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
58 from .googledrive import GoogleDriveIE
61 class GenericIE(InfoExtractor):
62 IE_DESC = 'Generic downloader that works on some sites'
66 # Direct link to a video
68 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
69 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
74 'upload_date': '20100513',
77 # Direct link to media delivered compressed (until Accept-Encoding is *)
79 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
80 'md5': '128c42e68b13950268b648275386fc74',
82 'id': 'FictionJunction-Parallel_Hearts',
84 'title': 'FictionJunction-Parallel_Hearts',
85 'upload_date': '20140522',
87 'expected_warnings': [
88 'URL could be a direct video link, returning it as such.'
91 # Direct download with broken HEAD
93 'url': 'http://ai-radio.org:8000/radio.opus',
100 'skip_download': True, # infinite live stream
102 'expected_warnings': [
103 r'501.*Not Implemented'
106 # Direct link with incorrect MIME type
108 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
109 'md5': '4ccbebe5f36706d85221f204d7eb5913',
111 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
112 'id': '5_Lennart_Poettering_-_Systemd',
114 'title': '5_Lennart_Poettering_-_Systemd',
115 'upload_date': '20141120',
117 'expected_warnings': [
118 'URL could be a direct video link, returning it as such.'
123 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
125 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
126 'title': 'Zero Punctuation',
127 'description': 're:.*groundbreaking video review series.*'
129 'playlist_mincount': 11,
131 # RSS feed with enclosure
133 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
135 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
137 'upload_date': '20150228',
138 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
141 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
143 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
147 'title': 'Automatics, robotics and biocybernetics',
148 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
149 'upload_date': '20130627',
150 'formats': 'mincount:16',
151 'subtitles': 'mincount:1',
154 'force_generic_extractor': True,
155 'skip_download': True,
158 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
160 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
165 'formats': 'mincount:1',
168 'skip_download': True,
171 # SMIL from https://www.restudy.dk/video/play/id/1637
173 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
177 'title': 'video_1637',
178 'formats': 'mincount:3',
181 'skip_download': True,
184 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
186 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
188 'id': 'smil-service',
190 'title': 'smil-service',
191 'formats': 'mincount:1',
194 'skip_download': True,
197 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
199 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
203 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
204 'formats': 'mincount:3',
207 'skip_download': True,
210 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
212 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
214 'id': 'mZlp2ctYIUEB',
216 'title': 'Tikibad ontruimd wegens brand',
217 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
218 'thumbnail': 're:^https?://.*\.jpg$',
222 'skip_download': True,
227 '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',
231 'upload_date': '20130224',
232 'uploader_id': 'TheVerge',
233 'description': 're:^Chris Ziegler takes a look at the\.*',
234 'uploader': 'The Verge',
235 'title': 'First Firefox OS phones side-by-side',
238 'skip_download': False,
242 # redirect in Refresh HTTP header
243 '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',
247 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
248 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
249 'upload_date': '20150917',
250 'uploader_id': 'brtvofficial',
251 'uploader': 'Boiler Room',
254 'skip_download': False,
258 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
259 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
261 'id': '13601338388002',
263 'uploader': 'www.hodiho.fr',
264 'title': 'R\u00e9gis plante sa Jeep',
267 # bandcamp page with custom domain
269 'add_ie': ['Bandcamp'],
270 'url': 'http://bronyrock.com/track/the-pony-mash',
274 'title': 'The Pony Mash',
275 'uploader': 'M_Pallante',
277 'skip': 'There is a limit of 200 free downloads / month for the test song',
279 # embedded brightcove video
280 # it also tests brightcove videos that need to set the 'Referer' in the
283 'add_ie': ['BrightcoveLegacy'],
284 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
286 'id': '2765128793001',
288 'title': 'Le cours de bourse : l’analyse technique',
289 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
290 'uploader': 'BFM BUSINESS',
293 'skip_download': True,
297 # https://github.com/rg3/youtube-dl/issues/2253
298 'url': 'http://bcove.me/i6nfkrc3',
299 'md5': '0ba9446db037002366bab3b3eb30c88c',
301 'id': '3101154703001',
303 'title': 'Still no power',
304 'uploader': 'thestar.com',
305 '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.',
307 'add_ie': ['BrightcoveLegacy'],
310 'url': 'http://www.championat.com/video/football/v/87/87499.html',
311 'md5': 'fb973ecf6e4a78a67453647444222983',
313 'id': '3414141473001',
315 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
316 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
317 'uploader': 'Championat',
321 # https://github.com/rg3/youtube-dl/issues/3541
322 'add_ie': ['BrightcoveLegacy'],
323 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
325 'id': '3866516442001',
327 'title': 'Leer mij vrouwen kennen: Aflevering 1',
328 'description': 'Leer mij vrouwen kennen: Aflevering 1',
329 'uploader': 'SBS Broadcasting',
331 'skip': 'Restricted to Netherlands',
333 'skip_download': True, # m3u8 download
338 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
339 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
341 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
343 'title': '2cc213299525360.mov', # that's what we get
346 'add_ie': ['Ooyala'],
349 # ooyala video embedded with http://player.ooyala.com/iframe.js
350 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
352 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
354 'title': '"Steve Jobs: Man in the Machine" trailer',
355 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
359 'skip_download': True,
362 # multiple ooyala embeds on SBN network websites
364 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
366 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
367 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
369 'playlist_mincount': 3,
371 'skip_download': True,
373 'add_ie': ['Ooyala'],
377 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
381 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
382 'upload_date': '20140225',
383 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
384 'uploader': 'Tested',
385 'uploader_id': 'testedcom',
387 # No need to test YoutubeIE here
389 'skip_download': True,
394 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
398 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
399 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
404 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
408 'title': 'Охотское море стало целиком российским',
409 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
413 'skip_download': True,
418 '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/',
422 'title': 'Дошкольное воспитание',
427 'url': 'http://www.vestifinance.ru/articles/25753',
430 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
435 'title': 'Госзаказ. День 3',
441 'title': 'Госзаказ. День 2',
447 'title': 'Госзаказ. День 1',
453 'skip_download': True,
458 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
460 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
462 'title': 'Ужастики, русский трейлер (2015)',
463 'thumbnail': 're:^https?://.*\.jpg$',
469 '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',
472 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
474 'playlist_mincount': 7,
478 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
479 'md5': '65fdff94098e4a607385a60c5177c638',
483 'title': 'Hidden miracles of the natural world',
484 'uploader': 'Louie Schwartzberg',
485 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
488 # Embeded Ustream video
490 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
491 'md5': '27b99cdb639c9b12a79bca876a073417',
495 'uploader': 'AU SPA: The NSA and Privacy',
496 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
499 # nowvideo embed hidden behind percent encoding
501 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
502 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
504 'id': '06e53103ca9aa',
506 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
507 'description': 'No description',
512 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
513 'md5': '7653032cbb25bf6c80d80f217055fa43',
515 'id': '048195-004_PLUS7-F',
518 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
519 'upload_date': '20140320',
522 'skip_download': 'Requires rtmpdump'
527 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
531 'title': 'Alcaline, le concert avec Calogero',
532 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
533 'upload_date': '20150226',
534 'timestamp': 1424989860,
539 'skip_download': True,
541 'expected_warnings': [
547 'url': 'http://www.wired.com/2014/04/honda-asimo/',
548 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
550 'id': '53501be369702d3275860000',
552 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
557 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
558 'md5': '441aeeb82eb72c422c7f14ec533999cd',
560 'id': 'k2mm4bCdJ6CQ2i7c8o2',
562 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
565 'add_ie': ['Dailymotion'],
569 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
573 'title': 'The NBL Auction 2014',
574 'uploader': 'BADMINTON England',
575 'uploader_id': 'BADMINTONEvents',
576 'upload_date': '20140603',
577 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
579 'add_ie': ['Youtube'],
581 'skip_download': True,
586 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
587 'md5': '35727f82f58c76d996fc188f9755b0d5',
589 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
592 'description': 'Mario\'s life in the fast lane has never looked so good.',
595 # YouTube embed via <data-embed-url="">
597 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
601 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
602 'uploader': 'Gameloft',
603 'uploader_id': 'gameloft',
604 'upload_date': '20140828',
605 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
608 'skip_download': True,
613 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
615 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
617 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
618 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
623 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
625 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
626 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
632 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
637 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
638 'md5': '9d65602bf31c6e20014319c7d07fba27',
640 'id': '5123ea6d5e5a7',
643 'uploader': 'www.handjobhub.com',
644 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
647 # Multiple brightcove videos
648 # https://github.com/rg3/youtube-dl/issues/2283
650 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
652 'id': 'always-never',
653 'title': 'Always / Never - The New Yorker',
657 'extract_flat': False,
658 'skip_download': True,
663 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
664 'md5': '96f09a37e44da40dd083e12d9a683327',
668 'title': 'Ump changes call to ball',
669 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
671 'timestamp': 1401537900,
672 'upload_date': '20140531',
673 'thumbnail': 're:^https?://.*\.jpg$',
678 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
679 'md5': '8788b683c777a5cf25621eaf286d0c23',
683 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
685 'filesize': 182808282,
686 'uploader': 'education-portal.com',
690 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
691 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
695 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
697 'uploader': 'thoughtworks.wistia.com',
702 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
706 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
707 'uploader': 'Sophos Security',
708 'title': 'Chet Chat 171 - Oct 29, 2014',
709 'upload_date': '20141029',
714 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
718 'upload_date': '20141112',
719 'title': 'Rosetta #CometLanding webcast HL 10',
724 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
727 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
729 'playlist_mincount': 2,
733 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
737 'upload_date': '20141126',
738 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
743 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
745 'id': '730m_DandD_1901_512k',
747 'uploader': 'www.abc.net.au',
748 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
751 # embedded viddler video
753 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
757 'uploader': 'deadspin',
758 'title': 'WALL-TO-GORTAT',
759 'timestamp': 1422285291,
760 'upload_date': '20150126',
762 'add_ie': ['Viddler'],
766 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
770 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
771 'description': 'md5:601cb790edd05908957dae8aaa866465',
772 'upload_date': '20150220',
777 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
781 'upload_date': '20150212',
782 'uploader': 'The National Archives UK',
783 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
784 'uploader_id': 'NationalArchives08',
785 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
790 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
791 'playlist_mincount': 5,
793 'id': 'aanslagen-kopenhagen',
794 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
799 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
803 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
808 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
812 'upload_date': '20150226',
813 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
815 'title': 'John Carlson Postgame 2/25/15',
818 # Kaltura embed (different embed code)
820 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
824 'upload_date': '20150127',
825 'uploader_id': 'PremierMedia',
827 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
830 # Kaltura embed protected with referrer
832 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
836 'title': 'Violetta - Achter De Schermen - Ruggero',
837 'description': 'Achter de schermen met Ruggero',
838 'timestamp': 1435133761,
839 'upload_date': '20150624',
840 'uploader_id': 'echojecka',
843 # Eagle.Platform embed (generic URL)
845 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
849 'title': 'Навальный вышел на свободу',
850 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
851 'thumbnail': 're:^https?://.*\.jpg$',
857 # ClipYou (Eagle.Platform) embed (custom URL)
859 'url': 'http://muz-tv.ru/play/7129/',
863 'title': "'O Sole Mio",
864 'thumbnail': 're:^https?://.*\.jpg$',
871 'url': 'http://muz-tv.ru/kinozal/view/7400/',
875 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
876 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
877 'thumbnail': 're:^https?://.*\.jpg$',
884 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
888 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
889 'thumbnail': 're:^https?://.*\.png$',
895 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
896 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
900 'title': 'Facebook Creates "On This Day" | Crunch Report',
905 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
909 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
914 # Crooks and Liars embed
916 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
920 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
921 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
922 'timestamp': 1428207000,
923 'upload_date': '20150405',
924 'uploader': 'Heather',
927 # Crooks and Liars external embed
929 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
931 'id': 'MTE3MjUtMzQ2MzA',
933 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
934 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
935 'timestamp': 1265032391,
936 'upload_date': '20100201',
937 'uploader': 'Heather',
940 # NBC Sports vplayer embed
942 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
944 'id': 'ln7x1qSThw4k',
946 'title': "PFT Live: New leader in the 'new-look' defense",
947 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
952 'url': 'http://www.udn.com/news/story/7314/822787',
953 'md5': 'fd2060e988c326991037b9aff9df21a6',
957 'title': '中一中男師變性 全校師生力挺',
958 'thumbnail': 're:^https?://.*\.jpg$',
963 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
965 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
967 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
968 'title': 'This is what separates the Excel masters from the wannabes',
973 'skip_download': True,
976 # Contains a SMIL manifest
978 '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',
982 'title': '+ Football: Lottery Champions League Europe',
983 'uploader': 'www.telewebion.com',
987 'skip_download': True,
990 # Brightcove URL in single quotes
992 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
993 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
995 'id': '4255764656001',
997 'title': 'SN Presents: Russell Martin, World Citizen',
998 '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.',
999 'uploader': 'Rogers Sportsnet',
1002 # Dailymotion Cloud video
1004 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1005 'md5': '49444254273501a64675a7e68c502681',
1007 'id': '5585de919473990de4bee11b',
1009 'title': 'Le débat',
1010 'thumbnail': 're:^https?://.*\.jpe?g$',
1013 # OnionStudios embed
1015 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1019 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1020 'thumbnail': 're:^https?://.*\.jpe?g$',
1021 'uploader': 'ClickHole',
1022 'uploader_id': 'clickhole',
1027 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1029 'id': '74849a00-85a9-11e1-9660-123139220831',
1031 'title': '#whilewewatch',
1034 # AdobeTVVideo embed
1036 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1037 'md5': '43662b577c018ad707a63766462b1e87',
1041 'title': 'New experience with Acrobat DC',
1042 'description': 'New experience with Acrobat DC',
1043 'duration': 248.667,
1046 # ScreenwaveMedia embed
1048 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1049 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1051 'id': 'cinemasnob-55d26273809dd',
1053 'title': 'cinemasnob',
1056 # BrightcoveInPageEmbed embed
1058 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1060 'id': '4238694884001',
1062 'title': 'Tabletop: Dread, Last Thoughts',
1063 'description': 'Tabletop: Dread, Last Thoughts',
1067 # JWPlayer with M3U8
1069 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1073 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1074 'uploader': 'ren.tv',
1078 'skip_download': True,
1083 def report_following_redirect(self, new_url):
1084 """Report information extraction."""
1085 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1087 def _extract_rss(self, url, video_id, doc):
1088 playlist_title = doc.find('./channel/title').text
1089 playlist_desc_el = doc.find('./channel/description')
1090 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1093 for it in doc.findall('./channel/item'):
1094 next_url = xpath_text(it, 'link', fatal=False)
1096 enclosure_nodes = it.findall('./enclosure')
1097 for e in enclosure_nodes:
1098 next_url = e.attrib.get('url')
1108 'title': it.find('title').text,
1112 '_type': 'playlist',
1114 'title': playlist_title,
1115 'description': playlist_desc,
1119 def _extract_camtasia(self, url, video_id, webpage):
1120 """ Returns None if no camtasia video can be found. """
1122 camtasia_cfg = self._search_regex(
1123 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1124 webpage, 'camtasia configuration file', default=None)
1125 if camtasia_cfg is None:
1128 title = self._html_search_meta('DC.title', webpage, fatal=True)
1130 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1131 camtasia_cfg = self._download_xml(
1132 camtasia_url, video_id,
1133 note='Downloading camtasia configuration',
1134 errnote='Failed to download camtasia configuration')
1135 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1138 for n in fileset_node.getchildren():
1139 url_n = n.find('./uri')
1144 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1145 'title': '%s - %s' % (title, n.tag),
1146 'url': compat_urlparse.urljoin(url, url_n.text),
1147 'duration': float_or_none(n.find('./duration').text),
1151 '_type': 'playlist',
1156 def _real_extract(self, url):
1157 if url.startswith('//'):
1160 'url': self.http_scheme() + url,
1163 parsed_url = compat_urlparse.urlparse(url)
1164 if not parsed_url.scheme:
1165 default_search = self._downloader.params.get('default_search')
1166 if default_search is None:
1167 default_search = 'fixup_error'
1169 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1171 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1172 return self.url_result('http://' + url)
1173 elif default_search != 'fixup_error':
1174 if default_search == 'auto_warning':
1175 if re.match(r'^(?:url|URL)$', url):
1176 raise ExtractorError(
1177 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1180 self._downloader.report_warning(
1181 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1182 return self.url_result('ytsearch:' + url)
1184 if default_search in ('error', 'fixup_error'):
1185 raise ExtractorError(
1186 '%r is not a valid URL. '
1187 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1188 % (url, url), expected=True)
1190 if ':' not in default_search:
1191 default_search += ':'
1192 return self.url_result(default_search + url)
1194 url, smuggled_data = unsmuggle_url(url)
1195 force_videoid = None
1196 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1197 if smuggled_data and 'force_videoid' in smuggled_data:
1198 force_videoid = smuggled_data['force_videoid']
1199 video_id = force_videoid
1201 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1203 self.to_screen('%s: Requesting header' % video_id)
1205 head_req = HEADRequest(url)
1206 head_response = self._request_webpage(
1208 note=False, errnote='Could not send HEAD request to %s' % url,
1211 if head_response is not False:
1212 # Check for redirect
1213 new_url = head_response.geturl()
1215 self.report_following_redirect(new_url)
1217 new_url = smuggle_url(
1218 new_url, {'force_videoid': force_videoid})
1219 return self.url_result(new_url)
1221 full_response = None
1222 if head_response is False:
1223 request = sanitized_Request(url)
1224 request.add_header('Accept-Encoding', '*')
1225 full_response = self._request_webpage(request, video_id)
1226 head_response = full_response
1228 # Check for direct link to a video
1229 content_type = head_response.headers.get('Content-Type', '')
1230 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1232 upload_date = unified_strdate(
1233 head_response.headers.get('Last-Modified'))
1236 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1239 'format_id': m.group('format_id'),
1241 'vcodec': 'none' if m.group('type') == 'audio' else None
1243 'upload_date': upload_date,
1246 if not self._downloader.params.get('test', False) and not is_intentional:
1247 force = self._downloader.params.get('force_generic_extractor', False)
1248 self._downloader.report_warning(
1249 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1251 if not full_response:
1252 request = sanitized_Request(url)
1253 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1254 # making it impossible to download only chunk of the file (yet we need only 512kB to
1255 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1256 # that will always result in downloading the whole file that is not desirable.
1257 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1258 # to accept raw bytes and being able to download only a chunk.
1259 # It may probably better to solve this by checking Content-Type for application/octet-stream
1260 # after HEAD request finishes, but not sure if we can rely on this.
1261 request.add_header('Accept-Encoding', '*')
1262 full_response = self._request_webpage(request, video_id)
1264 # Maybe it's a direct link to a video?
1265 # Be careful not to download the whole thing!
1266 first_bytes = full_response.read(512)
1267 if not is_html(first_bytes):
1268 self._downloader.report_warning(
1269 'URL could be a direct video link, returning it as such.')
1270 upload_date = unified_strdate(
1271 head_response.headers.get('Last-Modified'))
1274 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1277 'upload_date': upload_date,
1280 webpage = self._webpage_read_content(
1281 full_response, url, video_id, prefix=first_bytes)
1283 self.report_extraction(video_id)
1285 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1287 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1288 if doc.tag == 'rss':
1289 return self._extract_rss(url, video_id, doc)
1290 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1291 return self._parse_smil(doc, url, video_id)
1292 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1293 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1294 except compat_xml_parse_error:
1297 # Is it a Camtasia project?
1298 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1299 if camtasia_res is not None:
1302 # Sometimes embedded video player is hidden behind percent encoding
1303 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1304 # Unescaping the whole page allows to handle those cases in a generic way
1305 webpage = compat_urllib_parse_unquote(webpage)
1307 # it's tempting to parse this further, but you would
1308 # have to take into account all the variations like
1309 # Video Title - Site Name
1310 # Site Name | Video Title
1311 # Video Title - Tagline | Site Name
1312 # and so on and so forth; it's just not practical
1313 video_title = self._html_search_regex(
1314 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1317 # Try to detect age limit automatically
1318 age_limit = self._rta_search(webpage)
1319 # And then there are the jokers who advertise that they use RTA,
1320 # but actually don't.
1321 AGE_LIMIT_MARKERS = [
1322 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1324 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1327 # video uploader is domain name
1328 video_uploader = self._search_regex(
1329 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1332 def _playlist_from_matches(matches, getter=None, ie=None):
1334 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1336 return self.playlist_result(
1337 urlrs, playlist_id=video_id, playlist_title=video_title)
1339 # Look for Brightcove Legacy Studio embeds
1340 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1342 self.to_screen('Brightcove video detected.')
1345 'url': smuggle_url(bc_url, {'Referer': url}),
1346 'ie_key': 'BrightcoveLegacy'
1347 } for bc_url in bc_urls]
1350 '_type': 'playlist',
1351 'title': video_title,
1356 # Look for Brightcove New Studio embeds
1357 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1359 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1361 # Look for embedded rtl.nl player
1362 matches = re.findall(
1363 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1366 return _playlist_from_matches(matches, ie='RtlNl')
1368 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1369 if vimeo_url is not None:
1370 return self.url_result(vimeo_url)
1372 vid_me_embed_url = self._search_regex(
1373 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1374 webpage, 'vid.me embed', default=None)
1375 if vid_me_embed_url is not None:
1376 return self.url_result(vid_me_embed_url, 'Vidme')
1378 # Look for embedded YouTube player
1379 matches = re.findall(r'''(?x)
1388 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1392 return _playlist_from_matches(
1393 matches, lambda m: unescapeHTML(m[1]))
1395 # Look for lazyYT YouTube embed
1396 matches = re.findall(
1397 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1399 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1401 # Look for embedded Dailymotion player
1402 matches = re.findall(
1403 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1405 return _playlist_from_matches(
1406 matches, lambda m: unescapeHTML(m[1]))
1408 # Look for embedded Dailymotion playlist player (#3822)
1410 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1412 playlists = re.findall(
1413 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1415 return _playlist_from_matches(
1416 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1418 # Look for embedded Wistia player
1420 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1422 embed_url = self._proto_relative_url(
1423 unescapeHTML(match.group('url')))
1425 '_type': 'url_transparent',
1428 'uploader': video_uploader,
1429 'title': video_title,
1433 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1436 '_type': 'url_transparent',
1437 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1439 'uploader': video_uploader,
1440 'title': video_title,
1441 'id': match.group('id')
1444 # Look for embedded blip.tv player
1445 bliptv_url = BlipTVIE._extract_url(webpage)
1447 return self.url_result(bliptv_url, 'BlipTV')
1449 # Look for SVT player
1450 svt_url = SVTIE._extract_url(webpage)
1452 return self.url_result(svt_url, 'SVT')
1454 # Look for embedded condenast player
1455 matches = re.findall(
1456 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1460 '_type': 'playlist',
1463 'ie_key': 'CondeNast',
1465 } for ma in matches],
1466 'title': video_title,
1470 # Look for Bandcamp pages with custom domain
1471 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1472 if mobj is not None:
1473 burl = unescapeHTML(mobj.group(1))
1474 # Don't set the extractor because it can be a track url or an album
1475 return self.url_result(burl)
1477 # Look for embedded Vevo player
1479 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1480 if mobj is not None:
1481 return self.url_result(mobj.group('url'))
1483 # Look for embedded Viddler player
1485 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1487 if mobj is not None:
1488 return self.url_result(mobj.group('url'))
1490 # Look for NYTimes player
1492 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1494 if mobj is not None:
1495 return self.url_result(mobj.group('url'))
1497 # Look for Libsyn player
1499 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1500 if mobj is not None:
1501 return self.url_result(mobj.group('url'))
1503 # Look for Ooyala videos
1504 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1505 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1506 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1507 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1508 if mobj is not None:
1509 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1511 # Look for multiple Ooyala embeds on SBN network websites
1512 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1513 if mobj is not None:
1514 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1516 return _playlist_from_matches(
1517 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1519 # Look for Aparat videos
1520 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1521 if mobj is not None:
1522 return self.url_result(mobj.group(1), 'Aparat')
1524 # Look for MPORA videos
1525 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1526 if mobj is not None:
1527 return self.url_result(mobj.group(1), 'Mpora')
1529 # Look for embedded NovaMov-based player
1531 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1532 (?P<url>http://(?:(?:embed|www)\.)?
1534 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1535 videoweed\.(?:es|com)|
1536 movshare\.(?:net|sx|ag)|
1537 divxstage\.(?:eu|net|ch|co|at|ag))
1538 /embed\.php.+?)\1''', webpage)
1539 if mobj is not None:
1540 return self.url_result(mobj.group('url'))
1542 # Look for embedded Facebook player
1544 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1545 if mobj is not None:
1546 return self.url_result(mobj.group('url'), 'Facebook')
1548 # Look for embedded VK player
1549 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1550 if mobj is not None:
1551 return self.url_result(mobj.group('url'), 'VK')
1553 # Look for embedded ivi player
1554 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1555 if mobj is not None:
1556 return self.url_result(mobj.group('url'), 'Ivi')
1558 # Look for embedded Huffington Post player
1560 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1561 if mobj is not None:
1562 return self.url_result(mobj.group('url'), 'HuffPost')
1565 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1566 if mobj is not None:
1567 return self.url_result(mobj.group('url'))
1568 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1569 if mobj is not None:
1570 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1572 # Look for funnyordie embed
1573 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1575 return _playlist_from_matches(
1576 matches, getter=unescapeHTML, ie='FunnyOrDie')
1578 # Look for BBC iPlayer embed
1579 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1581 return _playlist_from_matches(matches, ie='BBCCoUk')
1583 # Look for embedded RUTV player
1584 rutv_url = RUTVIE._extract_url(webpage)
1586 return self.url_result(rutv_url, 'RUTV')
1588 # Look for embedded TVC player
1589 tvc_url = TVCIE._extract_url(webpage)
1591 return self.url_result(tvc_url, 'TVC')
1593 # Look for embedded SportBox player
1594 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1596 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1598 # Look for embedded PornHub player
1599 pornhub_url = PornHubIE._extract_url(webpage)
1601 return self.url_result(pornhub_url, 'PornHub')
1603 # Look for embedded XHamster player
1604 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1606 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1608 # Look for embedded Tvigle player
1610 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1611 if mobj is not None:
1612 return self.url_result(mobj.group('url'), 'Tvigle')
1614 # Look for embedded TED player
1616 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1617 if mobj is not None:
1618 return self.url_result(mobj.group('url'), 'TED')
1620 # Look for embedded Ustream videos
1622 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1623 if mobj is not None:
1624 return self.url_result(mobj.group('url'), 'Ustream')
1626 # Look for embedded arte.tv player
1628 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1630 if mobj is not None:
1631 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1633 # Look for embedded francetv player
1635 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1637 if mobj is not None:
1638 return self.url_result(mobj.group('url'))
1640 # Look for embedded smotri.com player
1641 smotri_url = SmotriIE._extract_url(webpage)
1643 return self.url_result(smotri_url, 'Smotri')
1645 # Look for embedded Myvi.ru player
1646 myvi_url = MyviIE._extract_url(webpage)
1648 return self.url_result(myvi_url)
1650 # Look for embeded soundcloud player
1652 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1654 if mobj is not None:
1655 url = unescapeHTML(mobj.group('url'))
1656 return self.url_result(url)
1658 # Look for embedded vulture.com player
1660 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1662 if mobj is not None:
1663 url = unescapeHTML(mobj.group('url'))
1664 return self.url_result(url, ie='Vulture')
1666 # Look for embedded mtvservices player
1667 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1669 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1671 # Look for embedded yahoo player
1673 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1675 if mobj is not None:
1676 return self.url_result(mobj.group('url'), 'Yahoo')
1678 # Look for embedded sbs.com.au player
1682 <meta\s+property="og:video"\s+content=|
1685 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1687 if mobj is not None:
1688 return self.url_result(mobj.group('url'), 'SBS')
1690 # Look for embedded Cinchcast player
1692 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1694 if mobj is not None:
1695 return self.url_result(mobj.group('url'), 'Cinchcast')
1698 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1702 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1704 if mobj is not None:
1705 return self.url_result(mobj.group('url'), 'MLB')
1708 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1710 if mobj is not None:
1711 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1714 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1716 if mobj is not None:
1717 return self.url_result(mobj.group('url'), 'Livestream')
1719 # Look for Zapiks embed
1721 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1722 if mobj is not None:
1723 return self.url_result(mobj.group('url'), 'Zapiks')
1725 # Look for Kaltura embeds
1726 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1727 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))
1728 if mobj is not None:
1729 return self.url_result(smuggle_url(
1730 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1731 {'source_url': url}), 'Kaltura')
1733 # Look for Eagle.Platform embeds
1735 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1736 if mobj is not None:
1737 return self.url_result(mobj.group('url'), 'EaglePlatform')
1739 # Look for ClipYou (uses Eagle.Platform) embeds
1741 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1742 if mobj is not None:
1743 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1745 # Look for Pladform embeds
1746 pladform_url = PladformIE._extract_url(webpage)
1748 return self.url_result(pladform_url)
1750 # Look for Playwire embeds
1752 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1753 if mobj is not None:
1754 return self.url_result(mobj.group('url'))
1756 # Look for 5min embeds
1758 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1759 if mobj is not None:
1760 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1762 # Look for Crooks and Liars embeds
1764 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1765 if mobj is not None:
1766 return self.url_result(mobj.group('url'))
1768 # Look for NBC Sports VPlayer embeds
1769 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1771 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1773 # Look for Google Drive embeds
1774 google_drive_url = GoogleDriveIE._extract_url(webpage)
1775 if google_drive_url:
1776 return self.url_result(google_drive_url, 'GoogleDrive')
1778 # Look for UDN embeds
1780 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1781 if mobj is not None:
1782 return self.url_result(
1783 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1785 # Look for Senate ISVP iframe
1786 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1788 return self.url_result(senate_isvp_url, 'SenateISVP')
1790 # Look for Dailymotion Cloud videos
1791 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1793 return self.url_result(dmcloud_url, 'DailymotionCloud')
1795 # Look for OnionStudios embeds
1796 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1797 if onionstudios_url:
1798 return self.url_result(onionstudios_url)
1800 # Look for SnagFilms embeds
1801 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1803 return self.url_result(snagfilms_url)
1805 # Look for ScreenwaveMedia embeds
1806 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1807 if mobj is not None:
1808 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1810 # Look for AdobeTVVideo embeds
1812 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1814 if mobj is not None:
1815 return self.url_result(
1816 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1819 def check_video(vurl):
1820 if YoutubeIE.suitable(vurl):
1822 vpath = compat_urlparse.urlparse(vurl).path
1823 vext = determine_ext(vpath)
1824 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1826 def filter_video(urls):
1827 return list(filter(check_video, urls))
1829 # Start with something easy: JW Player in SWFObject
1830 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1832 # Look for gorilla-vid style embedding
1833 found = filter_video(re.findall(r'''(?sx)
1837 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1840 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1842 # Broaden the search a little bit
1843 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1845 # Broaden the findall a little bit: JWPlayer JS loader
1846 found = filter_video(re.findall(
1847 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1850 found = filter_video(re.findall(r'''(?xs)
1851 flowplayer\("[^"]+",\s*
1853 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1854 ["']?url["']?\s*:\s*["']([^"']+)["']
1859 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1861 # Try to find twitter cards info
1862 found = filter_video(re.findall(
1863 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1865 # We look for Open Graph info:
1866 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1867 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1868 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1869 if m_video_type is not None:
1870 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1873 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1875 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1877 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1878 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1881 # Look also in Refresh HTTP header
1882 refresh_header = head_response.headers.get('Refresh')
1884 # In python 2 response HTTP headers are bytestrings
1885 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1886 refresh_header = refresh_header.decode('iso-8859-1')
1887 found = re.search(REDIRECT_REGEX, refresh_header)
1889 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1890 self.report_following_redirect(new_url)
1896 raise UnsupportedError(url)
1899 for video_url in found:
1900 video_url = video_url.replace('\\/', '/')
1901 video_url = compat_urlparse.urljoin(url, video_url)
1902 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1904 # Sometimes, jwplayer extraction will result in a YouTube URL
1905 if YoutubeIE.suitable(video_url):
1906 entries.append(self.url_result(video_url, 'Youtube'))
1909 # here's a fun little line of code for you:
1910 video_id = os.path.splitext(video_id)[0]
1914 'uploader': video_uploader,
1915 'title': video_title,
1916 'age_limit': age_limit,
1919 ext = determine_ext(video_url)
1921 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
1923 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1925 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
1927 entry_info_dict['url'] = video_url
1929 entries.append(entry_info_dict)
1931 if len(entries) == 1:
1934 for num, e in enumerate(entries, start=1):
1935 # 'url' results don't have a title
1936 if e.get('title') is not None:
1937 e['title'] = '%s (%d)' % (e['title'], num)
1939 '_type': 'playlist',