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
74 from .soundcloud import SoundcloudIE
75 from .vbox7 import Vbox7IE
76 from .dbtv import DBTVIE
79 class GenericIE(InfoExtractor):
80 IE_DESC = 'Generic downloader that works on some sites'
84 # Direct link to a video
86 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
87 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
92 'upload_date': '20100513',
95 # Direct link to media delivered compressed (until Accept-Encoding is *)
97 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
98 'md5': '128c42e68b13950268b648275386fc74',
100 'id': 'FictionJunction-Parallel_Hearts',
102 'title': 'FictionJunction-Parallel_Hearts',
103 'upload_date': '20140522',
105 'expected_warnings': [
106 'URL could be a direct video link, returning it as such.'
109 # Direct download with broken HEAD
111 'url': 'http://ai-radio.org:8000/radio.opus',
118 'skip_download': True, # infinite live stream
120 'expected_warnings': [
121 r'501.*Not Implemented',
125 # Direct link with incorrect MIME type
127 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
128 'md5': '4ccbebe5f36706d85221f204d7eb5913',
130 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
131 'id': '5_Lennart_Poettering_-_Systemd',
133 'title': '5_Lennart_Poettering_-_Systemd',
134 'upload_date': '20141120',
136 'expected_warnings': [
137 'URL could be a direct video link, returning it as such.'
142 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
144 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
145 'title': 'Zero Punctuation',
146 'description': 're:.*groundbreaking video review series.*'
148 'playlist_mincount': 11,
150 # RSS feed with enclosure
152 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
154 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
156 'upload_date': '20150228',
157 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
160 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
162 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
166 'title': 'Automatics, robotics and biocybernetics',
167 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
168 'upload_date': '20130627',
169 'formats': 'mincount:16',
170 'subtitles': 'mincount:1',
173 'force_generic_extractor': True,
174 'skip_download': True,
177 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
179 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
184 'formats': 'mincount:1',
187 'skip_download': True,
190 # SMIL from https://www.restudy.dk/video/play/id/1637
192 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
196 'title': 'video_1637',
197 'formats': 'mincount:3',
200 'skip_download': True,
203 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
205 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
207 'id': 'smil-service',
209 'title': 'smil-service',
210 'formats': 'mincount:1',
213 'skip_download': True,
216 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
218 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
222 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
223 'formats': 'mincount:3',
226 'skip_download': True,
229 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
231 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
233 'id': 'mZlp2ctYIUEB',
235 'title': 'Tikibad ontruimd wegens brand',
236 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
237 'thumbnail': 're:^https?://.*\.jpg$',
241 'skip_download': True,
244 # MPD from http://dash-mse-test.appspot.com/media.html
246 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
247 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
249 'id': 'car-20120827-manifest',
251 'title': 'car-20120827-manifest',
252 'formats': 'mincount:9',
253 'upload_date': '20130904',
256 'format': 'bestvideo',
259 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
261 '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',
266 'formats': 'mincount:8',
270 'skip_download': True,
273 # m3u8 served with Content-Type: text/plain
275 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
280 'upload_date': '20140720',
281 'formats': 'mincount:11',
285 'skip_download': True,
290 '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',
294 'upload_date': '20130224',
295 'uploader_id': 'TheVerge',
296 'description': 're:^Chris Ziegler takes a look at the\.*',
297 'uploader': 'The Verge',
298 'title': 'First Firefox OS phones side-by-side',
301 'skip_download': False,
305 # redirect in Refresh HTTP header
306 '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',
310 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
311 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
312 'upload_date': '20150917',
313 'uploader_id': 'brtvofficial',
314 'uploader': 'Boiler Room',
317 'skip_download': False,
321 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
322 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
324 'id': '13601338388002',
326 'uploader': 'www.hodiho.fr',
327 'title': 'R\u00e9gis plante sa Jeep',
330 # bandcamp page with custom domain
332 'add_ie': ['Bandcamp'],
333 'url': 'http://bronyrock.com/track/the-pony-mash',
337 'title': 'The Pony Mash',
338 'uploader': 'M_Pallante',
340 'skip': 'There is a limit of 200 free downloads / month for the test song',
342 # embedded brightcove video
343 # it also tests brightcove videos that need to set the 'Referer' in the
346 'add_ie': ['BrightcoveLegacy'],
347 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
349 'id': '2765128793001',
351 'title': 'Le cours de bourse : l’analyse technique',
352 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
353 'uploader': 'BFM BUSINESS',
356 'skip_download': True,
360 # https://github.com/rg3/youtube-dl/issues/2253
361 'url': 'http://bcove.me/i6nfkrc3',
362 'md5': '0ba9446db037002366bab3b3eb30c88c',
364 'id': '3101154703001',
366 'title': 'Still no power',
367 'uploader': 'thestar.com',
368 '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.',
370 'add_ie': ['BrightcoveLegacy'],
373 'url': 'http://www.championat.com/video/football/v/87/87499.html',
374 'md5': 'fb973ecf6e4a78a67453647444222983',
376 'id': '3414141473001',
378 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
379 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
380 'uploader': 'Championat',
384 # https://github.com/rg3/youtube-dl/issues/3541
385 'add_ie': ['BrightcoveLegacy'],
386 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
388 'id': '3866516442001',
390 'title': 'Leer mij vrouwen kennen: Aflevering 1',
391 'description': 'Leer mij vrouwen kennen: Aflevering 1',
392 'uploader': 'SBS Broadcasting',
394 'skip': 'Restricted to Netherlands',
396 'skip_download': True, # m3u8 download
401 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
402 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
404 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
406 'title': '2cc213299525360.mov', # that's what we get
409 'add_ie': ['Ooyala'],
412 # ooyala video embedded with http://player.ooyala.com/iframe.js
413 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
415 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
417 'title': '"Steve Jobs: Man in the Machine" trailer',
418 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
422 'skip_download': True,
427 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
431 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
432 'upload_date': '20140225',
433 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
434 'uploader': 'Tested',
435 'uploader_id': 'testedcom',
437 # No need to test YoutubeIE here
439 'skip_download': True,
444 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
448 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
449 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
454 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
458 'title': 'Охотское море стало целиком российским',
459 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
463 'skip_download': True,
468 '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/',
472 'title': 'Дошкольное воспитание',
477 'url': 'http://www.vestifinance.ru/articles/25753',
480 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
485 'title': 'Госзаказ. День 3',
491 'title': 'Госзаказ. День 2',
497 'title': 'Госзаказ. День 1',
503 'skip_download': True,
508 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
510 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
512 'title': 'Ужастики, русский трейлер (2015)',
513 'thumbnail': 're:^https?://.*\.jpg$',
519 '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',
522 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
524 'playlist_mincount': 7,
528 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
529 'md5': '65fdff94098e4a607385a60c5177c638',
533 'title': 'Hidden miracles of the natural world',
534 'uploader': 'Louie Schwartzberg',
535 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
538 # Embedded Ustream video
540 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
541 'md5': '27b99cdb639c9b12a79bca876a073417',
545 'uploader': 'AU SPA: The NSA and Privacy',
546 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
549 # nowvideo embed hidden behind percent encoding
551 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
552 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
554 'id': '06e53103ca9aa',
556 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
557 'description': 'No description',
562 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
563 'md5': '7653032cbb25bf6c80d80f217055fa43',
565 'id': '048195-004_PLUS7-F',
568 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
569 'upload_date': '20140320',
572 'skip_download': 'Requires rtmpdump'
577 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
581 'title': 'Alcaline, le concert avec Calogero',
582 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
583 'upload_date': '20150226',
584 'timestamp': 1424989860,
589 'skip_download': True,
591 'expected_warnings': [
597 'url': 'http://www.wired.com/2014/04/honda-asimo/',
598 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
600 'id': '53501be369702d3275860000',
602 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
607 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
608 'md5': '441aeeb82eb72c422c7f14ec533999cd',
610 'id': 'k2mm4bCdJ6CQ2i7c8o2',
612 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
613 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
615 'uploader_id': 'xgditw',
616 'upload_date': '20140425',
617 'timestamp': 1398441542,
619 'add_ie': ['Dailymotion'],
623 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
627 'title': 'The NBL Auction 2014',
628 'uploader': 'BADMINTON England',
629 'uploader_id': 'BADMINTONEvents',
630 'upload_date': '20140603',
631 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
633 'add_ie': ['Youtube'],
635 'skip_download': True,
640 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
641 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
643 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
645 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
646 'description': 'Two valets share their love for movie star Liam Neesons.',
647 'timestamp': 1349922600,
648 'upload_date': '20121011',
651 # YouTube embed via <data-embed-url="">
653 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
657 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
658 'uploader': 'Gameloft',
659 'uploader_id': 'gameloft',
660 'upload_date': '20140828',
661 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
664 'skip_download': True,
669 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
671 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
673 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
674 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
679 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
681 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
682 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
688 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
693 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
694 'md5': '9d65602bf31c6e20014319c7d07fba27',
696 'id': '5123ea6d5e5a7',
699 'uploader': 'www.handjobhub.com',
700 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
703 # Multiple brightcove videos
704 # https://github.com/rg3/youtube-dl/issues/2283
706 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
708 'id': 'always-never',
709 'title': 'Always / Never - The New Yorker',
713 'extract_flat': False,
714 'skip_download': True,
719 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
720 'md5': '96f09a37e44da40dd083e12d9a683327',
724 'title': 'Ump changes call to ball',
725 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
727 'timestamp': 1401537900,
728 'upload_date': '20140531',
729 'thumbnail': 're:^https?://.*\.jpg$',
734 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
735 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
739 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
740 'description': 'a Paywall Videos video from Remilon',
742 'uploader': 'study.com',
743 'timestamp': 1459678540,
744 'upload_date': '20160403',
745 'filesize': 24687186,
749 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
750 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
754 'title': 'Conversation about Hexagonal Rails Part 1',
755 'description': 'a Martin Fowler video from ThoughtWorks',
757 'uploader': 'thoughtworks.wistia.com',
758 'timestamp': 1401832161,
759 'upload_date': '20140603',
762 # Wistia standard embed (async)
764 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
768 'title': 'Drip Brennan Dunn Workshop',
769 'description': 'a JV Webinars video from getdrip-1',
771 'timestamp': 1463607249,
772 'upload_date': '20160518',
775 'skip_download': True,
780 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
784 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
785 'uploader': 'Sophos Security',
786 'title': 'Chet Chat 171 - Oct 29, 2014',
787 'upload_date': '20141029',
790 # Soundcloud multiple embeds
792 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
795 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
797 'playlist_mincount': 7,
801 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
805 'upload_date': '20141112',
806 'title': 'Rosetta #CometLanding webcast HL 10',
809 # Another Livestream embed, without 'new.' in URL
811 'url': 'https://www.freespeech.org/',
815 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
819 'skip_download': True,
824 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
827 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
829 'playlist_mincount': 2,
833 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
837 'upload_date': '20141126',
838 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
843 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
845 'id': '730m_DandD_1901_512k',
847 'uploader': 'www.abc.net.au',
848 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
851 # embedded viddler video
853 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
857 'uploader': 'deadspin',
858 'title': 'WALL-TO-GORTAT',
859 'timestamp': 1422285291,
860 'upload_date': '20150126',
862 'add_ie': ['Viddler'],
866 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
870 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
871 'description': 'md5:601cb790edd05908957dae8aaa866465',
872 'upload_date': '20150220',
874 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
878 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
882 'upload_date': '20150212',
883 'uploader': 'The National Archives UK',
884 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
885 'uploader_id': 'NationalArchives08',
886 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
891 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
892 'playlist_mincount': 5,
894 'id': 'aanslagen-kopenhagen',
895 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
900 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
904 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
907 # Kaltura embed (different embed code)
909 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
913 'upload_date': '20150127',
914 'uploader_id': 'PremierMedia',
916 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
919 # Kaltura embed protected with referrer
921 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
925 'title': 'Violetta - Achter De Schermen - Ruggero',
926 'description': 'Achter de schermen met Ruggero',
927 'timestamp': 1435133761,
928 'upload_date': '20150624',
929 'uploader_id': 'echojecka',
932 # Kaltura embed with single quotes
934 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
939 'timestamp': 1355743100,
940 'upload_date': '20121217',
941 'uploader_id': 'batchUser',
943 'add_ie': ['Kaltura'],
946 # Kaltura embedded via quoted entry_id
947 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
951 'title': '06_matthew_brender_raj_dutt',
952 'timestamp': 1466638791,
953 'upload_date': '20160622',
955 'add_ie': ['Kaltura'],
956 'expected_warnings': [
957 'Could not send HEAD request'
960 'skip_download': True,
963 # Eagle.Platform embed (generic URL)
965 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
966 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
970 'title': 'Навальный вышел на свободу',
971 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
972 'thumbnail': 're:^https?://.*\.jpg$',
978 # ClipYou (Eagle.Platform) embed (custom URL)
980 'url': 'http://muz-tv.ru/play/7129/',
981 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
985 'title': "'O Sole Mio",
986 'thumbnail': 're:^https?://.*\.jpg$',
993 'url': 'http://muz-tv.ru/kinozal/view/7400/',
997 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
998 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
999 'thumbnail': 're:^https?://.*\.jpg$',
1006 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1010 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1011 'thumbnail': 're:^https?://.*\.png$',
1017 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1018 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1022 'title': 'Facebook Creates "On This Day" | Crunch Report',
1027 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1031 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1036 # Crooks and Liars embed
1038 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1042 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1043 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1044 'timestamp': 1428207000,
1045 'upload_date': '20150405',
1046 'uploader': 'Heather',
1049 # Crooks and Liars external embed
1051 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1053 'id': 'MTE3MjUtMzQ2MzA',
1055 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1056 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1057 'timestamp': 1265032391,
1058 'upload_date': '20100201',
1059 'uploader': 'Heather',
1062 # NBC Sports vplayer embed
1064 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1066 'id': 'ln7x1qSThw4k',
1068 'title': "PFT Live: New leader in the 'new-look' defense",
1069 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1070 'uploader': 'NBCU-SPORTS',
1071 'upload_date': '20140107',
1072 'timestamp': 1389118457,
1077 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1078 'md5': '1aa589c675898ae6d37a17913cf68d66',
1080 'id': '701714499682',
1082 'title': 'PREVIEW: On Assignment: David Letterman',
1083 '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.',
1088 'url': 'https://video.udn.com/news/300346',
1089 'md5': 'fd2060e988c326991037b9aff9df21a6',
1093 'title': '中一中男師變性 全校師生力挺',
1094 'thumbnail': 're:^https?://.*\.jpg$',
1098 'skip_download': True,
1103 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1105 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1107 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1108 'title': 'This is what separates the Excel masters from the wannabes',
1109 'duration': 191.933,
1113 'skip_download': True,
1116 # Brightcove URL in single quotes
1118 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1119 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1121 'id': '4255764656001',
1123 'title': 'SN Presents: Russell Martin, World Citizen',
1124 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1125 'uploader': 'Rogers Sportsnet',
1126 'uploader_id': '1704050871',
1127 'upload_date': '20150525',
1128 'timestamp': 1432570283,
1131 # Dailymotion Cloud video
1133 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1134 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1138 'title': 'Sauvons les abeilles ! - Le débat',
1139 'description': 'md5:d9082128b1c5277987825d684939ca26',
1140 'thumbnail': 're:^https?://.*\.jpe?g$',
1141 'timestamp': 1434970506,
1142 'upload_date': '20150622',
1143 'uploader': 'Public Sénat',
1144 'uploader_id': 'xa9gza',
1147 # OnionStudios embed
1149 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1153 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1154 'thumbnail': 're:^https?://.*\.jpe?g$',
1155 'uploader': 'ClickHole',
1156 'uploader_id': 'clickhole',
1161 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1163 'id': '74849a00-85a9-11e1-9660-123139220831',
1165 'title': '#whilewewatch',
1168 # AdobeTVVideo embed
1170 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1171 'md5': '43662b577c018ad707a63766462b1e87',
1175 'title': 'New experience with Acrobat DC',
1176 'description': 'New experience with Acrobat DC',
1177 'duration': 248.667,
1180 # ScreenwaveMedia embed
1182 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1183 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1185 'id': 'cinemasnob-55d26273809dd',
1187 'title': 'cinemasnob',
1190 # BrightcoveInPageEmbed embed
1192 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1194 'id': '4238694884001',
1196 'title': 'Tabletop: Dread, Last Thoughts',
1197 'description': 'Tabletop: Dread, Last Thoughts',
1201 # JWPlayer with M3U8
1203 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1207 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1208 'uploader': 'ren.tv',
1212 'skip_download': True,
1215 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1216 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1218 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1220 'id': '4785848093001',
1222 'title': 'The Cardinal Pell Interview',
1223 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1224 'uploader': 'GlobeCast Australia - GlobeStream',
1225 'uploader_id': '2733773828001',
1226 'upload_date': '20160304',
1227 'timestamp': 1457083087,
1231 'skip_download': True,
1234 # Another form of arte.tv embed
1236 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1237 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1239 'id': '030273-562_PLUS7-F',
1241 'title': 'ARTE Reportage - Nulle part, en France',
1242 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1243 'upload_date': '20160409',
1248 'url': 'http://www.wykop.pl/link/3088787/',
1249 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1251 'id': '874_1459135191',
1253 'title': 'Man shows poor quality of new apartment building',
1254 'description': 'The wall is like a sand pile.',
1255 'uploader': 'Lake8737',
1258 # Duplicated embedded video URLs
1260 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1262 'id': '149298443_480_16c25b74_2',
1264 'title': 'vs. Blue Orange Spring Game',
1265 'uploader': 'www.hudl.com',
1268 # twitter:player:stream embed
1270 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1274 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1275 'uploader': 'www.rtl.be',
1279 'skip_download': True,
1282 # twitter:player embed
1284 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1285 'md5': 'a3e0df96369831de324f0778e126653c',
1287 'id': '4909620399001',
1289 'title': 'What Do Black Holes Sound Like?',
1290 'description': 'what do black holes sound like',
1291 'upload_date': '20160524',
1292 'uploader_id': '29913724001',
1293 'timestamp': 1464107587,
1294 'uploader': 'TheAtlantic',
1296 'add_ie': ['BrightcoveLegacy'],
1298 # Facebook <iframe> embed
1300 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1301 'md5': 'fbcde74f534176ecb015849146dd3aee',
1303 'id': '599637780109885',
1305 'title': 'Facebook video #599637780109885',
1308 # Facebook API embed
1310 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1311 'md5': 'a47372ee61b39a7b90287094d447d94e',
1313 'id': '10153467542406923',
1315 'title': 'Facebook video #10153467542406923',
1318 # Wordpress "YouTube Video Importer" plugin
1320 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1321 'md5': 'd16797741b560b485194eddda8121b48',
1323 'id': 'HNTXWDXV9Is',
1325 'title': 'Blue Devils Drumline Stanford lot 2016',
1326 'upload_date': '20160627',
1327 'uploader_id': 'GENOCIDE8GENERAL10',
1328 'uploader': 'cylus cyrus',
1332 # video stored on custom kaltura server
1333 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1334 'md5': '537617d06e64dfed891fa1593c4b30cc',
1338 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1339 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1340 'uploader_id': 'videos.expansion@el-mundo.net',
1341 'upload_date': '20150429',
1342 'timestamp': 1430303472,
1344 'add_ie': ['Kaltura'],
1347 # Non-standard Vimeo embed
1348 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1349 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1353 'title': 'Understanding the web - Teaser',
1354 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1355 'upload_date': '20151214',
1356 'uploader': 'OpenClassrooms',
1357 'uploader_id': 'openclassrooms',
1359 'add_ie': ['Vimeo'],
1362 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1363 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1365 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1367 'title': 'Big Buck Bunny',
1368 'description': 'Royalty free test video',
1369 'timestamp': 1432816365,
1370 'upload_date': '20150528',
1374 'skip_download': True,
1376 'add_ie': [ArkenaIE.ie_key()],
1379 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1383 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1386 'skip_download': True,
1388 'add_ie': [Vbox7IE.ie_key()],
1392 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1393 'playlist_mincount': 3,
1396 # # TODO: find another test
1397 # # http://schema.org/VideoObject
1398 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1399 # 'md5': '888dcf08b7ea671381f00fab74692755',
1401 # 'id': 'nyvTSJMKId',
1403 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1404 # 'description': '#love for cats.',
1405 # 'timestamp': 1461244995,
1406 # 'upload_date': '20160421',
1409 # 'force_generic_extractor': True,
1414 def report_following_redirect(self, new_url):
1415 """Report information extraction."""
1416 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1418 def _extract_rss(self, url, video_id, doc):
1419 playlist_title = doc.find('./channel/title').text
1420 playlist_desc_el = doc.find('./channel/description')
1421 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1424 for it in doc.findall('./channel/item'):
1425 next_url = xpath_text(it, 'link', fatal=False)
1427 enclosure_nodes = it.findall('./enclosure')
1428 for e in enclosure_nodes:
1429 next_url = e.attrib.get('url')
1439 'title': it.find('title').text,
1443 '_type': 'playlist',
1445 'title': playlist_title,
1446 'description': playlist_desc,
1450 def _extract_camtasia(self, url, video_id, webpage):
1451 """ Returns None if no camtasia video can be found. """
1453 camtasia_cfg = self._search_regex(
1454 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1455 webpage, 'camtasia configuration file', default=None)
1456 if camtasia_cfg is None:
1459 title = self._html_search_meta('DC.title', webpage, fatal=True)
1461 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1462 camtasia_cfg = self._download_xml(
1463 camtasia_url, video_id,
1464 note='Downloading camtasia configuration',
1465 errnote='Failed to download camtasia configuration')
1466 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1469 for n in fileset_node.getchildren():
1470 url_n = n.find('./uri')
1475 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1476 'title': '%s - %s' % (title, n.tag),
1477 'url': compat_urlparse.urljoin(url, url_n.text),
1478 'duration': float_or_none(n.find('./duration').text),
1482 '_type': 'playlist',
1487 def _real_extract(self, url):
1488 if url.startswith('//'):
1491 'url': self.http_scheme() + url,
1494 parsed_url = compat_urlparse.urlparse(url)
1495 if not parsed_url.scheme:
1496 default_search = self._downloader.params.get('default_search')
1497 if default_search is None:
1498 default_search = 'fixup_error'
1500 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1502 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1503 return self.url_result('http://' + url)
1504 elif default_search != 'fixup_error':
1505 if default_search == 'auto_warning':
1506 if re.match(r'^(?:url|URL)$', url):
1507 raise ExtractorError(
1508 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1511 self._downloader.report_warning(
1512 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1513 return self.url_result('ytsearch:' + url)
1515 if default_search in ('error', 'fixup_error'):
1516 raise ExtractorError(
1517 '%r is not a valid URL. '
1518 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1519 % (url, url), expected=True)
1521 if ':' not in default_search:
1522 default_search += ':'
1523 return self.url_result(default_search + url)
1525 url, smuggled_data = unsmuggle_url(url)
1526 force_videoid = None
1527 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1528 if smuggled_data and 'force_videoid' in smuggled_data:
1529 force_videoid = smuggled_data['force_videoid']
1530 video_id = force_videoid
1532 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1534 self.to_screen('%s: Requesting header' % video_id)
1536 head_req = HEADRequest(url)
1537 head_response = self._request_webpage(
1539 note=False, errnote='Could not send HEAD request to %s' % url,
1542 if head_response is not False:
1543 # Check for redirect
1544 new_url = head_response.geturl()
1546 self.report_following_redirect(new_url)
1548 new_url = smuggle_url(
1549 new_url, {'force_videoid': force_videoid})
1550 return self.url_result(new_url)
1552 full_response = None
1553 if head_response is False:
1554 request = sanitized_Request(url)
1555 request.add_header('Accept-Encoding', '*')
1556 full_response = self._request_webpage(request, video_id)
1557 head_response = full_response
1561 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1562 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1565 # Check for direct link to a video
1566 content_type = head_response.headers.get('Content-Type', '').lower()
1567 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1569 format_id = m.group('format_id')
1570 if format_id.endswith('mpegurl'):
1571 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1572 elif format_id == 'f4m':
1573 formats = self._extract_f4m_formats(url, video_id)
1576 'format_id': m.group('format_id'),
1578 'vcodec': 'none' if m.group('type') == 'audio' else None
1580 info_dict['direct'] = True
1581 self._sort_formats(formats)
1582 info_dict['formats'] = formats
1585 if not self._downloader.params.get('test', False) and not is_intentional:
1586 force = self._downloader.params.get('force_generic_extractor', False)
1587 self._downloader.report_warning(
1588 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1590 if not full_response:
1591 request = sanitized_Request(url)
1592 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1593 # making it impossible to download only chunk of the file (yet we need only 512kB to
1594 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1595 # that will always result in downloading the whole file that is not desirable.
1596 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1597 # to accept raw bytes and being able to download only a chunk.
1598 # It may probably better to solve this by checking Content-Type for application/octet-stream
1599 # after HEAD request finishes, but not sure if we can rely on this.
1600 request.add_header('Accept-Encoding', '*')
1601 full_response = self._request_webpage(request, video_id)
1603 first_bytes = full_response.read(512)
1605 # Is it an M3U playlist?
1606 if first_bytes.startswith(b'#EXTM3U'):
1607 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1608 self._sort_formats(info_dict['formats'])
1611 # Maybe it's a direct link to a video?
1612 # Be careful not to download the whole thing!
1613 if not is_html(first_bytes):
1614 self._downloader.report_warning(
1615 'URL could be a direct video link, returning it as such.')
1622 webpage = self._webpage_read_content(
1623 full_response, url, video_id, prefix=first_bytes)
1625 self.report_extraction(video_id)
1627 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1629 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1630 if doc.tag == 'rss':
1631 return self._extract_rss(url, video_id, doc)
1632 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1633 smil = self._parse_smil(doc, url, video_id)
1634 self._sort_formats(smil['formats'])
1636 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1637 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1638 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1639 info_dict['formats'] = self._parse_mpd_formats(
1640 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1641 self._sort_formats(info_dict['formats'])
1643 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1644 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1645 self._sort_formats(info_dict['formats'])
1647 except compat_xml_parse_error:
1650 # Is it a Camtasia project?
1651 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1652 if camtasia_res is not None:
1655 # Sometimes embedded video player is hidden behind percent encoding
1656 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1657 # Unescaping the whole page allows to handle those cases in a generic way
1658 webpage = compat_urllib_parse_unquote(webpage)
1660 # it's tempting to parse this further, but you would
1661 # have to take into account all the variations like
1662 # Video Title - Site Name
1663 # Site Name | Video Title
1664 # Video Title - Tagline | Site Name
1665 # and so on and so forth; it's just not practical
1666 video_title = self._og_search_title(
1667 webpage, default=None) or self._html_search_regex(
1668 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1671 # Try to detect age limit automatically
1672 age_limit = self._rta_search(webpage)
1673 # And then there are the jokers who advertise that they use RTA,
1674 # but actually don't.
1675 AGE_LIMIT_MARKERS = [
1676 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1678 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1681 # video uploader is domain name
1682 video_uploader = self._search_regex(
1683 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1685 video_description = self._og_search_description(webpage, default=None)
1686 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1689 def _playlist_from_matches(matches, getter=None, ie=None):
1691 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1693 return self.playlist_result(
1694 urlrs, playlist_id=video_id, playlist_title=video_title)
1696 # Look for Brightcove Legacy Studio embeds
1697 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1699 self.to_screen('Brightcove video detected.')
1702 'url': smuggle_url(bc_url, {'Referer': url}),
1703 'ie_key': 'BrightcoveLegacy'
1704 } for bc_url in bc_urls]
1707 '_type': 'playlist',
1708 'title': video_title,
1713 # Look for Brightcove New Studio embeds
1714 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1716 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1718 # Look for ThePlatform embeds
1719 tp_urls = ThePlatformIE._extract_urls(webpage)
1721 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1723 # Look for Vessel embeds
1724 vessel_urls = VesselIE._extract_urls(webpage)
1726 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1728 # Look for embedded rtl.nl player
1729 matches = re.findall(
1730 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1733 return _playlist_from_matches(matches, ie='RtlNl')
1735 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1736 if vimeo_url is not None:
1737 return self.url_result(vimeo_url)
1739 vid_me_embed_url = self._search_regex(
1740 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1741 webpage, 'vid.me embed', default=None)
1742 if vid_me_embed_url is not None:
1743 return self.url_result(vid_me_embed_url, 'Vidme')
1745 # Look for embedded YouTube player
1746 matches = re.findall(r'''(?x)
1755 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1759 return _playlist_from_matches(
1760 matches, lambda m: unescapeHTML(m[1]))
1762 # Look for lazyYT YouTube embed
1763 matches = re.findall(
1764 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1766 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1768 # Look for Wordpress "YouTube Video Importer" plugin
1769 matches = re.findall(r'''(?x)<div[^>]+
1770 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1771 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1773 return _playlist_from_matches(matches, lambda m: m[-1])
1775 matches = DailymotionIE._extract_urls(webpage)
1777 return _playlist_from_matches(matches)
1779 # Look for embedded Dailymotion playlist player (#3822)
1781 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1783 playlists = re.findall(
1784 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1786 return _playlist_from_matches(
1787 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1789 # Look for embedded Wistia player
1791 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1793 embed_url = self._proto_relative_url(
1794 unescapeHTML(match.group('url')))
1796 '_type': 'url_transparent',
1799 'uploader': video_uploader,
1802 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1805 '_type': 'url_transparent',
1806 'url': 'wistia:%s' % match.group('id'),
1808 'uploader': video_uploader,
1813 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1814 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1817 return self.url_result(self._proto_relative_url(
1818 'wistia:%s' % match.group('id')), 'Wistia')
1820 # Look for SVT player
1821 svt_url = SVTIE._extract_url(webpage)
1823 return self.url_result(svt_url, 'SVT')
1825 # Look for embedded condenast player
1826 matches = re.findall(
1827 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1831 '_type': 'playlist',
1834 'ie_key': 'CondeNast',
1836 } for ma in matches],
1837 'title': video_title,
1841 # Look for Bandcamp pages with custom domain
1842 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1843 if mobj is not None:
1844 burl = unescapeHTML(mobj.group(1))
1845 # Don't set the extractor because it can be a track url or an album
1846 return self.url_result(burl)
1848 # Look for embedded Vevo player
1850 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1851 if mobj is not None:
1852 return self.url_result(mobj.group('url'))
1854 # Look for embedded Viddler player
1856 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1858 if mobj is not None:
1859 return self.url_result(mobj.group('url'))
1861 # Look for NYTimes player
1863 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1865 if mobj is not None:
1866 return self.url_result(mobj.group('url'))
1868 # Look for Libsyn player
1870 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1871 if mobj is not None:
1872 return self.url_result(mobj.group('url'))
1874 # Look for Ooyala videos
1875 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1876 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1877 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1878 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1879 if mobj is not None:
1880 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1882 # Look for multiple Ooyala embeds on SBN network websites
1883 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1884 if mobj is not None:
1885 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1887 return _playlist_from_matches(
1888 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1890 # Look for Aparat videos
1891 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1892 if mobj is not None:
1893 return self.url_result(mobj.group(1), 'Aparat')
1895 # Look for MPORA videos
1896 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1897 if mobj is not None:
1898 return self.url_result(mobj.group(1), 'Mpora')
1900 # Look for embedded NovaMov-based player
1902 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1903 (?P<url>http://(?:(?:embed|www)\.)?
1905 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1906 videoweed\.(?:es|com)|
1907 movshare\.(?:net|sx|ag)|
1908 divxstage\.(?:eu|net|ch|co|at|ag))
1909 /embed\.php.+?)\1''', webpage)
1910 if mobj is not None:
1911 return self.url_result(mobj.group('url'))
1913 # Look for embedded Facebook player
1914 facebook_url = FacebookIE._extract_url(webpage)
1915 if facebook_url is not None:
1916 return self.url_result(facebook_url, 'Facebook')
1918 # Look for embedded VK player
1919 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1920 if mobj is not None:
1921 return self.url_result(mobj.group('url'), 'VK')
1923 # Look for embedded Odnoklassniki player
1924 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1925 if mobj is not None:
1926 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1928 # Look for embedded ivi player
1929 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1930 if mobj is not None:
1931 return self.url_result(mobj.group('url'), 'Ivi')
1933 # Look for embedded Huffington Post player
1935 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1936 if mobj is not None:
1937 return self.url_result(mobj.group('url'), 'HuffPost')
1940 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1941 if mobj is not None:
1942 return self.url_result(mobj.group('url'))
1943 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1944 if mobj is not None:
1945 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1947 # Look for funnyordie embed
1948 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1950 return _playlist_from_matches(
1951 matches, getter=unescapeHTML, ie='FunnyOrDie')
1953 # Look for BBC iPlayer embed
1954 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1956 return _playlist_from_matches(matches, ie='BBCCoUk')
1958 # Look for embedded RUTV player
1959 rutv_url = RUTVIE._extract_url(webpage)
1961 return self.url_result(rutv_url, 'RUTV')
1963 # Look for embedded TVC player
1964 tvc_url = TVCIE._extract_url(webpage)
1966 return self.url_result(tvc_url, 'TVC')
1968 # Look for embedded SportBox player
1969 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1971 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1973 # Look for embedded PornHub player
1974 pornhub_url = PornHubIE._extract_url(webpage)
1976 return self.url_result(pornhub_url, 'PornHub')
1978 # Look for embedded XHamster player
1979 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1981 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1983 # Look for embedded TNAFlixNetwork player
1984 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1986 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1988 # Look for embedded Tvigle player
1990 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1991 if mobj is not None:
1992 return self.url_result(mobj.group('url'), 'Tvigle')
1994 # Look for embedded TED player
1996 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1997 if mobj is not None:
1998 return self.url_result(mobj.group('url'), 'TED')
2000 # Look for embedded Ustream videos
2002 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
2003 if mobj is not None:
2004 return self.url_result(mobj.group('url'), 'Ustream')
2006 # Look for embedded arte.tv player
2008 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2010 if mobj is not None:
2011 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2013 # Look for embedded francetv player
2015 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2017 if mobj is not None:
2018 return self.url_result(mobj.group('url'))
2020 # Look for embedded smotri.com player
2021 smotri_url = SmotriIE._extract_url(webpage)
2023 return self.url_result(smotri_url, 'Smotri')
2025 # Look for embedded Myvi.ru player
2026 myvi_url = MyviIE._extract_url(webpage)
2028 return self.url_result(myvi_url)
2030 # Look for embedded soundcloud player
2031 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2033 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2035 # Look for embedded mtvservices player
2036 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2038 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2040 # Look for embedded yahoo player
2042 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2044 if mobj is not None:
2045 return self.url_result(mobj.group('url'), 'Yahoo')
2047 # Look for embedded sbs.com.au player
2051 <meta\s+property="og:video"\s+content=|
2054 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2056 if mobj is not None:
2057 return self.url_result(mobj.group('url'), 'SBS')
2059 # Look for embedded Cinchcast player
2061 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2063 if mobj is not None:
2064 return self.url_result(mobj.group('url'), 'Cinchcast')
2067 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2071 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2073 if mobj is not None:
2074 return self.url_result(mobj.group('url'), 'MLB')
2077 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2079 if mobj is not None:
2080 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2083 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2085 if mobj is not None:
2086 return self.url_result(mobj.group('url'), 'Livestream')
2088 # Look for Zapiks embed
2090 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2091 if mobj is not None:
2092 return self.url_result(mobj.group('url'), 'Zapiks')
2094 # Look for Kaltura embeds
2095 kaltura_url = KalturaIE._extract_url(webpage)
2097 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2099 # Look for Eagle.Platform embeds
2100 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2101 if eagleplatform_url:
2102 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2104 # Look for ClipYou (uses Eagle.Platform) embeds
2106 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2107 if mobj is not None:
2108 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2110 # Look for Pladform embeds
2111 pladform_url = PladformIE._extract_url(webpage)
2113 return self.url_result(pladform_url)
2115 # Look for Videomore embeds
2116 videomore_url = VideomoreIE._extract_url(webpage)
2118 return self.url_result(videomore_url)
2120 # Look for Playwire embeds
2122 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2123 if mobj is not None:
2124 return self.url_result(mobj.group('url'))
2126 # Look for 5min embeds
2128 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2129 if mobj is not None:
2130 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2132 # Look for Crooks and Liars embeds
2134 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2135 if mobj is not None:
2136 return self.url_result(mobj.group('url'))
2138 # Look for NBC Sports VPlayer embeds
2139 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2141 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2143 # Look for NBC News embeds
2144 nbc_news_embed_url = re.search(
2145 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2146 if nbc_news_embed_url:
2147 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2149 # Look for Google Drive embeds
2150 google_drive_url = GoogleDriveIE._extract_url(webpage)
2151 if google_drive_url:
2152 return self.url_result(google_drive_url, 'GoogleDrive')
2154 # Look for UDN embeds
2156 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2157 if mobj is not None:
2158 return self.url_result(
2159 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2161 # Look for Senate ISVP iframe
2162 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2164 return self.url_result(senate_isvp_url, 'SenateISVP')
2166 # Look for Dailymotion Cloud videos
2167 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2169 return self.url_result(dmcloud_url, 'DailymotionCloud')
2171 # Look for OnionStudios embeds
2172 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2173 if onionstudios_url:
2174 return self.url_result(onionstudios_url)
2176 # Look for ViewLift embeds
2177 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2179 return self.url_result(viewlift_url)
2181 # Look for JWPlatform embeds
2182 jwplatform_url = JWPlatformIE._extract_url(webpage)
2184 return self.url_result(jwplatform_url, 'JWPlatform')
2186 # Look for ScreenwaveMedia embeds
2187 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2188 if mobj is not None:
2189 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2191 # Look for Digiteka embeds
2192 digiteka_url = DigitekaIE._extract_url(webpage)
2194 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2196 # Look for Arkena embeds
2197 arkena_url = ArkenaIE._extract_url(webpage)
2199 return self.url_result(arkena_url, ArkenaIE.ie_key())
2201 # Look for Limelight embeds
2202 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2206 'Channel': 'channel',
2207 'ChannelList': 'channel_list',
2209 return self.url_result('limelight:%s:%s' % (
2210 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2212 # Look for AdobeTVVideo embeds
2214 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2216 if mobj is not None:
2217 return self.url_result(
2218 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2221 # Look for Vine embeds
2223 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2225 if mobj is not None:
2226 return self.url_result(
2227 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2229 # Look for VODPlatform embeds
2231 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vod-platform\.net/embed/[^/?#]+)',
2233 if mobj is not None:
2234 return self.url_result(
2235 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'VODPlatform')
2237 # Look for Instagram embeds
2238 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2239 if instagram_embed_url is not None:
2240 return self.url_result(
2241 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2243 # Look for LiveLeak embeds
2244 liveleak_url = LiveLeakIE._extract_url(webpage)
2246 return self.url_result(liveleak_url, 'LiveLeak')
2248 # Look for 3Q SDN embeds
2249 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2252 '_type': 'url_transparent',
2253 'ie_key': ThreeQSDNIE.ie_key(),
2254 'url': self._proto_relative_url(threeqsdn_url),
2255 'title': video_title,
2256 'description': video_description,
2257 'thumbnail': video_thumbnail,
2258 'uploader': video_uploader,
2261 # Look for VBOX7 embeds
2262 vbox7_url = Vbox7IE._extract_url(webpage)
2264 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2266 # Look for DBTV embeds
2267 dbtv_urls = DBTVIE._extract_urls(webpage)
2269 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2271 # Looking for http://schema.org/VideoObject
2272 json_ld = self._search_json_ld(
2273 webpage, video_id, default={}, expected_type='VideoObject')
2274 if json_ld.get('url'):
2276 'title': video_title or info_dict['title'],
2277 'description': video_description,
2278 'thumbnail': video_thumbnail,
2279 'age_limit': age_limit
2281 info_dict.update(json_ld)
2284 def check_video(vurl):
2285 if YoutubeIE.suitable(vurl):
2287 vpath = compat_urlparse.urlparse(vurl).path
2288 vext = determine_ext(vpath)
2289 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2291 def filter_video(urls):
2292 return list(filter(check_video, urls))
2294 # Start with something easy: JW Player in SWFObject
2295 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2297 # Look for gorilla-vid style embedding
2298 found = filter_video(re.findall(r'''(?sx)
2302 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2305 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2307 # Broaden the search a little bit
2308 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2310 # Broaden the findall a little bit: JWPlayer JS loader
2311 found = filter_video(re.findall(
2312 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2315 found = filter_video(re.findall(r'''(?xs)
2316 flowplayer\("[^"]+",\s*
2318 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2319 ["']?url["']?\s*:\s*["']([^"']+)["']
2324 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2326 # Try to find twitter cards info
2327 # twitter:player:stream should be checked before twitter:player since
2328 # it is expected to contain a raw stream (see
2329 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2330 found = filter_video(re.findall(
2331 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2333 # We look for Open Graph info:
2334 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2335 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2336 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2337 if m_video_type is not None:
2338 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2341 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2343 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2345 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2346 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2349 # Look also in Refresh HTTP header
2350 refresh_header = head_response.headers.get('Refresh')
2352 # In python 2 response HTTP headers are bytestrings
2353 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2354 refresh_header = refresh_header.decode('iso-8859-1')
2355 found = re.search(REDIRECT_REGEX, refresh_header)
2357 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2358 self.report_following_redirect(new_url)
2365 # twitter:player is a https URL to iframe player that may or may not
2366 # be supported by youtube-dl thus this is checked the very last (see
2367 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2368 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2370 return self.url_result(embed_url)
2373 raise UnsupportedError(url)
2376 for video_url in orderedSet(found):
2377 video_url = unescapeHTML(video_url)
2378 video_url = video_url.replace('\\/', '/')
2379 video_url = compat_urlparse.urljoin(url, video_url)
2380 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2382 # Sometimes, jwplayer extraction will result in a YouTube URL
2383 if YoutubeIE.suitable(video_url):
2384 entries.append(self.url_result(video_url, 'Youtube'))
2387 # here's a fun little line of code for you:
2388 video_id = os.path.splitext(video_id)[0]
2392 'uploader': video_uploader,
2393 'title': video_title,
2394 'age_limit': age_limit,
2397 ext = determine_ext(video_url)
2399 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2401 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2403 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2405 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2407 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2409 entry_info_dict['url'] = video_url
2411 if entry_info_dict.get('formats'):
2412 self._sort_formats(entry_info_dict['formats'])
2414 entries.append(entry_info_dict)
2416 if len(entries) == 1:
2419 for num, e in enumerate(entries, start=1):
2420 # 'url' results don't have a title
2421 if e.get('title') is not None:
2422 e['title'] = '%s (%d)' % (e['title'], num)
2424 '_type': 'playlist',