3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
15 compat_xml_parse_error,
33 from .brightcove import (
37 from .nbc import NBCSportsVPlayerIE
38 from .ooyala import OoyalaIE
39 from .rutv import RUTVIE
40 from .tvc import TVCIE
41 from .sportbox import SportBoxEmbedIE
42 from .smotri import SmotriIE
43 from .myvi import MyviIE
44 from .condenast import CondeNastIE
45 from .udn import UDNEmbedIE
46 from .senateisvp import SenateISVPIE
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
55 from .mtv import MTVServicesEmbeddedIE
56 from .jwplatform import JWPlatformIE
59 class GenericIE(InfoExtractor):
60 IE_DESC = 'Generic downloader that works on some sites'
64 # Direct link to a video
66 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
67 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
72 'upload_date': '20100513',
75 # Direct link to media delivered compressed (until Accept-Encoding is *)
77 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
78 'md5': '128c42e68b13950268b648275386fc74',
80 'id': 'FictionJunction-Parallel_Hearts',
82 'title': 'FictionJunction-Parallel_Hearts',
83 'upload_date': '20140522',
85 'expected_warnings': [
86 'URL could be a direct video link, returning it as such.'
89 # Direct download with broken HEAD
91 'url': 'http://ai-radio.org:8000/radio.opus',
98 'skip_download': True, # infinite live stream
100 'expected_warnings': [
101 r'501.*Not Implemented'
104 # Direct link with incorrect MIME type
106 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
107 'md5': '4ccbebe5f36706d85221f204d7eb5913',
109 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
110 'id': '5_Lennart_Poettering_-_Systemd',
112 'title': '5_Lennart_Poettering_-_Systemd',
113 'upload_date': '20141120',
115 'expected_warnings': [
116 'URL could be a direct video link, returning it as such.'
121 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
123 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
124 'title': 'Zero Punctuation',
125 'description': 're:.*groundbreaking video review series.*'
127 'playlist_mincount': 11,
129 # RSS feed with enclosure
131 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
133 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
135 'upload_date': '20150228',
136 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
139 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
141 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
145 'title': 'Automatics, robotics and biocybernetics',
146 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
147 'upload_date': '20130627',
148 'formats': 'mincount:16',
149 'subtitles': 'mincount:1',
152 'force_generic_extractor': True,
153 'skip_download': True,
156 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
158 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
163 'formats': 'mincount:1',
166 'skip_download': True,
169 # SMIL from https://www.restudy.dk/video/play/id/1637
171 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
175 'title': 'video_1637',
176 'formats': 'mincount:3',
179 'skip_download': True,
182 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
184 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
186 'id': 'smil-service',
188 'title': 'smil-service',
189 'formats': 'mincount:1',
192 'skip_download': True,
195 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
197 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
201 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
202 'formats': 'mincount:3',
205 'skip_download': True,
208 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
210 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
212 'id': 'mZlp2ctYIUEB',
214 'title': 'Tikibad ontruimd wegens brand',
215 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
216 'thumbnail': 're:^https?://.*\.jpg$',
220 'skip_download': True,
225 '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',
229 'upload_date': '20130224',
230 'uploader_id': 'TheVerge',
231 'description': 're:^Chris Ziegler takes a look at the\.*',
232 'uploader': 'The Verge',
233 'title': 'First Firefox OS phones side-by-side',
236 'skip_download': False,
240 # redirect in Refresh HTTP header
241 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
245 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
246 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
247 'upload_date': '20150917',
248 'uploader_id': 'brtvofficial',
249 'uploader': 'Boiler Room',
252 'skip_download': False,
256 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
257 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
259 'id': '13601338388002',
261 'uploader': 'www.hodiho.fr',
262 'title': 'R\u00e9gis plante sa Jeep',
265 # bandcamp page with custom domain
267 'add_ie': ['Bandcamp'],
268 'url': 'http://bronyrock.com/track/the-pony-mash',
272 'title': 'The Pony Mash',
273 'uploader': 'M_Pallante',
275 'skip': 'There is a limit of 200 free downloads / month for the test song',
277 # embedded brightcove video
278 # it also tests brightcove videos that need to set the 'Referer' in the
281 'add_ie': ['BrightcoveLegacy'],
282 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
284 'id': '2765128793001',
286 'title': 'Le cours de bourse : l’analyse technique',
287 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
288 'uploader': 'BFM BUSINESS',
291 'skip_download': True,
295 # https://github.com/rg3/youtube-dl/issues/2253
296 'url': 'http://bcove.me/i6nfkrc3',
297 'md5': '0ba9446db037002366bab3b3eb30c88c',
299 'id': '3101154703001',
301 'title': 'Still no power',
302 'uploader': 'thestar.com',
303 '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.',
305 'add_ie': ['BrightcoveLegacy'],
308 'url': 'http://www.championat.com/video/football/v/87/87499.html',
309 'md5': 'fb973ecf6e4a78a67453647444222983',
311 'id': '3414141473001',
313 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
314 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
315 'uploader': 'Championat',
319 # https://github.com/rg3/youtube-dl/issues/3541
320 'add_ie': ['BrightcoveLegacy'],
321 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
323 'id': '3866516442001',
325 'title': 'Leer mij vrouwen kennen: Aflevering 1',
326 'description': 'Leer mij vrouwen kennen: Aflevering 1',
327 'uploader': 'SBS Broadcasting',
329 'skip': 'Restricted to Netherlands',
331 'skip_download': True, # m3u8 download
336 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
337 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
339 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
341 'title': '2cc213299525360.mov', # that's what we get
343 'add_ie': ['Ooyala'],
346 # ooyala video embedded with http://player.ooyala.com/iframe.js
347 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
349 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
351 'title': '"Steve Jobs: Man in the Machine" trailer',
352 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
355 'skip_download': True,
358 # multiple ooyala embeds on SBN network websites
360 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
362 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
363 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
365 'playlist_mincount': 3,
367 'skip_download': True,
369 'add_ie': ['Ooyala'],
373 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
377 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
378 'upload_date': '20140225',
379 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
380 'uploader': 'Tested',
381 'uploader_id': 'testedcom',
383 # No need to test YoutubeIE here
385 'skip_download': True,
390 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
394 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
395 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
400 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
404 'title': 'Охотское море стало целиком российским',
405 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
409 'skip_download': True,
414 '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/',
418 'title': 'Дошкольное воспитание',
423 'url': 'http://www.vestifinance.ru/articles/25753',
426 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
431 'title': 'Госзаказ. День 3',
437 'title': 'Госзаказ. День 2',
443 'title': 'Госзаказ. День 1',
449 'skip_download': True,
454 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
456 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
458 'title': 'Ужастики, русский трейлер (2015)',
459 'thumbnail': 're:^https?://.*\.jpg$',
465 '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',
468 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
470 'playlist_mincount': 7,
474 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
475 'md5': '65fdff94098e4a607385a60c5177c638',
479 'title': 'Hidden miracles of the natural world',
480 'uploader': 'Louie Schwartzberg',
481 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
484 # Embeded Ustream video
486 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
487 'md5': '27b99cdb639c9b12a79bca876a073417',
491 'uploader': 'AU SPA: The NSA and Privacy',
492 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
495 # nowvideo embed hidden behind percent encoding
497 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
498 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
500 'id': '06e53103ca9aa',
502 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
503 'description': 'No description',
508 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
509 'md5': '7653032cbb25bf6c80d80f217055fa43',
511 'id': '048195-004_PLUS7-F',
514 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
515 'upload_date': '20140320',
518 'skip_download': 'Requires rtmpdump'
523 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
527 'title': 'Alcaline, le concert avec Calogero',
528 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
529 'upload_date': '20150226',
530 'timestamp': 1424989860,
535 'skip_download': True,
537 'expected_warnings': [
543 'url': 'http://www.wired.com/2014/04/honda-asimo/',
544 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
546 'id': '53501be369702d3275860000',
548 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
553 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
554 'md5': '441aeeb82eb72c422c7f14ec533999cd',
556 'id': 'k2mm4bCdJ6CQ2i7c8o2',
558 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
561 'add_ie': ['Dailymotion'],
565 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
569 'title': 'The NBL Auction 2014',
570 'uploader': 'BADMINTON England',
571 'uploader_id': 'BADMINTONEvents',
572 'upload_date': '20140603',
573 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
575 'add_ie': ['Youtube'],
577 'skip_download': True,
582 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
583 'md5': '35727f82f58c76d996fc188f9755b0d5',
585 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
588 'description': 'Mario\'s life in the fast lane has never looked so good.',
591 # YouTube embed via <data-embed-url="">
593 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
597 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
598 'uploader': 'Gameloft',
599 'uploader_id': 'gameloft',
600 'upload_date': '20140828',
601 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
604 'skip_download': True,
609 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
611 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
613 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
614 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
619 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
621 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
622 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
628 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
633 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
634 'md5': '9d65602bf31c6e20014319c7d07fba27',
636 'id': '5123ea6d5e5a7',
639 'uploader': 'www.handjobhub.com',
640 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
643 # Multiple brightcove videos
644 # https://github.com/rg3/youtube-dl/issues/2283
646 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
648 'id': 'always-never',
649 'title': 'Always / Never - The New Yorker',
653 'extract_flat': False,
654 'skip_download': True,
659 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
660 'md5': '96f09a37e44da40dd083e12d9a683327',
664 'title': 'Ump changes call to ball',
665 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
667 'timestamp': 1401537900,
668 'upload_date': '20140531',
669 'thumbnail': 're:^https?://.*\.jpg$',
674 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
675 'md5': '8788b683c777a5cf25621eaf286d0c23',
679 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
681 'filesize': 182808282,
682 'uploader': 'education-portal.com',
686 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
687 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
691 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
693 'uploader': 'thoughtworks.wistia.com',
698 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
702 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
703 'uploader': 'Sophos Security',
704 'title': 'Chet Chat 171 - Oct 29, 2014',
705 'upload_date': '20141029',
710 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
714 'upload_date': '20141112',
715 'title': 'Rosetta #CometLanding webcast HL 10',
720 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
723 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
725 'playlist_mincount': 2,
729 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
733 'upload_date': '20141126',
734 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
739 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
741 'id': '730m_DandD_1901_512k',
743 'uploader': 'www.abc.net.au',
744 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
747 # embedded viddler video
749 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
753 'uploader': 'deadspin',
754 'title': 'WALL-TO-GORTAT',
755 'timestamp': 1422285291,
756 'upload_date': '20150126',
758 'add_ie': ['Viddler'],
762 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
766 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
767 'description': 'md5:601cb790edd05908957dae8aaa866465',
768 'upload_date': '20150220',
773 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
777 'upload_date': '20150212',
778 'uploader': 'The National Archives UK',
779 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
780 'uploader_id': 'NationalArchives08',
781 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
786 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
787 'playlist_mincount': 5,
789 'id': 'aanslagen-kopenhagen',
790 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
795 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
799 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
804 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
808 'upload_date': '20150226',
809 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
811 'title': 'John Carlson Postgame 2/25/15',
814 # Kaltura embed (different embed code)
816 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
820 'upload_date': '20150127',
821 'uploader_id': 'PremierMedia',
823 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
826 # Kaltura embed protected with referrer
828 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
832 'title': 'Violetta - Achter De Schermen - Ruggero',
833 'description': 'Achter de schermen met Ruggero',
834 'timestamp': 1435133761,
835 'upload_date': '20150624',
836 'uploader_id': 'echojecka',
839 # Eagle.Platform embed (generic URL)
841 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
845 'title': 'Навальный вышел на свободу',
846 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
847 'thumbnail': 're:^https?://.*\.jpg$',
853 # ClipYou (Eagle.Platform) embed (custom URL)
855 'url': 'http://muz-tv.ru/play/7129/',
859 'title': "'O Sole Mio",
860 'thumbnail': 're:^https?://.*\.jpg$',
867 'url': 'http://muz-tv.ru/kinozal/view/7400/',
871 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
872 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
873 'thumbnail': 're:^https?://.*\.jpg$',
880 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
884 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
885 'thumbnail': 're:^https?://.*\.png$',
891 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
892 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
896 'title': 'Facebook Creates "On This Day" | Crunch Report',
901 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
905 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
910 # Crooks and Liars embed
912 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
916 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
917 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
918 'timestamp': 1428207000,
919 'upload_date': '20150405',
920 'uploader': 'Heather',
923 # Crooks and Liars external embed
925 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
927 'id': 'MTE3MjUtMzQ2MzA',
929 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
930 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
931 'timestamp': 1265032391,
932 'upload_date': '20100201',
933 'uploader': 'Heather',
936 # NBC Sports vplayer embed
938 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
940 'id': 'ln7x1qSThw4k',
942 'title': "PFT Live: New leader in the 'new-look' defense",
943 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
948 'url': 'http://www.udn.com/news/story/7314/822787',
949 'md5': 'fd2060e988c326991037b9aff9df21a6',
953 'title': '中一中男師變性 全校師生力挺',
954 'thumbnail': 're:^https?://.*\.jpg$',
959 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
961 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
963 'description': 'VIDEO: Index/Match versus VLOOKUP.',
964 'title': 'This is what separates the Excel masters from the wannabes',
968 'skip_download': True,
971 # Contains a SMIL manifest
973 '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',
977 'title': '+ Football: Lottery Champions League Europe',
978 'uploader': 'www.telewebion.com',
982 'skip_download': True,
985 # Brightcove URL in single quotes
987 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
988 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
990 'id': '4255764656001',
992 'title': 'SN Presents: Russell Martin, World Citizen',
993 '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.',
994 'uploader': 'Rogers Sportsnet',
997 # Dailymotion Cloud video
999 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1000 'md5': '49444254273501a64675a7e68c502681',
1002 'id': '5585de919473990de4bee11b',
1004 'title': 'Le débat',
1005 'thumbnail': 're:^https?://.*\.jpe?g$',
1008 # OnionStudios embed
1010 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1014 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1015 'thumbnail': 're:^https?://.*\.jpe?g$',
1016 'uploader': 'ClickHole',
1017 'uploader_id': 'clickhole',
1022 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1024 'id': '74849a00-85a9-11e1-9660-123139220831',
1026 'title': '#whilewewatch',
1029 # AdobeTVVideo embed
1031 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1032 'md5': '43662b577c018ad707a63766462b1e87',
1036 'title': 'New experience with Acrobat DC',
1037 'description': 'New experience with Acrobat DC',
1038 'duration': 248.667,
1041 # ScreenwaveMedia embed
1043 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1044 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1046 'id': 'cinemasnob-55d26273809dd',
1048 'title': 'cinemasnob',
1051 # BrightcoveInPageEmbed embed
1053 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1055 'id': '4238694884001',
1057 'title': 'Tabletop: Dread, Last Thoughts',
1058 'description': 'Tabletop: Dread, Last Thoughts',
1062 # JWPlayer with M3U8
1064 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1068 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1069 'uploader': 'ren.tv',
1073 'skip_download': True,
1078 def report_following_redirect(self, new_url):
1079 """Report information extraction."""
1080 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1082 def _extract_rss(self, url, video_id, doc):
1083 playlist_title = doc.find('./channel/title').text
1084 playlist_desc_el = doc.find('./channel/description')
1085 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1088 for it in doc.findall('./channel/item'):
1089 next_url = xpath_text(it, 'link', fatal=False)
1091 enclosure_nodes = it.findall('./enclosure')
1092 for e in enclosure_nodes:
1093 next_url = e.attrib.get('url')
1103 'title': it.find('title').text,
1107 '_type': 'playlist',
1109 'title': playlist_title,
1110 'description': playlist_desc,
1114 def _extract_camtasia(self, url, video_id, webpage):
1115 """ Returns None if no camtasia video can be found. """
1117 camtasia_cfg = self._search_regex(
1118 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1119 webpage, 'camtasia configuration file', default=None)
1120 if camtasia_cfg is None:
1123 title = self._html_search_meta('DC.title', webpage, fatal=True)
1125 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1126 camtasia_cfg = self._download_xml(
1127 camtasia_url, video_id,
1128 note='Downloading camtasia configuration',
1129 errnote='Failed to download camtasia configuration')
1130 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1133 for n in fileset_node.getchildren():
1134 url_n = n.find('./uri')
1139 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1140 'title': '%s - %s' % (title, n.tag),
1141 'url': compat_urlparse.urljoin(url, url_n.text),
1142 'duration': float_or_none(n.find('./duration').text),
1146 '_type': 'playlist',
1151 def _real_extract(self, url):
1152 if url.startswith('//'):
1155 'url': self.http_scheme() + url,
1158 parsed_url = compat_urlparse.urlparse(url)
1159 if not parsed_url.scheme:
1160 default_search = self._downloader.params.get('default_search')
1161 if default_search is None:
1162 default_search = 'fixup_error'
1164 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1166 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1167 return self.url_result('http://' + url)
1168 elif default_search != 'fixup_error':
1169 if default_search == 'auto_warning':
1170 if re.match(r'^(?:url|URL)$', url):
1171 raise ExtractorError(
1172 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1175 self._downloader.report_warning(
1176 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1177 return self.url_result('ytsearch:' + url)
1179 if default_search in ('error', 'fixup_error'):
1180 raise ExtractorError(
1181 '%r is not a valid URL. '
1182 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1183 % (url, url), expected=True)
1185 if ':' not in default_search:
1186 default_search += ':'
1187 return self.url_result(default_search + url)
1189 url, smuggled_data = unsmuggle_url(url)
1190 force_videoid = None
1191 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1192 if smuggled_data and 'force_videoid' in smuggled_data:
1193 force_videoid = smuggled_data['force_videoid']
1194 video_id = force_videoid
1196 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1198 self.to_screen('%s: Requesting header' % video_id)
1200 head_req = HEADRequest(url)
1201 head_response = self._request_webpage(
1203 note=False, errnote='Could not send HEAD request to %s' % url,
1206 if head_response is not False:
1207 # Check for redirect
1208 new_url = head_response.geturl()
1210 self.report_following_redirect(new_url)
1212 new_url = smuggle_url(
1213 new_url, {'force_videoid': force_videoid})
1214 return self.url_result(new_url)
1216 full_response = None
1217 if head_response is False:
1218 request = sanitized_Request(url)
1219 request.add_header('Accept-Encoding', '*')
1220 full_response = self._request_webpage(request, video_id)
1221 head_response = full_response
1223 # Check for direct link to a video
1224 content_type = head_response.headers.get('Content-Type', '')
1225 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1227 upload_date = unified_strdate(
1228 head_response.headers.get('Last-Modified'))
1231 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1234 'format_id': m.group('format_id'),
1236 'vcodec': 'none' if m.group('type') == 'audio' else None
1238 'upload_date': upload_date,
1241 if not self._downloader.params.get('test', False) and not is_intentional:
1242 force = self._downloader.params.get('force_generic_extractor', False)
1243 self._downloader.report_warning(
1244 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1246 if not full_response:
1247 request = sanitized_Request(url)
1248 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1249 # making it impossible to download only chunk of the file (yet we need only 512kB to
1250 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1251 # that will always result in downloading the whole file that is not desirable.
1252 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1253 # to accept raw bytes and being able to download only a chunk.
1254 # It may probably better to solve this by checking Content-Type for application/octet-stream
1255 # after HEAD request finishes, but not sure if we can rely on this.
1256 request.add_header('Accept-Encoding', '*')
1257 full_response = self._request_webpage(request, video_id)
1259 # Maybe it's a direct link to a video?
1260 # Be careful not to download the whole thing!
1261 first_bytes = full_response.read(512)
1262 if not is_html(first_bytes):
1263 self._downloader.report_warning(
1264 'URL could be a direct video link, returning it as such.')
1265 upload_date = unified_strdate(
1266 head_response.headers.get('Last-Modified'))
1269 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1272 'upload_date': upload_date,
1275 webpage = self._webpage_read_content(
1276 full_response, url, video_id, prefix=first_bytes)
1278 self.report_extraction(video_id)
1280 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1282 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1283 if doc.tag == 'rss':
1284 return self._extract_rss(url, video_id, doc)
1285 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1286 return self._parse_smil(doc, url, video_id)
1287 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1288 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1289 except compat_xml_parse_error:
1292 # Is it a Camtasia project?
1293 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1294 if camtasia_res is not None:
1297 # Sometimes embedded video player is hidden behind percent encoding
1298 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1299 # Unescaping the whole page allows to handle those cases in a generic way
1300 webpage = compat_urllib_parse_unquote(webpage)
1302 # it's tempting to parse this further, but you would
1303 # have to take into account all the variations like
1304 # Video Title - Site Name
1305 # Site Name | Video Title
1306 # Video Title - Tagline | Site Name
1307 # and so on and so forth; it's just not practical
1308 video_title = self._html_search_regex(
1309 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1312 # Try to detect age limit automatically
1313 age_limit = self._rta_search(webpage)
1314 # And then there are the jokers who advertise that they use RTA,
1315 # but actually don't.
1316 AGE_LIMIT_MARKERS = [
1317 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1319 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1322 # video uploader is domain name
1323 video_uploader = self._search_regex(
1324 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1327 def _playlist_from_matches(matches, getter=None, ie=None):
1329 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1331 return self.playlist_result(
1332 urlrs, playlist_id=video_id, playlist_title=video_title)
1334 # Look for Brightcove Legacy Studio embeds
1335 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1337 self.to_screen('Brightcove video detected.')
1340 'url': smuggle_url(bc_url, {'Referer': url}),
1341 'ie_key': 'BrightcoveLegacy'
1342 } for bc_url in bc_urls]
1345 '_type': 'playlist',
1346 'title': video_title,
1351 # Look for Brightcove New Studio embeds
1352 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1354 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1356 # Look for embedded rtl.nl player
1357 matches = re.findall(
1358 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1361 return _playlist_from_matches(matches, ie='RtlNl')
1363 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1364 if vimeo_url is not None:
1365 return self.url_result(vimeo_url)
1367 vid_me_embed_url = self._search_regex(
1368 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1369 webpage, 'vid.me embed', default=None)
1370 if vid_me_embed_url is not None:
1371 return self.url_result(vid_me_embed_url, 'Vidme')
1373 # Look for embedded YouTube player
1374 matches = re.findall(r'''(?x)
1383 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1387 return _playlist_from_matches(
1388 matches, lambda m: unescapeHTML(m[1]))
1390 # Look for lazyYT YouTube embed
1391 matches = re.findall(
1392 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1394 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1396 # Look for embedded Dailymotion player
1397 matches = re.findall(
1398 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1400 return _playlist_from_matches(
1401 matches, lambda m: unescapeHTML(m[1]))
1403 # Look for embedded Dailymotion playlist player (#3822)
1405 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1407 playlists = re.findall(
1408 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1410 return _playlist_from_matches(
1411 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1413 # Look for embedded Wistia player
1415 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1417 embed_url = self._proto_relative_url(
1418 unescapeHTML(match.group('url')))
1420 '_type': 'url_transparent',
1423 'uploader': video_uploader,
1424 'title': video_title,
1428 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1431 '_type': 'url_transparent',
1432 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1434 'uploader': video_uploader,
1435 'title': video_title,
1436 'id': match.group('id')
1439 # Look for SVT player
1440 svt_url = SVTIE._extract_url(webpage)
1442 return self.url_result(svt_url, 'SVT')
1444 # Look for embedded condenast player
1445 matches = re.findall(
1446 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1450 '_type': 'playlist',
1453 'ie_key': 'CondeNast',
1455 } for ma in matches],
1456 'title': video_title,
1460 # Look for Bandcamp pages with custom domain
1461 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1462 if mobj is not None:
1463 burl = unescapeHTML(mobj.group(1))
1464 # Don't set the extractor because it can be a track url or an album
1465 return self.url_result(burl)
1467 # Look for embedded Vevo player
1469 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1470 if mobj is not None:
1471 return self.url_result(mobj.group('url'))
1473 # Look for embedded Viddler player
1475 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1477 if mobj is not None:
1478 return self.url_result(mobj.group('url'))
1480 # Look for NYTimes player
1482 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1484 if mobj is not None:
1485 return self.url_result(mobj.group('url'))
1487 # Look for Libsyn player
1489 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1490 if mobj is not None:
1491 return self.url_result(mobj.group('url'))
1493 # Look for Ooyala videos
1494 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1495 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1496 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1497 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1498 if mobj is not None:
1499 return OoyalaIE._build_url_result(mobj.group('ec'))
1501 # Look for multiple Ooyala embeds on SBN network websites
1502 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1503 if mobj is not None:
1504 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1506 return _playlist_from_matches(
1507 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1509 # Look for Aparat videos
1510 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1511 if mobj is not None:
1512 return self.url_result(mobj.group(1), 'Aparat')
1514 # Look for MPORA videos
1515 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1516 if mobj is not None:
1517 return self.url_result(mobj.group(1), 'Mpora')
1519 # Look for embedded NovaMov-based player
1521 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1522 (?P<url>http://(?:(?:embed|www)\.)?
1524 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1525 videoweed\.(?:es|com)|
1526 movshare\.(?:net|sx|ag)|
1527 divxstage\.(?:eu|net|ch|co|at|ag))
1528 /embed\.php.+?)\1''', webpage)
1529 if mobj is not None:
1530 return self.url_result(mobj.group('url'))
1532 # Look for embedded Facebook player
1534 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1535 if mobj is not None:
1536 return self.url_result(mobj.group('url'), 'Facebook')
1538 # Look for embedded VK player
1539 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1540 if mobj is not None:
1541 return self.url_result(mobj.group('url'), 'VK')
1543 # Look for embedded ivi player
1544 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1545 if mobj is not None:
1546 return self.url_result(mobj.group('url'), 'Ivi')
1548 # Look for embedded Huffington Post player
1550 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1551 if mobj is not None:
1552 return self.url_result(mobj.group('url'), 'HuffPost')
1555 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1556 if mobj is not None:
1557 return self.url_result(mobj.group('url'))
1558 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1559 if mobj is not None:
1560 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1562 # Look for funnyordie embed
1563 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1565 return _playlist_from_matches(
1566 matches, getter=unescapeHTML, ie='FunnyOrDie')
1568 # Look for BBC iPlayer embed
1569 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1571 return _playlist_from_matches(matches, ie='BBCCoUk')
1573 # Look for embedded RUTV player
1574 rutv_url = RUTVIE._extract_url(webpage)
1576 return self.url_result(rutv_url, 'RUTV')
1578 # Look for embedded TVC player
1579 tvc_url = TVCIE._extract_url(webpage)
1581 return self.url_result(tvc_url, 'TVC')
1583 # Look for embedded SportBox player
1584 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1586 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1588 # Look for embedded PornHub player
1589 pornhub_url = PornHubIE._extract_url(webpage)
1591 return self.url_result(pornhub_url, 'PornHub')
1593 # Look for embedded XHamster player
1594 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1596 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1598 # Look for embedded Tvigle player
1600 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1601 if mobj is not None:
1602 return self.url_result(mobj.group('url'), 'Tvigle')
1604 # Look for embedded TED player
1606 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1607 if mobj is not None:
1608 return self.url_result(mobj.group('url'), 'TED')
1610 # Look for embedded Ustream videos
1612 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1613 if mobj is not None:
1614 return self.url_result(mobj.group('url'), 'Ustream')
1616 # Look for embedded arte.tv player
1618 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1620 if mobj is not None:
1621 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1623 # Look for embedded francetv player
1625 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1627 if mobj is not None:
1628 return self.url_result(mobj.group('url'))
1630 # Look for embedded smotri.com player
1631 smotri_url = SmotriIE._extract_url(webpage)
1633 return self.url_result(smotri_url, 'Smotri')
1635 # Look for embedded Myvi.ru player
1636 myvi_url = MyviIE._extract_url(webpage)
1638 return self.url_result(myvi_url)
1640 # Look for embeded soundcloud player
1642 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1644 if mobj is not None:
1645 url = unescapeHTML(mobj.group('url'))
1646 return self.url_result(url)
1648 # Look for embedded vulture.com player
1650 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1652 if mobj is not None:
1653 url = unescapeHTML(mobj.group('url'))
1654 return self.url_result(url, ie='Vulture')
1656 # Look for embedded mtvservices player
1657 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1659 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1661 # Look for embedded yahoo player
1663 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1665 if mobj is not None:
1666 return self.url_result(mobj.group('url'), 'Yahoo')
1668 # Look for embedded sbs.com.au player
1672 <meta\s+property="og:video"\s+content=|
1675 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1677 if mobj is not None:
1678 return self.url_result(mobj.group('url'), 'SBS')
1680 # Look for embedded Cinchcast player
1682 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1684 if mobj is not None:
1685 return self.url_result(mobj.group('url'), 'Cinchcast')
1688 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1692 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1694 if mobj is not None:
1695 return self.url_result(mobj.group('url'), 'MLB')
1698 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1700 if mobj is not None:
1701 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1704 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1706 if mobj is not None:
1707 return self.url_result(mobj.group('url'), 'Livestream')
1709 # Look for Zapiks embed
1711 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1712 if mobj is not None:
1713 return self.url_result(mobj.group('url'), 'Zapiks')
1715 # Look for Kaltura embeds
1716 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1717 re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
1718 if mobj is not None:
1719 return self.url_result(smuggle_url(
1720 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1721 {'source_url': url}), 'Kaltura')
1723 # Look for Eagle.Platform embeds
1725 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1726 if mobj is not None:
1727 return self.url_result(mobj.group('url'), 'EaglePlatform')
1729 # Look for ClipYou (uses Eagle.Platform) embeds
1731 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1732 if mobj is not None:
1733 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1735 # Look for Pladform embeds
1737 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1738 if mobj is not None:
1739 return self.url_result(mobj.group('url'), 'Pladform')
1741 # Look for Playwire embeds
1743 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1744 if mobj is not None:
1745 return self.url_result(mobj.group('url'))
1747 # Look for 5min embeds
1749 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1750 if mobj is not None:
1751 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1753 # Look for Crooks and Liars embeds
1755 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1756 if mobj is not None:
1757 return self.url_result(mobj.group('url'))
1759 # Look for NBC Sports VPlayer embeds
1760 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1762 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1764 # Look for UDN embeds
1766 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1767 if mobj is not None:
1768 return self.url_result(
1769 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1771 # Look for Senate ISVP iframe
1772 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1774 return self.url_result(senate_isvp_url, 'SenateISVP')
1776 # Look for Dailymotion Cloud videos
1777 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1779 return self.url_result(dmcloud_url, 'DailymotionCloud')
1781 # Look for OnionStudios embeds
1782 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1783 if onionstudios_url:
1784 return self.url_result(onionstudios_url)
1786 # Look for SnagFilms embeds
1787 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1789 return self.url_result(snagfilms_url)
1791 # Look for JWPlatform embeds
1792 jwplatform_url = JWPlatformIE._extract_url(webpage)
1794 return self.url_result(jwplatform_url, 'JWPlatform')
1796 # Look for ScreenwaveMedia embeds
1797 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1798 if mobj is not None:
1799 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1801 # Look for AdobeTVVideo embeds
1803 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1805 if mobj is not None:
1806 return self.url_result(
1807 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1810 def check_video(vurl):
1811 if YoutubeIE.suitable(vurl):
1813 vpath = compat_urlparse.urlparse(vurl).path
1814 vext = determine_ext(vpath)
1815 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1817 def filter_video(urls):
1818 return list(filter(check_video, urls))
1820 # Start with something easy: JW Player in SWFObject
1821 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1823 # Look for gorilla-vid style embedding
1824 found = filter_video(re.findall(r'''(?sx)
1828 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1831 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1833 # Broaden the search a little bit
1834 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1836 # Broaden the findall a little bit: JWPlayer JS loader
1837 found = filter_video(re.findall(
1838 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1841 found = filter_video(re.findall(r'''(?xs)
1842 flowplayer\("[^"]+",\s*
1844 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1845 ["']?url["']?\s*:\s*["']([^"']+)["']
1850 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1852 # Try to find twitter cards info
1853 found = filter_video(re.findall(
1854 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1856 # We look for Open Graph info:
1857 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1858 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1859 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1860 if m_video_type is not None:
1861 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1864 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1866 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1868 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1869 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1872 # Look also in Refresh HTTP header
1873 refresh_header = head_response.headers.get('Refresh')
1875 # In python 2 response HTTP headers are bytestrings
1876 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1877 refresh_header = refresh_header.decode('iso-8859-1')
1878 found = re.search(REDIRECT_REGEX, refresh_header)
1880 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1881 self.report_following_redirect(new_url)
1887 raise UnsupportedError(url)
1890 for video_url in found:
1891 video_url = video_url.replace('\\/', '/')
1892 video_url = compat_urlparse.urljoin(url, video_url)
1893 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1895 # Sometimes, jwplayer extraction will result in a YouTube URL
1896 if YoutubeIE.suitable(video_url):
1897 entries.append(self.url_result(video_url, 'Youtube'))
1900 # here's a fun little line of code for you:
1901 video_id = os.path.splitext(video_id)[0]
1905 'uploader': video_uploader,
1906 'title': video_title,
1907 'age_limit': age_limit,
1910 ext = determine_ext(video_url)
1912 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
1914 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1916 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
1918 entry_info_dict['url'] = video_url
1920 entries.append(entry_info_dict)
1922 if len(entries) == 1:
1925 for num, e in enumerate(entries, start=1):
1926 # 'url' results don't have a title
1927 if e.get('title') is not None:
1928 e['title'] = '%s (%d)' % (e['title'], num)
1930 '_type': 'playlist',