Europe',
835 'uploader': 'www.telewebion.com',
839 'skip_download': True,
842 # Brightcove URL in single quotes
844 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
845 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
847 'id': '4255764656001',
849 'title': 'SN Presents: Russell Martin, World Citizen',
850 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
851 'uploader': 'Rogers Sportsnet',
854 # Dailymotion Cloud video
856 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
857 'md5': '49444254273501a64675a7e68c502681',
859 'id': '5585de919473990de4bee11b',
862 'thumbnail': 're:^https?://.*\.jpe?g$',
867 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
871 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
872 'thumbnail': 're:^https?://.*\.jpe?g$',
873 'uploader': 'ClickHole',
874 'uploader_id': 'clickhole',
879 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
881 'id': '74849a00-85a9-11e1-9660-123139220831',
883 'title': '#whilewewatch',
888 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
889 'md5': '43662b577c018ad707a63766462b1e87',
893 'title': 'New experience with Acrobat DC',
894 'description': 'New experience with Acrobat DC',
900 def report_following_redirect(self, new_url):
901 """Report information extraction."""
902 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
904 def _extract_rss(self, url, video_id, doc):
905 playlist_title = doc.find('./channel/title').text
906 playlist_desc_el = doc.find('./channel/description')
907 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
910 for it in doc.findall('./channel/item'):
911 next_url = xpath_text(it, 'link', fatal=False)
913 enclosure_nodes = it.findall('./enclosure')
914 for e in enclosure_nodes:
915 next_url = e.attrib.get('url')
925 'title': it.find('title').text,
931 'title': playlist_title,
932 'description': playlist_desc,
936 def _extract_camtasia(self, url, video_id, webpage):
937 """ Returns None if no camtasia video can be found. """
939 camtasia_cfg = self._search_regex(
940 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
941 webpage, 'camtasia configuration file', default=None)
942 if camtasia_cfg is None:
945 title = self._html_search_meta('DC.title', webpage, fatal=True)
947 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
948 camtasia_cfg = self._download_xml(
949 camtasia_url, video_id,
950 note='Downloading camtasia configuration',
951 errnote='Failed to download camtasia configuration')
952 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
955 for n in fileset_node.getchildren():
956 url_n = n.find('./uri')
961 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
962 'title': '%s - %s' % (title, n.tag),
963 'url': compat_urlparse.urljoin(url, url_n.text),
964 'duration': float_or_none(n.find('./duration').text),
973 def _real_extract(self, url):
974 if url.startswith('//'):
977 'url': self.http_scheme() + url,
980 parsed_url = compat_urlparse.urlparse(url)
981 if not parsed_url.scheme:
982 default_search = self._downloader.params.get('default_search')
983 if default_search is None:
984 default_search = 'fixup_error'
986 if default_search in ('auto', 'auto_warning', 'fixup_error'):
988 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
989 return self.url_result('http://' + url)
990 elif default_search != 'fixup_error':
991 if default_search == 'auto_warning':
992 if re.match(r'^(?:url|URL)$', url):
993 raise ExtractorError(
994 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
997 self._downloader.report_warning(
998 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
999 return self.url_result('ytsearch:' + url)
1001 if default_search in ('error', 'fixup_error'):
1002 raise ExtractorError(
1003 '%r is not a valid URL. '
1004 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1005 % (url, url), expected=True)
1007 if ':' not in default_search:
1008 default_search += ':'
1009 return self.url_result(default_search + url)
1011 url, smuggled_data = unsmuggle_url(url)
1012 force_videoid = None
1013 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1014 if smuggled_data and 'force_videoid' in smuggled_data:
1015 force_videoid = smuggled_data['force_videoid']
1016 video_id = force_videoid
1018 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1020 self.to_screen('%s: Requesting header' % video_id)
1022 head_req = HEADRequest(url)
1023 head_response = self._request_webpage(
1025 note=False, errnote='Could not send HEAD request to %s' % url,
1028 if head_response is not False:
1029 # Check for redirect
1030 new_url = head_response.geturl()
1032 self.report_following_redirect(new_url)
1034 new_url = smuggle_url(
1035 new_url, {'force_videoid': force_videoid})
1036 return self.url_result(new_url)
1038 full_response = None
1039 if head_response is False:
1040 request = compat_urllib_request.Request(url)
1041 request.add_header('Accept-Encoding', '*')
1042 full_response = self._request_webpage(request, video_id)
1043 head_response = full_response
1045 # Check for direct link to a video
1046 content_type = head_response.headers.get('Content-Type', '')
1047 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1049 upload_date = unified_strdate(
1050 head_response.headers.get('Last-Modified'))
1053 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1056 'format_id': m.group('format_id'),
1058 'vcodec': 'none' if m.group('type') == 'audio' else None
1060 'upload_date': upload_date,
1063 if not self._downloader.params.get('test', False) and not is_intentional:
1064 force = self._downloader.params.get('force_generic_extractor', False)
1065 self._downloader.report_warning(
1066 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1068 if not full_response:
1069 request = compat_urllib_request.Request(url)
1070 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1071 # making it impossible to download only chunk of the file (yet we need only 512kB to
1072 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1073 # that will always result in downloading the whole file that is not desirable.
1074 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1075 # to accept raw bytes and being able to download only a chunk.
1076 # It may probably better to solve this by checking Content-Type for application/octet-stream
1077 # after HEAD request finishes, but not sure if we can rely on this.
1078 request.add_header('Accept-Encoding', '*')
1079 full_response = self._request_webpage(request, video_id)
1081 # Maybe it's a direct link to a video?
1082 # Be careful not to download the whole thing!
1083 first_bytes = full_response.read(512)
1084 if not is_html(first_bytes):
1085 self._downloader.report_warning(
1086 'URL could be a direct video link, returning it as such.')
1087 upload_date = unified_strdate(
1088 head_response.headers.get('Last-Modified'))
1091 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1094 'upload_date': upload_date,
1097 webpage = self._webpage_read_content(
1098 full_response, url, video_id, prefix=first_bytes)
1100 self.report_extraction(video_id)
1102 # Is it an RSS feed?
1104 doc = parse_xml(webpage)
1105 if doc.tag == 'rss':
1106 return self._extract_rss(url, video_id, doc)
1107 except compat_xml_parse_error:
1110 # Is it a Camtasia project?
1111 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1112 if camtasia_res is not None:
1115 # Sometimes embedded video player is hidden behind percent encoding
1116 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1117 # Unescaping the whole page allows to handle those cases in a generic way
1118 webpage = compat_urllib_parse.unquote(webpage)
1120 # it's tempting to parse this further, but you would
1121 # have to take into account all the variations like
1122 # Video Title - Site Name
1123 # Site Name | Video Title
1124 # Video Title - Tagline | Site Name
1125 # and so on and so forth; it's just not practical
1126 video_title = self._html_search_regex(
1127 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1130 # Try to detect age limit automatically
1131 age_limit = self._rta_search(webpage)
1132 # And then there are the jokers who advertise that they use RTA,
1133 # but actually don't.
1134 AGE_LIMIT_MARKERS = [
1135 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1137 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1140 # video uploader is domain name
1141 video_uploader = self._search_regex(
1142 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1145 def _playlist_from_matches(matches, getter=None, ie=None):
1147 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1149 return self.playlist_result(
1150 urlrs, playlist_id=video_id, playlist_title=video_title)
1152 # Look for BrightCove:
1153 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1155 self.to_screen('Brightcove video detected.')
1158 'url': smuggle_url(bc_url, {'Referer': url}),
1159 'ie_key': 'Brightcove'
1160 } for bc_url in bc_urls]
1163 '_type': 'playlist',
1164 'title': video_title,
1169 # Look for embedded rtl.nl player
1170 matches = re.findall(
1171 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1174 return _playlist_from_matches(matches, ie='RtlNl')
1176 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1177 if vimeo_url is not None:
1178 return self.url_result(vimeo_url)
1180 # Look for embedded YouTube player
1181 matches = re.findall(r'''(?x)
1190 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1194 return _playlist_from_matches(
1195 matches, lambda m: unescapeHTML(m[1]))
1197 # Look for lazyYT YouTube embed
1198 matches = re.findall(
1199 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1201 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1203 # Look for embedded Dailymotion player
1204 matches = re.findall(
1205 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1207 return _playlist_from_matches(
1208 matches, lambda m: unescapeHTML(m[1]))
1210 # Look for embedded Dailymotion playlist player (#3822)
1212 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1214 playlists = re.findall(
1215 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1217 return _playlist_from_matches(
1218 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1220 # Look for embedded Wistia player
1222 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1224 embed_url = self._proto_relative_url(
1225 unescapeHTML(match.group('url')))
1227 '_type': 'url_transparent',
1230 'uploader': video_uploader,
1231 'title': video_title,
1235 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1238 '_type': 'url_transparent',
1239 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1241 'uploader': video_uploader,
1242 'title': video_title,
1243 'id': match.group('id')
1246 # Look for embedded blip.tv player
1247 bliptv_url = BlipTVIE._extract_url(webpage)
1249 return self.url_result(bliptv_url, 'BlipTV')
1251 # Look for SVT player
1252 svt_url = SVTIE._extract_url(webpage)
1254 return self.url_result(svt_url, 'SVT')
1256 # Look for embedded condenast player
1257 matches = re.findall(
1258 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1262 '_type': 'playlist',
1265 'ie_key': 'CondeNast',
1267 } for ma in matches],
1268 'title': video_title,
1272 # Look for Bandcamp pages with custom domain
1273 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1274 if mobj is not None:
1275 burl = unescapeHTML(mobj.group(1))
1276 # Don't set the extractor because it can be a track url or an album
1277 return self.url_result(burl)
1279 # Look for embedded Vevo player
1281 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1282 if mobj is not None:
1283 return self.url_result(mobj.group('url'))
1285 # Look for embedded Viddler player
1287 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1289 if mobj is not None:
1290 return self.url_result(mobj.group('url'))
1292 # Look for NYTimes player
1294 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1296 if mobj is not None:
1297 return self.url_result(mobj.group('url'))
1299 # Look for Libsyn player
1301 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1302 if mobj is not None:
1303 return self.url_result(mobj.group('url'))
1305 # Look for Ooyala videos
1306 mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1307 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1308 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1309 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1310 if mobj is not None:
1311 return OoyalaIE._build_url_result(mobj.group('ec'))
1313 # Look for multiple Ooyala embeds on SBN network websites
1314 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1315 if mobj is not None:
1316 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1318 return _playlist_from_matches(
1319 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1321 # Look for Aparat videos
1322 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1323 if mobj is not None:
1324 return self.url_result(mobj.group(1), 'Aparat')
1326 # Look for MPORA videos
1327 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1328 if mobj is not None:
1329 return self.url_result(mobj.group(1), 'Mpora')
1331 # Look for embedded NovaMov-based player
1333 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1334 (?P<url>http://(?:(?:embed|www)\.)?
1336 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1337 videoweed\.(?:es|com)|
1338 movshare\.(?:net|sx|ag)|
1339 divxstage\.(?:eu|net|ch|co|at|ag))
1340 /embed\.php.+?)\1''', webpage)
1341 if mobj is not None:
1342 return self.url_result(mobj.group('url'))
1344 # Look for embedded Facebook player
1346 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1347 if mobj is not None:
1348 return self.url_result(mobj.group('url'), 'Facebook')
1350 # Look for embedded VK player
1351 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1352 if mobj is not None:
1353 return self.url_result(mobj.group('url'), 'VK')
1355 # Look for embedded ivi player
1356 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1357 if mobj is not None:
1358 return self.url_result(mobj.group('url'), 'Ivi')
1360 # Look for embedded Huffington Post player
1362 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1363 if mobj is not None:
1364 return self.url_result(mobj.group('url'), 'HuffPost')
1367 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1368 if mobj is not None:
1369 return self.url_result(mobj.group('url'))
1370 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1371 if mobj is not None:
1372 return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
1374 # Look for funnyordie embed
1375 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1377 return _playlist_from_matches(
1378 matches, getter=unescapeHTML, ie='FunnyOrDie')
1380 # Look for BBC iPlayer embed
1381 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1383 return _playlist_from_matches(matches, ie='BBCCoUk')
1385 # Look for embedded RUTV player
1386 rutv_url = RUTVIE._extract_url(webpage)
1388 return self.url_result(rutv_url, 'RUTV')
1390 # Look for embedded TVC player
1391 tvc_url = TVCIE._extract_url(webpage)
1393 return self.url_result(tvc_url, 'TVC')
1395 # Look for embedded SportBox player
1396 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1398 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1400 # Look for embedded PornHub player
1401 pornhub_url = PornHubIE._extract_url(webpage)
1403 return self.url_result(pornhub_url, 'PornHub')
1405 # Look for embedded XHamster player
1406 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1408 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1410 # Look for embedded Tvigle player
1412 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1413 if mobj is not None:
1414 return self.url_result(mobj.group('url'), 'Tvigle')
1416 # Look for embedded TED player
1418 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1419 if mobj is not None:
1420 return self.url_result(mobj.group('url'), 'TED')
1422 # Look for embedded Ustream videos
1424 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1425 if mobj is not None:
1426 return self.url_result(mobj.group('url'), 'Ustream')
1428 # Look for embedded arte.tv player
1430 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1432 if mobj is not None:
1433 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1435 # Look for embedded smotri.com player
1436 smotri_url = SmotriIE._extract_url(webpage)
1438 return self.url_result(smotri_url, 'Smotri')
1440 # Look for embedded Myvi.ru player
1441 myvi_url = MyviIE._extract_url(webpage)
1443 return self.url_result(myvi_url)
1445 # Look for embeded soundcloud player
1447 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1449 if mobj is not None:
1450 url = unescapeHTML(mobj.group('url'))
1451 return self.url_result(url)
1453 # Look for embedded vulture.com player
1455 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1457 if mobj is not None:
1458 url = unescapeHTML(mobj.group('url'))
1459 return self.url_result(url, ie='Vulture')
1461 # Look for embedded mtvservices player
1463 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1465 if mobj is not None:
1466 url = unescapeHTML(mobj.group('url'))
1467 return self.url_result(url, ie='MTVServicesEmbedded')
1469 # Look for embedded yahoo player
1471 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1473 if mobj is not None:
1474 return self.url_result(mobj.group('url'), 'Yahoo')
1476 # Look for embedded sbs.com.au player
1480 <meta\s+property="og:video"\s+content=|
1483 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1485 if mobj is not None:
1486 return self.url_result(mobj.group('url'), 'SBS')
1488 # Look for embedded Cinchcast player
1490 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1492 if mobj is not None:
1493 return self.url_result(mobj.group('url'), 'Cinchcast')
1496 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1500 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1502 if mobj is not None:
1503 return self.url_result(mobj.group('url'), 'MLB')
1506 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1508 if mobj is not None:
1509 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1512 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1514 if mobj is not None:
1515 return self.url_result(mobj.group('url'), 'Livestream')
1517 # Look for Zapiks embed
1519 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1520 if mobj is not None:
1521 return self.url_result(mobj.group('url'), 'Zapiks')
1523 # Look for Kaltura embeds
1524 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1525 re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
1526 if mobj is not None:
1527 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1529 # Look for Eagle.Platform embeds
1531 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1532 if mobj is not None:
1533 return self.url_result(mobj.group('url'), 'EaglePlatform')
1535 # Look for ClipYou (uses Eagle.Platform) embeds
1537 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1538 if mobj is not None:
1539 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1541 # Look for Pladform embeds
1543 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1544 if mobj is not None:
1545 return self.url_result(mobj.group('url'), 'Pladform')
1547 # Look for Playwire embeds
1549 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1550 if mobj is not None:
1551 return self.url_result(mobj.group('url'))
1553 # Look for 5min embeds
1555 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1556 if mobj is not None:
1557 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1559 # Look for Crooks and Liars embeds
1561 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1562 if mobj is not None:
1563 return self.url_result(mobj.group('url'))
1565 # Look for NBC Sports VPlayer embeds
1566 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1568 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1570 # Look for UDN embeds
1572 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1573 if mobj is not None:
1574 return self.url_result(
1575 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1577 # Look for Senate ISVP iframe
1578 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1580 return self.url_result(senate_isvp_url, 'SenateISVP')
1582 # Look for Dailymotion Cloud videos
1583 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1585 return self.url_result(dmcloud_url, 'DailymotionCloud')
1587 # Look for OnionStudios embeds
1588 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1589 if onionstudios_url:
1590 return self.url_result(onionstudios_url)
1592 # Look for SnagFilms embeds
1593 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1595 return self.url_result(snagfilms_url)
1597 # Look for AdobeTVVideo embeds
1599 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1601 if mobj is not None:
1602 return self.url_result(
1603 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1606 def check_video(vurl):
1607 if YoutubeIE.suitable(vurl):
1609 vpath = compat_urlparse.urlparse(vurl).path
1610 vext = determine_ext(vpath)
1611 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1613 def filter_video(urls):
1614 return list(filter(check_video, urls))
1616 # Start with something easy: JW Player in SWFObject
1617 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1619 # Look for gorilla-vid style embedding
1620 found = filter_video(re.findall(r'''(?sx)
1624 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1627 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1629 # Broaden the search a little bit
1630 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1632 # Broaden the findall a little bit: JWPlayer JS loader
1633 found = filter_video(re.findall(
1634 r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1637 found = filter_video(re.findall(r'''(?xs)
1638 flowplayer\("[^"]+",\s*
1640 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1641 ["']?url["']?\s*:\s*["']([^"']+)["']
1646 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1648 # Try to find twitter cards info
1649 found = filter_video(re.findall(
1650 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1652 # We look for Open Graph info:
1653 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1654 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1655 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1656 if m_video_type is not None:
1657 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1660 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1662 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1664 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1665 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1668 # Look also in Refresh HTTP header
1669 refresh_header = head_response.headers.get('Refresh')
1671 found = re.search(REDIRECT_REGEX, refresh_header)
1673 new_url = compat_urlparse.urljoin(url, found.group(1))
1674 self.report_following_redirect(new_url)
1680 raise UnsupportedError(url)
1683 for video_url in found:
1684 video_url = compat_urlparse.urljoin(url, video_url)
1685 video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
1687 # Sometimes, jwplayer extraction will result in a YouTube URL
1688 if YoutubeIE.suitable(video_url):
1689 entries.append(self.url_result(video_url, 'Youtube'))
1692 # here's a fun little line of code for you:
1693 video_id = os.path.splitext(video_id)[0]
1695 if determine_ext(video_url) == 'smil':
1698 'formats': self._extract_smil_formats(video_url, video_id),
1699 'uploader': video_uploader,
1700 'title': video_title,
1701 'age_limit': age_limit,
1707 'uploader': video_uploader,
1708 'title': video_title,
1709 'age_limit': age_limit,
1712 if len(entries) == 1:
1715 for num, e in enumerate(entries, start=1):
1716 # 'url' results don't have a title
1717 if e.get('title') is not None:
1718 e['title'] = '%s (%d)' % (e['title'], num)
1720 '_type': 'playlist',