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.'
108 'skip': 'URL invalid',
110 # Direct download with broken HEAD
112 'url': 'http://ai-radio.org:8000/radio.opus',
119 'skip_download': True, # infinite live stream
121 'expected_warnings': [
122 r'501.*Not Implemented',
126 # Direct link with incorrect MIME type
128 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
129 'md5': '4ccbebe5f36706d85221f204d7eb5913',
131 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
132 'id': '5_Lennart_Poettering_-_Systemd',
134 'title': '5_Lennart_Poettering_-_Systemd',
135 'upload_date': '20141120',
137 'expected_warnings': [
138 'URL could be a direct video link, returning it as such.'
143 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
145 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
146 'title': 'Zero Punctuation',
147 'description': 're:.*groundbreaking video review series.*'
149 'playlist_mincount': 11,
151 # RSS feed with enclosure
153 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
155 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
157 'upload_date': '20150228',
158 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
161 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
163 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
167 'title': 'Automatics, robotics and biocybernetics',
168 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
169 'upload_date': '20130627',
170 'formats': 'mincount:16',
171 'subtitles': 'mincount:1',
174 'force_generic_extractor': True,
175 'skip_download': True,
178 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
180 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
185 'formats': 'mincount:1',
188 'skip_download': True,
191 # SMIL from https://www.restudy.dk/video/play/id/1637
193 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
197 'title': 'video_1637',
198 'formats': 'mincount:3',
201 'skip_download': True,
204 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
206 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
208 'id': 'smil-service',
210 'title': 'smil-service',
211 'formats': 'mincount:1',
214 'skip_download': True,
217 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
219 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
223 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
224 'formats': 'mincount:3',
227 'skip_download': True,
230 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
232 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
234 'id': 'mZlp2ctYIUEB',
236 'title': 'Tikibad ontruimd wegens brand',
237 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
238 'thumbnail': 're:^https?://.*\.jpg$',
242 'skip_download': True,
245 # MPD from http://dash-mse-test.appspot.com/media.html
247 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
248 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
250 'id': 'car-20120827-manifest',
252 'title': 'car-20120827-manifest',
253 'formats': 'mincount:9',
254 'upload_date': '20130904',
257 'format': 'bestvideo',
260 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
262 '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',
267 'formats': 'mincount:8',
271 'skip_download': True,
273 'skip': 'video gone',
275 # m3u8 served with Content-Type: text/plain
277 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
282 'upload_date': '20140720',
283 'formats': 'mincount:11',
287 'skip_download': True,
289 'skip': 'video gone',
293 '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',
297 'upload_date': '20130224',
298 'uploader_id': 'TheVerge',
299 'description': 're:^Chris Ziegler takes a look at the\.*',
300 'uploader': 'The Verge',
301 'title': 'First Firefox OS phones side-by-side',
304 'skip_download': False,
308 # redirect in Refresh HTTP header
309 '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',
313 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
314 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
315 'upload_date': '20150917',
316 'uploader_id': 'brtvofficial',
317 'uploader': 'Boiler Room',
320 'skip_download': False,
324 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
325 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
327 'id': '13601338388002',
329 'uploader': 'www.hodiho.fr',
330 'title': 'R\u00e9gis plante sa Jeep',
333 # bandcamp page with custom domain
335 'add_ie': ['Bandcamp'],
336 'url': 'http://bronyrock.com/track/the-pony-mash',
340 'title': 'The Pony Mash',
341 'uploader': 'M_Pallante',
343 'skip': 'There is a limit of 200 free downloads / month for the test song',
345 # embedded brightcove video
346 # it also tests brightcove videos that need to set the 'Referer' in the
349 'add_ie': ['BrightcoveLegacy'],
350 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
352 'id': '2765128793001',
354 'title': 'Le cours de bourse : l’analyse technique',
355 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
356 'uploader': 'BFM BUSINESS',
359 'skip_download': True,
363 # https://github.com/rg3/youtube-dl/issues/2253
364 'url': 'http://bcove.me/i6nfkrc3',
365 'md5': '0ba9446db037002366bab3b3eb30c88c',
367 'id': '3101154703001',
369 'title': 'Still no power',
370 'uploader': 'thestar.com',
371 '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.',
373 'add_ie': ['BrightcoveLegacy'],
374 'skip': 'video gone',
377 'url': 'http://www.championat.com/video/football/v/87/87499.html',
378 'md5': 'fb973ecf6e4a78a67453647444222983',
380 'id': '3414141473001',
382 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
383 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
384 'uploader': 'Championat',
388 # https://github.com/rg3/youtube-dl/issues/3541
389 'add_ie': ['BrightcoveLegacy'],
390 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
392 'id': '3866516442001',
394 'title': 'Leer mij vrouwen kennen: Aflevering 1',
395 'description': 'Leer mij vrouwen kennen: Aflevering 1',
396 'uploader': 'SBS Broadcasting',
398 'skip': 'Restricted to Netherlands',
400 'skip_download': True, # m3u8 download
405 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
406 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
408 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
410 'title': '2cc213299525360.mov', # that's what we get
413 'add_ie': ['Ooyala'],
416 # ooyala video embedded with http://player.ooyala.com/iframe.js
417 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
419 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
421 'title': '"Steve Jobs: Man in the Machine" trailer',
422 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
426 'skip_download': True,
428 'skip': 'movie expired',
432 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
436 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
437 'upload_date': '20140225',
438 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
439 'uploader': 'Tested',
440 'uploader_id': 'testedcom',
442 # No need to test YoutubeIE here
444 'skip_download': True,
449 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
453 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
454 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
456 # HEAD requests lead to endless 301, while GET is OK
457 'expected_warnings': ['301'],
461 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
465 'title': 'Охотское море стало целиком российским',
466 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
470 'skip_download': True,
475 '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/',
479 'title': 'Дошкольное воспитание',
484 'url': 'http://www.vestifinance.ru/articles/25753',
487 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
492 'title': 'Госзаказ. День 3',
498 'title': 'Госзаказ. День 2',
504 'title': 'Госзаказ. День 1',
510 'skip_download': True,
515 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
517 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
519 'title': 'Ужастики, русский трейлер (2015)',
520 'thumbnail': 're:^https?://.*\.jpg$',
526 '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',
529 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
531 'playlist_mincount': 7,
532 # This forum does not allow <iframe> syntaxes anymore
533 # Now HTML tags are displayed as-is
534 'skip': 'No videos on this page',
538 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
539 'md5': '65fdff94098e4a607385a60c5177c638',
543 'title': 'Hidden miracles of the natural world',
544 'uploader': 'Louie Schwartzberg',
545 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
548 # Embedded Ustream video
550 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
551 'md5': '27b99cdb639c9b12a79bca876a073417',
555 'uploader': 'AU SPA: The NSA and Privacy',
556 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
559 # nowvideo embed hidden behind percent encoding
561 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
562 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
564 'id': '06e53103ca9aa',
566 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
567 'description': 'No description',
572 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
573 'md5': '7653032cbb25bf6c80d80f217055fa43',
575 'id': '048195-004_PLUS7-F',
578 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
579 'upload_date': '20140320',
582 'skip_download': 'Requires rtmpdump'
584 'skip': 'video gone',
588 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
592 'title': 'Alcaline, le concert avec Calogero',
593 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
594 'upload_date': '20150226',
595 'timestamp': 1424989860,
600 'skip_download': True,
602 'expected_warnings': [
608 'url': 'http://www.wired.com/2014/04/honda-asimo/',
609 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
611 'id': '53501be369702d3275860000',
613 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
618 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
619 'md5': '441aeeb82eb72c422c7f14ec533999cd',
621 'id': 'k2mm4bCdJ6CQ2i7c8o2',
623 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
624 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
626 'uploader_id': 'xgditw',
627 'upload_date': '20140425',
628 'timestamp': 1398441542,
630 'add_ie': ['Dailymotion'],
634 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
638 'title': 'The NBL Auction 2014',
639 'uploader': 'BADMINTON England',
640 'uploader_id': 'BADMINTONEvents',
641 'upload_date': '20140603',
642 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
644 'add_ie': ['Youtube'],
646 'skip_download': True,
651 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
652 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
654 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
656 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
657 'description': 'Two valets share their love for movie star Liam Neesons.',
658 'timestamp': 1349922600,
659 'upload_date': '20121011',
662 # YouTube embed via <data-embed-url="">
664 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
668 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
669 'uploader': 'Gameloft',
670 'uploader_id': 'gameloft',
671 'upload_date': '20140828',
672 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
675 'skip_download': True,
680 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
682 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
684 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
685 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
690 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
692 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
693 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
699 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
704 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
705 'md5': '9d65602bf31c6e20014319c7d07fba27',
707 'id': '5123ea6d5e5a7',
710 'uploader': 'www.handjobhub.com',
711 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
714 # Multiple brightcove videos
715 # https://github.com/rg3/youtube-dl/issues/2283
717 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
719 'id': 'always-never',
720 'title': 'Always / Never - The New Yorker',
724 'extract_flat': False,
725 'skip_download': True,
730 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
731 'md5': '96f09a37e44da40dd083e12d9a683327',
735 'title': 'Ump changes call to ball',
736 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
738 'timestamp': 1401537900,
739 'upload_date': '20140531',
740 'thumbnail': 're:^https?://.*\.jpg$',
745 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
746 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
750 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
751 'description': 'a Paywall Videos video from Remilon',
753 'uploader': 'study.com',
754 'timestamp': 1459678540,
755 'upload_date': '20160403',
756 'filesize': 24687186,
760 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
761 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
765 'title': 'Conversation about Hexagonal Rails Part 1',
766 'description': 'a Martin Fowler video from ThoughtWorks',
768 'uploader': 'thoughtworks.wistia.com',
769 'timestamp': 1401832161,
770 'upload_date': '20140603',
773 # Wistia standard embed (async)
775 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
779 'title': 'Drip Brennan Dunn Workshop',
780 'description': 'a JV Webinars video from getdrip-1',
782 'timestamp': 1463607249,
783 'upload_date': '20160518',
786 'skip_download': True,
791 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
795 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
796 'uploader': 'Sophos Security',
797 'title': 'Chet Chat 171 - Oct 29, 2014',
798 'upload_date': '20141029',
801 # Soundcloud multiple embeds
803 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
806 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
808 'playlist_mincount': 7,
812 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
816 'upload_date': '20141112',
817 'title': 'Rosetta #CometLanding webcast HL 10',
820 # Another Livestream embed, without 'new.' in URL
822 'url': 'https://www.freespeech.org/',
826 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
830 'skip_download': True,
835 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
838 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
840 'playlist_mincount': 2,
844 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
848 'upload_date': '20141126',
849 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
854 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
856 'id': '730m_DandD_1901_512k',
858 'uploader': 'www.abc.net.au',
859 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
862 # embedded viddler video
864 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
868 'uploader': 'deadspin',
869 'title': 'WALL-TO-GORTAT',
870 'timestamp': 1422285291,
871 'upload_date': '20150126',
873 'add_ie': ['Viddler'],
877 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
881 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
882 'description': 'md5:601cb790edd05908957dae8aaa866465',
883 'upload_date': '20150220',
885 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
889 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
893 'upload_date': '20150212',
894 'uploader': 'The National Archives UK',
895 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
896 'uploader_id': 'NationalArchives08',
897 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
902 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
903 'playlist_mincount': 5,
905 'id': 'aanslagen-kopenhagen',
906 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
911 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
915 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
918 # Kaltura embed (different embed code)
920 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
924 'upload_date': '20150127',
925 'uploader_id': 'PremierMedia',
927 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
930 # Kaltura embed protected with referrer
932 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
936 'title': 'Violetta - Achter De Schermen - Ruggero',
937 'description': 'Achter de schermen met Ruggero',
938 'timestamp': 1435133761,
939 'upload_date': '20150624',
940 'uploader_id': 'echojecka',
943 # Kaltura embed with single quotes
945 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
950 'timestamp': 1355743100,
951 'upload_date': '20121217',
952 'uploader_id': 'batchUser',
954 'add_ie': ['Kaltura'],
957 # Kaltura embedded via quoted entry_id
958 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
962 'title': '06_matthew_brender_raj_dutt',
963 'timestamp': 1466638791,
964 'upload_date': '20160622',
966 'add_ie': ['Kaltura'],
967 'expected_warnings': [
968 'Could not send HEAD request'
971 'skip_download': True,
974 # Eagle.Platform embed (generic URL)
976 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
977 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
981 'title': 'Навальный вышел на свободу',
982 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
983 'thumbnail': 're:^https?://.*\.jpg$',
989 # ClipYou (Eagle.Platform) embed (custom URL)
991 'url': 'http://muz-tv.ru/play/7129/',
992 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
996 'title': "'O Sole Mio",
997 'thumbnail': 're:^https?://.*\.jpg$',
1004 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1008 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1009 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1010 'thumbnail': 're:^https?://.*\.jpg$',
1017 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1021 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1022 'thumbnail': 're:^https?://.*\.png$',
1028 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1029 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1033 'title': 'Facebook Creates "On This Day" | Crunch Report',
1038 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1042 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1047 # Crooks and Liars embed
1049 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1053 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1054 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1055 'timestamp': 1428207000,
1056 'upload_date': '20150405',
1057 'uploader': 'Heather',
1060 # Crooks and Liars external embed
1062 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1064 'id': 'MTE3MjUtMzQ2MzA',
1066 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1067 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1068 'timestamp': 1265032391,
1069 'upload_date': '20100201',
1070 'uploader': 'Heather',
1073 # NBC Sports vplayer embed
1075 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1077 'id': 'ln7x1qSThw4k',
1079 'title': "PFT Live: New leader in the 'new-look' defense",
1080 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1081 'uploader': 'NBCU-SPORTS',
1082 'upload_date': '20140107',
1083 'timestamp': 1389118457,
1088 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1089 'md5': '1aa589c675898ae6d37a17913cf68d66',
1091 'id': '701714499682',
1093 'title': 'PREVIEW: On Assignment: David Letterman',
1094 '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.',
1099 'url': 'https://video.udn.com/news/300346',
1100 'md5': 'fd2060e988c326991037b9aff9df21a6',
1104 'title': '中一中男師變性 全校師生力挺',
1105 'thumbnail': 're:^https?://.*\.jpg$',
1109 'skip_download': True,
1114 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1116 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1118 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1119 'title': 'This is what separates the Excel masters from the wannabes',
1120 'duration': 191.933,
1124 'skip_download': True,
1127 # Brightcove URL in single quotes
1129 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1130 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1132 'id': '4255764656001',
1134 'title': 'SN Presents: Russell Martin, World Citizen',
1135 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1136 'uploader': 'Rogers Sportsnet',
1137 'uploader_id': '1704050871',
1138 'upload_date': '20150525',
1139 'timestamp': 1432570283,
1142 # Dailymotion Cloud video
1144 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1145 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1149 'title': 'Sauvons les abeilles ! - Le débat',
1150 'description': 'md5:d9082128b1c5277987825d684939ca26',
1151 'thumbnail': 're:^https?://.*\.jpe?g$',
1152 'timestamp': 1434970506,
1153 'upload_date': '20150622',
1154 'uploader': 'Public Sénat',
1155 'uploader_id': 'xa9gza',
1158 # OnionStudios embed
1160 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1164 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1165 'thumbnail': 're:^https?://.*\.jpe?g$',
1166 'uploader': 'ClickHole',
1167 'uploader_id': 'clickhole',
1172 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1174 'id': '74849a00-85a9-11e1-9660-123139220831',
1176 'title': '#whilewewatch',
1179 # AdobeTVVideo embed
1181 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1182 'md5': '43662b577c018ad707a63766462b1e87',
1186 'title': 'New experience with Acrobat DC',
1187 'description': 'New experience with Acrobat DC',
1188 'duration': 248.667,
1191 # ScreenwaveMedia embed
1193 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1194 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1196 'id': 'cinemasnob-55d26273809dd',
1198 'title': 'cinemasnob',
1201 # BrightcoveInPageEmbed embed
1203 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1205 'id': '4238694884001',
1207 'title': 'Tabletop: Dread, Last Thoughts',
1208 'description': 'Tabletop: Dread, Last Thoughts',
1212 # JWPlayer with M3U8
1214 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1218 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1219 'uploader': 'ren.tv',
1223 'skip_download': True,
1226 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1227 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1229 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1231 'id': '4785848093001',
1233 'title': 'The Cardinal Pell Interview',
1234 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1235 'uploader': 'GlobeCast Australia - GlobeStream',
1236 'uploader_id': '2733773828001',
1237 'upload_date': '20160304',
1238 'timestamp': 1457083087,
1242 'skip_download': True,
1245 # Another form of arte.tv embed
1247 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1248 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1250 'id': '030273-562_PLUS7-F',
1252 'title': 'ARTE Reportage - Nulle part, en France',
1253 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1254 'upload_date': '20160409',
1259 'url': 'http://www.wykop.pl/link/3088787/',
1260 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1262 'id': '874_1459135191',
1264 'title': 'Man shows poor quality of new apartment building',
1265 'description': 'The wall is like a sand pile.',
1266 'uploader': 'Lake8737',
1269 # Duplicated embedded video URLs
1271 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1273 'id': '149298443_480_16c25b74_2',
1275 'title': 'vs. Blue Orange Spring Game',
1276 'uploader': 'www.hudl.com',
1279 # twitter:player:stream embed
1281 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1285 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1286 'uploader': 'www.rtl.be',
1290 'skip_download': True,
1293 # twitter:player embed
1295 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1296 'md5': 'a3e0df96369831de324f0778e126653c',
1298 'id': '4909620399001',
1300 'title': 'What Do Black Holes Sound Like?',
1301 'description': 'what do black holes sound like',
1302 'upload_date': '20160524',
1303 'uploader_id': '29913724001',
1304 'timestamp': 1464107587,
1305 'uploader': 'TheAtlantic',
1307 'add_ie': ['BrightcoveLegacy'],
1309 # Facebook <iframe> embed
1311 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1312 'md5': 'fbcde74f534176ecb015849146dd3aee',
1314 'id': '599637780109885',
1316 'title': 'Facebook video #599637780109885',
1319 # Facebook API embed
1321 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1322 'md5': 'a47372ee61b39a7b90287094d447d94e',
1324 'id': '10153467542406923',
1326 'title': 'Facebook video #10153467542406923',
1329 # Wordpress "YouTube Video Importer" plugin
1331 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1332 'md5': 'd16797741b560b485194eddda8121b48',
1334 'id': 'HNTXWDXV9Is',
1336 'title': 'Blue Devils Drumline Stanford lot 2016',
1337 'upload_date': '20160627',
1338 'uploader_id': 'GENOCIDE8GENERAL10',
1339 'uploader': 'cylus cyrus',
1343 # video stored on custom kaltura server
1344 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1345 'md5': '537617d06e64dfed891fa1593c4b30cc',
1349 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1350 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1351 'uploader_id': 'videos.expansion@el-mundo.net',
1352 'upload_date': '20150429',
1353 'timestamp': 1430303472,
1355 'add_ie': ['Kaltura'],
1358 # Non-standard Vimeo embed
1359 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1360 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1364 'title': 'Understanding the web - Teaser',
1365 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1366 'upload_date': '20151214',
1367 'uploader': 'OpenClassrooms',
1368 'uploader_id': 'openclassrooms',
1370 'add_ie': ['Vimeo'],
1373 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1374 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1376 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1378 'title': 'Big Buck Bunny',
1379 'description': 'Royalty free test video',
1380 'timestamp': 1432816365,
1381 'upload_date': '20150528',
1385 'skip_download': True,
1387 'add_ie': [ArkenaIE.ie_key()],
1390 '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/',
1394 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1397 'skip_download': True,
1399 'add_ie': [Vbox7IE.ie_key()],
1403 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1406 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1408 'playlist_mincount': 3,
1411 # # TODO: find another test
1412 # # http://schema.org/VideoObject
1413 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1414 # 'md5': '888dcf08b7ea671381f00fab74692755',
1416 # 'id': 'nyvTSJMKId',
1418 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1419 # 'description': '#love for cats.',
1420 # 'timestamp': 1461244995,
1421 # 'upload_date': '20160421',
1424 # 'force_generic_extractor': True,
1429 def report_following_redirect(self, new_url):
1430 """Report information extraction."""
1431 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1433 def _extract_rss(self, url, video_id, doc):
1434 playlist_title = doc.find('./channel/title').text
1435 playlist_desc_el = doc.find('./channel/description')
1436 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1439 for it in doc.findall('./channel/item'):
1440 next_url = xpath_text(it, 'link', fatal=False)
1442 enclosure_nodes = it.findall('./enclosure')
1443 for e in enclosure_nodes:
1444 next_url = e.attrib.get('url')
1454 'title': it.find('title').text,
1458 '_type': 'playlist',
1460 'title': playlist_title,
1461 'description': playlist_desc,
1465 def _extract_camtasia(self, url, video_id, webpage):
1466 """ Returns None if no camtasia video can be found. """
1468 camtasia_cfg = self._search_regex(
1469 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1470 webpage, 'camtasia configuration file', default=None)
1471 if camtasia_cfg is None:
1474 title = self._html_search_meta('DC.title', webpage, fatal=True)
1476 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1477 camtasia_cfg = self._download_xml(
1478 camtasia_url, video_id,
1479 note='Downloading camtasia configuration',
1480 errnote='Failed to download camtasia configuration')
1481 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1484 for n in fileset_node.getchildren():
1485 url_n = n.find('./uri')
1490 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1491 'title': '%s - %s' % (title, n.tag),
1492 'url': compat_urlparse.urljoin(url, url_n.text),
1493 'duration': float_or_none(n.find('./duration').text),
1497 '_type': 'playlist',
1502 def _real_extract(self, url):
1503 if url.startswith('//'):
1506 'url': self.http_scheme() + url,
1509 parsed_url = compat_urlparse.urlparse(url)
1510 if not parsed_url.scheme:
1511 default_search = self._downloader.params.get('default_search')
1512 if default_search is None:
1513 default_search = 'fixup_error'
1515 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1517 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1518 return self.url_result('http://' + url)
1519 elif default_search != 'fixup_error':
1520 if default_search == 'auto_warning':
1521 if re.match(r'^(?:url|URL)$', url):
1522 raise ExtractorError(
1523 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1526 self._downloader.report_warning(
1527 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1528 return self.url_result('ytsearch:' + url)
1530 if default_search in ('error', 'fixup_error'):
1531 raise ExtractorError(
1532 '%r is not a valid URL. '
1533 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1534 % (url, url), expected=True)
1536 if ':' not in default_search:
1537 default_search += ':'
1538 return self.url_result(default_search + url)
1540 url, smuggled_data = unsmuggle_url(url)
1541 force_videoid = None
1542 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1543 if smuggled_data and 'force_videoid' in smuggled_data:
1544 force_videoid = smuggled_data['force_videoid']
1545 video_id = force_videoid
1547 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1549 self.to_screen('%s: Requesting header' % video_id)
1551 head_req = HEADRequest(url)
1552 head_response = self._request_webpage(
1554 note=False, errnote='Could not send HEAD request to %s' % url,
1557 if head_response is not False:
1558 # Check for redirect
1559 new_url = head_response.geturl()
1561 self.report_following_redirect(new_url)
1563 new_url = smuggle_url(
1564 new_url, {'force_videoid': force_videoid})
1565 return self.url_result(new_url)
1567 full_response = None
1568 if head_response is False:
1569 request = sanitized_Request(url)
1570 request.add_header('Accept-Encoding', '*')
1571 full_response = self._request_webpage(request, video_id)
1572 head_response = full_response
1576 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1577 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1580 # Check for direct link to a video
1581 content_type = head_response.headers.get('Content-Type', '').lower()
1582 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1584 format_id = m.group('format_id')
1585 if format_id.endswith('mpegurl'):
1586 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1587 elif format_id == 'f4m':
1588 formats = self._extract_f4m_formats(url, video_id)
1591 'format_id': m.group('format_id'),
1593 'vcodec': 'none' if m.group('type') == 'audio' else None
1595 info_dict['direct'] = True
1596 self._sort_formats(formats)
1597 info_dict['formats'] = formats
1600 if not self._downloader.params.get('test', False) and not is_intentional:
1601 force = self._downloader.params.get('force_generic_extractor', False)
1602 self._downloader.report_warning(
1603 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1605 if not full_response:
1606 request = sanitized_Request(url)
1607 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1608 # making it impossible to download only chunk of the file (yet we need only 512kB to
1609 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1610 # that will always result in downloading the whole file that is not desirable.
1611 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1612 # to accept raw bytes and being able to download only a chunk.
1613 # It may probably better to solve this by checking Content-Type for application/octet-stream
1614 # after HEAD request finishes, but not sure if we can rely on this.
1615 request.add_header('Accept-Encoding', '*')
1616 full_response = self._request_webpage(request, video_id)
1618 first_bytes = full_response.read(512)
1620 # Is it an M3U playlist?
1621 if first_bytes.startswith(b'#EXTM3U'):
1622 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1623 self._sort_formats(info_dict['formats'])
1626 # Maybe it's a direct link to a video?
1627 # Be careful not to download the whole thing!
1628 if not is_html(first_bytes):
1629 self._downloader.report_warning(
1630 'URL could be a direct video link, returning it as such.')
1637 webpage = self._webpage_read_content(
1638 full_response, url, video_id, prefix=first_bytes)
1640 self.report_extraction(video_id)
1642 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1644 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1645 if doc.tag == 'rss':
1646 return self._extract_rss(url, video_id, doc)
1647 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1648 smil = self._parse_smil(doc, url, video_id)
1649 self._sort_formats(smil['formats'])
1651 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1652 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1653 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1654 info_dict['formats'] = self._parse_mpd_formats(
1655 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1656 self._sort_formats(info_dict['formats'])
1658 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1659 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1660 self._sort_formats(info_dict['formats'])
1662 except compat_xml_parse_error:
1665 # Is it a Camtasia project?
1666 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1667 if camtasia_res is not None:
1670 # Sometimes embedded video player is hidden behind percent encoding
1671 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1672 # Unescaping the whole page allows to handle those cases in a generic way
1673 webpage = compat_urllib_parse_unquote(webpage)
1675 # it's tempting to parse this further, but you would
1676 # have to take into account all the variations like
1677 # Video Title - Site Name
1678 # Site Name | Video Title
1679 # Video Title - Tagline | Site Name
1680 # and so on and so forth; it's just not practical
1681 video_title = self._og_search_title(
1682 webpage, default=None) or self._html_search_regex(
1683 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1686 # Try to detect age limit automatically
1687 age_limit = self._rta_search(webpage)
1688 # And then there are the jokers who advertise that they use RTA,
1689 # but actually don't.
1690 AGE_LIMIT_MARKERS = [
1691 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1693 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1696 # video uploader is domain name
1697 video_uploader = self._search_regex(
1698 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1700 video_description = self._og_search_description(webpage, default=None)
1701 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1704 def _playlist_from_matches(matches, getter=None, ie=None):
1706 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1708 return self.playlist_result(
1709 urlrs, playlist_id=video_id, playlist_title=video_title)
1711 # Look for Brightcove Legacy Studio embeds
1712 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1714 self.to_screen('Brightcove video detected.')
1717 'url': smuggle_url(bc_url, {'Referer': url}),
1718 'ie_key': 'BrightcoveLegacy'
1719 } for bc_url in bc_urls]
1722 '_type': 'playlist',
1723 'title': video_title,
1728 # Look for Brightcove New Studio embeds
1729 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1731 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1733 # Look for ThePlatform embeds
1734 tp_urls = ThePlatformIE._extract_urls(webpage)
1736 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1738 # Look for Vessel embeds
1739 vessel_urls = VesselIE._extract_urls(webpage)
1741 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1743 # Look for embedded rtl.nl player
1744 matches = re.findall(
1745 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1748 return _playlist_from_matches(matches, ie='RtlNl')
1750 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1751 if vimeo_url is not None:
1752 return self.url_result(vimeo_url)
1754 vid_me_embed_url = self._search_regex(
1755 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1756 webpage, 'vid.me embed', default=None)
1757 if vid_me_embed_url is not None:
1758 return self.url_result(vid_me_embed_url, 'Vidme')
1760 # Look for embedded YouTube player
1761 matches = re.findall(r'''(?x)
1770 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1774 return _playlist_from_matches(
1775 matches, lambda m: unescapeHTML(m[1]))
1777 # Look for lazyYT YouTube embed
1778 matches = re.findall(
1779 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1781 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1783 # Look for Wordpress "YouTube Video Importer" plugin
1784 matches = re.findall(r'''(?x)<div[^>]+
1785 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1786 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1788 return _playlist_from_matches(matches, lambda m: m[-1])
1790 matches = DailymotionIE._extract_urls(webpage)
1792 return _playlist_from_matches(matches)
1794 # Look for embedded Dailymotion playlist player (#3822)
1796 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1798 playlists = re.findall(
1799 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1801 return _playlist_from_matches(
1802 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1804 # Look for embedded Wistia player
1806 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1808 embed_url = self._proto_relative_url(
1809 unescapeHTML(match.group('url')))
1811 '_type': 'url_transparent',
1814 'uploader': video_uploader,
1817 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1820 '_type': 'url_transparent',
1821 'url': 'wistia:%s' % match.group('id'),
1823 'uploader': video_uploader,
1828 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1829 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1832 return self.url_result(self._proto_relative_url(
1833 'wistia:%s' % match.group('id')), 'Wistia')
1835 # Look for SVT player
1836 svt_url = SVTIE._extract_url(webpage)
1838 return self.url_result(svt_url, 'SVT')
1840 # Look for embedded condenast player
1841 matches = re.findall(
1842 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1846 '_type': 'playlist',
1849 'ie_key': 'CondeNast',
1851 } for ma in matches],
1852 'title': video_title,
1856 # Look for Bandcamp pages with custom domain
1857 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1858 if mobj is not None:
1859 burl = unescapeHTML(mobj.group(1))
1860 # Don't set the extractor because it can be a track url or an album
1861 return self.url_result(burl)
1863 # Look for embedded Vevo player
1865 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1866 if mobj is not None:
1867 return self.url_result(mobj.group('url'))
1869 # Look for embedded Viddler player
1871 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1873 if mobj is not None:
1874 return self.url_result(mobj.group('url'))
1876 # Look for NYTimes player
1878 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1880 if mobj is not None:
1881 return self.url_result(mobj.group('url'))
1883 # Look for Libsyn player
1885 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1886 if mobj is not None:
1887 return self.url_result(mobj.group('url'))
1889 # Look for Ooyala videos
1890 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1891 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1892 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1893 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1894 if mobj is not None:
1895 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1897 # Look for multiple Ooyala embeds on SBN network websites
1898 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1899 if mobj is not None:
1900 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1902 return _playlist_from_matches(
1903 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1905 # Look for Aparat videos
1906 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1907 if mobj is not None:
1908 return self.url_result(mobj.group(1), 'Aparat')
1910 # Look for MPORA videos
1911 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1912 if mobj is not None:
1913 return self.url_result(mobj.group(1), 'Mpora')
1915 # Look for embedded NovaMov-based player
1917 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1918 (?P<url>http://(?:(?:embed|www)\.)?
1920 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1921 videoweed\.(?:es|com)|
1922 movshare\.(?:net|sx|ag)|
1923 divxstage\.(?:eu|net|ch|co|at|ag))
1924 /embed\.php.+?)\1''', webpage)
1925 if mobj is not None:
1926 return self.url_result(mobj.group('url'))
1928 # Look for embedded Facebook player
1929 facebook_url = FacebookIE._extract_url(webpage)
1930 if facebook_url is not None:
1931 return self.url_result(facebook_url, 'Facebook')
1933 # Look for embedded VK player
1934 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1935 if mobj is not None:
1936 return self.url_result(mobj.group('url'), 'VK')
1938 # Look for embedded Odnoklassniki player
1939 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1940 if mobj is not None:
1941 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1943 # Look for embedded ivi player
1944 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1945 if mobj is not None:
1946 return self.url_result(mobj.group('url'), 'Ivi')
1948 # Look for embedded Huffington Post player
1950 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1951 if mobj is not None:
1952 return self.url_result(mobj.group('url'), 'HuffPost')
1955 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1956 if mobj is not None:
1957 return self.url_result(mobj.group('url'))
1958 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1959 if mobj is not None:
1960 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1962 # Look for funnyordie embed
1963 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1965 return _playlist_from_matches(
1966 matches, getter=unescapeHTML, ie='FunnyOrDie')
1968 # Look for BBC iPlayer embed
1969 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1971 return _playlist_from_matches(matches, ie='BBCCoUk')
1973 # Look for embedded RUTV player
1974 rutv_url = RUTVIE._extract_url(webpage)
1976 return self.url_result(rutv_url, 'RUTV')
1978 # Look for embedded TVC player
1979 tvc_url = TVCIE._extract_url(webpage)
1981 return self.url_result(tvc_url, 'TVC')
1983 # Look for embedded SportBox player
1984 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1986 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1988 # Look for embedded PornHub player
1989 pornhub_url = PornHubIE._extract_url(webpage)
1991 return self.url_result(pornhub_url, 'PornHub')
1993 # Look for embedded XHamster player
1994 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1996 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1998 # Look for embedded TNAFlixNetwork player
1999 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2001 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
2003 # Look for embedded Tvigle player
2005 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2006 if mobj is not None:
2007 return self.url_result(mobj.group('url'), 'Tvigle')
2009 # Look for embedded TED player
2011 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2012 if mobj is not None:
2013 return self.url_result(mobj.group('url'), 'TED')
2015 # Look for embedded Ustream videos
2017 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
2018 if mobj is not None:
2019 return self.url_result(mobj.group('url'), 'Ustream')
2021 # Look for embedded arte.tv player
2023 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2025 if mobj is not None:
2026 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2028 # Look for embedded francetv player
2030 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2032 if mobj is not None:
2033 return self.url_result(mobj.group('url'))
2035 # Look for embedded smotri.com player
2036 smotri_url = SmotriIE._extract_url(webpage)
2038 return self.url_result(smotri_url, 'Smotri')
2040 # Look for embedded Myvi.ru player
2041 myvi_url = MyviIE._extract_url(webpage)
2043 return self.url_result(myvi_url)
2045 # Look for embedded soundcloud player
2046 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2048 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2050 # Look for embedded mtvservices player
2051 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2053 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2055 # Look for embedded yahoo player
2057 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2059 if mobj is not None:
2060 return self.url_result(mobj.group('url'), 'Yahoo')
2062 # Look for embedded sbs.com.au player
2066 <meta\s+property="og:video"\s+content=|
2069 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2071 if mobj is not None:
2072 return self.url_result(mobj.group('url'), 'SBS')
2074 # Look for embedded Cinchcast player
2076 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2078 if mobj is not None:
2079 return self.url_result(mobj.group('url'), 'Cinchcast')
2082 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2086 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2088 if mobj is not None:
2089 return self.url_result(mobj.group('url'), 'MLB')
2092 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2094 if mobj is not None:
2095 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2098 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2100 if mobj is not None:
2101 return self.url_result(mobj.group('url'), 'Livestream')
2103 # Look for Zapiks embed
2105 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2106 if mobj is not None:
2107 return self.url_result(mobj.group('url'), 'Zapiks')
2109 # Look for Kaltura embeds
2110 kaltura_url = KalturaIE._extract_url(webpage)
2112 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2114 # Look for Eagle.Platform embeds
2115 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2116 if eagleplatform_url:
2117 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2119 # Look for ClipYou (uses Eagle.Platform) embeds
2121 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2122 if mobj is not None:
2123 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2125 # Look for Pladform embeds
2126 pladform_url = PladformIE._extract_url(webpage)
2128 return self.url_result(pladform_url)
2130 # Look for Videomore embeds
2131 videomore_url = VideomoreIE._extract_url(webpage)
2133 return self.url_result(videomore_url)
2135 # Look for Playwire embeds
2137 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2138 if mobj is not None:
2139 return self.url_result(mobj.group('url'))
2141 # Look for 5min embeds
2143 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2144 if mobj is not None:
2145 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2147 # Look for Crooks and Liars embeds
2149 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2150 if mobj is not None:
2151 return self.url_result(mobj.group('url'))
2153 # Look for NBC Sports VPlayer embeds
2154 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2156 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2158 # Look for NBC News embeds
2159 nbc_news_embed_url = re.search(
2160 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2161 if nbc_news_embed_url:
2162 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2164 # Look for Google Drive embeds
2165 google_drive_url = GoogleDriveIE._extract_url(webpage)
2166 if google_drive_url:
2167 return self.url_result(google_drive_url, 'GoogleDrive')
2169 # Look for UDN embeds
2171 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2172 if mobj is not None:
2173 return self.url_result(
2174 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2176 # Look for Senate ISVP iframe
2177 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2179 return self.url_result(senate_isvp_url, 'SenateISVP')
2181 # Look for Dailymotion Cloud videos
2182 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2184 return self.url_result(dmcloud_url, 'DailymotionCloud')
2186 # Look for OnionStudios embeds
2187 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2188 if onionstudios_url:
2189 return self.url_result(onionstudios_url)
2191 # Look for ViewLift embeds
2192 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2194 return self.url_result(viewlift_url)
2196 # Look for JWPlatform embeds
2197 jwplatform_url = JWPlatformIE._extract_url(webpage)
2199 return self.url_result(jwplatform_url, 'JWPlatform')
2201 # Look for ScreenwaveMedia embeds
2202 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2203 if mobj is not None:
2204 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2206 # Look for Digiteka embeds
2207 digiteka_url = DigitekaIE._extract_url(webpage)
2209 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2211 # Look for Arkena embeds
2212 arkena_url = ArkenaIE._extract_url(webpage)
2214 return self.url_result(arkena_url, ArkenaIE.ie_key())
2216 # Look for Limelight embeds
2217 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2221 'Channel': 'channel',
2222 'ChannelList': 'channel_list',
2224 return self.url_result('limelight:%s:%s' % (
2225 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2227 # Look for AdobeTVVideo embeds
2229 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2231 if mobj is not None:
2232 return self.url_result(
2233 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2236 # Look for Vine embeds
2238 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2240 if mobj is not None:
2241 return self.url_result(
2242 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2244 # Look for VODPlatform embeds
2246 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2248 if mobj is not None:
2249 return self.url_result(
2250 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2252 # Look for Instagram embeds
2253 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2254 if instagram_embed_url is not None:
2255 return self.url_result(
2256 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2258 # Look for LiveLeak embeds
2259 liveleak_url = LiveLeakIE._extract_url(webpage)
2261 return self.url_result(liveleak_url, 'LiveLeak')
2263 # Look for 3Q SDN embeds
2264 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2267 '_type': 'url_transparent',
2268 'ie_key': ThreeQSDNIE.ie_key(),
2269 'url': self._proto_relative_url(threeqsdn_url),
2270 'title': video_title,
2271 'description': video_description,
2272 'thumbnail': video_thumbnail,
2273 'uploader': video_uploader,
2276 # Look for VBOX7 embeds
2277 vbox7_url = Vbox7IE._extract_url(webpage)
2279 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2281 # Look for DBTV embeds
2282 dbtv_urls = DBTVIE._extract_urls(webpage)
2284 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2286 # Looking for http://schema.org/VideoObject
2287 json_ld = self._search_json_ld(
2288 webpage, video_id, default={}, expected_type='VideoObject')
2289 if json_ld.get('url'):
2291 'title': video_title or info_dict['title'],
2292 'description': video_description,
2293 'thumbnail': video_thumbnail,
2294 'age_limit': age_limit
2296 info_dict.update(json_ld)
2299 def check_video(vurl):
2300 if YoutubeIE.suitable(vurl):
2302 vpath = compat_urlparse.urlparse(vurl).path
2303 vext = determine_ext(vpath)
2304 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2306 def filter_video(urls):
2307 return list(filter(check_video, urls))
2309 # Start with something easy: JW Player in SWFObject
2310 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2312 # Look for gorilla-vid style embedding
2313 found = filter_video(re.findall(r'''(?sx)
2317 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2320 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2322 # Broaden the search a little bit
2323 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2325 # Broaden the findall a little bit: JWPlayer JS loader
2326 found = filter_video(re.findall(
2327 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2330 found = filter_video(re.findall(r'''(?xs)
2331 flowplayer\("[^"]+",\s*
2333 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2334 ["']?url["']?\s*:\s*["']([^"']+)["']
2339 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2341 # Try to find twitter cards info
2342 # twitter:player:stream should be checked before twitter:player since
2343 # it is expected to contain a raw stream (see
2344 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2345 found = filter_video(re.findall(
2346 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2348 # We look for Open Graph info:
2349 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2350 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2351 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2352 if m_video_type is not None:
2353 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2356 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2358 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2360 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2361 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2364 # Look also in Refresh HTTP header
2365 refresh_header = head_response.headers.get('Refresh')
2367 # In python 2 response HTTP headers are bytestrings
2368 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2369 refresh_header = refresh_header.decode('iso-8859-1')
2370 found = re.search(REDIRECT_REGEX, refresh_header)
2372 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2373 self.report_following_redirect(new_url)
2380 # twitter:player is a https URL to iframe player that may or may not
2381 # be supported by youtube-dl thus this is checked the very last (see
2382 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2383 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2385 return self.url_result(embed_url)
2388 raise UnsupportedError(url)
2391 for video_url in orderedSet(found):
2392 video_url = unescapeHTML(video_url)
2393 video_url = video_url.replace('\\/', '/')
2394 video_url = compat_urlparse.urljoin(url, video_url)
2395 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2397 # Sometimes, jwplayer extraction will result in a YouTube URL
2398 if YoutubeIE.suitable(video_url):
2399 entries.append(self.url_result(video_url, 'Youtube'))
2402 # here's a fun little line of code for you:
2403 video_id = os.path.splitext(video_id)[0]
2407 'uploader': video_uploader,
2408 'title': video_title,
2409 'age_limit': age_limit,
2412 ext = determine_ext(video_url)
2414 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2416 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2418 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2420 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2422 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2424 entry_info_dict['url'] = video_url
2426 if entry_info_dict.get('formats'):
2427 self._sort_formats(entry_info_dict['formats'])
2429 entries.append(entry_info_dict)
2431 if len(entries) == 1:
2434 for num, e in enumerate(entries, start=1):
2435 # 'url' results don't have a title
2436 if e.get('title') is not None:
2437 e['title'] = '%s (%d)' % (e['title'], num)
2439 '_type': 'playlist',