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 .bliptv import BlipTVIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import DailymotionCloudIE
53 from .onionstudios import OnionStudiosIE
54 from .snagfilms import SnagFilmsEmbedIE
55 from .screenwavemedia import ScreenwaveMediaIE
56 from .mtv import MTVServicesEmbeddedIE
57 from .pladform import PladformIE
60 class GenericIE(InfoExtractor):
61 IE_DESC = 'Generic downloader that works on some sites'
65 # Direct link to a video
67 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
68 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
73 'upload_date': '20100513',
76 # Direct link to media delivered compressed (until Accept-Encoding is *)
78 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
79 'md5': '128c42e68b13950268b648275386fc74',
81 'id': 'FictionJunction-Parallel_Hearts',
83 'title': 'FictionJunction-Parallel_Hearts',
84 'upload_date': '20140522',
86 'expected_warnings': [
87 'URL could be a direct video link, returning it as such.'
90 # Direct download with broken HEAD
92 'url': 'http://ai-radio.org:8000/radio.opus',
99 'skip_download': True, # infinite live stream
101 'expected_warnings': [
102 r'501.*Not Implemented'
105 # Direct link with incorrect MIME type
107 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
108 'md5': '4ccbebe5f36706d85221f204d7eb5913',
110 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
111 'id': '5_Lennart_Poettering_-_Systemd',
113 'title': '5_Lennart_Poettering_-_Systemd',
114 'upload_date': '20141120',
116 'expected_warnings': [
117 'URL could be a direct video link, returning it as such.'
122 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
124 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
125 'title': 'Zero Punctuation',
126 'description': 're:.*groundbreaking video review series.*'
128 'playlist_mincount': 11,
130 # RSS feed with enclosure
132 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
134 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
136 'upload_date': '20150228',
137 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
140 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
142 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
146 'title': 'Automatics, robotics and biocybernetics',
147 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
148 'upload_date': '20130627',
149 'formats': 'mincount:16',
150 'subtitles': 'mincount:1',
153 'force_generic_extractor': True,
154 'skip_download': True,
157 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
159 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
164 'formats': 'mincount:1',
167 'skip_download': True,
170 # SMIL from https://www.restudy.dk/video/play/id/1637
172 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
176 'title': 'video_1637',
177 'formats': 'mincount:3',
180 'skip_download': True,
183 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
185 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
187 'id': 'smil-service',
189 'title': 'smil-service',
190 'formats': 'mincount:1',
193 'skip_download': True,
196 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
198 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
202 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
203 'formats': 'mincount:3',
206 'skip_download': True,
209 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
211 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
213 'id': 'mZlp2ctYIUEB',
215 'title': 'Tikibad ontruimd wegens brand',
216 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
217 'thumbnail': 're:^https?://.*\.jpg$',
221 'skip_download': True,
226 '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',
230 'upload_date': '20130224',
231 'uploader_id': 'TheVerge',
232 'description': 're:^Chris Ziegler takes a look at the\.*',
233 'uploader': 'The Verge',
234 'title': 'First Firefox OS phones side-by-side',
237 'skip_download': False,
241 # redirect in Refresh HTTP header
242 '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',
246 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
247 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
248 'upload_date': '20150917',
249 'uploader_id': 'brtvofficial',
250 'uploader': 'Boiler Room',
253 'skip_download': False,
257 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
258 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
260 'id': '13601338388002',
262 'uploader': 'www.hodiho.fr',
263 'title': 'R\u00e9gis plante sa Jeep',
266 # bandcamp page with custom domain
268 'add_ie': ['Bandcamp'],
269 'url': 'http://bronyrock.com/track/the-pony-mash',
273 'title': 'The Pony Mash',
274 'uploader': 'M_Pallante',
276 'skip': 'There is a limit of 200 free downloads / month for the test song',
278 # embedded brightcove video
279 # it also tests brightcove videos that need to set the 'Referer' in the
282 'add_ie': ['BrightcoveLegacy'],
283 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
285 'id': '2765128793001',
287 'title': 'Le cours de bourse : l’analyse technique',
288 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
289 'uploader': 'BFM BUSINESS',
292 'skip_download': True,
296 # https://github.com/rg3/youtube-dl/issues/2253
297 'url': 'http://bcove.me/i6nfkrc3',
298 'md5': '0ba9446db037002366bab3b3eb30c88c',
300 'id': '3101154703001',
302 'title': 'Still no power',
303 'uploader': 'thestar.com',
304 '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.',
306 'add_ie': ['BrightcoveLegacy'],
309 'url': 'http://www.championat.com/video/football/v/87/87499.html',
310 'md5': 'fb973ecf6e4a78a67453647444222983',
312 'id': '3414141473001',
314 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
315 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
316 'uploader': 'Championat',
320 # https://github.com/rg3/youtube-dl/issues/3541
321 'add_ie': ['BrightcoveLegacy'],
322 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
324 'id': '3866516442001',
326 'title': 'Leer mij vrouwen kennen: Aflevering 1',
327 'description': 'Leer mij vrouwen kennen: Aflevering 1',
328 'uploader': 'SBS Broadcasting',
330 'skip': 'Restricted to Netherlands',
332 'skip_download': True, # m3u8 download
337 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
338 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
340 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
342 'title': '2cc213299525360.mov', # that's what we get
345 'add_ie': ['Ooyala'],
348 # ooyala video embedded with http://player.ooyala.com/iframe.js
349 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
351 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
353 'title': '"Steve Jobs: Man in the Machine" trailer',
354 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
358 'skip_download': True,
361 # multiple ooyala embeds on SBN network websites
363 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
365 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
366 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
368 'playlist_mincount': 3,
370 'skip_download': True,
372 'add_ie': ['Ooyala'],
376 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
380 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
381 'upload_date': '20140225',
382 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
383 'uploader': 'Tested',
384 'uploader_id': 'testedcom',
386 # No need to test YoutubeIE here
388 'skip_download': True,
393 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
397 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
398 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
403 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
407 'title': 'Охотское море стало целиком российским',
408 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
412 'skip_download': True,
417 '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/',
421 'title': 'Дошкольное воспитание',
426 'url': 'http://www.vestifinance.ru/articles/25753',
429 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
434 'title': 'Госзаказ. День 3',
440 'title': 'Госзаказ. День 2',
446 'title': 'Госзаказ. День 1',
452 'skip_download': True,
457 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
459 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
461 'title': 'Ужастики, русский трейлер (2015)',
462 'thumbnail': 're:^https?://.*\.jpg$',
468 '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',
471 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
473 'playlist_mincount': 7,
477 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
478 'md5': '65fdff94098e4a607385a60c5177c638',
482 'title': 'Hidden miracles of the natural world',
483 'uploader': 'Louie Schwartzberg',
484 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
487 # Embeded Ustream video
489 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
490 'md5': '27b99cdb639c9b12a79bca876a073417',
494 'uploader': 'AU SPA: The NSA and Privacy',
495 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
498 # nowvideo embed hidden behind percent encoding
500 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
501 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
503 'id': '06e53103ca9aa',
505 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
506 'description': 'No description',
511 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
512 'md5': '7653032cbb25bf6c80d80f217055fa43',
514 'id': '048195-004_PLUS7-F',
517 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
518 'upload_date': '20140320',
521 'skip_download': 'Requires rtmpdump'
526 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
530 'title': 'Alcaline, le concert avec Calogero',
531 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
532 'upload_date': '20150226',
533 'timestamp': 1424989860,
538 'skip_download': True,
540 'expected_warnings': [
546 'url': 'http://www.wired.com/2014/04/honda-asimo/',
547 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
549 'id': '53501be369702d3275860000',
551 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
556 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
557 'md5': '441aeeb82eb72c422c7f14ec533999cd',
559 'id': 'k2mm4bCdJ6CQ2i7c8o2',
561 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
564 'add_ie': ['Dailymotion'],
568 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
572 'title': 'The NBL Auction 2014',
573 'uploader': 'BADMINTON England',
574 'uploader_id': 'BADMINTONEvents',
575 'upload_date': '20140603',
576 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
578 'add_ie': ['Youtube'],
580 'skip_download': True,
585 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
586 'md5': '35727f82f58c76d996fc188f9755b0d5',
588 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
591 'description': 'Mario\'s life in the fast lane has never looked so good.',
594 # YouTube embed via <data-embed-url="">
596 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
600 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
601 'uploader': 'Gameloft',
602 'uploader_id': 'gameloft',
603 'upload_date': '20140828',
604 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
607 'skip_download': True,
612 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
614 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
616 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
617 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
622 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
624 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
625 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
631 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
636 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
637 'md5': '9d65602bf31c6e20014319c7d07fba27',
639 'id': '5123ea6d5e5a7',
642 'uploader': 'www.handjobhub.com',
643 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
646 # Multiple brightcove videos
647 # https://github.com/rg3/youtube-dl/issues/2283
649 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
651 'id': 'always-never',
652 'title': 'Always / Never - The New Yorker',
656 'extract_flat': False,
657 'skip_download': True,
662 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
663 'md5': '96f09a37e44da40dd083e12d9a683327',
667 'title': 'Ump changes call to ball',
668 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
670 'timestamp': 1401537900,
671 'upload_date': '20140531',
672 'thumbnail': 're:^https?://.*\.jpg$',
677 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
678 'md5': '8788b683c777a5cf25621eaf286d0c23',
682 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
684 'filesize': 182808282,
685 'uploader': 'education-portal.com',
689 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
690 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
694 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
696 'uploader': 'thoughtworks.wistia.com',
701 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
705 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
706 'uploader': 'Sophos Security',
707 'title': 'Chet Chat 171 - Oct 29, 2014',
708 'upload_date': '20141029',
713 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
717 'upload_date': '20141112',
718 'title': 'Rosetta #CometLanding webcast HL 10',
723 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
726 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
728 'playlist_mincount': 2,
732 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
736 'upload_date': '20141126',
737 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
742 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
744 'id': '730m_DandD_1901_512k',
746 'uploader': 'www.abc.net.au',
747 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
750 # embedded viddler video
752 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
756 'uploader': 'deadspin',
757 'title': 'WALL-TO-GORTAT',
758 'timestamp': 1422285291,
759 'upload_date': '20150126',
761 'add_ie': ['Viddler'],
765 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
769 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
770 'description': 'md5:601cb790edd05908957dae8aaa866465',
771 'upload_date': '20150220',
776 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
780 'upload_date': '20150212',
781 'uploader': 'The National Archives UK',
782 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
783 'uploader_id': 'NationalArchives08',
784 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
789 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
790 'playlist_mincount': 5,
792 'id': 'aanslagen-kopenhagen',
793 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
798 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
802 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
807 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
811 'upload_date': '20150226',
812 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
814 'title': 'John Carlson Postgame 2/25/15',
817 # Kaltura embed (different embed code)
819 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
823 'upload_date': '20150127',
824 'uploader_id': 'PremierMedia',
826 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
829 # Kaltura embed protected with referrer
831 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
835 'title': 'Violetta - Achter De Schermen - Ruggero',
836 'description': 'Achter de schermen met Ruggero',
837 'timestamp': 1435133761,
838 'upload_date': '20150624',
839 'uploader_id': 'echojecka',
842 # Eagle.Platform embed (generic URL)
844 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
848 'title': 'Навальный вышел на свободу',
849 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
850 'thumbnail': 're:^https?://.*\.jpg$',
856 # ClipYou (Eagle.Platform) embed (custom URL)
858 'url': 'http://muz-tv.ru/play/7129/',
862 'title': "'O Sole Mio",
863 'thumbnail': 're:^https?://.*\.jpg$',
870 'url': 'http://muz-tv.ru/kinozal/view/7400/',
874 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
875 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
876 'thumbnail': 're:^https?://.*\.jpg$',
883 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
887 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
888 'thumbnail': 're:^https?://.*\.png$',
894 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
895 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
899 'title': 'Facebook Creates "On This Day" | Crunch Report',
904 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
908 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
913 # Crooks and Liars embed
915 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
919 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
920 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
921 'timestamp': 1428207000,
922 'upload_date': '20150405',
923 'uploader': 'Heather',
926 # Crooks and Liars external embed
928 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
930 'id': 'MTE3MjUtMzQ2MzA',
932 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
933 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
934 'timestamp': 1265032391,
935 'upload_date': '20100201',
936 'uploader': 'Heather',
939 # NBC Sports vplayer embed
941 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
943 'id': 'ln7x1qSThw4k',
945 'title': "PFT Live: New leader in the 'new-look' defense",
946 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
951 'url': 'http://www.udn.com/news/story/7314/822787',
952 'md5': 'fd2060e988c326991037b9aff9df21a6',
956 'title': '中一中男師變性 全校師生力挺',
957 'thumbnail': 're:^https?://.*\.jpg$',
962 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
964 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
966 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
967 'title': 'This is what separates the Excel masters from the wannabes',
972 'skip_download': True,
975 # Contains a SMIL manifest
977 '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',
981 'title': '+ Football: Lottery Champions League Europe',
982 'uploader': 'www.telewebion.com',
986 'skip_download': True,
989 # Brightcove URL in single quotes
991 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
992 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
994 'id': '4255764656001',
996 'title': 'SN Presents: Russell Martin, World Citizen',
997 '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.',
998 'uploader': 'Rogers Sportsnet',
1001 # Dailymotion Cloud video
1003 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1004 'md5': '49444254273501a64675a7e68c502681',
1006 'id': '5585de919473990de4bee11b',
1008 'title': 'Le débat',
1009 'thumbnail': 're:^https?://.*\.jpe?g$',
1012 # OnionStudios embed
1014 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1018 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1019 'thumbnail': 're:^https?://.*\.jpe?g$',
1020 'uploader': 'ClickHole',
1021 'uploader_id': 'clickhole',
1026 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1028 'id': '74849a00-85a9-11e1-9660-123139220831',
1030 'title': '#whilewewatch',
1033 # AdobeTVVideo embed
1035 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1036 'md5': '43662b577c018ad707a63766462b1e87',
1040 'title': 'New experience with Acrobat DC',
1041 'description': 'New experience with Acrobat DC',
1042 'duration': 248.667,
1045 # ScreenwaveMedia embed
1047 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1048 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1050 'id': 'cinemasnob-55d26273809dd',
1052 'title': 'cinemasnob',
1055 # BrightcoveInPageEmbed embed
1057 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1059 'id': '4238694884001',
1061 'title': 'Tabletop: Dread, Last Thoughts',
1062 'description': 'Tabletop: Dread, Last Thoughts',
1066 # JWPlayer with M3U8
1068 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1072 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1073 'uploader': 'ren.tv',
1077 'skip_download': True,
1082 def report_following_redirect(self, new_url):
1083 """Report information extraction."""
1084 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1086 def _extract_rss(self, url, video_id, doc):
1087 playlist_title = doc.find('./channel/title').text
1088 playlist_desc_el = doc.find('./channel/description')
1089 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1092 for it in doc.findall('./channel/item'):
1093 next_url = xpath_text(it, 'link', fatal=False)
1095 enclosure_nodes = it.findall('./enclosure')
1096 for e in enclosure_nodes:
1097 next_url = e.attrib.get('url')
1107 'title': it.find('title').text,
1111 '_type': 'playlist',
1113 'title': playlist_title,
1114 'description': playlist_desc,
1118 def _extract_camtasia(self, url, video_id, webpage):
1119 """ Returns None if no camtasia video can be found. """
1121 camtasia_cfg = self._search_regex(
1122 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1123 webpage, 'camtasia configuration file', default=None)
1124 if camtasia_cfg is None:
1127 title = self._html_search_meta('DC.title', webpage, fatal=True)
1129 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1130 camtasia_cfg = self._download_xml(
1131 camtasia_url, video_id,
1132 note='Downloading camtasia configuration',
1133 errnote='Failed to download camtasia configuration')
1134 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1137 for n in fileset_node.getchildren():
1138 url_n = n.find('./uri')
1143 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1144 'title': '%s - %s' % (title, n.tag),
1145 'url': compat_urlparse.urljoin(url, url_n.text),
1146 'duration': float_or_none(n.find('./duration').text),
1150 '_type': 'playlist',
1155 def _real_extract(self, url):
1156 if url.startswith('//'):
1159 'url': self.http_scheme() + url,
1162 parsed_url = compat_urlparse.urlparse(url)
1163 if not parsed_url.scheme:
1164 default_search = self._downloader.params.get('default_search')
1165 if default_search is None:
1166 default_search = 'fixup_error'
1168 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1170 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1171 return self.url_result('http://' + url)
1172 elif default_search != 'fixup_error':
1173 if default_search == 'auto_warning':
1174 if re.match(r'^(?:url|URL)$', url):
1175 raise ExtractorError(
1176 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1179 self._downloader.report_warning(
1180 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1181 return self.url_result('ytsearch:' + url)
1183 if default_search in ('error', 'fixup_error'):
1184 raise ExtractorError(
1185 '%r is not a valid URL. '
1186 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1187 % (url, url), expected=True)
1189 if ':' not in default_search:
1190 default_search += ':'
1191 return self.url_result(default_search + url)
1193 url, smuggled_data = unsmuggle_url(url)
1194 force_videoid = None
1195 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1196 if smuggled_data and 'force_videoid' in smuggled_data:
1197 force_videoid = smuggled_data['force_videoid']
1198 video_id = force_videoid
1200 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1202 self.to_screen('%s: Requesting header' % video_id)
1204 head_req = HEADRequest(url)
1205 head_response = self._request_webpage(
1207 note=False, errnote='Could not send HEAD request to %s' % url,
1210 if head_response is not False:
1211 # Check for redirect
1212 new_url = head_response.geturl()
1214 self.report_following_redirect(new_url)
1216 new_url = smuggle_url(
1217 new_url, {'force_videoid': force_videoid})
1218 return self.url_result(new_url)
1220 full_response = None
1221 if head_response is False:
1222 request = sanitized_Request(url)
1223 request.add_header('Accept-Encoding', '*')
1224 full_response = self._request_webpage(request, video_id)
1225 head_response = full_response
1227 # Check for direct link to a video
1228 content_type = head_response.headers.get('Content-Type', '')
1229 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1231 upload_date = unified_strdate(
1232 head_response.headers.get('Last-Modified'))
1235 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1238 'format_id': m.group('format_id'),
1240 'vcodec': 'none' if m.group('type') == 'audio' else None
1242 'upload_date': upload_date,
1245 if not self._downloader.params.get('test', False) and not is_intentional:
1246 force = self._downloader.params.get('force_generic_extractor', False)
1247 self._downloader.report_warning(
1248 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1250 if not full_response:
1251 request = sanitized_Request(url)
1252 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1253 # making it impossible to download only chunk of the file (yet we need only 512kB to
1254 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1255 # that will always result in downloading the whole file that is not desirable.
1256 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1257 # to accept raw bytes and being able to download only a chunk.
1258 # It may probably better to solve this by checking Content-Type for application/octet-stream
1259 # after HEAD request finishes, but not sure if we can rely on this.
1260 request.add_header('Accept-Encoding', '*')
1261 full_response = self._request_webpage(request, video_id)
1263 # Maybe it's a direct link to a video?
1264 # Be careful not to download the whole thing!
1265 first_bytes = full_response.read(512)
1266 if not is_html(first_bytes):
1267 self._downloader.report_warning(
1268 'URL could be a direct video link, returning it as such.')
1269 upload_date = unified_strdate(
1270 head_response.headers.get('Last-Modified'))
1273 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1276 'upload_date': upload_date,
1279 webpage = self._webpage_read_content(
1280 full_response, url, video_id, prefix=first_bytes)
1282 self.report_extraction(video_id)
1284 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1286 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1287 if doc.tag == 'rss':
1288 return self._extract_rss(url, video_id, doc)
1289 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1290 return self._parse_smil(doc, url, video_id)
1291 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1292 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1293 except compat_xml_parse_error:
1296 # Is it a Camtasia project?
1297 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1298 if camtasia_res is not None:
1301 # Sometimes embedded video player is hidden behind percent encoding
1302 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1303 # Unescaping the whole page allows to handle those cases in a generic way
1304 webpage = compat_urllib_parse_unquote(webpage)
1306 # it's tempting to parse this further, but you would
1307 # have to take into account all the variations like
1308 # Video Title - Site Name
1309 # Site Name | Video Title
1310 # Video Title - Tagline | Site Name
1311 # and so on and so forth; it's just not practical
1312 video_title = self._html_search_regex(
1313 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1316 # Try to detect age limit automatically
1317 age_limit = self._rta_search(webpage)
1318 # And then there are the jokers who advertise that they use RTA,
1319 # but actually don't.
1320 AGE_LIMIT_MARKERS = [
1321 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1323 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1326 # video uploader is domain name
1327 video_uploader = self._search_regex(
1328 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1331 def _playlist_from_matches(matches, getter=None, ie=None):
1333 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1335 return self.playlist_result(
1336 urlrs, playlist_id=video_id, playlist_title=video_title)
1338 # Look for Brightcove Legacy Studio embeds
1339 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1341 self.to_screen('Brightcove video detected.')
1344 'url': smuggle_url(bc_url, {'Referer': url}),
1345 'ie_key': 'BrightcoveLegacy'
1346 } for bc_url in bc_urls]
1349 '_type': 'playlist',
1350 'title': video_title,
1355 # Look for Brightcove New Studio embeds
1356 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1358 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1360 # Look for embedded rtl.nl player
1361 matches = re.findall(
1362 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1365 return _playlist_from_matches(matches, ie='RtlNl')
1367 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1368 if vimeo_url is not None:
1369 return self.url_result(vimeo_url)
1371 vid_me_embed_url = self._search_regex(
1372 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1373 webpage, 'vid.me embed', default=None)
1374 if vid_me_embed_url is not None:
1375 return self.url_result(vid_me_embed_url, 'Vidme')
1377 # Look for embedded YouTube player
1378 matches = re.findall(r'''(?x)
1387 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1391 return _playlist_from_matches(
1392 matches, lambda m: unescapeHTML(m[1]))
1394 # Look for lazyYT YouTube embed
1395 matches = re.findall(
1396 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1398 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1400 # Look for embedded Dailymotion player
1401 matches = re.findall(
1402 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1404 return _playlist_from_matches(
1405 matches, lambda m: unescapeHTML(m[1]))
1407 # Look for embedded Dailymotion playlist player (#3822)
1409 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1411 playlists = re.findall(
1412 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1414 return _playlist_from_matches(
1415 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1417 # Look for embedded Wistia player
1419 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1421 embed_url = self._proto_relative_url(
1422 unescapeHTML(match.group('url')))
1424 '_type': 'url_transparent',
1427 'uploader': video_uploader,
1428 'title': video_title,
1432 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1435 '_type': 'url_transparent',
1436 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1438 'uploader': video_uploader,
1439 'title': video_title,
1440 'id': match.group('id')
1443 # Look for embedded blip.tv player
1444 bliptv_url = BlipTVIE._extract_url(webpage)
1446 return self.url_result(bliptv_url, 'BlipTV')
1448 # Look for SVT player
1449 svt_url = SVTIE._extract_url(webpage)
1451 return self.url_result(svt_url, 'SVT')
1453 # Look for embedded condenast player
1454 matches = re.findall(
1455 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1459 '_type': 'playlist',
1462 'ie_key': 'CondeNast',
1464 } for ma in matches],
1465 'title': video_title,
1469 # Look for Bandcamp pages with custom domain
1470 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1471 if mobj is not None:
1472 burl = unescapeHTML(mobj.group(1))
1473 # Don't set the extractor because it can be a track url or an album
1474 return self.url_result(burl)
1476 # Look for embedded Vevo player
1478 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1479 if mobj is not None:
1480 return self.url_result(mobj.group('url'))
1482 # Look for embedded Viddler player
1484 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1486 if mobj is not None:
1487 return self.url_result(mobj.group('url'))
1489 # Look for NYTimes player
1491 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1493 if mobj is not None:
1494 return self.url_result(mobj.group('url'))
1496 # Look for Libsyn player
1498 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1499 if mobj is not None:
1500 return self.url_result(mobj.group('url'))
1502 # Look for Ooyala videos
1503 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1504 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1505 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1506 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1507 if mobj is not None:
1508 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1510 # Look for multiple Ooyala embeds on SBN network websites
1511 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1512 if mobj is not None:
1513 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1515 return _playlist_from_matches(
1516 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1518 # Look for Aparat videos
1519 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1520 if mobj is not None:
1521 return self.url_result(mobj.group(1), 'Aparat')
1523 # Look for MPORA videos
1524 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1525 if mobj is not None:
1526 return self.url_result(mobj.group(1), 'Mpora')
1528 # Look for embedded NovaMov-based player
1530 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1531 (?P<url>http://(?:(?:embed|www)\.)?
1533 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1534 videoweed\.(?:es|com)|
1535 movshare\.(?:net|sx|ag)|
1536 divxstage\.(?:eu|net|ch|co|at|ag))
1537 /embed\.php.+?)\1''', webpage)
1538 if mobj is not None:
1539 return self.url_result(mobj.group('url'))
1541 # Look for embedded Facebook player
1543 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1544 if mobj is not None:
1545 return self.url_result(mobj.group('url'), 'Facebook')
1547 # Look for embedded VK player
1548 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1549 if mobj is not None:
1550 return self.url_result(mobj.group('url'), 'VK')
1552 # Look for embedded ivi player
1553 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1554 if mobj is not None:
1555 return self.url_result(mobj.group('url'), 'Ivi')
1557 # Look for embedded Huffington Post player
1559 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1560 if mobj is not None:
1561 return self.url_result(mobj.group('url'), 'HuffPost')
1564 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1565 if mobj is not None:
1566 return self.url_result(mobj.group('url'))
1567 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1568 if mobj is not None:
1569 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1571 # Look for funnyordie embed
1572 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1574 return _playlist_from_matches(
1575 matches, getter=unescapeHTML, ie='FunnyOrDie')
1577 # Look for BBC iPlayer embed
1578 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1580 return _playlist_from_matches(matches, ie='BBCCoUk')
1582 # Look for embedded RUTV player
1583 rutv_url = RUTVIE._extract_url(webpage)
1585 return self.url_result(rutv_url, 'RUTV')
1587 # Look for embedded TVC player
1588 tvc_url = TVCIE._extract_url(webpage)
1590 return self.url_result(tvc_url, 'TVC')
1592 # Look for embedded SportBox player
1593 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1595 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1597 # Look for embedded PornHub player
1598 pornhub_url = PornHubIE._extract_url(webpage)
1600 return self.url_result(pornhub_url, 'PornHub')
1602 # Look for embedded XHamster player
1603 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1605 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1607 # Look for embedded Tvigle player
1609 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1610 if mobj is not None:
1611 return self.url_result(mobj.group('url'), 'Tvigle')
1613 # Look for embedded TED player
1615 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1616 if mobj is not None:
1617 return self.url_result(mobj.group('url'), 'TED')
1619 # Look for embedded Ustream videos
1621 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1622 if mobj is not None:
1623 return self.url_result(mobj.group('url'), 'Ustream')
1625 # Look for embedded arte.tv player
1627 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1629 if mobj is not None:
1630 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1632 # Look for embedded francetv player
1634 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1636 if mobj is not None:
1637 return self.url_result(mobj.group('url'))
1639 # Look for embedded smotri.com player
1640 smotri_url = SmotriIE._extract_url(webpage)
1642 return self.url_result(smotri_url, 'Smotri')
1644 # Look for embedded Myvi.ru player
1645 myvi_url = MyviIE._extract_url(webpage)
1647 return self.url_result(myvi_url)
1649 # Look for embeded soundcloud player
1651 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1653 if mobj is not None:
1654 url = unescapeHTML(mobj.group('url'))
1655 return self.url_result(url)
1657 # Look for embedded vulture.com player
1659 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1661 if mobj is not None:
1662 url = unescapeHTML(mobj.group('url'))
1663 return self.url_result(url, ie='Vulture')
1665 # Look for embedded mtvservices player
1666 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1668 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1670 # Look for embedded yahoo player
1672 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1674 if mobj is not None:
1675 return self.url_result(mobj.group('url'), 'Yahoo')
1677 # Look for embedded sbs.com.au player
1681 <meta\s+property="og:video"\s+content=|
1684 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1686 if mobj is not None:
1687 return self.url_result(mobj.group('url'), 'SBS')
1689 # Look for embedded Cinchcast player
1691 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1693 if mobj is not None:
1694 return self.url_result(mobj.group('url'), 'Cinchcast')
1697 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1701 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1703 if mobj is not None:
1704 return self.url_result(mobj.group('url'), 'MLB')
1707 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1709 if mobj is not None:
1710 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1713 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1715 if mobj is not None:
1716 return self.url_result(mobj.group('url'), 'Livestream')
1718 # Look for Zapiks embed
1720 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1721 if mobj is not None:
1722 return self.url_result(mobj.group('url'), 'Zapiks')
1724 # Look for Kaltura embeds
1725 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1726 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))
1727 if mobj is not None:
1728 return self.url_result(smuggle_url(
1729 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1730 {'source_url': url}), 'Kaltura')
1732 # Look for Eagle.Platform embeds
1734 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1735 if mobj is not None:
1736 return self.url_result(mobj.group('url'), 'EaglePlatform')
1738 # Look for ClipYou (uses Eagle.Platform) embeds
1740 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1741 if mobj is not None:
1742 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1744 # Look for Pladform embeds
1745 pladform_url = PladformIE._extract_url(webpage)
1747 return self.url_result(pladform_url)
1749 # Look for Playwire embeds
1751 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1752 if mobj is not None:
1753 return self.url_result(mobj.group('url'))
1755 # Look for 5min embeds
1757 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1758 if mobj is not None:
1759 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1761 # Look for Crooks and Liars embeds
1763 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1764 if mobj is not None:
1765 return self.url_result(mobj.group('url'))
1767 # Look for NBC Sports VPlayer embeds
1768 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1770 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1772 # Look for UDN embeds
1774 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1775 if mobj is not None:
1776 return self.url_result(
1777 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1779 # Look for Senate ISVP iframe
1780 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1782 return self.url_result(senate_isvp_url, 'SenateISVP')
1784 # Look for Dailymotion Cloud videos
1785 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1787 return self.url_result(dmcloud_url, 'DailymotionCloud')
1789 # Look for OnionStudios embeds
1790 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1791 if onionstudios_url:
1792 return self.url_result(onionstudios_url)
1794 # Look for SnagFilms embeds
1795 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1797 return self.url_result(snagfilms_url)
1799 # Look for ScreenwaveMedia embeds
1800 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1801 if mobj is not None:
1802 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1804 # Look for AdobeTVVideo embeds
1806 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1808 if mobj is not None:
1809 return self.url_result(
1810 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1813 def check_video(vurl):
1814 if YoutubeIE.suitable(vurl):
1816 vpath = compat_urlparse.urlparse(vurl).path
1817 vext = determine_ext(vpath)
1818 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1820 def filter_video(urls):
1821 return list(filter(check_video, urls))
1823 # Start with something easy: JW Player in SWFObject
1824 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1826 # Look for gorilla-vid style embedding
1827 found = filter_video(re.findall(r'''(?sx)
1831 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1834 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1836 # Broaden the search a little bit
1837 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1839 # Broaden the findall a little bit: JWPlayer JS loader
1840 found = filter_video(re.findall(
1841 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1844 found = filter_video(re.findall(r'''(?xs)
1845 flowplayer\("[^"]+",\s*
1847 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1848 ["']?url["']?\s*:\s*["']([^"']+)["']
1853 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1855 # Try to find twitter cards info
1856 found = filter_video(re.findall(
1857 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1859 # We look for Open Graph info:
1860 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1861 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1862 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1863 if m_video_type is not None:
1864 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1867 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1869 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1871 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1872 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1875 # Look also in Refresh HTTP header
1876 refresh_header = head_response.headers.get('Refresh')
1878 # In python 2 response HTTP headers are bytestrings
1879 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1880 refresh_header = refresh_header.decode('iso-8859-1')
1881 found = re.search(REDIRECT_REGEX, refresh_header)
1883 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1884 self.report_following_redirect(new_url)
1890 raise UnsupportedError(url)
1893 for video_url in found:
1894 video_url = video_url.replace('\\/', '/')
1895 video_url = compat_urlparse.urljoin(url, video_url)
1896 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1898 # Sometimes, jwplayer extraction will result in a YouTube URL
1899 if YoutubeIE.suitable(video_url):
1900 entries.append(self.url_result(video_url, 'Youtube'))
1903 # here's a fun little line of code for you:
1904 video_id = os.path.splitext(video_id)[0]
1908 'uploader': video_uploader,
1909 'title': video_title,
1910 'age_limit': age_limit,
1913 ext = determine_ext(video_url)
1915 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
1917 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1919 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
1921 entry_info_dict['url'] = video_url
1923 entries.append(entry_info_dict)
1925 if len(entries) == 1:
1928 for num, e in enumerate(entries, start=1):
1929 # 'url' results don't have a title
1930 if e.get('title') is not None:
1931 e['title'] = '%s (%d)' % (e['title'], num)
1933 '_type': 'playlist',