3 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .youtube import YoutubeIE
10 from ..compat import (
11 compat_urllib_parse_unquote,
12 compat_urllib_request,
14 compat_xml_parse_error,
32 from .brightcove import (
34 BrightcoveInPageEmbedIE,
36 from .nbc import NBCSportsVPlayerIE
37 from .ooyala import OoyalaIE
38 from .rutv import RUTVIE
39 from .tvc import TVCIE
40 from .sportbox import SportBoxEmbedIE
41 from .smotri import SmotriIE
42 from .myvi import MyviIE
43 from .condenast import CondeNastIE
44 from .udn import UDNEmbedIE
45 from .senateisvp import SenateISVPIE
46 from .bliptv import BlipTVIE
47 from .svt import SVTIE
48 from .pornhub import PornHubIE
49 from .xhamster import XHamsterEmbedIE
50 from .vimeo import VimeoIE
51 from .dailymotion import DailymotionCloudIE
52 from .onionstudios import OnionStudiosIE
53 from .snagfilms import SnagFilmsEmbedIE
54 from .screenwavemedia import ScreenwaveMediaIE
57 class GenericIE(InfoExtractor):
58 IE_DESC = 'Generic downloader that works on some sites'
62 # Direct link to a video
64 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
65 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
70 'upload_date': '20100513',
73 # Direct link to media delivered compressed (until Accept-Encoding is *)
75 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
76 'md5': '128c42e68b13950268b648275386fc74',
78 'id': 'FictionJunction-Parallel_Hearts',
80 'title': 'FictionJunction-Parallel_Hearts',
81 'upload_date': '20140522',
83 'expected_warnings': [
84 'URL could be a direct video link, returning it as such.'
87 # Direct download with broken HEAD
89 'url': 'http://ai-radio.org:8000/radio.opus',
96 'skip_download': True, # infinite live stream
98 'expected_warnings': [
99 r'501.*Not Implemented'
102 # Direct link with incorrect MIME type
104 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
105 'md5': '4ccbebe5f36706d85221f204d7eb5913',
107 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
108 'id': '5_Lennart_Poettering_-_Systemd',
110 'title': '5_Lennart_Poettering_-_Systemd',
111 'upload_date': '20141120',
113 'expected_warnings': [
114 'URL could be a direct video link, returning it as such.'
119 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
121 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
122 'title': 'Zero Punctuation',
123 'description': 're:.*groundbreaking video review series.*'
125 'playlist_mincount': 11,
127 # RSS feed with enclosure
129 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
131 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
133 'upload_date': '20150228',
134 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
137 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
139 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
143 'title': 'Automatics, robotics and biocybernetics',
144 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
145 'formats': 'mincount:16',
146 'subtitles': 'mincount:1',
149 'force_generic_extractor': True,
150 'skip_download': True,
153 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
155 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
160 'formats': 'mincount:1',
163 'skip_download': True,
166 # SMIL from https://www.restudy.dk/video/play/id/1637
168 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
172 'title': 'video_1637',
173 'formats': 'mincount:3',
176 'skip_download': True,
179 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
181 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
183 'id': 'smil-service',
185 'title': 'smil-service',
186 'formats': 'mincount:1',
189 'skip_download': True,
192 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
194 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
198 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
199 'formats': 'mincount:3',
202 'skip_download': True,
205 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
207 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
209 'id': 'mZlp2ctYIUEB',
211 'title': 'Tikibad ontruimd wegens brand',
212 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
213 'thumbnail': 're:^https?://.*\.jpg$',
217 'skip_download': True,
222 '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',
226 'upload_date': '20130224',
227 'uploader_id': 'TheVerge',
228 'description': 're:^Chris Ziegler takes a look at the\.*',
229 'uploader': 'The Verge',
230 'title': 'First Firefox OS phones side-by-side',
233 'skip_download': False,
237 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
238 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
240 'id': '13601338388002',
242 'uploader': 'www.hodiho.fr',
243 'title': 'R\u00e9gis plante sa Jeep',
246 # bandcamp page with custom domain
248 'add_ie': ['Bandcamp'],
249 'url': 'http://bronyrock.com/track/the-pony-mash',
253 'title': 'The Pony Mash',
254 'uploader': 'M_Pallante',
256 'skip': 'There is a limit of 200 free downloads / month for the test song',
258 # embedded brightcove video
259 # it also tests brightcove videos that need to set the 'Referer' in the
262 'add_ie': ['Brightcove'],
263 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
265 'id': '2765128793001',
267 'title': 'Le cours de bourse : l’analyse technique',
268 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
269 'uploader': 'BFM BUSINESS',
272 'skip_download': True,
276 # https://github.com/rg3/youtube-dl/issues/2253
277 'url': 'http://bcove.me/i6nfkrc3',
278 'md5': '0ba9446db037002366bab3b3eb30c88c',
280 'id': '3101154703001',
282 'title': 'Still no power',
283 'uploader': 'thestar.com',
284 '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.',
286 'add_ie': ['Brightcove'],
289 'url': 'http://www.championat.com/video/football/v/87/87499.html',
290 'md5': 'fb973ecf6e4a78a67453647444222983',
292 'id': '3414141473001',
294 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
295 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
296 'uploader': 'Championat',
300 # https://github.com/rg3/youtube-dl/issues/3541
301 'add_ie': ['Brightcove'],
302 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
304 'id': '3866516442001',
306 'title': 'Leer mij vrouwen kennen: Aflevering 1',
307 'description': 'Leer mij vrouwen kennen: Aflevering 1',
308 'uploader': 'SBS Broadcasting',
310 'skip': 'Restricted to Netherlands',
312 'skip_download': True, # m3u8 download
317 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
318 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
320 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
322 'title': '2cc213299525360.mov', # that's what we get
324 'add_ie': ['Ooyala'],
327 # ooyala video embedded with http://player.ooyala.com/iframe.js
328 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
330 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
332 'title': '"Steve Jobs: Man in the Machine" trailer',
333 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
336 'skip_download': True,
339 # multiple ooyala embeds on SBN network websites
341 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
343 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
344 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
346 'playlist_mincount': 3,
348 'skip_download': True,
350 'add_ie': ['Ooyala'],
354 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
358 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
359 'upload_date': '20140225',
360 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
361 'uploader': 'Tested',
362 'uploader_id': 'testedcom',
364 # No need to test YoutubeIE here
366 'skip_download': True,
371 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
375 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
376 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
381 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
385 'title': 'Охотское море стало целиком российским',
386 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
390 'skip_download': True,
395 '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/',
399 'title': 'Дошкольное воспитание',
404 'url': 'http://www.vestifinance.ru/articles/25753',
407 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
412 'title': 'Госзаказ. День 3',
418 'title': 'Госзаказ. День 2',
424 'title': 'Госзаказ. День 1',
430 'skip_download': True,
435 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
437 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
439 'title': 'Ужастики, русский трейлер (2015)',
440 'thumbnail': 're:^https?://.*\.jpg$',
446 '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',
449 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
451 'playlist_mincount': 7,
455 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
456 'md5': '65fdff94098e4a607385a60c5177c638',
460 'title': 'Hidden miracles of the natural world',
461 'uploader': 'Louie Schwartzberg',
462 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
465 # Embeded Ustream video
467 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
468 'md5': '27b99cdb639c9b12a79bca876a073417',
472 'uploader': 'AU SPA: The NSA and Privacy',
473 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
476 # nowvideo embed hidden behind percent encoding
478 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
479 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
481 'id': '06e53103ca9aa',
483 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
484 'description': 'No description',
489 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
490 'md5': '7653032cbb25bf6c80d80f217055fa43',
492 'id': '048195-004_PLUS7-F',
495 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
496 'upload_date': '20140320',
499 'skip_download': 'Requires rtmpdump'
504 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
508 'title': 'Alcaline, le concert avec Calogero',
509 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
510 'upload_date': '20150226',
511 'timestamp': 1424989860,
516 'skip_download': True,
518 'expected_warnings': [
524 'url': 'http://www.wired.com/2014/04/honda-asimo/',
525 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
527 'id': '53501be369702d3275860000',
529 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
534 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
535 'md5': '441aeeb82eb72c422c7f14ec533999cd',
537 'id': 'k2mm4bCdJ6CQ2i7c8o2',
539 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
542 'add_ie': ['Dailymotion'],
546 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
550 'title': 'The NBL Auction 2014',
551 'uploader': 'BADMINTON England',
552 'uploader_id': 'BADMINTONEvents',
553 'upload_date': '20140603',
554 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
556 'add_ie': ['Youtube'],
558 'skip_download': True,
563 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
564 'md5': '35727f82f58c76d996fc188f9755b0d5',
566 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
569 'description': 'Mario\'s life in the fast lane has never looked so good.',
572 # YouTube embed via <data-embed-url="">
574 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
578 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
579 'uploader': 'Gameloft',
580 'uploader_id': 'gameloft',
581 'upload_date': '20140828',
582 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
585 'skip_download': True,
590 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
592 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
594 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
595 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
600 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
602 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
603 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
609 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
614 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
615 'md5': '9d65602bf31c6e20014319c7d07fba27',
617 'id': '5123ea6d5e5a7',
620 'uploader': 'www.handjobhub.com',
621 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
624 # Multiple brightcove videos
625 # https://github.com/rg3/youtube-dl/issues/2283
627 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
629 'id': 'always-never',
630 'title': 'Always / Never - The New Yorker',
634 'extract_flat': False,
635 'skip_download': True,
640 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
641 'md5': '96f09a37e44da40dd083e12d9a683327',
645 'title': 'Ump changes call to ball',
646 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
648 'timestamp': 1401537900,
649 'upload_date': '20140531',
650 'thumbnail': 're:^https?://.*\.jpg$',
655 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
656 'md5': '8788b683c777a5cf25621eaf286d0c23',
660 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
662 'filesize': 182808282,
663 'uploader': 'education-portal.com',
667 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
668 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
672 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
674 'uploader': 'thoughtworks.wistia.com',
679 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
683 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
684 'uploader': 'Sophos Security',
685 'title': 'Chet Chat 171 - Oct 29, 2014',
686 'upload_date': '20141029',
691 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
695 'upload_date': '20141112',
696 'title': 'Rosetta #CometLanding webcast HL 10',
701 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
704 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
706 'playlist_mincount': 2,
710 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
714 'upload_date': '20141126',
715 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
720 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
722 'id': '730m_DandD_1901_512k',
724 'uploader': 'www.abc.net.au',
725 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
728 # embedded viddler video
730 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
734 'uploader': 'deadspin',
735 'title': 'WALL-TO-GORTAT',
736 'timestamp': 1422285291,
737 'upload_date': '20150126',
739 'add_ie': ['Viddler'],
743 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
747 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
748 'description': 'md5:601cb790edd05908957dae8aaa866465',
749 'upload_date': '20150220',
754 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
758 'upload_date': '20150212',
759 'uploader': 'The National Archives UK',
760 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
761 'uploader_id': 'NationalArchives08',
762 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
767 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
768 'playlist_mincount': 5,
770 'id': 'aanslagen-kopenhagen',
771 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
776 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
780 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
785 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
789 'upload_date': '20150226',
790 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
792 'title': 'John Carlson Postgame 2/25/15',
795 # Kaltura embed (different embed code)
797 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
801 'upload_date': '20150127',
802 'uploader_id': 'PremierMedia',
804 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
807 # Eagle.Platform embed (generic URL)
809 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
813 'title': 'Навальный вышел на свободу',
814 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
815 'thumbnail': 're:^https?://.*\.jpg$',
821 # ClipYou (Eagle.Platform) embed (custom URL)
823 'url': 'http://muz-tv.ru/play/7129/',
827 'title': "'O Sole Mio",
828 'thumbnail': 're:^https?://.*\.jpg$',
835 'url': 'http://muz-tv.ru/kinozal/view/7400/',
839 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
840 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
841 'thumbnail': 're:^https?://.*\.jpg$',
848 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
852 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
853 'thumbnail': 're:^https?://.*\.png$',
859 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
860 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
864 'title': 'Facebook Creates "On This Day" | Crunch Report',
869 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
873 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
878 # Crooks and Liars embed
880 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
884 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
885 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
886 'timestamp': 1428207000,
887 'upload_date': '20150405',
888 'uploader': 'Heather',
891 # Crooks and Liars external embed
893 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
895 'id': 'MTE3MjUtMzQ2MzA',
897 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
898 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
899 'timestamp': 1265032391,
900 'upload_date': '20100201',
901 'uploader': 'Heather',
904 # NBC Sports vplayer embed
906 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
908 'id': 'ln7x1qSThw4k',
910 'title': "PFT Live: New leader in the 'new-look' defense",
911 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
916 'url': 'http://www.udn.com/news/story/7314/822787',
917 'md5': 'fd2060e988c326991037b9aff9df21a6',
921 'title': '中一中男師變性 全校師生力挺',
922 'thumbnail': 're:^https?://.*\.jpg$',
927 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
929 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
931 'description': 'VIDEO: Index/Match versus VLOOKUP.',
932 'title': 'This is what separates the Excel masters from the wannabes',
936 'skip_download': True,
939 # Contains a SMIL manifest
941 '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',
945 'title': '+ Football: Lottery Champions League Europe',
946 'uploader': 'www.telewebion.com',
950 'skip_download': True,
953 # Brightcove URL in single quotes
955 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
956 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
958 'id': '4255764656001',
960 'title': 'SN Presents: Russell Martin, World Citizen',
961 '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.',
962 'uploader': 'Rogers Sportsnet',
965 # Dailymotion Cloud video
967 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
968 'md5': '49444254273501a64675a7e68c502681',
970 'id': '5585de919473990de4bee11b',
973 'thumbnail': 're:^https?://.*\.jpe?g$',
978 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
982 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
983 'thumbnail': 're:^https?://.*\.jpe?g$',
984 'uploader': 'ClickHole',
985 'uploader_id': 'clickhole',
990 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
992 'id': '74849a00-85a9-11e1-9660-123139220831',
994 'title': '#whilewewatch',
999 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1000 'md5': '43662b577c018ad707a63766462b1e87',
1004 'title': 'New experience with Acrobat DC',
1005 'description': 'New experience with Acrobat DC',
1006 'duration': 248.667,
1009 # ScreenwaveMedia embed
1011 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1012 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1014 'id': 'cinemasnob-55d26273809dd',
1016 'title': 'cinemasnob',
1019 # BrightcoveInPageEmbed embed
1021 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1023 'id': '4238694884001',
1025 'title': 'Tabletop: Dread, Last Thoughts',
1026 'description': 'Tabletop: Dread, Last Thoughts',
1032 def report_following_redirect(self, new_url):
1033 """Report information extraction."""
1034 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1036 def _extract_rss(self, url, video_id, doc):
1037 playlist_title = doc.find('./channel/title').text
1038 playlist_desc_el = doc.find('./channel/description')
1039 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1042 for it in doc.findall('./channel/item'):
1043 next_url = xpath_text(it, 'link', fatal=False)
1045 enclosure_nodes = it.findall('./enclosure')
1046 for e in enclosure_nodes:
1047 next_url = e.attrib.get('url')
1057 'title': it.find('title').text,
1061 '_type': 'playlist',
1063 'title': playlist_title,
1064 'description': playlist_desc,
1068 def _extract_camtasia(self, url, video_id, webpage):
1069 """ Returns None if no camtasia video can be found. """
1071 camtasia_cfg = self._search_regex(
1072 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1073 webpage, 'camtasia configuration file', default=None)
1074 if camtasia_cfg is None:
1077 title = self._html_search_meta('DC.title', webpage, fatal=True)
1079 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1080 camtasia_cfg = self._download_xml(
1081 camtasia_url, video_id,
1082 note='Downloading camtasia configuration',
1083 errnote='Failed to download camtasia configuration')
1084 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1087 for n in fileset_node.getchildren():
1088 url_n = n.find('./uri')
1093 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1094 'title': '%s - %s' % (title, n.tag),
1095 'url': compat_urlparse.urljoin(url, url_n.text),
1096 'duration': float_or_none(n.find('./duration').text),
1100 '_type': 'playlist',
1105 def _real_extract(self, url):
1106 if url.startswith('//'):
1109 'url': self.http_scheme() + url,
1112 parsed_url = compat_urlparse.urlparse(url)
1113 if not parsed_url.scheme:
1114 default_search = self._downloader.params.get('default_search')
1115 if default_search is None:
1116 default_search = 'fixup_error'
1118 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1120 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1121 return self.url_result('http://' + url)
1122 elif default_search != 'fixup_error':
1123 if default_search == 'auto_warning':
1124 if re.match(r'^(?:url|URL)$', url):
1125 raise ExtractorError(
1126 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1129 self._downloader.report_warning(
1130 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1131 return self.url_result('ytsearch:' + url)
1133 if default_search in ('error', 'fixup_error'):
1134 raise ExtractorError(
1135 '%r is not a valid URL. '
1136 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1137 % (url, url), expected=True)
1139 if ':' not in default_search:
1140 default_search += ':'
1141 return self.url_result(default_search + url)
1143 url, smuggled_data = unsmuggle_url(url)
1144 force_videoid = None
1145 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1146 if smuggled_data and 'force_videoid' in smuggled_data:
1147 force_videoid = smuggled_data['force_videoid']
1148 video_id = force_videoid
1150 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1152 self.to_screen('%s: Requesting header' % video_id)
1154 head_req = HEADRequest(url)
1155 head_response = self._request_webpage(
1157 note=False, errnote='Could not send HEAD request to %s' % url,
1160 if head_response is not False:
1161 # Check for redirect
1162 new_url = head_response.geturl()
1164 self.report_following_redirect(new_url)
1166 new_url = smuggle_url(
1167 new_url, {'force_videoid': force_videoid})
1168 return self.url_result(new_url)
1170 full_response = None
1171 if head_response is False:
1172 request = compat_urllib_request.Request(url)
1173 request.add_header('Accept-Encoding', '*')
1174 full_response = self._request_webpage(request, video_id)
1175 head_response = full_response
1177 # Check for direct link to a video
1178 content_type = head_response.headers.get('Content-Type', '')
1179 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1181 upload_date = unified_strdate(
1182 head_response.headers.get('Last-Modified'))
1185 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1188 'format_id': m.group('format_id'),
1190 'vcodec': 'none' if m.group('type') == 'audio' else None
1192 'upload_date': upload_date,
1195 if not self._downloader.params.get('test', False) and not is_intentional:
1196 force = self._downloader.params.get('force_generic_extractor', False)
1197 self._downloader.report_warning(
1198 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1200 if not full_response:
1201 request = compat_urllib_request.Request(url)
1202 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1203 # making it impossible to download only chunk of the file (yet we need only 512kB to
1204 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1205 # that will always result in downloading the whole file that is not desirable.
1206 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1207 # to accept raw bytes and being able to download only a chunk.
1208 # It may probably better to solve this by checking Content-Type for application/octet-stream
1209 # after HEAD request finishes, but not sure if we can rely on this.
1210 request.add_header('Accept-Encoding', '*')
1211 full_response = self._request_webpage(request, video_id)
1213 # Maybe it's a direct link to a video?
1214 # Be careful not to download the whole thing!
1215 first_bytes = full_response.read(512)
1216 if not is_html(first_bytes):
1217 self._downloader.report_warning(
1218 'URL could be a direct video link, returning it as such.')
1219 upload_date = unified_strdate(
1220 head_response.headers.get('Last-Modified'))
1223 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1226 'upload_date': upload_date,
1229 webpage = self._webpage_read_content(
1230 full_response, url, video_id, prefix=first_bytes)
1232 self.report_extraction(video_id)
1234 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1236 doc = parse_xml(webpage)
1237 if doc.tag == 'rss':
1238 return self._extract_rss(url, video_id, doc)
1239 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1240 return self._parse_smil(doc, url, video_id)
1241 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1242 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1243 except compat_xml_parse_error:
1246 # Is it a Camtasia project?
1247 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1248 if camtasia_res is not None:
1251 # Sometimes embedded video player is hidden behind percent encoding
1252 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1253 # Unescaping the whole page allows to handle those cases in a generic way
1254 webpage = compat_urllib_parse_unquote(webpage)
1256 # it's tempting to parse this further, but you would
1257 # have to take into account all the variations like
1258 # Video Title - Site Name
1259 # Site Name | Video Title
1260 # Video Title - Tagline | Site Name
1261 # and so on and so forth; it's just not practical
1262 video_title = self._html_search_regex(
1263 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1266 # Try to detect age limit automatically
1267 age_limit = self._rta_search(webpage)
1268 # And then there are the jokers who advertise that they use RTA,
1269 # but actually don't.
1270 AGE_LIMIT_MARKERS = [
1271 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1273 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1276 # video uploader is domain name
1277 video_uploader = self._search_regex(
1278 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1281 def _playlist_from_matches(matches, getter=None, ie=None):
1283 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1285 return self.playlist_result(
1286 urlrs, playlist_id=video_id, playlist_title=video_title)
1288 # Look for BrightCove:
1289 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1291 self.to_screen('Brightcove video detected.')
1294 'url': smuggle_url(bc_url, {'Referer': url}),
1295 'ie_key': 'Brightcove'
1296 } for bc_url in bc_urls]
1299 '_type': 'playlist',
1300 'title': video_title,
1305 # Look for Brightcove In Page Embed:
1306 brightcove_in_page_embed_url = BrightcoveInPageEmbedIE._extract_url(webpage)
1307 if brightcove_in_page_embed_url:
1308 return self.url_result(brightcove_in_page_embed_url, 'BrightcoveInPageEmbed')
1310 # Look for embedded rtl.nl player
1311 matches = re.findall(
1312 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1315 return _playlist_from_matches(matches, ie='RtlNl')
1317 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1318 if vimeo_url is not None:
1319 return self.url_result(vimeo_url)
1321 vid_me_embed_url = self._search_regex(
1322 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1323 webpage, 'vid.me embed', default=None)
1324 if vid_me_embed_url is not None:
1325 return self.url_result(vid_me_embed_url, 'Vidme')
1327 # Look for embedded YouTube player
1328 matches = re.findall(r'''(?x)
1337 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1341 return _playlist_from_matches(
1342 matches, lambda m: unescapeHTML(m[1]))
1344 # Look for lazyYT YouTube embed
1345 matches = re.findall(
1346 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1348 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1350 # Look for embedded Dailymotion player
1351 matches = re.findall(
1352 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1354 return _playlist_from_matches(
1355 matches, lambda m: unescapeHTML(m[1]))
1357 # Look for embedded Dailymotion playlist player (#3822)
1359 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1361 playlists = re.findall(
1362 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1364 return _playlist_from_matches(
1365 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1367 # Look for embedded Wistia player
1369 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1371 embed_url = self._proto_relative_url(
1372 unescapeHTML(match.group('url')))
1374 '_type': 'url_transparent',
1377 'uploader': video_uploader,
1378 'title': video_title,
1382 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1385 '_type': 'url_transparent',
1386 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1388 'uploader': video_uploader,
1389 'title': video_title,
1390 'id': match.group('id')
1393 # Look for embedded blip.tv player
1394 bliptv_url = BlipTVIE._extract_url(webpage)
1396 return self.url_result(bliptv_url, 'BlipTV')
1398 # Look for SVT player
1399 svt_url = SVTIE._extract_url(webpage)
1401 return self.url_result(svt_url, 'SVT')
1403 # Look for embedded condenast player
1404 matches = re.findall(
1405 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1409 '_type': 'playlist',
1412 'ie_key': 'CondeNast',
1414 } for ma in matches],
1415 'title': video_title,
1419 # Look for Bandcamp pages with custom domain
1420 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1421 if mobj is not None:
1422 burl = unescapeHTML(mobj.group(1))
1423 # Don't set the extractor because it can be a track url or an album
1424 return self.url_result(burl)
1426 # Look for embedded Vevo player
1428 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1429 if mobj is not None:
1430 return self.url_result(mobj.group('url'))
1432 # Look for embedded Viddler player
1434 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1436 if mobj is not None:
1437 return self.url_result(mobj.group('url'))
1439 # Look for NYTimes player
1441 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1443 if mobj is not None:
1444 return self.url_result(mobj.group('url'))
1446 # Look for Libsyn player
1448 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1449 if mobj is not None:
1450 return self.url_result(mobj.group('url'))
1452 # Look for Ooyala videos
1453 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1454 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1455 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1456 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1457 if mobj is not None:
1458 return OoyalaIE._build_url_result(mobj.group('ec'))
1460 # Look for multiple Ooyala embeds on SBN network websites
1461 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1462 if mobj is not None:
1463 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1465 return _playlist_from_matches(
1466 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1468 # Look for Aparat videos
1469 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1470 if mobj is not None:
1471 return self.url_result(mobj.group(1), 'Aparat')
1473 # Look for MPORA videos
1474 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1475 if mobj is not None:
1476 return self.url_result(mobj.group(1), 'Mpora')
1478 # Look for embedded NovaMov-based player
1480 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1481 (?P<url>http://(?:(?:embed|www)\.)?
1483 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1484 videoweed\.(?:es|com)|
1485 movshare\.(?:net|sx|ag)|
1486 divxstage\.(?:eu|net|ch|co|at|ag))
1487 /embed\.php.+?)\1''', webpage)
1488 if mobj is not None:
1489 return self.url_result(mobj.group('url'))
1491 # Look for embedded Facebook player
1493 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1494 if mobj is not None:
1495 return self.url_result(mobj.group('url'), 'Facebook')
1497 # Look for embedded VK player
1498 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1499 if mobj is not None:
1500 return self.url_result(mobj.group('url'), 'VK')
1502 # Look for embedded ivi player
1503 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1504 if mobj is not None:
1505 return self.url_result(mobj.group('url'), 'Ivi')
1507 # Look for embedded Huffington Post player
1509 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1510 if mobj is not None:
1511 return self.url_result(mobj.group('url'), 'HuffPost')
1514 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1515 if mobj is not None:
1516 return self.url_result(mobj.group('url'))
1517 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1518 if mobj is not None:
1519 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1521 # Look for funnyordie embed
1522 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1524 return _playlist_from_matches(
1525 matches, getter=unescapeHTML, ie='FunnyOrDie')
1527 # Look for BBC iPlayer embed
1528 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1530 return _playlist_from_matches(matches, ie='BBCCoUk')
1532 # Look for embedded RUTV player
1533 rutv_url = RUTVIE._extract_url(webpage)
1535 return self.url_result(rutv_url, 'RUTV')
1537 # Look for embedded TVC player
1538 tvc_url = TVCIE._extract_url(webpage)
1540 return self.url_result(tvc_url, 'TVC')
1542 # Look for embedded SportBox player
1543 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1545 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1547 # Look for embedded PornHub player
1548 pornhub_url = PornHubIE._extract_url(webpage)
1550 return self.url_result(pornhub_url, 'PornHub')
1552 # Look for embedded XHamster player
1553 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1555 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1557 # Look for embedded Tvigle player
1559 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1560 if mobj is not None:
1561 return self.url_result(mobj.group('url'), 'Tvigle')
1563 # Look for embedded TED player
1565 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1566 if mobj is not None:
1567 return self.url_result(mobj.group('url'), 'TED')
1569 # Look for embedded Ustream videos
1571 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1572 if mobj is not None:
1573 return self.url_result(mobj.group('url'), 'Ustream')
1575 # Look for embedded arte.tv player
1577 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1579 if mobj is not None:
1580 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1582 # Look for embedded francetv player
1584 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1586 if mobj is not None:
1587 return self.url_result(mobj.group('url'))
1589 # Look for embedded smotri.com player
1590 smotri_url = SmotriIE._extract_url(webpage)
1592 return self.url_result(smotri_url, 'Smotri')
1594 # Look for embedded Myvi.ru player
1595 myvi_url = MyviIE._extract_url(webpage)
1597 return self.url_result(myvi_url)
1599 # Look for embeded soundcloud player
1601 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1603 if mobj is not None:
1604 url = unescapeHTML(mobj.group('url'))
1605 return self.url_result(url)
1607 # Look for embedded vulture.com player
1609 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1611 if mobj is not None:
1612 url = unescapeHTML(mobj.group('url'))
1613 return self.url_result(url, ie='Vulture')
1615 # Look for embedded mtvservices player
1617 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1619 if mobj is not None:
1620 url = unescapeHTML(mobj.group('url'))
1621 return self.url_result(url, ie='MTVServicesEmbedded')
1623 # Look for embedded yahoo player
1625 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1627 if mobj is not None:
1628 return self.url_result(mobj.group('url'), 'Yahoo')
1630 # Look for embedded sbs.com.au player
1634 <meta\s+property="og:video"\s+content=|
1637 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1639 if mobj is not None:
1640 return self.url_result(mobj.group('url'), 'SBS')
1642 # Look for embedded Cinchcast player
1644 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1646 if mobj is not None:
1647 return self.url_result(mobj.group('url'), 'Cinchcast')
1650 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1654 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1656 if mobj is not None:
1657 return self.url_result(mobj.group('url'), 'MLB')
1660 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1662 if mobj is not None:
1663 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1666 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1668 if mobj is not None:
1669 return self.url_result(mobj.group('url'), 'Livestream')
1671 # Look for Zapiks embed
1673 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1674 if mobj is not None:
1675 return self.url_result(mobj.group('url'), 'Zapiks')
1677 # Look for Kaltura embeds
1678 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1679 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))
1680 if mobj is not None:
1681 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1683 # Look for Eagle.Platform embeds
1685 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1686 if mobj is not None:
1687 return self.url_result(mobj.group('url'), 'EaglePlatform')
1689 # Look for ClipYou (uses Eagle.Platform) embeds
1691 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1692 if mobj is not None:
1693 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1695 # Look for Pladform embeds
1697 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1698 if mobj is not None:
1699 return self.url_result(mobj.group('url'), 'Pladform')
1701 # Look for Playwire embeds
1703 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1704 if mobj is not None:
1705 return self.url_result(mobj.group('url'))
1707 # Look for 5min embeds
1709 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1710 if mobj is not None:
1711 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1713 # Look for Crooks and Liars embeds
1715 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1716 if mobj is not None:
1717 return self.url_result(mobj.group('url'))
1719 # Look for NBC Sports VPlayer embeds
1720 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1722 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1724 # Look for UDN embeds
1726 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1727 if mobj is not None:
1728 return self.url_result(
1729 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1731 # Look for Senate ISVP iframe
1732 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1734 return self.url_result(senate_isvp_url, 'SenateISVP')
1736 # Look for Dailymotion Cloud videos
1737 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1739 return self.url_result(dmcloud_url, 'DailymotionCloud')
1741 # Look for OnionStudios embeds
1742 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1743 if onionstudios_url:
1744 return self.url_result(onionstudios_url)
1746 # Look for SnagFilms embeds
1747 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1749 return self.url_result(snagfilms_url)
1751 # Look for ScreenwaveMedia embeds
1752 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1753 if mobj is not None:
1754 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1756 # Look for AdobeTVVideo embeds
1758 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1760 if mobj is not None:
1761 return self.url_result(
1762 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1765 def check_video(vurl):
1766 if YoutubeIE.suitable(vurl):
1768 vpath = compat_urlparse.urlparse(vurl).path
1769 vext = determine_ext(vpath)
1770 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1772 def filter_video(urls):
1773 return list(filter(check_video, urls))
1775 # Start with something easy: JW Player in SWFObject
1776 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1778 # Look for gorilla-vid style embedding
1779 found = filter_video(re.findall(r'''(?sx)
1783 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1786 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1788 # Broaden the search a little bit
1789 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1791 # Broaden the findall a little bit: JWPlayer JS loader
1792 found = filter_video(re.findall(
1793 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1796 found = filter_video(re.findall(r'''(?xs)
1797 flowplayer\("[^"]+",\s*
1799 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1800 ["']?url["']?\s*:\s*["']([^"']+)["']
1805 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1807 # Try to find twitter cards info
1808 found = filter_video(re.findall(
1809 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1811 # We look for Open Graph info:
1812 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1813 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1814 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1815 if m_video_type is not None:
1816 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1819 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1821 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1823 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1824 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1827 # Look also in Refresh HTTP header
1828 refresh_header = head_response.headers.get('Refresh')
1830 found = re.search(REDIRECT_REGEX, refresh_header)
1832 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1833 self.report_following_redirect(new_url)
1839 raise UnsupportedError(url)
1842 for video_url in found:
1843 video_url = compat_urlparse.urljoin(url, video_url)
1844 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1846 # Sometimes, jwplayer extraction will result in a YouTube URL
1847 if YoutubeIE.suitable(video_url):
1848 entries.append(self.url_result(video_url, 'Youtube'))
1851 # here's a fun little line of code for you:
1852 video_id = os.path.splitext(video_id)[0]
1854 ext = determine_ext(video_url)
1858 'formats': self._extract_smil_formats(video_url, video_id),
1859 'uploader': video_uploader,
1860 'title': video_title,
1861 'age_limit': age_limit,
1864 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1869 'uploader': video_uploader,
1870 'title': video_title,
1871 'age_limit': age_limit,
1874 if len(entries) == 1:
1877 for num, e in enumerate(entries, start=1):
1878 # 'url' results don't have a title
1879 if e.get('title') is not None:
1880 e['title'] = '%s (%d)' % (e['title'], num)
1882 '_type': 'playlist',