3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
15 compat_xml_parse_error,
33 from .brightcove import (
37 from .nbc import NBCSportsVPlayerIE
38 from .ooyala import OoyalaIE
39 from .rutv import RUTVIE
40 from .tvc import TVCIE
41 from .sportbox import SportBoxEmbedIE
42 from .smotri import SmotriIE
43 from .myvi import MyviIE
44 from .condenast import CondeNastIE
45 from .udn import UDNEmbedIE
46 from .senateisvp import SenateISVPIE
47 from .svt import SVTIE
48 from .pornhub import PornHubIE
49 from .xhamster import XHamsterEmbedIE
50 from .tnaflix import TNAFlixNetworkEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import DailymotionCloudIE
53 from .onionstudios import OnionStudiosIE
54 from .viewlift import ViewLiftEmbedIE
55 from .screenwavemedia import ScreenwaveMediaIE
56 from .mtv import MTVServicesEmbeddedIE
57 from .pladform import PladformIE
58 from .videomore import VideomoreIE
59 from .googledrive import GoogleDriveIE
60 from .jwplatform import JWPlatformIE
61 from .digiteka import DigitekaIE
62 from .instagram import InstagramIE
63 from .liveleak import LiveLeakIE
64 from .threeqsdn import ThreeQSDNIE
67 class GenericIE(InfoExtractor):
68 IE_DESC = 'Generic downloader that works on some sites'
72 # Direct link to a video
74 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
75 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
80 'upload_date': '20100513',
83 # Direct link to media delivered compressed (until Accept-Encoding is *)
85 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
86 'md5': '128c42e68b13950268b648275386fc74',
88 'id': 'FictionJunction-Parallel_Hearts',
90 'title': 'FictionJunction-Parallel_Hearts',
91 'upload_date': '20140522',
93 'expected_warnings': [
94 'URL could be a direct video link, returning it as such.'
97 # Direct download with broken HEAD
99 'url': 'http://ai-radio.org:8000/radio.opus',
106 'skip_download': True, # infinite live stream
108 'expected_warnings': [
109 r'501.*Not Implemented',
113 # Direct link with incorrect MIME type
115 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
116 'md5': '4ccbebe5f36706d85221f204d7eb5913',
118 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
119 'id': '5_Lennart_Poettering_-_Systemd',
121 'title': '5_Lennart_Poettering_-_Systemd',
122 'upload_date': '20141120',
124 'expected_warnings': [
125 'URL could be a direct video link, returning it as such.'
130 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
132 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
133 'title': 'Zero Punctuation',
134 'description': 're:.*groundbreaking video review series.*'
136 'playlist_mincount': 11,
138 # RSS feed with enclosure
140 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
142 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
144 'upload_date': '20150228',
145 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
148 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
150 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
154 'title': 'Automatics, robotics and biocybernetics',
155 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
156 'upload_date': '20130627',
157 'formats': 'mincount:16',
158 'subtitles': 'mincount:1',
161 'force_generic_extractor': True,
162 'skip_download': True,
165 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
167 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
172 'formats': 'mincount:1',
175 'skip_download': True,
178 # SMIL from https://www.restudy.dk/video/play/id/1637
180 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
184 'title': 'video_1637',
185 'formats': 'mincount:3',
188 'skip_download': True,
191 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
193 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
195 'id': 'smil-service',
197 'title': 'smil-service',
198 'formats': 'mincount:1',
201 'skip_download': True,
204 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
206 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
210 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
211 'formats': 'mincount:3',
214 'skip_download': True,
217 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
219 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
221 'id': 'mZlp2ctYIUEB',
223 'title': 'Tikibad ontruimd wegens brand',
224 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
225 'thumbnail': 're:^https?://.*\.jpg$',
229 'skip_download': True,
232 # MPD from http://dash-mse-test.appspot.com/media.html
234 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
235 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
237 'id': 'car-20120827-manifest',
239 'title': 'car-20120827-manifest',
240 'formats': 'mincount:9',
241 'upload_date': '20130904',
244 'format': 'bestvideo',
247 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
249 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
254 'formats': 'mincount:8',
258 'skip_download': True,
261 # m3u8 served with Content-Type: text/plain
263 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
268 'upload_date': '20140720',
269 'formats': 'mincount:11',
273 'skip_download': True,
278 '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',
282 'upload_date': '20130224',
283 'uploader_id': 'TheVerge',
284 'description': 're:^Chris Ziegler takes a look at the\.*',
285 'uploader': 'The Verge',
286 'title': 'First Firefox OS phones side-by-side',
289 'skip_download': False,
293 # redirect in Refresh HTTP header
294 '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',
298 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
299 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
300 'upload_date': '20150917',
301 'uploader_id': 'brtvofficial',
302 'uploader': 'Boiler Room',
305 'skip_download': False,
309 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
310 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
312 'id': '13601338388002',
314 'uploader': 'www.hodiho.fr',
315 'title': 'R\u00e9gis plante sa Jeep',
318 # bandcamp page with custom domain
320 'add_ie': ['Bandcamp'],
321 'url': 'http://bronyrock.com/track/the-pony-mash',
325 'title': 'The Pony Mash',
326 'uploader': 'M_Pallante',
328 'skip': 'There is a limit of 200 free downloads / month for the test song',
330 # embedded brightcove video
331 # it also tests brightcove videos that need to set the 'Referer' in the
334 'add_ie': ['BrightcoveLegacy'],
335 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
337 'id': '2765128793001',
339 'title': 'Le cours de bourse : l’analyse technique',
340 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
341 'uploader': 'BFM BUSINESS',
344 'skip_download': True,
348 # https://github.com/rg3/youtube-dl/issues/2253
349 'url': 'http://bcove.me/i6nfkrc3',
350 'md5': '0ba9446db037002366bab3b3eb30c88c',
352 'id': '3101154703001',
354 'title': 'Still no power',
355 'uploader': 'thestar.com',
356 '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.',
358 'add_ie': ['BrightcoveLegacy'],
361 'url': 'http://www.championat.com/video/football/v/87/87499.html',
362 'md5': 'fb973ecf6e4a78a67453647444222983',
364 'id': '3414141473001',
366 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
367 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
368 'uploader': 'Championat',
372 # https://github.com/rg3/youtube-dl/issues/3541
373 'add_ie': ['BrightcoveLegacy'],
374 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
376 'id': '3866516442001',
378 'title': 'Leer mij vrouwen kennen: Aflevering 1',
379 'description': 'Leer mij vrouwen kennen: Aflevering 1',
380 'uploader': 'SBS Broadcasting',
382 'skip': 'Restricted to Netherlands',
384 'skip_download': True, # m3u8 download
389 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
390 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
392 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
394 'title': '2cc213299525360.mov', # that's what we get
397 'add_ie': ['Ooyala'],
400 # ooyala video embedded with http://player.ooyala.com/iframe.js
401 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
403 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
405 'title': '"Steve Jobs: Man in the Machine" trailer',
406 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
410 'skip_download': True,
415 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
419 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
420 'upload_date': '20140225',
421 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
422 'uploader': 'Tested',
423 'uploader_id': 'testedcom',
425 # No need to test YoutubeIE here
427 'skip_download': True,
432 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
436 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
437 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
442 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
446 'title': 'Охотское море стало целиком российским',
447 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
451 'skip_download': True,
456 '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/',
460 'title': 'Дошкольное воспитание',
465 'url': 'http://www.vestifinance.ru/articles/25753',
468 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
473 'title': 'Госзаказ. День 3',
479 'title': 'Госзаказ. День 2',
485 'title': 'Госзаказ. День 1',
491 'skip_download': True,
496 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
498 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
500 'title': 'Ужастики, русский трейлер (2015)',
501 'thumbnail': 're:^https?://.*\.jpg$',
507 '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',
510 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
512 'playlist_mincount': 7,
516 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
517 'md5': '65fdff94098e4a607385a60c5177c638',
521 'title': 'Hidden miracles of the natural world',
522 'uploader': 'Louie Schwartzberg',
523 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
526 # Embedded Ustream video
528 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
529 'md5': '27b99cdb639c9b12a79bca876a073417',
533 'uploader': 'AU SPA: The NSA and Privacy',
534 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
537 # nowvideo embed hidden behind percent encoding
539 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
540 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
542 'id': '06e53103ca9aa',
544 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
545 'description': 'No description',
550 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
551 'md5': '7653032cbb25bf6c80d80f217055fa43',
553 'id': '048195-004_PLUS7-F',
556 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
557 'upload_date': '20140320',
560 'skip_download': 'Requires rtmpdump'
565 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
569 'title': 'Alcaline, le concert avec Calogero',
570 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
571 'upload_date': '20150226',
572 'timestamp': 1424989860,
577 'skip_download': True,
579 'expected_warnings': [
585 'url': 'http://www.wired.com/2014/04/honda-asimo/',
586 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
588 'id': '53501be369702d3275860000',
590 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
595 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
596 'md5': '441aeeb82eb72c422c7f14ec533999cd',
598 'id': 'k2mm4bCdJ6CQ2i7c8o2',
600 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
601 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
603 'uploader_id': 'xgditw',
604 'upload_date': '20140425',
605 'timestamp': 1398441542,
607 'add_ie': ['Dailymotion'],
611 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
615 'title': 'The NBL Auction 2014',
616 'uploader': 'BADMINTON England',
617 'uploader_id': 'BADMINTONEvents',
618 'upload_date': '20140603',
619 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
621 'add_ie': ['Youtube'],
623 'skip_download': True,
628 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
629 'md5': '35727f82f58c76d996fc188f9755b0d5',
631 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
634 'description': 'Mario\'s life in the fast lane has never looked so good.',
637 # YouTube embed via <data-embed-url="">
639 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
643 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
644 'uploader': 'Gameloft',
645 'uploader_id': 'gameloft',
646 'upload_date': '20140828',
647 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
650 'skip_download': True,
655 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
657 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
659 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
660 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
665 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
667 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
668 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
674 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
679 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
680 'md5': '9d65602bf31c6e20014319c7d07fba27',
682 'id': '5123ea6d5e5a7',
685 'uploader': 'www.handjobhub.com',
686 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
689 # Multiple brightcove videos
690 # https://github.com/rg3/youtube-dl/issues/2283
692 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
694 'id': 'always-never',
695 'title': 'Always / Never - The New Yorker',
699 'extract_flat': False,
700 'skip_download': True,
705 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
706 'md5': '96f09a37e44da40dd083e12d9a683327',
710 'title': 'Ump changes call to ball',
711 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
713 'timestamp': 1401537900,
714 'upload_date': '20140531',
715 'thumbnail': 're:^https?://.*\.jpg$',
720 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
721 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
725 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
726 'description': 'a Paywall Videos video from Remilon',
728 'uploader': 'study.com',
729 'timestamp': 1459678540,
730 'upload_date': '20160403',
731 'filesize': 24687186,
735 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
736 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
740 'title': 'Conversation about Hexagonal Rails Part 1',
741 'description': 'a Martin Fowler video from ThoughtWorks',
743 'uploader': 'thoughtworks.wistia.com',
744 'timestamp': 1401832161,
745 'upload_date': '20140603',
748 # Wistia standard embed (async)
750 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
754 'title': 'Drip Brennan Dunn Workshop',
755 'description': 'a JV Webinars video from getdrip-1',
757 'timestamp': 1463607249,
758 'upload_date': '20160518',
761 'skip_download': True,
766 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
770 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
771 'uploader': 'Sophos Security',
772 'title': 'Chet Chat 171 - Oct 29, 2014',
773 'upload_date': '20141029',
778 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
782 'upload_date': '20141112',
783 'title': 'Rosetta #CometLanding webcast HL 10',
788 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
791 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
793 'playlist_mincount': 2,
797 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
801 'upload_date': '20141126',
802 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
807 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
809 'id': '730m_DandD_1901_512k',
811 'uploader': 'www.abc.net.au',
812 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
815 # embedded viddler video
817 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
821 'uploader': 'deadspin',
822 'title': 'WALL-TO-GORTAT',
823 'timestamp': 1422285291,
824 'upload_date': '20150126',
826 'add_ie': ['Viddler'],
830 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
834 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
835 'description': 'md5:601cb790edd05908957dae8aaa866465',
836 'upload_date': '20150220',
841 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
845 'upload_date': '20150212',
846 'uploader': 'The National Archives UK',
847 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
848 'uploader_id': 'NationalArchives08',
849 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
854 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
855 'playlist_mincount': 5,
857 'id': 'aanslagen-kopenhagen',
858 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
863 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
867 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
872 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
876 'upload_date': '20150226',
877 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
879 'title': 'John Carlson Postgame 2/25/15',
882 # Kaltura embed (different embed code)
884 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
888 'upload_date': '20150127',
889 'uploader_id': 'PremierMedia',
891 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
894 # Kaltura embed protected with referrer
896 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
900 'title': 'Violetta - Achter De Schermen - Ruggero',
901 'description': 'Achter de schermen met Ruggero',
902 'timestamp': 1435133761,
903 'upload_date': '20150624',
904 'uploader_id': 'echojecka',
907 # Eagle.Platform embed (generic URL)
909 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
910 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
914 'title': 'Навальный вышел на свободу',
915 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
916 'thumbnail': 're:^https?://.*\.jpg$',
922 # ClipYou (Eagle.Platform) embed (custom URL)
924 'url': 'http://muz-tv.ru/play/7129/',
925 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
929 'title': "'O Sole Mio",
930 'thumbnail': 're:^https?://.*\.jpg$',
937 'url': 'http://muz-tv.ru/kinozal/view/7400/',
941 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
942 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
943 'thumbnail': 're:^https?://.*\.jpg$',
950 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
954 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
955 'thumbnail': 're:^https?://.*\.png$',
961 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
962 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
966 'title': 'Facebook Creates "On This Day" | Crunch Report',
971 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
975 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
980 # Crooks and Liars embed
982 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
986 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
987 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
988 'timestamp': 1428207000,
989 'upload_date': '20150405',
990 'uploader': 'Heather',
993 # Crooks and Liars external embed
995 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
997 'id': 'MTE3MjUtMzQ2MzA',
999 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1000 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1001 'timestamp': 1265032391,
1002 'upload_date': '20100201',
1003 'uploader': 'Heather',
1006 # NBC Sports vplayer embed
1008 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1010 'id': 'ln7x1qSThw4k',
1012 'title': "PFT Live: New leader in the 'new-look' defense",
1013 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1014 'uploader': 'NBCU-SPORTS',
1015 'upload_date': '20140107',
1016 'timestamp': 1389118457,
1021 'url': 'http://www.udn.com/news/story/7314/822787',
1022 'md5': 'fd2060e988c326991037b9aff9df21a6',
1026 'title': '中一中男師變性 全校師生力挺',
1027 'thumbnail': 're:^https?://.*\.jpg$',
1032 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1034 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1036 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1037 'title': 'This is what separates the Excel masters from the wannabes',
1038 'duration': 191.933,
1042 'skip_download': True,
1045 # Contains a SMIL manifest
1047 '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',
1051 'title': '+ Football: Lottery Champions League Europe',
1052 'uploader': 'www.telewebion.com',
1056 'skip_download': True,
1059 # Brightcove URL in single quotes
1061 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1062 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1064 'id': '4255764656001',
1066 'title': 'SN Presents: Russell Martin, World Citizen',
1067 '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.',
1068 'uploader': 'Rogers Sportsnet',
1069 'uploader_id': '1704050871',
1070 'upload_date': '20150525',
1071 'timestamp': 1432570283,
1074 # Dailymotion Cloud video
1076 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1077 'md5': '49444254273501a64675a7e68c502681',
1079 'id': '5585de919473990de4bee11b',
1081 'title': 'Le débat',
1082 'thumbnail': 're:^https?://.*\.jpe?g$',
1085 # OnionStudios embed
1087 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1091 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1092 'thumbnail': 're:^https?://.*\.jpe?g$',
1093 'uploader': 'ClickHole',
1094 'uploader_id': 'clickhole',
1099 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1101 'id': '74849a00-85a9-11e1-9660-123139220831',
1103 'title': '#whilewewatch',
1106 # AdobeTVVideo embed
1108 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1109 'md5': '43662b577c018ad707a63766462b1e87',
1113 'title': 'New experience with Acrobat DC',
1114 'description': 'New experience with Acrobat DC',
1115 'duration': 248.667,
1118 # ScreenwaveMedia embed
1120 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1121 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1123 'id': 'cinemasnob-55d26273809dd',
1125 'title': 'cinemasnob',
1128 # BrightcoveInPageEmbed embed
1130 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1132 'id': '4238694884001',
1134 'title': 'Tabletop: Dread, Last Thoughts',
1135 'description': 'Tabletop: Dread, Last Thoughts',
1139 # JWPlayer with M3U8
1141 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1145 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1146 'uploader': 'ren.tv',
1150 'skip_download': True,
1153 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1154 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1156 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1158 'id': '4785848093001',
1160 'title': 'The Cardinal Pell Interview',
1161 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1162 'uploader': 'GlobeCast Australia - GlobeStream',
1163 'uploader_id': '2733773828001',
1164 'upload_date': '20160304',
1165 'timestamp': 1457083087,
1169 'skip_download': True,
1172 # Another form of arte.tv embed
1174 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1175 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1177 'id': '030273-562_PLUS7-F',
1179 'title': 'ARTE Reportage - Nulle part, en France',
1180 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1181 'upload_date': '20160409',
1186 'url': 'http://www.wykop.pl/link/3088787/',
1187 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1189 'id': '874_1459135191',
1191 'title': 'Man shows poor quality of new apartment building',
1192 'description': 'The wall is like a sand pile.',
1193 'uploader': 'Lake8737',
1198 def report_following_redirect(self, new_url):
1199 """Report information extraction."""
1200 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1202 def _extract_rss(self, url, video_id, doc):
1203 playlist_title = doc.find('./channel/title').text
1204 playlist_desc_el = doc.find('./channel/description')
1205 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1208 for it in doc.findall('./channel/item'):
1209 next_url = xpath_text(it, 'link', fatal=False)
1211 enclosure_nodes = it.findall('./enclosure')
1212 for e in enclosure_nodes:
1213 next_url = e.attrib.get('url')
1223 'title': it.find('title').text,
1227 '_type': 'playlist',
1229 'title': playlist_title,
1230 'description': playlist_desc,
1234 def _extract_camtasia(self, url, video_id, webpage):
1235 """ Returns None if no camtasia video can be found. """
1237 camtasia_cfg = self._search_regex(
1238 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1239 webpage, 'camtasia configuration file', default=None)
1240 if camtasia_cfg is None:
1243 title = self._html_search_meta('DC.title', webpage, fatal=True)
1245 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1246 camtasia_cfg = self._download_xml(
1247 camtasia_url, video_id,
1248 note='Downloading camtasia configuration',
1249 errnote='Failed to download camtasia configuration')
1250 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1253 for n in fileset_node.getchildren():
1254 url_n = n.find('./uri')
1259 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1260 'title': '%s - %s' % (title, n.tag),
1261 'url': compat_urlparse.urljoin(url, url_n.text),
1262 'duration': float_or_none(n.find('./duration').text),
1266 '_type': 'playlist',
1271 def _real_extract(self, url):
1272 if url.startswith('//'):
1275 'url': self.http_scheme() + url,
1278 parsed_url = compat_urlparse.urlparse(url)
1279 if not parsed_url.scheme:
1280 default_search = self._downloader.params.get('default_search')
1281 if default_search is None:
1282 default_search = 'fixup_error'
1284 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1286 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1287 return self.url_result('http://' + url)
1288 elif default_search != 'fixup_error':
1289 if default_search == 'auto_warning':
1290 if re.match(r'^(?:url|URL)$', url):
1291 raise ExtractorError(
1292 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1295 self._downloader.report_warning(
1296 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1297 return self.url_result('ytsearch:' + url)
1299 if default_search in ('error', 'fixup_error'):
1300 raise ExtractorError(
1301 '%r is not a valid URL. '
1302 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1303 % (url, url), expected=True)
1305 if ':' not in default_search:
1306 default_search += ':'
1307 return self.url_result(default_search + url)
1309 url, smuggled_data = unsmuggle_url(url)
1310 force_videoid = None
1311 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1312 if smuggled_data and 'force_videoid' in smuggled_data:
1313 force_videoid = smuggled_data['force_videoid']
1314 video_id = force_videoid
1316 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1318 self.to_screen('%s: Requesting header' % video_id)
1320 head_req = HEADRequest(url)
1321 head_response = self._request_webpage(
1323 note=False, errnote='Could not send HEAD request to %s' % url,
1326 if head_response is not False:
1327 # Check for redirect
1328 new_url = head_response.geturl()
1330 self.report_following_redirect(new_url)
1332 new_url = smuggle_url(
1333 new_url, {'force_videoid': force_videoid})
1334 return self.url_result(new_url)
1336 full_response = None
1337 if head_response is False:
1338 request = sanitized_Request(url)
1339 request.add_header('Accept-Encoding', '*')
1340 full_response = self._request_webpage(request, video_id)
1341 head_response = full_response
1345 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1346 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1349 # Check for direct link to a video
1350 content_type = head_response.headers.get('Content-Type', '').lower()
1351 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1353 format_id = m.group('format_id')
1354 if format_id.endswith('mpegurl'):
1355 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1356 elif format_id == 'f4m':
1357 formats = self._extract_f4m_formats(url, video_id)
1360 'format_id': m.group('format_id'),
1362 'vcodec': 'none' if m.group('type') == 'audio' else None
1364 info_dict['direct'] = True
1365 self._sort_formats(formats)
1366 info_dict['formats'] = formats
1369 if not self._downloader.params.get('test', False) and not is_intentional:
1370 force = self._downloader.params.get('force_generic_extractor', False)
1371 self._downloader.report_warning(
1372 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1374 if not full_response:
1375 request = sanitized_Request(url)
1376 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1377 # making it impossible to download only chunk of the file (yet we need only 512kB to
1378 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1379 # that will always result in downloading the whole file that is not desirable.
1380 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1381 # to accept raw bytes and being able to download only a chunk.
1382 # It may probably better to solve this by checking Content-Type for application/octet-stream
1383 # after HEAD request finishes, but not sure if we can rely on this.
1384 request.add_header('Accept-Encoding', '*')
1385 full_response = self._request_webpage(request, video_id)
1387 first_bytes = full_response.read(512)
1389 # Is it an M3U playlist?
1390 if first_bytes.startswith(b'#EXTM3U'):
1391 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1392 self._sort_formats(info_dict['formats'])
1395 # Maybe it's a direct link to a video?
1396 # Be careful not to download the whole thing!
1397 if not is_html(first_bytes):
1398 self._downloader.report_warning(
1399 'URL could be a direct video link, returning it as such.')
1406 webpage = self._webpage_read_content(
1407 full_response, url, video_id, prefix=first_bytes)
1409 self.report_extraction(video_id)
1411 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1413 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1414 if doc.tag == 'rss':
1415 return self._extract_rss(url, video_id, doc)
1416 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1417 smil = self._parse_smil(doc, url, video_id)
1418 self._sort_formats(smil['formats'])
1420 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1421 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1422 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1423 info_dict['formats'] = self._parse_mpd_formats(
1424 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1425 self._sort_formats(info_dict['formats'])
1427 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1428 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1429 self._sort_formats(info_dict['formats'])
1431 except compat_xml_parse_error:
1434 # Is it a Camtasia project?
1435 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1436 if camtasia_res is not None:
1439 # Sometimes embedded video player is hidden behind percent encoding
1440 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1441 # Unescaping the whole page allows to handle those cases in a generic way
1442 webpage = compat_urllib_parse_unquote(webpage)
1444 # it's tempting to parse this further, but you would
1445 # have to take into account all the variations like
1446 # Video Title - Site Name
1447 # Site Name | Video Title
1448 # Video Title - Tagline | Site Name
1449 # and so on and so forth; it's just not practical
1450 video_title = self._og_search_title(
1451 webpage, default=None) or self._html_search_regex(
1452 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1455 # Try to detect age limit automatically
1456 age_limit = self._rta_search(webpage)
1457 # And then there are the jokers who advertise that they use RTA,
1458 # but actually don't.
1459 AGE_LIMIT_MARKERS = [
1460 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1462 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1465 # video uploader is domain name
1466 video_uploader = self._search_regex(
1467 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1469 video_description = self._og_search_description(webpage, default=None)
1470 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1473 def _playlist_from_matches(matches, getter=None, ie=None):
1475 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1477 return self.playlist_result(
1478 urlrs, playlist_id=video_id, playlist_title=video_title)
1480 # Look for Brightcove Legacy Studio embeds
1481 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1483 self.to_screen('Brightcove video detected.')
1486 'url': smuggle_url(bc_url, {'Referer': url}),
1487 'ie_key': 'BrightcoveLegacy'
1488 } for bc_url in bc_urls]
1491 '_type': 'playlist',
1492 'title': video_title,
1497 # Look for Brightcove New Studio embeds
1498 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1500 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1502 # Look for embedded rtl.nl player
1503 matches = re.findall(
1504 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1507 return _playlist_from_matches(matches, ie='RtlNl')
1509 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1510 if vimeo_url is not None:
1511 return self.url_result(vimeo_url)
1513 vid_me_embed_url = self._search_regex(
1514 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1515 webpage, 'vid.me embed', default=None)
1516 if vid_me_embed_url is not None:
1517 return self.url_result(vid_me_embed_url, 'Vidme')
1519 # Look for embedded YouTube player
1520 matches = re.findall(r'''(?x)
1529 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1533 return _playlist_from_matches(
1534 matches, lambda m: unescapeHTML(m[1]))
1536 # Look for lazyYT YouTube embed
1537 matches = re.findall(
1538 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1540 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1542 # Look for embedded Dailymotion player
1543 matches = re.findall(
1544 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1546 return _playlist_from_matches(
1547 matches, lambda m: unescapeHTML(m[1]))
1549 # Look for embedded Dailymotion playlist player (#3822)
1551 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1553 playlists = re.findall(
1554 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1556 return _playlist_from_matches(
1557 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1559 # Look for embedded Wistia player
1561 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1563 embed_url = self._proto_relative_url(
1564 unescapeHTML(match.group('url')))
1566 '_type': 'url_transparent',
1569 'uploader': video_uploader,
1572 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1575 '_type': 'url_transparent',
1576 'url': 'wistia:%s' % match.group('id'),
1578 'uploader': video_uploader,
1583 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1584 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1587 return self.url_result(self._proto_relative_url(
1588 'wistia:%s' % match.group('id')), 'Wistia')
1590 # Look for SVT player
1591 svt_url = SVTIE._extract_url(webpage)
1593 return self.url_result(svt_url, 'SVT')
1595 # Look for embedded condenast player
1596 matches = re.findall(
1597 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1601 '_type': 'playlist',
1604 'ie_key': 'CondeNast',
1606 } for ma in matches],
1607 'title': video_title,
1611 # Look for Bandcamp pages with custom domain
1612 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1613 if mobj is not None:
1614 burl = unescapeHTML(mobj.group(1))
1615 # Don't set the extractor because it can be a track url or an album
1616 return self.url_result(burl)
1618 # Look for embedded Vevo player
1620 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1621 if mobj is not None:
1622 return self.url_result(mobj.group('url'))
1624 # Look for embedded Viddler player
1626 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1628 if mobj is not None:
1629 return self.url_result(mobj.group('url'))
1631 # Look for NYTimes player
1633 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1635 if mobj is not None:
1636 return self.url_result(mobj.group('url'))
1638 # Look for Libsyn player
1640 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1641 if mobj is not None:
1642 return self.url_result(mobj.group('url'))
1644 # Look for Ooyala videos
1645 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1646 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1647 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1648 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1649 if mobj is not None:
1650 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1652 # Look for multiple Ooyala embeds on SBN network websites
1653 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1654 if mobj is not None:
1655 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1657 return _playlist_from_matches(
1658 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1660 # Look for Aparat videos
1661 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1662 if mobj is not None:
1663 return self.url_result(mobj.group(1), 'Aparat')
1665 # Look for MPORA videos
1666 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1667 if mobj is not None:
1668 return self.url_result(mobj.group(1), 'Mpora')
1670 # Look for embedded NovaMov-based player
1672 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1673 (?P<url>http://(?:(?:embed|www)\.)?
1675 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1676 videoweed\.(?:es|com)|
1677 movshare\.(?:net|sx|ag)|
1678 divxstage\.(?:eu|net|ch|co|at|ag))
1679 /embed\.php.+?)\1''', webpage)
1680 if mobj is not None:
1681 return self.url_result(mobj.group('url'))
1683 # Look for embedded Facebook player
1685 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1686 if mobj is not None:
1687 return self.url_result(mobj.group('url'), 'Facebook')
1689 # Look for embedded VK player
1690 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1691 if mobj is not None:
1692 return self.url_result(mobj.group('url'), 'VK')
1694 # Look for embedded Odnoklassniki player
1695 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1696 if mobj is not None:
1697 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1699 # Look for embedded ivi player
1700 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1701 if mobj is not None:
1702 return self.url_result(mobj.group('url'), 'Ivi')
1704 # Look for embedded Huffington Post player
1706 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1707 if mobj is not None:
1708 return self.url_result(mobj.group('url'), 'HuffPost')
1711 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1712 if mobj is not None:
1713 return self.url_result(mobj.group('url'))
1714 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1715 if mobj is not None:
1716 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1718 # Look for funnyordie embed
1719 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1721 return _playlist_from_matches(
1722 matches, getter=unescapeHTML, ie='FunnyOrDie')
1724 # Look for BBC iPlayer embed
1725 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1727 return _playlist_from_matches(matches, ie='BBCCoUk')
1729 # Look for embedded RUTV player
1730 rutv_url = RUTVIE._extract_url(webpage)
1732 return self.url_result(rutv_url, 'RUTV')
1734 # Look for embedded TVC player
1735 tvc_url = TVCIE._extract_url(webpage)
1737 return self.url_result(tvc_url, 'TVC')
1739 # Look for embedded SportBox player
1740 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1742 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1744 # Look for embedded PornHub player
1745 pornhub_url = PornHubIE._extract_url(webpage)
1747 return self.url_result(pornhub_url, 'PornHub')
1749 # Look for embedded XHamster player
1750 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1752 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1754 # Look for embedded TNAFlixNetwork player
1755 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1757 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1759 # Look for embedded Tvigle player
1761 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1762 if mobj is not None:
1763 return self.url_result(mobj.group('url'), 'Tvigle')
1765 # Look for embedded TED player
1767 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1768 if mobj is not None:
1769 return self.url_result(mobj.group('url'), 'TED')
1771 # Look for embedded Ustream videos
1773 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1774 if mobj is not None:
1775 return self.url_result(mobj.group('url'), 'Ustream')
1777 # Look for embedded arte.tv player
1779 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1781 if mobj is not None:
1782 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1784 # Look for embedded francetv player
1786 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1788 if mobj is not None:
1789 return self.url_result(mobj.group('url'))
1791 # Look for embedded smotri.com player
1792 smotri_url = SmotriIE._extract_url(webpage)
1794 return self.url_result(smotri_url, 'Smotri')
1796 # Look for embedded Myvi.ru player
1797 myvi_url = MyviIE._extract_url(webpage)
1799 return self.url_result(myvi_url)
1801 # Look for embedded soundcloud player
1803 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1805 if mobj is not None:
1806 url = unescapeHTML(mobj.group('url'))
1807 return self.url_result(url)
1809 # Look for embedded vulture.com player
1811 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1813 if mobj is not None:
1814 url = unescapeHTML(mobj.group('url'))
1815 return self.url_result(url, ie='Vulture')
1817 # Look for embedded mtvservices player
1818 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1820 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1822 # Look for embedded yahoo player
1824 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1826 if mobj is not None:
1827 return self.url_result(mobj.group('url'), 'Yahoo')
1829 # Look for embedded sbs.com.au player
1833 <meta\s+property="og:video"\s+content=|
1836 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1838 if mobj is not None:
1839 return self.url_result(mobj.group('url'), 'SBS')
1841 # Look for embedded Cinchcast player
1843 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1845 if mobj is not None:
1846 return self.url_result(mobj.group('url'), 'Cinchcast')
1849 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1853 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1855 if mobj is not None:
1856 return self.url_result(mobj.group('url'), 'MLB')
1859 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1861 if mobj is not None:
1862 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1865 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1867 if mobj is not None:
1868 return self.url_result(mobj.group('url'), 'Livestream')
1870 # Look for Zapiks embed
1872 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1873 if mobj is not None:
1874 return self.url_result(mobj.group('url'), 'Zapiks')
1876 # Look for Kaltura embeds
1877 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1878 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))
1879 if mobj is not None:
1880 return self.url_result(smuggle_url(
1881 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1882 {'source_url': url}), 'Kaltura')
1884 # Look for Eagle.Platform embeds
1886 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1887 if mobj is not None:
1888 return self.url_result(mobj.group('url'), 'EaglePlatform')
1890 # Look for ClipYou (uses Eagle.Platform) embeds
1892 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1893 if mobj is not None:
1894 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1896 # Look for Pladform embeds
1897 pladform_url = PladformIE._extract_url(webpage)
1899 return self.url_result(pladform_url)
1901 # Look for Videomore embeds
1902 videomore_url = VideomoreIE._extract_url(webpage)
1904 return self.url_result(videomore_url)
1906 # Look for Playwire embeds
1908 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1909 if mobj is not None:
1910 return self.url_result(mobj.group('url'))
1912 # Look for 5min embeds
1914 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1915 if mobj is not None:
1916 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1918 # Look for Crooks and Liars embeds
1920 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1921 if mobj is not None:
1922 return self.url_result(mobj.group('url'))
1924 # Look for NBC Sports VPlayer embeds
1925 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1927 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1929 # Look for Google Drive embeds
1930 google_drive_url = GoogleDriveIE._extract_url(webpage)
1931 if google_drive_url:
1932 return self.url_result(google_drive_url, 'GoogleDrive')
1934 # Look for UDN embeds
1936 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1937 if mobj is not None:
1938 return self.url_result(
1939 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1941 # Look for Senate ISVP iframe
1942 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1944 return self.url_result(senate_isvp_url, 'SenateISVP')
1946 # Look for Dailymotion Cloud videos
1947 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1949 return self.url_result(dmcloud_url, 'DailymotionCloud')
1951 # Look for OnionStudios embeds
1952 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1953 if onionstudios_url:
1954 return self.url_result(onionstudios_url)
1956 # Look for ViewLift embeds
1957 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
1959 return self.url_result(viewlift_url)
1961 # Look for JWPlatform embeds
1962 jwplatform_url = JWPlatformIE._extract_url(webpage)
1964 return self.url_result(jwplatform_url, 'JWPlatform')
1966 # Look for ScreenwaveMedia embeds
1967 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1968 if mobj is not None:
1969 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1971 # Look for Digiteka embeds
1972 digiteka_url = DigitekaIE._extract_url(webpage)
1974 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1976 # Look for Limelight embeds
1977 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1981 'Channel': 'channel',
1982 'ChannelList': 'channel_list',
1984 return self.url_result('limelight:%s:%s' % (
1985 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1987 # Look for AdobeTVVideo embeds
1989 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1991 if mobj is not None:
1992 return self.url_result(
1993 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1996 # Look for Vine embeds
1998 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2000 if mobj is not None:
2001 return self.url_result(
2002 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2004 # Look for Instagram embeds
2005 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2006 if instagram_embed_url is not None:
2007 return self.url_result(
2008 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2010 # Look for LiveLeak embeds
2011 liveleak_url = LiveLeakIE._extract_url(webpage)
2013 return self.url_result(liveleak_url, 'LiveLeak')
2015 # Look for 3Q SDN embeds
2016 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2019 '_type': 'url_transparent',
2020 'ie_key': ThreeQSDNIE.ie_key(),
2021 'url': self._proto_relative_url(threeqsdn_url),
2022 'title': video_title,
2023 'description': video_description,
2024 'thumbnail': video_thumbnail,
2025 'uploader': video_uploader,
2028 def check_video(vurl):
2029 if YoutubeIE.suitable(vurl):
2031 vpath = compat_urlparse.urlparse(vurl).path
2032 vext = determine_ext(vpath)
2033 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2035 def filter_video(urls):
2036 return list(filter(check_video, urls))
2038 # Start with something easy: JW Player in SWFObject
2039 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2041 # Look for gorilla-vid style embedding
2042 found = filter_video(re.findall(r'''(?sx)
2046 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2049 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2051 # Broaden the search a little bit
2052 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2054 # Broaden the findall a little bit: JWPlayer JS loader
2055 found = filter_video(re.findall(
2056 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2059 found = filter_video(re.findall(r'''(?xs)
2060 flowplayer\("[^"]+",\s*
2062 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2063 ["']?url["']?\s*:\s*["']([^"']+)["']
2068 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2070 # Try to find twitter cards info
2071 found = filter_video(re.findall(
2072 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2074 # We look for Open Graph info:
2075 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2076 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2077 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2078 if m_video_type is not None:
2079 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2082 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2084 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2086 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2087 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2090 # Look also in Refresh HTTP header
2091 refresh_header = head_response.headers.get('Refresh')
2093 # In python 2 response HTTP headers are bytestrings
2094 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2095 refresh_header = refresh_header.decode('iso-8859-1')
2096 found = re.search(REDIRECT_REGEX, refresh_header)
2098 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2099 self.report_following_redirect(new_url)
2105 raise UnsupportedError(url)
2108 for video_url in found:
2109 video_url = unescapeHTML(video_url)
2110 video_url = video_url.replace('\\/', '/')
2111 video_url = compat_urlparse.urljoin(url, video_url)
2112 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2114 # Sometimes, jwplayer extraction will result in a YouTube URL
2115 if YoutubeIE.suitable(video_url):
2116 entries.append(self.url_result(video_url, 'Youtube'))
2119 # here's a fun little line of code for you:
2120 video_id = os.path.splitext(video_id)[0]
2124 'uploader': video_uploader,
2125 'title': video_title,
2126 'age_limit': age_limit,
2129 ext = determine_ext(video_url)
2131 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2133 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2135 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2137 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2139 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2141 entry_info_dict['url'] = video_url
2143 if entry_info_dict.get('formats'):
2144 self._sort_formats(entry_info_dict['formats'])
2146 entries.append(entry_info_dict)
2148 if len(entries) == 1:
2151 for num, e in enumerate(entries, start=1):
2152 # 'url' results don't have a title
2153 if e.get('title') is not None:
2154 e['title'] = '%s (%d)' % (e['title'], num)
2156 '_type': 'playlist',