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 (
56 from .onionstudios import OnionStudiosIE
57 from .viewlift import ViewLiftEmbedIE
58 from .screenwavemedia import ScreenwaveMediaIE
59 from .mtv import MTVServicesEmbeddedIE
60 from .pladform import PladformIE
61 from .videomore import VideomoreIE
62 from .googledrive import GoogleDriveIE
63 from .jwplatform import JWPlatformIE
64 from .digiteka import DigitekaIE
65 from .arkena import ArkenaIE
66 from .instagram import InstagramIE
67 from .liveleak import LiveLeakIE
68 from .threeqsdn import ThreeQSDNIE
69 from .theplatform import ThePlatformIE
70 from .vessel import VesselIE
71 from .kaltura import KalturaIE
72 from .eagleplatform import EaglePlatformIE
73 from .facebook import FacebookIE
76 class GenericIE(InfoExtractor):
77 IE_DESC = 'Generic downloader that works on some sites'
81 # Direct link to a video
83 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
84 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
89 'upload_date': '20100513',
92 # Direct link to media delivered compressed (until Accept-Encoding is *)
94 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
95 'md5': '128c42e68b13950268b648275386fc74',
97 'id': 'FictionJunction-Parallel_Hearts',
99 'title': 'FictionJunction-Parallel_Hearts',
100 'upload_date': '20140522',
102 'expected_warnings': [
103 'URL could be a direct video link, returning it as such.'
106 # Direct download with broken HEAD
108 'url': 'http://ai-radio.org:8000/radio.opus',
115 'skip_download': True, # infinite live stream
117 'expected_warnings': [
118 r'501.*Not Implemented',
122 # Direct link with incorrect MIME type
124 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
125 'md5': '4ccbebe5f36706d85221f204d7eb5913',
127 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
128 'id': '5_Lennart_Poettering_-_Systemd',
130 'title': '5_Lennart_Poettering_-_Systemd',
131 'upload_date': '20141120',
133 'expected_warnings': [
134 'URL could be a direct video link, returning it as such.'
139 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
141 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
142 'title': 'Zero Punctuation',
143 'description': 're:.*groundbreaking video review series.*'
145 'playlist_mincount': 11,
147 # RSS feed with enclosure
149 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
151 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
153 'upload_date': '20150228',
154 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
157 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
159 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
163 'title': 'Automatics, robotics and biocybernetics',
164 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
165 'upload_date': '20130627',
166 'formats': 'mincount:16',
167 'subtitles': 'mincount:1',
170 'force_generic_extractor': True,
171 'skip_download': True,
174 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
176 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
181 'formats': 'mincount:1',
184 'skip_download': True,
187 # SMIL from https://www.restudy.dk/video/play/id/1637
189 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
193 'title': 'video_1637',
194 'formats': 'mincount:3',
197 'skip_download': True,
200 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
202 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
204 'id': 'smil-service',
206 'title': 'smil-service',
207 'formats': 'mincount:1',
210 'skip_download': True,
213 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
215 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
219 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
220 'formats': 'mincount:3',
223 'skip_download': True,
226 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
228 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
230 'id': 'mZlp2ctYIUEB',
232 'title': 'Tikibad ontruimd wegens brand',
233 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
234 'thumbnail': 're:^https?://.*\.jpg$',
238 'skip_download': True,
241 # MPD from http://dash-mse-test.appspot.com/media.html
243 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
244 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
246 'id': 'car-20120827-manifest',
248 'title': 'car-20120827-manifest',
249 'formats': 'mincount:9',
250 'upload_date': '20130904',
253 'format': 'bestvideo',
256 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
258 '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',
263 'formats': 'mincount:8',
267 'skip_download': True,
270 # m3u8 served with Content-Type: text/plain
272 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
277 'upload_date': '20140720',
278 'formats': 'mincount:11',
282 'skip_download': True,
287 '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',
291 'upload_date': '20130224',
292 'uploader_id': 'TheVerge',
293 'description': 're:^Chris Ziegler takes a look at the\.*',
294 'uploader': 'The Verge',
295 'title': 'First Firefox OS phones side-by-side',
298 'skip_download': False,
302 # redirect in Refresh HTTP header
303 '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',
307 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
308 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
309 'upload_date': '20150917',
310 'uploader_id': 'brtvofficial',
311 'uploader': 'Boiler Room',
314 'skip_download': False,
318 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
319 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
321 'id': '13601338388002',
323 'uploader': 'www.hodiho.fr',
324 'title': 'R\u00e9gis plante sa Jeep',
327 # bandcamp page with custom domain
329 'add_ie': ['Bandcamp'],
330 'url': 'http://bronyrock.com/track/the-pony-mash',
334 'title': 'The Pony Mash',
335 'uploader': 'M_Pallante',
337 'skip': 'There is a limit of 200 free downloads / month for the test song',
339 # embedded brightcove video
340 # it also tests brightcove videos that need to set the 'Referer' in the
343 'add_ie': ['BrightcoveLegacy'],
344 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
346 'id': '2765128793001',
348 'title': 'Le cours de bourse : l’analyse technique',
349 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
350 'uploader': 'BFM BUSINESS',
353 'skip_download': True,
357 # https://github.com/rg3/youtube-dl/issues/2253
358 'url': 'http://bcove.me/i6nfkrc3',
359 'md5': '0ba9446db037002366bab3b3eb30c88c',
361 'id': '3101154703001',
363 'title': 'Still no power',
364 'uploader': 'thestar.com',
365 '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.',
367 'add_ie': ['BrightcoveLegacy'],
370 'url': 'http://www.championat.com/video/football/v/87/87499.html',
371 'md5': 'fb973ecf6e4a78a67453647444222983',
373 'id': '3414141473001',
375 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
376 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
377 'uploader': 'Championat',
381 # https://github.com/rg3/youtube-dl/issues/3541
382 'add_ie': ['BrightcoveLegacy'],
383 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
385 'id': '3866516442001',
387 'title': 'Leer mij vrouwen kennen: Aflevering 1',
388 'description': 'Leer mij vrouwen kennen: Aflevering 1',
389 'uploader': 'SBS Broadcasting',
391 'skip': 'Restricted to Netherlands',
393 'skip_download': True, # m3u8 download
398 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
399 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
401 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
403 'title': '2cc213299525360.mov', # that's what we get
406 'add_ie': ['Ooyala'],
409 # ooyala video embedded with http://player.ooyala.com/iframe.js
410 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
412 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
414 'title': '"Steve Jobs: Man in the Machine" trailer',
415 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
419 'skip_download': True,
424 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
428 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
429 'upload_date': '20140225',
430 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
431 'uploader': 'Tested',
432 'uploader_id': 'testedcom',
434 # No need to test YoutubeIE here
436 'skip_download': True,
441 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
445 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
446 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
451 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
455 'title': 'Охотское море стало целиком российским',
456 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
460 'skip_download': True,
465 '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/',
469 'title': 'Дошкольное воспитание',
474 'url': 'http://www.vestifinance.ru/articles/25753',
477 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
482 'title': 'Госзаказ. День 3',
488 'title': 'Госзаказ. День 2',
494 'title': 'Госзаказ. День 1',
500 'skip_download': True,
505 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
507 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
509 'title': 'Ужастики, русский трейлер (2015)',
510 'thumbnail': 're:^https?://.*\.jpg$',
516 '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',
519 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
521 'playlist_mincount': 7,
525 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
526 'md5': '65fdff94098e4a607385a60c5177c638',
530 'title': 'Hidden miracles of the natural world',
531 'uploader': 'Louie Schwartzberg',
532 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
535 # Embedded Ustream video
537 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
538 'md5': '27b99cdb639c9b12a79bca876a073417',
542 'uploader': 'AU SPA: The NSA and Privacy',
543 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
546 # nowvideo embed hidden behind percent encoding
548 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
549 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
551 'id': '06e53103ca9aa',
553 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
554 'description': 'No description',
559 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
560 'md5': '7653032cbb25bf6c80d80f217055fa43',
562 'id': '048195-004_PLUS7-F',
565 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
566 'upload_date': '20140320',
569 'skip_download': 'Requires rtmpdump'
574 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
578 'title': 'Alcaline, le concert avec Calogero',
579 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
580 'upload_date': '20150226',
581 'timestamp': 1424989860,
586 'skip_download': True,
588 'expected_warnings': [
594 'url': 'http://www.wired.com/2014/04/honda-asimo/',
595 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
597 'id': '53501be369702d3275860000',
599 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
604 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
605 'md5': '441aeeb82eb72c422c7f14ec533999cd',
607 'id': 'k2mm4bCdJ6CQ2i7c8o2',
609 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
610 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
612 'uploader_id': 'xgditw',
613 'upload_date': '20140425',
614 'timestamp': 1398441542,
616 'add_ie': ['Dailymotion'],
620 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
624 'title': 'The NBL Auction 2014',
625 'uploader': 'BADMINTON England',
626 'uploader_id': 'BADMINTONEvents',
627 'upload_date': '20140603',
628 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
630 'add_ie': ['Youtube'],
632 'skip_download': True,
637 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
638 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
640 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
642 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
643 'description': 'Two valets share their love for movie star Liam Neesons.',
646 # YouTube embed via <data-embed-url="">
648 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
652 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
653 'uploader': 'Gameloft',
654 'uploader_id': 'gameloft',
655 'upload_date': '20140828',
656 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
659 'skip_download': True,
664 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
666 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
668 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
669 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
674 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
676 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
677 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
683 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
688 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
689 'md5': '9d65602bf31c6e20014319c7d07fba27',
691 'id': '5123ea6d5e5a7',
694 'uploader': 'www.handjobhub.com',
695 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
698 # Multiple brightcove videos
699 # https://github.com/rg3/youtube-dl/issues/2283
701 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
703 'id': 'always-never',
704 'title': 'Always / Never - The New Yorker',
708 'extract_flat': False,
709 'skip_download': True,
714 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
715 'md5': '96f09a37e44da40dd083e12d9a683327',
719 'title': 'Ump changes call to ball',
720 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
722 'timestamp': 1401537900,
723 'upload_date': '20140531',
724 'thumbnail': 're:^https?://.*\.jpg$',
729 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
730 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
734 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
735 'description': 'a Paywall Videos video from Remilon',
737 'uploader': 'study.com',
738 'timestamp': 1459678540,
739 'upload_date': '20160403',
740 'filesize': 24687186,
744 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
745 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
749 'title': 'Conversation about Hexagonal Rails Part 1',
750 'description': 'a Martin Fowler video from ThoughtWorks',
752 'uploader': 'thoughtworks.wistia.com',
753 'timestamp': 1401832161,
754 'upload_date': '20140603',
757 # Wistia standard embed (async)
759 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
763 'title': 'Drip Brennan Dunn Workshop',
764 'description': 'a JV Webinars video from getdrip-1',
766 'timestamp': 1463607249,
767 'upload_date': '20160518',
770 'skip_download': True,
775 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
779 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
780 'uploader': 'Sophos Security',
781 'title': 'Chet Chat 171 - Oct 29, 2014',
782 'upload_date': '20141029',
787 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
791 'upload_date': '20141112',
792 'title': 'Rosetta #CometLanding webcast HL 10',
795 # Another Livestream embed, without 'new.' in URL
797 'url': 'https://www.freespeech.org/',
801 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
805 'skip_download': True,
810 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
813 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
815 'playlist_mincount': 2,
819 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
823 'upload_date': '20141126',
824 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
829 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
831 'id': '730m_DandD_1901_512k',
833 'uploader': 'www.abc.net.au',
834 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
837 # embedded viddler video
839 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
843 'uploader': 'deadspin',
844 'title': 'WALL-TO-GORTAT',
845 'timestamp': 1422285291,
846 'upload_date': '20150126',
848 'add_ie': ['Viddler'],
852 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
856 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
857 'description': 'md5:601cb790edd05908957dae8aaa866465',
858 'upload_date': '20150220',
863 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
867 'upload_date': '20150212',
868 'uploader': 'The National Archives UK',
869 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
870 'uploader_id': 'NationalArchives08',
871 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
876 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
877 'playlist_mincount': 5,
879 'id': 'aanslagen-kopenhagen',
880 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
885 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
889 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
892 # Kaltura embed (different embed code)
894 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
898 'upload_date': '20150127',
899 'uploader_id': 'PremierMedia',
901 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
904 # Kaltura embed protected with referrer
906 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
910 'title': 'Violetta - Achter De Schermen - Ruggero',
911 'description': 'Achter de schermen met Ruggero',
912 'timestamp': 1435133761,
913 'upload_date': '20150624',
914 'uploader_id': 'echojecka',
917 # Kaltura embed with single quotes
919 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
924 'timestamp': 1355743100,
925 'upload_date': '20121217',
926 'uploader_id': 'batchUser',
928 'add_ie': ['Kaltura'],
931 # Kaltura embedded via quoted entry_id
932 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
936 'title': '06_matthew_brender_raj_dutt',
937 'timestamp': 1466638791,
938 'upload_date': '20160622',
940 'add_ie': ['Kaltura'],
941 'expected_warnings': [
942 'Could not send HEAD request'
945 'skip_download': True,
948 # Eagle.Platform embed (generic URL)
950 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
951 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
955 'title': 'Навальный вышел на свободу',
956 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
957 'thumbnail': 're:^https?://.*\.jpg$',
963 # ClipYou (Eagle.Platform) embed (custom URL)
965 'url': 'http://muz-tv.ru/play/7129/',
966 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
970 'title': "'O Sole Mio",
971 'thumbnail': 're:^https?://.*\.jpg$',
978 'url': 'http://muz-tv.ru/kinozal/view/7400/',
982 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
983 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
984 'thumbnail': 're:^https?://.*\.jpg$',
991 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
995 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
996 'thumbnail': 're:^https?://.*\.png$',
1002 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1003 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1007 'title': 'Facebook Creates "On This Day" | Crunch Report',
1012 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1016 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1021 # Crooks and Liars embed
1023 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1027 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1028 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1029 'timestamp': 1428207000,
1030 'upload_date': '20150405',
1031 'uploader': 'Heather',
1034 # Crooks and Liars external embed
1036 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1038 'id': 'MTE3MjUtMzQ2MzA',
1040 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1041 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1042 'timestamp': 1265032391,
1043 'upload_date': '20100201',
1044 'uploader': 'Heather',
1047 # NBC Sports vplayer embed
1049 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1051 'id': 'ln7x1qSThw4k',
1053 'title': "PFT Live: New leader in the 'new-look' defense",
1054 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1055 'uploader': 'NBCU-SPORTS',
1056 'upload_date': '20140107',
1057 'timestamp': 1389118457,
1062 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1063 'md5': '1aa589c675898ae6d37a17913cf68d66',
1065 'id': '701714499682',
1067 'title': 'PREVIEW: On Assignment: David Letterman',
1068 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1073 'url': 'https://video.udn.com/news/300346',
1074 'md5': 'fd2060e988c326991037b9aff9df21a6',
1078 'title': '中一中男師變性 全校師生力挺',
1079 'thumbnail': 're:^https?://.*\.jpg$',
1083 'skip_download': True,
1088 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1090 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1092 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1093 'title': 'This is what separates the Excel masters from the wannabes',
1094 'duration': 191.933,
1098 'skip_download': True,
1101 # Brightcove URL in single quotes
1103 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1104 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1106 'id': '4255764656001',
1108 'title': 'SN Presents: Russell Martin, World Citizen',
1109 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1110 'uploader': 'Rogers Sportsnet',
1111 'uploader_id': '1704050871',
1112 'upload_date': '20150525',
1113 'timestamp': 1432570283,
1116 # Dailymotion Cloud video
1118 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1119 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1123 'title': 'Sauvons les abeilles ! - Le débat',
1124 'description': 'md5:d9082128b1c5277987825d684939ca26',
1125 'thumbnail': 're:^https?://.*\.jpe?g$',
1126 'timestamp': 1434970506,
1127 'upload_date': '20150622',
1128 'uploader': 'Public Sénat',
1129 'uploader_id': 'xa9gza',
1132 # OnionStudios embed
1134 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1138 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1139 'thumbnail': 're:^https?://.*\.jpe?g$',
1140 'uploader': 'ClickHole',
1141 'uploader_id': 'clickhole',
1146 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1148 'id': '74849a00-85a9-11e1-9660-123139220831',
1150 'title': '#whilewewatch',
1153 # AdobeTVVideo embed
1155 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1156 'md5': '43662b577c018ad707a63766462b1e87',
1160 'title': 'New experience with Acrobat DC',
1161 'description': 'New experience with Acrobat DC',
1162 'duration': 248.667,
1165 # ScreenwaveMedia embed
1167 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1168 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1170 'id': 'cinemasnob-55d26273809dd',
1172 'title': 'cinemasnob',
1175 # BrightcoveInPageEmbed embed
1177 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1179 'id': '4238694884001',
1181 'title': 'Tabletop: Dread, Last Thoughts',
1182 'description': 'Tabletop: Dread, Last Thoughts',
1186 # JWPlayer with M3U8
1188 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1192 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1193 'uploader': 'ren.tv',
1197 'skip_download': True,
1200 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1201 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1203 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1205 'id': '4785848093001',
1207 'title': 'The Cardinal Pell Interview',
1208 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1209 'uploader': 'GlobeCast Australia - GlobeStream',
1210 'uploader_id': '2733773828001',
1211 'upload_date': '20160304',
1212 'timestamp': 1457083087,
1216 'skip_download': True,
1219 # Another form of arte.tv embed
1221 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1222 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1224 'id': '030273-562_PLUS7-F',
1226 'title': 'ARTE Reportage - Nulle part, en France',
1227 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1228 'upload_date': '20160409',
1233 'url': 'http://www.wykop.pl/link/3088787/',
1234 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1236 'id': '874_1459135191',
1238 'title': 'Man shows poor quality of new apartment building',
1239 'description': 'The wall is like a sand pile.',
1240 'uploader': 'Lake8737',
1243 # Duplicated embedded video URLs
1245 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1247 'id': '149298443_480_16c25b74_2',
1249 'title': 'vs. Blue Orange Spring Game',
1250 'uploader': 'www.hudl.com',
1253 # twitter:player:stream embed
1255 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1259 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1260 'uploader': 'www.rtl.be',
1264 'skip_download': True,
1267 # twitter:player embed
1269 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1270 'md5': 'a3e0df96369831de324f0778e126653c',
1272 'id': '4909620399001',
1274 'title': 'What Do Black Holes Sound Like?',
1275 'description': 'what do black holes sound like',
1276 'upload_date': '20160524',
1277 'uploader_id': '29913724001',
1278 'timestamp': 1464107587,
1279 'uploader': 'TheAtlantic',
1281 'add_ie': ['BrightcoveLegacy'],
1283 # Facebook <iframe> embed
1285 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1286 'md5': 'fbcde74f534176ecb015849146dd3aee',
1288 'id': '599637780109885',
1290 'title': 'Facebook video #599637780109885',
1293 # Facebook API embed
1295 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1296 'md5': 'a47372ee61b39a7b90287094d447d94e',
1298 'id': '10153467542406923',
1300 'title': 'Facebook video #10153467542406923',
1303 # Wordpress "YouTube Video Importer" plugin
1305 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1306 'md5': 'd16797741b560b485194eddda8121b48',
1308 'id': 'HNTXWDXV9Is',
1310 'title': 'Blue Devils Drumline Stanford lot 2016',
1311 'upload_date': '20160627',
1312 'uploader_id': 'GENOCIDE8GENERAL10',
1313 'uploader': 'cylus cyrus',
1317 # video stored on custom kaltura server
1318 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1319 'md5': '537617d06e64dfed891fa1593c4b30cc',
1323 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1324 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1325 'uploader_id': 'videos.expansion@el-mundo.net',
1326 'upload_date': '20150429',
1327 'timestamp': 1430303472,
1329 'add_ie': ['Kaltura'],
1332 # Non-standard Vimeo embed
1333 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1334 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1338 'title': 'Understanding the web - Teaser',
1339 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1340 'upload_date': '20151214',
1341 'uploader': 'OpenClassrooms',
1342 'uploader_id': 'openclassrooms',
1344 'add_ie': ['Vimeo'],
1347 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1348 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1350 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1352 'title': 'Big Buck Bunny',
1353 'description': 'Royalty free test video',
1354 'timestamp': 1432816365,
1355 'upload_date': '20150528',
1359 'skip_download': True,
1361 'add_ie': [ArkenaIE.ie_key()],
1364 # # TODO: find another test
1365 # # http://schema.org/VideoObject
1366 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1367 # 'md5': '888dcf08b7ea671381f00fab74692755',
1369 # 'id': 'nyvTSJMKId',
1371 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1372 # 'description': '#love for cats.',
1373 # 'timestamp': 1461244995,
1374 # 'upload_date': '20160421',
1377 # 'force_generic_extractor': True,
1382 def report_following_redirect(self, new_url):
1383 """Report information extraction."""
1384 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1386 def _extract_rss(self, url, video_id, doc):
1387 playlist_title = doc.find('./channel/title').text
1388 playlist_desc_el = doc.find('./channel/description')
1389 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1392 for it in doc.findall('./channel/item'):
1393 next_url = xpath_text(it, 'link', fatal=False)
1395 enclosure_nodes = it.findall('./enclosure')
1396 for e in enclosure_nodes:
1397 next_url = e.attrib.get('url')
1407 'title': it.find('title').text,
1411 '_type': 'playlist',
1413 'title': playlist_title,
1414 'description': playlist_desc,
1418 def _extract_camtasia(self, url, video_id, webpage):
1419 """ Returns None if no camtasia video can be found. """
1421 camtasia_cfg = self._search_regex(
1422 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1423 webpage, 'camtasia configuration file', default=None)
1424 if camtasia_cfg is None:
1427 title = self._html_search_meta('DC.title', webpage, fatal=True)
1429 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1430 camtasia_cfg = self._download_xml(
1431 camtasia_url, video_id,
1432 note='Downloading camtasia configuration',
1433 errnote='Failed to download camtasia configuration')
1434 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1437 for n in fileset_node.getchildren():
1438 url_n = n.find('./uri')
1443 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1444 'title': '%s - %s' % (title, n.tag),
1445 'url': compat_urlparse.urljoin(url, url_n.text),
1446 'duration': float_or_none(n.find('./duration').text),
1450 '_type': 'playlist',
1455 def _real_extract(self, url):
1456 if url.startswith('//'):
1459 'url': self.http_scheme() + url,
1462 parsed_url = compat_urlparse.urlparse(url)
1463 if not parsed_url.scheme:
1464 default_search = self._downloader.params.get('default_search')
1465 if default_search is None:
1466 default_search = 'fixup_error'
1468 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1470 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1471 return self.url_result('http://' + url)
1472 elif default_search != 'fixup_error':
1473 if default_search == 'auto_warning':
1474 if re.match(r'^(?:url|URL)$', url):
1475 raise ExtractorError(
1476 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1479 self._downloader.report_warning(
1480 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1481 return self.url_result('ytsearch:' + url)
1483 if default_search in ('error', 'fixup_error'):
1484 raise ExtractorError(
1485 '%r is not a valid URL. '
1486 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1487 % (url, url), expected=True)
1489 if ':' not in default_search:
1490 default_search += ':'
1491 return self.url_result(default_search + url)
1493 url, smuggled_data = unsmuggle_url(url)
1494 force_videoid = None
1495 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1496 if smuggled_data and 'force_videoid' in smuggled_data:
1497 force_videoid = smuggled_data['force_videoid']
1498 video_id = force_videoid
1500 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1502 self.to_screen('%s: Requesting header' % video_id)
1504 head_req = HEADRequest(url)
1505 head_response = self._request_webpage(
1507 note=False, errnote='Could not send HEAD request to %s' % url,
1510 if head_response is not False:
1511 # Check for redirect
1512 new_url = head_response.geturl()
1514 self.report_following_redirect(new_url)
1516 new_url = smuggle_url(
1517 new_url, {'force_videoid': force_videoid})
1518 return self.url_result(new_url)
1520 full_response = None
1521 if head_response is False:
1522 request = sanitized_Request(url)
1523 request.add_header('Accept-Encoding', '*')
1524 full_response = self._request_webpage(request, video_id)
1525 head_response = full_response
1529 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1530 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1533 # Check for direct link to a video
1534 content_type = head_response.headers.get('Content-Type', '').lower()
1535 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1537 format_id = m.group('format_id')
1538 if format_id.endswith('mpegurl'):
1539 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1540 elif format_id == 'f4m':
1541 formats = self._extract_f4m_formats(url, video_id)
1544 'format_id': m.group('format_id'),
1546 'vcodec': 'none' if m.group('type') == 'audio' else None
1548 info_dict['direct'] = True
1549 self._sort_formats(formats)
1550 info_dict['formats'] = formats
1553 if not self._downloader.params.get('test', False) and not is_intentional:
1554 force = self._downloader.params.get('force_generic_extractor', False)
1555 self._downloader.report_warning(
1556 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1558 if not full_response:
1559 request = sanitized_Request(url)
1560 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1561 # making it impossible to download only chunk of the file (yet we need only 512kB to
1562 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1563 # that will always result in downloading the whole file that is not desirable.
1564 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1565 # to accept raw bytes and being able to download only a chunk.
1566 # It may probably better to solve this by checking Content-Type for application/octet-stream
1567 # after HEAD request finishes, but not sure if we can rely on this.
1568 request.add_header('Accept-Encoding', '*')
1569 full_response = self._request_webpage(request, video_id)
1571 first_bytes = full_response.read(512)
1573 # Is it an M3U playlist?
1574 if first_bytes.startswith(b'#EXTM3U'):
1575 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1576 self._sort_formats(info_dict['formats'])
1579 # Maybe it's a direct link to a video?
1580 # Be careful not to download the whole thing!
1581 if not is_html(first_bytes):
1582 self._downloader.report_warning(
1583 'URL could be a direct video link, returning it as such.')
1590 webpage = self._webpage_read_content(
1591 full_response, url, video_id, prefix=first_bytes)
1593 self.report_extraction(video_id)
1595 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1597 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1598 if doc.tag == 'rss':
1599 return self._extract_rss(url, video_id, doc)
1600 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1601 smil = self._parse_smil(doc, url, video_id)
1602 self._sort_formats(smil['formats'])
1604 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1605 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1606 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1607 info_dict['formats'] = self._parse_mpd_formats(
1608 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1609 self._sort_formats(info_dict['formats'])
1611 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1612 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1613 self._sort_formats(info_dict['formats'])
1615 except compat_xml_parse_error:
1618 # Is it a Camtasia project?
1619 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1620 if camtasia_res is not None:
1623 # Sometimes embedded video player is hidden behind percent encoding
1624 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1625 # Unescaping the whole page allows to handle those cases in a generic way
1626 webpage = compat_urllib_parse_unquote(webpage)
1628 # it's tempting to parse this further, but you would
1629 # have to take into account all the variations like
1630 # Video Title - Site Name
1631 # Site Name | Video Title
1632 # Video Title - Tagline | Site Name
1633 # and so on and so forth; it's just not practical
1634 video_title = self._og_search_title(
1635 webpage, default=None) or self._html_search_regex(
1636 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1639 # Try to detect age limit automatically
1640 age_limit = self._rta_search(webpage)
1641 # And then there are the jokers who advertise that they use RTA,
1642 # but actually don't.
1643 AGE_LIMIT_MARKERS = [
1644 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1646 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1649 # video uploader is domain name
1650 video_uploader = self._search_regex(
1651 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1653 video_description = self._og_search_description(webpage, default=None)
1654 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1657 def _playlist_from_matches(matches, getter=None, ie=None):
1659 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1661 return self.playlist_result(
1662 urlrs, playlist_id=video_id, playlist_title=video_title)
1664 # Look for Brightcove Legacy Studio embeds
1665 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1667 self.to_screen('Brightcove video detected.')
1670 'url': smuggle_url(bc_url, {'Referer': url}),
1671 'ie_key': 'BrightcoveLegacy'
1672 } for bc_url in bc_urls]
1675 '_type': 'playlist',
1676 'title': video_title,
1681 # Look for Brightcove New Studio embeds
1682 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1684 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1686 # Look for ThePlatform embeds
1687 tp_urls = ThePlatformIE._extract_urls(webpage)
1689 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1691 # Look for Vessel embeds
1692 vessel_urls = VesselIE._extract_urls(webpage)
1694 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1696 # Look for embedded rtl.nl player
1697 matches = re.findall(
1698 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1701 return _playlist_from_matches(matches, ie='RtlNl')
1703 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1704 if vimeo_url is not None:
1705 return self.url_result(vimeo_url)
1707 vid_me_embed_url = self._search_regex(
1708 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1709 webpage, 'vid.me embed', default=None)
1710 if vid_me_embed_url is not None:
1711 return self.url_result(vid_me_embed_url, 'Vidme')
1713 # Look for embedded YouTube player
1714 matches = re.findall(r'''(?x)
1723 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1727 return _playlist_from_matches(
1728 matches, lambda m: unescapeHTML(m[1]))
1730 # Look for lazyYT YouTube embed
1731 matches = re.findall(
1732 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1734 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1736 # Look for Wordpress "YouTube Video Importer" plugin
1737 matches = re.findall(r'''(?x)<div[^>]+
1738 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1739 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1741 return _playlist_from_matches(matches, lambda m: m[-1])
1743 matches = DailymotionIE._extract_urls(webpage)
1745 return _playlist_from_matches(matches)
1747 # Look for embedded Dailymotion playlist player (#3822)
1749 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1751 playlists = re.findall(
1752 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1754 return _playlist_from_matches(
1755 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1757 # Look for embedded Wistia player
1759 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1761 embed_url = self._proto_relative_url(
1762 unescapeHTML(match.group('url')))
1764 '_type': 'url_transparent',
1767 'uploader': video_uploader,
1770 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1773 '_type': 'url_transparent',
1774 'url': 'wistia:%s' % match.group('id'),
1776 'uploader': video_uploader,
1781 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1782 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1785 return self.url_result(self._proto_relative_url(
1786 'wistia:%s' % match.group('id')), 'Wistia')
1788 # Look for SVT player
1789 svt_url = SVTIE._extract_url(webpage)
1791 return self.url_result(svt_url, 'SVT')
1793 # Look for embedded condenast player
1794 matches = re.findall(
1795 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1799 '_type': 'playlist',
1802 'ie_key': 'CondeNast',
1804 } for ma in matches],
1805 'title': video_title,
1809 # Look for Bandcamp pages with custom domain
1810 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1811 if mobj is not None:
1812 burl = unescapeHTML(mobj.group(1))
1813 # Don't set the extractor because it can be a track url or an album
1814 return self.url_result(burl)
1816 # Look for embedded Vevo player
1818 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1819 if mobj is not None:
1820 return self.url_result(mobj.group('url'))
1822 # Look for embedded Viddler player
1824 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1826 if mobj is not None:
1827 return self.url_result(mobj.group('url'))
1829 # Look for NYTimes player
1831 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1833 if mobj is not None:
1834 return self.url_result(mobj.group('url'))
1836 # Look for Libsyn player
1838 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1839 if mobj is not None:
1840 return self.url_result(mobj.group('url'))
1842 # Look for Ooyala videos
1843 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1844 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1845 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1846 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1847 if mobj is not None:
1848 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1850 # Look for multiple Ooyala embeds on SBN network websites
1851 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1852 if mobj is not None:
1853 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1855 return _playlist_from_matches(
1856 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1858 # Look for Aparat videos
1859 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1860 if mobj is not None:
1861 return self.url_result(mobj.group(1), 'Aparat')
1863 # Look for MPORA videos
1864 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1865 if mobj is not None:
1866 return self.url_result(mobj.group(1), 'Mpora')
1868 # Look for embedded NovaMov-based player
1870 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1871 (?P<url>http://(?:(?:embed|www)\.)?
1873 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1874 videoweed\.(?:es|com)|
1875 movshare\.(?:net|sx|ag)|
1876 divxstage\.(?:eu|net|ch|co|at|ag))
1877 /embed\.php.+?)\1''', webpage)
1878 if mobj is not None:
1879 return self.url_result(mobj.group('url'))
1881 # Look for embedded Facebook player
1882 facebook_url = FacebookIE._extract_url(webpage)
1883 if facebook_url is not None:
1884 return self.url_result(facebook_url, 'Facebook')
1886 # Look for embedded VK player
1887 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1888 if mobj is not None:
1889 return self.url_result(mobj.group('url'), 'VK')
1891 # Look for embedded Odnoklassniki player
1892 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1893 if mobj is not None:
1894 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1896 # Look for embedded ivi player
1897 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1898 if mobj is not None:
1899 return self.url_result(mobj.group('url'), 'Ivi')
1901 # Look for embedded Huffington Post player
1903 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1904 if mobj is not None:
1905 return self.url_result(mobj.group('url'), 'HuffPost')
1908 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1909 if mobj is not None:
1910 return self.url_result(mobj.group('url'))
1911 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1912 if mobj is not None:
1913 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1915 # Look for funnyordie embed
1916 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1918 return _playlist_from_matches(
1919 matches, getter=unescapeHTML, ie='FunnyOrDie')
1921 # Look for BBC iPlayer embed
1922 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1924 return _playlist_from_matches(matches, ie='BBCCoUk')
1926 # Look for embedded RUTV player
1927 rutv_url = RUTVIE._extract_url(webpage)
1929 return self.url_result(rutv_url, 'RUTV')
1931 # Look for embedded TVC player
1932 tvc_url = TVCIE._extract_url(webpage)
1934 return self.url_result(tvc_url, 'TVC')
1936 # Look for embedded SportBox player
1937 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1939 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1941 # Look for embedded PornHub player
1942 pornhub_url = PornHubIE._extract_url(webpage)
1944 return self.url_result(pornhub_url, 'PornHub')
1946 # Look for embedded XHamster player
1947 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1949 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1951 # Look for embedded TNAFlixNetwork player
1952 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1954 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1956 # Look for embedded Tvigle player
1958 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1959 if mobj is not None:
1960 return self.url_result(mobj.group('url'), 'Tvigle')
1962 # Look for embedded TED player
1964 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1965 if mobj is not None:
1966 return self.url_result(mobj.group('url'), 'TED')
1968 # Look for embedded Ustream videos
1970 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1971 if mobj is not None:
1972 return self.url_result(mobj.group('url'), 'Ustream')
1974 # Look for embedded arte.tv player
1976 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1978 if mobj is not None:
1979 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1981 # Look for embedded francetv player
1983 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1985 if mobj is not None:
1986 return self.url_result(mobj.group('url'))
1988 # Look for embedded smotri.com player
1989 smotri_url = SmotriIE._extract_url(webpage)
1991 return self.url_result(smotri_url, 'Smotri')
1993 # Look for embedded Myvi.ru player
1994 myvi_url = MyviIE._extract_url(webpage)
1996 return self.url_result(myvi_url)
1998 # Look for embedded soundcloud player
2000 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
2002 if mobj is not None:
2003 url = unescapeHTML(mobj.group('url'))
2004 return self.url_result(url)
2006 # Look for embedded mtvservices player
2007 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2009 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2011 # Look for embedded yahoo player
2013 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2015 if mobj is not None:
2016 return self.url_result(mobj.group('url'), 'Yahoo')
2018 # Look for embedded sbs.com.au player
2022 <meta\s+property="og:video"\s+content=|
2025 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2027 if mobj is not None:
2028 return self.url_result(mobj.group('url'), 'SBS')
2030 # Look for embedded Cinchcast player
2032 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2034 if mobj is not None:
2035 return self.url_result(mobj.group('url'), 'Cinchcast')
2038 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2042 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2044 if mobj is not None:
2045 return self.url_result(mobj.group('url'), 'MLB')
2048 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2050 if mobj is not None:
2051 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2054 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2056 if mobj is not None:
2057 return self.url_result(mobj.group('url'), 'Livestream')
2059 # Look for Zapiks embed
2061 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2062 if mobj is not None:
2063 return self.url_result(mobj.group('url'), 'Zapiks')
2065 # Look for Kaltura embeds
2066 kaltura_url = KalturaIE._extract_url(webpage)
2068 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2070 # Look for Eagle.Platform embeds
2071 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2072 if eagleplatform_url:
2073 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2075 # Look for ClipYou (uses Eagle.Platform) embeds
2077 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2078 if mobj is not None:
2079 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2081 # Look for Pladform embeds
2082 pladform_url = PladformIE._extract_url(webpage)
2084 return self.url_result(pladform_url)
2086 # Look for Videomore embeds
2087 videomore_url = VideomoreIE._extract_url(webpage)
2089 return self.url_result(videomore_url)
2091 # Look for Playwire embeds
2093 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2094 if mobj is not None:
2095 return self.url_result(mobj.group('url'))
2097 # Look for 5min embeds
2099 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2100 if mobj is not None:
2101 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2103 # Look for Crooks and Liars embeds
2105 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2106 if mobj is not None:
2107 return self.url_result(mobj.group('url'))
2109 # Look for NBC Sports VPlayer embeds
2110 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2112 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2114 # Look for NBC News embeds
2115 nbc_news_embed_url = re.search(
2116 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2117 if nbc_news_embed_url:
2118 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2120 # Look for Google Drive embeds
2121 google_drive_url = GoogleDriveIE._extract_url(webpage)
2122 if google_drive_url:
2123 return self.url_result(google_drive_url, 'GoogleDrive')
2125 # Look for UDN embeds
2127 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2128 if mobj is not None:
2129 return self.url_result(
2130 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2132 # Look for Senate ISVP iframe
2133 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2135 return self.url_result(senate_isvp_url, 'SenateISVP')
2137 # Look for Dailymotion Cloud videos
2138 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2140 return self.url_result(dmcloud_url, 'DailymotionCloud')
2142 # Look for OnionStudios embeds
2143 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2144 if onionstudios_url:
2145 return self.url_result(onionstudios_url)
2147 # Look for ViewLift embeds
2148 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2150 return self.url_result(viewlift_url)
2152 # Look for JWPlatform embeds
2153 jwplatform_url = JWPlatformIE._extract_url(webpage)
2155 return self.url_result(jwplatform_url, 'JWPlatform')
2157 # Look for ScreenwaveMedia embeds
2158 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2159 if mobj is not None:
2160 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2162 # Look for Digiteka embeds
2163 digiteka_url = DigitekaIE._extract_url(webpage)
2165 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2167 # Look for Arkena embeds
2168 arkena_url = ArkenaIE._extract_url(webpage)
2170 return self.url_result(arkena_url, ArkenaIE.ie_key())
2172 # Look for Limelight embeds
2173 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2177 'Channel': 'channel',
2178 'ChannelList': 'channel_list',
2180 return self.url_result('limelight:%s:%s' % (
2181 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2183 # Look for AdobeTVVideo embeds
2185 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2187 if mobj is not None:
2188 return self.url_result(
2189 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2192 # Look for Vine embeds
2194 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2196 if mobj is not None:
2197 return self.url_result(
2198 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2200 # Look for Instagram embeds
2201 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2202 if instagram_embed_url is not None:
2203 return self.url_result(
2204 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2206 # Look for LiveLeak embeds
2207 liveleak_url = LiveLeakIE._extract_url(webpage)
2209 return self.url_result(liveleak_url, 'LiveLeak')
2211 # Look for 3Q SDN embeds
2212 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2215 '_type': 'url_transparent',
2216 'ie_key': ThreeQSDNIE.ie_key(),
2217 'url': self._proto_relative_url(threeqsdn_url),
2218 'title': video_title,
2219 'description': video_description,
2220 'thumbnail': video_thumbnail,
2221 'uploader': video_uploader,
2224 # Looking for http://schema.org/VideoObject
2225 json_ld = self._search_json_ld(
2226 webpage, video_id, default=None, expected_type='VideoObject')
2227 if json_ld and json_ld.get('url'):
2229 'title': video_title or info_dict['title'],
2230 'description': video_description,
2231 'thumbnail': video_thumbnail,
2232 'age_limit': age_limit
2234 info_dict.update(json_ld)
2237 def check_video(vurl):
2238 if YoutubeIE.suitable(vurl):
2240 vpath = compat_urlparse.urlparse(vurl).path
2241 vext = determine_ext(vpath)
2242 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2244 def filter_video(urls):
2245 return list(filter(check_video, urls))
2247 # Start with something easy: JW Player in SWFObject
2248 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2250 # Look for gorilla-vid style embedding
2251 found = filter_video(re.findall(r'''(?sx)
2255 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2258 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2260 # Broaden the search a little bit
2261 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2263 # Broaden the findall a little bit: JWPlayer JS loader
2264 found = filter_video(re.findall(
2265 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2268 found = filter_video(re.findall(r'''(?xs)
2269 flowplayer\("[^"]+",\s*
2271 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2272 ["']?url["']?\s*:\s*["']([^"']+)["']
2277 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2279 # Try to find twitter cards info
2280 # twitter:player:stream should be checked before twitter:player since
2281 # it is expected to contain a raw stream (see
2282 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2283 found = filter_video(re.findall(
2284 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2286 # We look for Open Graph info:
2287 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2288 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2289 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2290 if m_video_type is not None:
2291 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2294 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2296 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2298 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2299 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2302 # Look also in Refresh HTTP header
2303 refresh_header = head_response.headers.get('Refresh')
2305 # In python 2 response HTTP headers are bytestrings
2306 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2307 refresh_header = refresh_header.decode('iso-8859-1')
2308 found = re.search(REDIRECT_REGEX, refresh_header)
2310 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2311 self.report_following_redirect(new_url)
2318 # twitter:player is a https URL to iframe player that may or may not
2319 # be supported by youtube-dl thus this is checked the very last (see
2320 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2321 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2323 return self.url_result(embed_url)
2326 raise UnsupportedError(url)
2329 for video_url in orderedSet(found):
2330 video_url = unescapeHTML(video_url)
2331 video_url = video_url.replace('\\/', '/')
2332 video_url = compat_urlparse.urljoin(url, video_url)
2333 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2335 # Sometimes, jwplayer extraction will result in a YouTube URL
2336 if YoutubeIE.suitable(video_url):
2337 entries.append(self.url_result(video_url, 'Youtube'))
2340 # here's a fun little line of code for you:
2341 video_id = os.path.splitext(video_id)[0]
2345 'uploader': video_uploader,
2346 'title': video_title,
2347 'age_limit': age_limit,
2350 ext = determine_ext(video_url)
2352 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2354 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2356 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2358 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2360 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2362 entry_info_dict['url'] = video_url
2364 if entry_info_dict.get('formats'):
2365 self._sort_formats(entry_info_dict['formats'])
2367 entries.append(entry_info_dict)
2369 if len(entries) == 1:
2372 for num, e in enumerate(entries, start=1):
2373 # 'url' results don't have a title
2374 if e.get('title') is not None:
2375 e['title'] = '%s (%d)' % (e['title'], num)
2377 '_type': 'playlist',