3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
14 compat_urllib_parse_unquote,
16 compat_xml_parse_error,
34 from .commonprotocols import RtmpIE
35 from .brightcove import (
43 from .nbc import NBCSportsVPlayerIE
44 from .ooyala import OoyalaIE
45 from .rutv import RUTVIE
46 from .tvc import TVCIE
47 from .sportbox import SportBoxEmbedIE
48 from .smotri import SmotriIE
49 from .myvi import MyviIE
50 from .condenast import CondeNastIE
51 from .udn import UDNEmbedIE
52 from .senateisvp import SenateISVPIE
53 from .svt import SVTIE
54 from .pornhub import PornHubIE
55 from .xhamster import XHamsterEmbedIE
56 from .tnaflix import TNAFlixNetworkEmbedIE
57 from .drtuber import DrTuberIE
58 from .redtube import RedTubeIE
59 from .vimeo import VimeoIE
60 from .dailymotion import (
64 from .dailymail import DailyMailIE
65 from .onionstudios import OnionStudiosIE
66 from .viewlift import ViewLiftEmbedIE
67 from .mtv import MTVServicesEmbeddedIE
68 from .pladform import PladformIE
69 from .videomore import VideomoreIE
70 from .webcaster import WebcasterFeedIE
71 from .googledrive import GoogleDriveIE
72 from .jwplatform import JWPlatformIE
73 from .digiteka import DigitekaIE
74 from .arkena import ArkenaIE
75 from .instagram import InstagramIE
76 from .liveleak import LiveLeakIE
77 from .threeqsdn import ThreeQSDNIE
78 from .theplatform import ThePlatformIE
79 from .vessel import VesselIE
80 from .kaltura import KalturaIE
81 from .eagleplatform import EaglePlatformIE
82 from .facebook import FacebookIE
83 from .soundcloud import SoundcloudIE
84 from .tunein import TuneInBaseIE
85 from .vbox7 import Vbox7IE
86 from .dbtv import DBTVIE
87 from .piksel import PikselIE
88 from .videa import VideaIE
89 from .twentymin import TwentyMinutenIE
90 from .ustream import UstreamIE
91 from .openload import OpenloadIE
92 from .videopress import VideoPressIE
93 from .rutube import RutubeIE
94 from .limelight import LimelightBaseIE
95 from .anvato import AnvatoIE
96 from .washingtonpost import WashingtonPostIE
97 from .wistia import WistiaIE
98 from .mediaset import MediasetIE
99 from .joj import JojIE
100 from .megaphone import MegaphoneIE
103 class GenericIE(InfoExtractor):
104 IE_DESC = 'Generic downloader that works on some sites'
108 # Direct link to a video
110 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
111 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
116 'upload_date': '20100513',
119 # Direct link to media delivered compressed (until Accept-Encoding is *)
121 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
122 'md5': '128c42e68b13950268b648275386fc74',
124 'id': 'FictionJunction-Parallel_Hearts',
126 'title': 'FictionJunction-Parallel_Hearts',
127 'upload_date': '20140522',
129 'expected_warnings': [
130 'URL could be a direct video link, returning it as such.'
132 'skip': 'URL invalid',
134 # Direct download with broken HEAD
136 'url': 'http://ai-radio.org:8000/radio.opus',
143 'skip_download': True, # infinite live stream
145 'expected_warnings': [
146 r'501.*Not Implemented',
150 # Direct link with incorrect MIME type
152 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
153 'md5': '4ccbebe5f36706d85221f204d7eb5913',
155 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
156 'id': '5_Lennart_Poettering_-_Systemd',
158 'title': '5_Lennart_Poettering_-_Systemd',
159 'upload_date': '20141120',
161 'expected_warnings': [
162 'URL could be a direct video link, returning it as such.'
167 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
169 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
170 'title': 'Zero Punctuation',
171 'description': 're:.*groundbreaking video review series.*'
173 'playlist_mincount': 11,
175 # RSS feed with enclosure
177 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
179 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
181 'upload_date': '20150228',
182 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
185 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
187 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
191 'title': 'Automatics, robotics and biocybernetics',
192 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
193 'upload_date': '20130627',
194 'formats': 'mincount:16',
195 'subtitles': 'mincount:1',
198 'force_generic_extractor': True,
199 'skip_download': True,
202 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
204 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
209 'formats': 'mincount:1',
212 'skip_download': True,
215 # SMIL from https://www.restudy.dk/video/play/id/1637
217 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
221 'title': 'video_1637',
222 'formats': 'mincount:3',
225 'skip_download': True,
228 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
230 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
232 'id': 'smil-service',
234 'title': 'smil-service',
235 'formats': 'mincount:1',
238 'skip_download': True,
241 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
243 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
247 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
248 'formats': 'mincount:3',
251 'skip_download': True,
254 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
256 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
258 'id': 'mZlp2ctYIUEB',
260 'title': 'Tikibad ontruimd wegens brand',
261 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
262 'thumbnail': r're:^https?://.*\.jpg$',
266 'skip_download': True,
269 # MPD from http://dash-mse-test.appspot.com/media.html
271 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
272 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
274 'id': 'car-20120827-manifest',
276 'title': 'car-20120827-manifest',
277 'formats': 'mincount:9',
278 'upload_date': '20130904',
281 'format': 'bestvideo',
284 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
286 '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',
291 'formats': 'mincount:8',
295 'skip_download': True,
297 'skip': 'video gone',
299 # m3u8 served with Content-Type: text/plain
301 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
306 'upload_date': '20140720',
307 'formats': 'mincount:11',
311 'skip_download': True,
313 'skip': 'video gone',
317 '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',
321 'upload_date': '20130224',
322 'uploader_id': 'TheVerge',
323 'description': r're:^Chris Ziegler takes a look at the\.*',
324 'uploader': 'The Verge',
325 'title': 'First Firefox OS phones side-by-side',
328 'skip_download': False,
332 # redirect in Refresh HTTP header
333 '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',
337 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
338 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
339 'upload_date': '20150917',
340 'uploader_id': 'brtvofficial',
341 'uploader': 'Boiler Room',
344 'skip_download': False,
348 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
349 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
351 'id': '13601338388002',
353 'uploader': 'www.hodiho.fr',
354 'title': 'R\u00e9gis plante sa Jeep',
357 # bandcamp page with custom domain
359 'add_ie': ['Bandcamp'],
360 'url': 'http://bronyrock.com/track/the-pony-mash',
364 'title': 'The Pony Mash',
365 'uploader': 'M_Pallante',
367 'skip': 'There is a limit of 200 free downloads / month for the test song',
370 # embedded brightcove video
371 # it also tests brightcove videos that need to set the 'Referer'
372 # in the http requests
373 'add_ie': ['BrightcoveLegacy'],
374 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
376 'id': '2765128793001',
378 'title': 'Le cours de bourse : l’analyse technique',
379 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
380 'uploader': 'BFM BUSINESS',
383 'skip_download': True,
387 # embedded with itemprop embedURL and video id spelled as `idVideo`
388 'add_id': ['BrightcoveLegacy'],
389 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
391 'id': '5255628253001',
393 'title': 'md5:37c519b1128915607601e75a87995fc0',
394 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
395 'uploader': 'BFM BUSINESS',
396 'uploader_id': '876450612001',
397 'timestamp': 1482255315,
398 'upload_date': '20161220',
401 'skip_download': True,
405 # https://github.com/rg3/youtube-dl/issues/2253
406 'url': 'http://bcove.me/i6nfkrc3',
407 'md5': '0ba9446db037002366bab3b3eb30c88c',
409 'id': '3101154703001',
411 'title': 'Still no power',
412 'uploader': 'thestar.com',
413 '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.',
415 'add_ie': ['BrightcoveLegacy'],
416 'skip': 'video gone',
419 'url': 'http://www.championat.com/video/football/v/87/87499.html',
420 'md5': 'fb973ecf6e4a78a67453647444222983',
422 'id': '3414141473001',
424 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
425 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
426 'uploader': 'Championat',
430 # https://github.com/rg3/youtube-dl/issues/3541
431 'add_ie': ['BrightcoveLegacy'],
432 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
434 'id': '3866516442001',
436 'title': 'Leer mij vrouwen kennen: Aflevering 1',
437 'description': 'Leer mij vrouwen kennen: Aflevering 1',
438 'uploader': 'SBS Broadcasting',
440 'skip': 'Restricted to Netherlands',
442 'skip_download': True, # m3u8 download
446 # Brightcove video in <iframe>
447 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
448 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
450 'id': '5360463607001',
452 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
453 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
454 'uploader': 'United Nations',
455 'uploader_id': '1362235914001',
456 'timestamp': 1489593889,
457 'upload_date': '20170315',
459 'add_ie': ['BrightcoveLegacy'],
462 # Brightcove with alternative playerID key
463 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
465 'id': 'nmeth.2062_SV1',
466 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
470 'id': '2228375078001',
472 'title': 'nmeth.2062-sv1',
473 'description': 'nmeth.2062-sv1',
474 'timestamp': 1363357591,
475 'upload_date': '20130315',
476 'uploader': 'Nature Publishing Group',
477 'uploader_id': '1964492299001',
482 # Brightcove with UUID in videoPlayer
483 'url': 'http://www8.hp.com/cn/zh/home.html',
485 'id': '5255815316001',
487 'title': 'Sprocket Video - China',
488 'description': 'Sprocket Video - China',
489 'uploader': 'HP-Video Gallery',
490 'timestamp': 1482263210,
491 'upload_date': '20161220',
492 'uploader_id': '1107601872001',
495 'skip_download': True, # m3u8 download
497 'skip': 'video rotates...weekly?',
500 # Brightcove:new type [2].
501 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
502 'md5': '2b35148fcf48da41c9fb4591650784f3',
504 'id': '5348741021001',
506 'upload_date': '20170306',
507 'uploader_id': '4191638492001',
508 'timestamp': 1488769918,
509 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
514 # Alternative brightcove <video> attributes
515 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
517 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
518 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
521 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
523 'id': '5311302538001',
525 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
526 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
527 'timestamp': 1486321708,
528 'upload_date': '20170205',
529 'uploader_id': '800000640001',
531 'only_matching': True,
535 # Brightcove with UUID in videoPlayer
536 'url': 'http://www8.hp.com/cn/zh/home.html',
538 'id': '5255815316001',
540 'title': 'Sprocket Video - China',
541 'description': 'Sprocket Video - China',
542 'uploader': 'HP-Video Gallery',
543 'timestamp': 1482263210,
544 'upload_date': '20161220',
545 'uploader_id': '1107601872001',
548 'skip_download': True, # m3u8 download
553 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
554 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
556 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
558 'title': '2cc213299525360.mov', # that's what we get
561 'add_ie': ['Ooyala'],
564 # ooyala video embedded with http://player.ooyala.com/iframe.js
565 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
567 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
569 'title': '"Steve Jobs: Man in the Machine" trailer',
570 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
574 'skip_download': True,
576 'skip': 'movie expired',
578 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
580 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
582 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
584 'title': 'Steampunk Fest Comes to Honesdale',
588 'skip_download': True,
593 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
597 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
598 'upload_date': '20140225',
599 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
600 'uploader': 'Tested',
601 'uploader_id': 'testedcom',
603 # No need to test YoutubeIE here
605 'skip_download': True,
610 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
614 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
615 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
617 # HEAD requests lead to endless 301, while GET is OK
618 'expected_warnings': ['301'],
622 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
626 'title': 'Охотское море стало целиком российским',
627 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
631 'skip_download': True,
636 '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/',
640 'title': 'Дошкольное воспитание',
645 'url': 'http://www.vestifinance.ru/articles/25753',
648 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
653 'title': 'Госзаказ. День 3',
659 'title': 'Госзаказ. День 2',
665 'title': 'Госзаказ. День 1',
671 'skip_download': True,
676 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
678 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
680 'title': 'Ужастики, русский трейлер (2015)',
681 'thumbnail': r're:^https?://.*\.jpg$',
687 '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',
690 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
692 'playlist_mincount': 7,
693 # This forum does not allow <iframe> syntaxes anymore
694 # Now HTML tags are displayed as-is
695 'skip': 'No videos on this page',
699 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
700 'md5': '65fdff94098e4a607385a60c5177c638',
704 'title': 'Hidden miracles of the natural world',
705 'uploader': 'Louie Schwartzberg',
706 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
709 # nowvideo embed hidden behind percent encoding
711 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
712 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
714 'id': '06e53103ca9aa',
716 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
717 'description': 'No description',
722 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
723 'md5': '7653032cbb25bf6c80d80f217055fa43',
725 'id': '048195-004_PLUS7-F',
728 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
729 'upload_date': '20140320',
732 'skip_download': 'Requires rtmpdump'
734 'skip': 'video gone',
738 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
742 'title': 'Alcaline, le concert avec Calogero',
743 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
744 'upload_date': '20150226',
745 'timestamp': 1424989860,
750 'skip_download': True,
752 'expected_warnings': [
758 'url': 'http://www.wired.com/2014/04/honda-asimo/',
759 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
761 'id': '53501be369702d3275860000',
763 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
768 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
769 'md5': '441aeeb82eb72c422c7f14ec533999cd',
771 'id': 'k2mm4bCdJ6CQ2i7c8o2',
773 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
774 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
776 'uploader_id': 'xgditw',
777 'upload_date': '20140425',
778 'timestamp': 1398441542,
780 'add_ie': ['Dailymotion'],
784 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
788 'title': 'Care worker punches elderly dementia patient in head 11 times',
789 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
791 'add_ie': ['DailyMail'],
793 'skip_download': True,
798 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
802 'title': 'The NBL Auction 2014',
803 'uploader': 'BADMINTON England',
804 'uploader_id': 'BADMINTONEvents',
805 'upload_date': '20140603',
806 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
808 'add_ie': ['Youtube'],
810 'skip_download': True,
815 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
816 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
818 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
820 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
821 'description': 'Two valets share their love for movie star Liam Neesons.',
822 'timestamp': 1349922600,
823 'upload_date': '20121011',
826 # YouTube embed via <data-embed-url="">
828 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
832 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
833 'uploader': 'Gameloft',
834 'uploader_id': 'gameloft',
835 'upload_date': '20140828',
836 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
839 'skip_download': True,
842 # YouTube <object> embed
844 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
845 'md5': '516718101ec834f74318df76259fb3cc',
849 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
850 'upload_date': '20080526',
851 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
852 'uploader': 'Christopher Sykes',
853 'uploader_id': 'ChristopherJSykes',
855 'add_ie': ['Youtube'],
859 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
861 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
863 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
864 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
869 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
871 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
872 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
878 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
883 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
884 'md5': '9d65602bf31c6e20014319c7d07fba27',
886 'id': '5123ea6d5e5a7',
889 'uploader': 'www.handjobhub.com',
890 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
893 # Multiple brightcove videos
894 # https://github.com/rg3/youtube-dl/issues/2283
896 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
898 'id': 'always-never',
899 'title': 'Always / Never - The New Yorker',
903 'extract_flat': False,
904 'skip_download': True,
909 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
910 'md5': '96f09a37e44da40dd083e12d9a683327',
914 'title': 'Ump changes call to ball',
915 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
917 'timestamp': 1401537900,
918 'upload_date': '20140531',
919 'thumbnail': r're:^https?://.*\.jpg$',
924 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
925 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
929 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
930 'description': 'a Paywall Videos video from Remilon',
932 'uploader': 'study.com',
933 'timestamp': 1459678540,
934 'upload_date': '20160403',
935 'filesize': 24687186,
939 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
940 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
944 'title': 'Conversation about Hexagonal Rails Part 1',
945 'description': 'a Martin Fowler video from ThoughtWorks',
947 'uploader': 'thoughtworks.wistia.com',
948 'timestamp': 1401832161,
949 'upload_date': '20140603',
952 # Wistia standard embed (async)
954 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
958 'title': 'Drip Brennan Dunn Workshop',
959 'description': 'a JV Webinars video from getdrip-1',
961 'timestamp': 1463607249,
962 'upload_date': '20160518',
965 'skip_download': True,
970 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
974 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
975 'uploader': 'Sophos Security',
976 'title': 'Chet Chat 171 - Oct 29, 2014',
977 'upload_date': '20141029',
980 # Soundcloud multiple embeds
982 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
985 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
987 'playlist_mincount': 7,
989 # TuneIn station embed
991 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
996 'location': 'Paris, France',
1001 'skip_download': True,
1006 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1010 'upload_date': '20141112',
1011 'title': 'Rosetta #CometLanding webcast HL 10',
1014 # Another Livestream embed, without 'new.' in URL
1016 'url': 'https://www.freespeech.org/',
1020 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1024 'skip_download': True,
1029 'url': 'https://skiplagged.com/',
1032 'title': 'Skiplagged: The smart way to find cheap flights',
1034 'playlist_mincount': 1,
1035 'add_ie': ['Youtube'],
1039 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1043 'upload_date': '20141126',
1044 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1049 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1051 'id': '730m_DandD_1901_512k',
1053 'uploader': 'www.abc.net.au',
1054 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1057 # embedded viddler video
1059 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1063 'uploader': 'deadspin',
1064 'title': 'WALL-TO-GORTAT',
1065 'timestamp': 1422285291,
1066 'upload_date': '20150126',
1068 'add_ie': ['Viddler'],
1072 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1076 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1077 'description': 'md5:601cb790edd05908957dae8aaa866465',
1078 'upload_date': '20150220',
1080 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1084 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1086 'id': 'Mrj4DVp2zeA',
1088 'upload_date': '20150212',
1089 'uploader': 'The National Archives UK',
1090 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1091 'uploader_id': 'NationalArchives08',
1092 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1097 'url': 'http://www.suffolk.edu/sjc/',
1101 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1102 'uploader': 'www.suffolk.edu',
1105 'skip_download': True,
1110 'url': 'http://www.indiedb.com/games/king-machine/videos',
1114 'title': 'king machine trailer 1',
1115 'thumbnail': r're:^https?://.*\.jpg$',
1119 # JWPlayer config passed as variable
1120 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1124 'title': 'ARIELE | Tube Cup',
1125 'uploader': 'www.txxx.com',
1129 'skip_download': True,
1134 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1135 'playlist_mincount': 5,
1137 'id': 'aanslagen-kopenhagen',
1138 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1143 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1147 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1150 # Kaltura embed (different embed code)
1152 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1156 'upload_date': '20150127',
1157 'uploader_id': 'PremierMedia',
1159 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1162 # Kaltura embed with single quotes
1164 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1169 'timestamp': 1355743100,
1170 'upload_date': '20121217',
1171 'uploader_id': 'batchUser',
1173 'add_ie': ['Kaltura'],
1176 # Kaltura embedded via quoted entry_id
1177 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1181 'title': '06_matthew_brender_raj_dutt',
1182 'timestamp': 1466638791,
1183 'upload_date': '20160622',
1185 'add_ie': ['Kaltura'],
1186 'expected_warnings': [
1187 'Could not send HEAD request'
1190 'skip_download': True,
1194 # Kaltura embedded, some fileExt broken (#11480)
1195 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1199 'title': 'Our "Standard Models" of particle physics and cosmology',
1200 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1201 'timestamp': 1321158993,
1202 'upload_date': '20111113',
1203 'uploader_id': 'kps1',
1205 'add_ie': ['Kaltura'],
1208 # Kaltura iframe embed
1209 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1210 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1214 'title': 'I. M. Pei: A Centennial Celebration',
1215 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1216 'upload_date': '20170403',
1217 'uploader_id': 'batchUser',
1218 'timestamp': 1491232186,
1220 'add_ie': ['Kaltura'],
1222 # EaglePlatform embed (generic URL)
1224 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1225 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1229 'title': 'Навальный вышел на свободу',
1230 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1231 'thumbnail': r're:^https?://.*\.jpg$',
1237 'skip_download': True,
1240 # referrer protected EaglePlatform embed
1242 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1246 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1247 'thumbnail': r're:^https?://.*\.jpg$',
1252 'skip_download': True,
1255 # ClipYou (EaglePlatform) embed (custom URL)
1257 'url': 'http://muz-tv.ru/play/7129/',
1258 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1262 'title': "'O Sole Mio",
1263 'thumbnail': r're:^https?://.*\.jpg$',
1268 'skip_download': True,
1273 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1277 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1278 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1279 'thumbnail': r're:^https?://.*\.jpg$',
1286 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1290 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1291 'thumbnail': r're:^https?://.*\.png$',
1297 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1298 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1302 'title': 'Facebook Creates "On This Day" | Crunch Report',
1307 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1311 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1316 # Crooks and Liars embed
1318 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1322 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1323 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1324 'timestamp': 1428207000,
1325 'upload_date': '20150405',
1326 'uploader': 'Heather',
1329 # Crooks and Liars external embed
1331 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1333 'id': 'MTE3MjUtMzQ2MzA',
1335 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1336 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1337 'timestamp': 1265032391,
1338 'upload_date': '20100201',
1339 'uploader': 'Heather',
1342 # NBC Sports vplayer embed
1344 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1346 'id': 'ln7x1qSThw4k',
1348 'title': "PFT Live: New leader in the 'new-look' defense",
1349 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1350 'uploader': 'NBCU-SPORTS',
1351 'upload_date': '20140107',
1352 'timestamp': 1389118457,
1357 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1358 'md5': '1aa589c675898ae6d37a17913cf68d66',
1360 'id': '701714499682',
1362 'title': 'PREVIEW: On Assignment: David Letterman',
1363 '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.',
1368 'url': 'https://video.udn.com/news/300346',
1369 'md5': 'fd2060e988c326991037b9aff9df21a6',
1373 'title': '中一中男師變性 全校師生力挺',
1374 'thumbnail': r're:^https?://.*\.jpg$',
1378 'skip_download': True,
1383 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1385 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1387 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1388 'title': 'This is what separates the Excel masters from the wannabes',
1389 'duration': 191.933,
1393 'skip_download': True,
1396 # Brightcove URL in single quotes
1398 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1399 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1401 'id': '4255764656001',
1403 'title': 'SN Presents: Russell Martin, World Citizen',
1404 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1405 'uploader': 'Rogers Sportsnet',
1406 'uploader_id': '1704050871',
1407 'upload_date': '20150525',
1408 'timestamp': 1432570283,
1411 # Dailymotion Cloud video
1413 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1414 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1418 'title': 'Sauvons les abeilles ! - Le débat',
1419 'description': 'md5:d9082128b1c5277987825d684939ca26',
1420 'thumbnail': r're:^https?://.*\.jpe?g$',
1421 'timestamp': 1434970506,
1422 'upload_date': '20150622',
1423 'uploader': 'Public Sénat',
1424 'uploader_id': 'xa9gza',
1427 # OnionStudios embed
1429 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1433 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1434 'thumbnail': r're:^https?://.*\.jpe?g$',
1435 'uploader': 'ClickHole',
1436 'uploader_id': 'clickhole',
1441 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1443 'id': '74849a00-85a9-11e1-9660-123139220831',
1445 'title': '#whilewewatch',
1448 # AdobeTVVideo embed
1450 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1451 'md5': '43662b577c018ad707a63766462b1e87',
1455 'title': 'New experience with Acrobat DC',
1456 'description': 'New experience with Acrobat DC',
1457 'duration': 248.667,
1460 # BrightcoveInPageEmbed embed
1462 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1464 'id': '4238694884001',
1466 'title': 'Tabletop: Dread, Last Thoughts',
1467 'description': 'Tabletop: Dread, Last Thoughts',
1471 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1472 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1474 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1476 'id': '4785848093001',
1478 'title': 'The Cardinal Pell Interview',
1479 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1480 'uploader': 'GlobeCast Australia - GlobeStream',
1481 'uploader_id': '2733773828001',
1482 'upload_date': '20160304',
1483 'timestamp': 1457083087,
1487 'skip_download': True,
1491 # Brightcove embed with whitespace around attribute names
1492 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1494 'id': '3167554373001',
1496 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1497 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1498 'uploader_id': '1079349493',
1499 'upload_date': '20140207',
1500 'timestamp': 1391810548,
1503 'skip_download': True,
1506 # Another form of arte.tv embed
1508 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1509 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1511 'id': '030273-562_PLUS7-F',
1513 'title': 'ARTE Reportage - Nulle part, en France',
1514 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1515 'upload_date': '20160409',
1520 'url': 'http://www.wykop.pl/link/3088787/',
1521 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1523 'id': '874_1459135191',
1525 'title': 'Man shows poor quality of new apartment building',
1526 'description': 'The wall is like a sand pile.',
1527 'uploader': 'Lake8737',
1530 # Duplicated embedded video URLs
1532 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1534 'id': '149298443_480_16c25b74_2',
1536 'title': 'vs. Blue Orange Spring Game',
1537 'uploader': 'www.hudl.com',
1540 # twitter:player:stream embed
1542 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1546 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1547 'uploader': 'www.rtl.be',
1551 'skip_download': True,
1554 # twitter:player embed
1556 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1557 'md5': 'a3e0df96369831de324f0778e126653c',
1559 'id': '4909620399001',
1561 'title': 'What Do Black Holes Sound Like?',
1562 'description': 'what do black holes sound like',
1563 'upload_date': '20160524',
1564 'uploader_id': '29913724001',
1565 'timestamp': 1464107587,
1566 'uploader': 'TheAtlantic',
1568 'add_ie': ['BrightcoveLegacy'],
1572 'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
1576 'title': "Yesterday's Jam (OV)",
1577 'description': 'md5:09bc0984723fed34e2581624a84e05f0',
1578 'timestamp': 1492594816,
1579 'upload_date': '20170419',
1582 'format': 'bestvideo',
1583 'skip_download': True,
1586 # Facebook <iframe> embed
1588 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1589 'md5': 'fbcde74f534176ecb015849146dd3aee',
1591 'id': '599637780109885',
1593 'title': 'Facebook video #599637780109885',
1596 # Facebook <iframe> embed, plugin video
1598 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1600 'id': '1754168231264132',
1602 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1603 'uploader': 'Tariq Ramadan (official)',
1604 'timestamp': 1496758379,
1605 'upload_date': '20170606',
1608 'skip_download': True,
1611 # Facebook API embed
1613 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1614 'md5': 'a47372ee61b39a7b90287094d447d94e',
1616 'id': '10153467542406923',
1618 'title': 'Facebook video #10153467542406923',
1621 # Wordpress "YouTube Video Importer" plugin
1623 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1624 'md5': 'd16797741b560b485194eddda8121b48',
1626 'id': 'HNTXWDXV9Is',
1628 'title': 'Blue Devils Drumline Stanford lot 2016',
1629 'upload_date': '20160627',
1630 'uploader_id': 'GENOCIDE8GENERAL10',
1631 'uploader': 'cylus cyrus',
1635 # video stored on custom kaltura server
1636 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1637 'md5': '537617d06e64dfed891fa1593c4b30cc',
1641 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1642 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1643 'uploader_id': 'videos.expansion@el-mundo.net',
1644 'upload_date': '20150429',
1645 'timestamp': 1430303472,
1647 'add_ie': ['Kaltura'],
1650 # Non-standard Vimeo embed
1651 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1652 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1656 'title': 'Understanding the web - Teaser',
1657 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1658 'upload_date': '20151214',
1659 'uploader': 'OpenClassrooms',
1660 'uploader_id': 'openclassrooms',
1662 'add_ie': ['Vimeo'],
1665 # generic vimeo embed that requires original URL passed as Referer
1666 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1667 'only_matching': True,
1670 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1671 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1673 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1675 'title': 'Big Buck Bunny',
1676 'description': 'Royalty free test video',
1677 'timestamp': 1432816365,
1678 'upload_date': '20150528',
1682 'skip_download': True,
1684 'add_ie': [ArkenaIE.ie_key()],
1687 '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/',
1691 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1694 'skip_download': True,
1696 'add_ie': [Vbox7IE.ie_key()],
1700 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1703 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1705 'playlist_mincount': 3,
1709 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1711 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1712 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1714 'playlist_mincount': 2,
1718 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1722 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1723 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1726 'skip_download': True,
1728 'add_ie': [TwentyMinutenIE.ie_key()],
1732 'url': 'https://en.support.wordpress.com/videopress/',
1736 'title': 'IMG_5786',
1737 'timestamp': 1435711927,
1738 'upload_date': '20150701',
1741 'skip_download': True,
1743 'add_ie': [VideoPressIE.ie_key()],
1747 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1749 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1751 'title': 'Магаззино: Казань 2',
1752 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1753 'uploader': 'Магаззино',
1754 'upload_date': '20170228',
1755 'uploader_id': '996642',
1758 'skip_download': True,
1760 'add_ie': [RutubeIE.ie_key()],
1763 # ThePlatform embedded with whitespaces in URLs
1764 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1765 'only_matching': True,
1768 # Senate ISVP iframe https
1769 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1770 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1772 'id': 'govtaff020316',
1774 'title': 'Integrated Senate Video Player',
1776 'add_ie': [SenateISVPIE.ie_key()],
1779 # Limelight embeds (1 channel embed + 4 media embeds)
1780 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1782 'id': 'FacilitatorTraining2017',
1783 'title': 'Facilitator Training 2017',
1785 'playlist_mincount': 5,
1788 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1790 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1791 'title': 'Standoff with Walnut Creek murder suspect ends',
1792 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1794 'playlist_mincount': 4,
1797 # WashingtonPost embed
1798 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1800 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1802 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1803 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1804 'timestamp': 1455216756,
1805 'uploader': 'The Washington Post',
1806 'upload_date': '20160211',
1808 'add_ie': [WashingtonPostIE.ie_key()],
1812 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1816 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1819 'skip_download': True,
1821 'add_ie': [MediasetIE.ie_key()],
1825 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1827 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1828 'title': 'Slovenskom sa prehnala vlna silných búrok',
1830 'playlist_mincount': 5,
1831 'add_ie': [JojIE.ie_key()],
1834 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1835 'url': 'https://tvrain.ru/amp/418921/',
1836 'md5': 'cc00413936695987e8de148b67d14f1d',
1840 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1844 # # TODO: find another test
1845 # # http://schema.org/VideoObject
1846 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1847 # 'md5': '888dcf08b7ea671381f00fab74692755',
1849 # 'id': 'nyvTSJMKId',
1851 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1852 # 'description': '#love for cats.',
1853 # 'timestamp': 1461244995,
1854 # 'upload_date': '20160421',
1857 # 'force_generic_extractor': True,
1862 def report_following_redirect(self, new_url):
1863 """Report information extraction."""
1864 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1866 def _extract_rss(self, url, video_id, doc):
1867 playlist_title = doc.find('./channel/title').text
1868 playlist_desc_el = doc.find('./channel/description')
1869 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1872 for it in doc.findall('./channel/item'):
1873 next_url = xpath_text(it, 'link', fatal=False)
1875 enclosure_nodes = it.findall('./enclosure')
1876 for e in enclosure_nodes:
1877 next_url = e.attrib.get('url')
1885 '_type': 'url_transparent',
1887 'title': it.find('title').text,
1891 '_type': 'playlist',
1893 'title': playlist_title,
1894 'description': playlist_desc,
1898 def _extract_camtasia(self, url, video_id, webpage):
1899 """ Returns None if no camtasia video can be found. """
1901 camtasia_cfg = self._search_regex(
1902 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1903 webpage, 'camtasia configuration file', default=None)
1904 if camtasia_cfg is None:
1907 title = self._html_search_meta('DC.title', webpage, fatal=True)
1909 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1910 camtasia_cfg = self._download_xml(
1911 camtasia_url, video_id,
1912 note='Downloading camtasia configuration',
1913 errnote='Failed to download camtasia configuration')
1914 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1917 for n in fileset_node.getchildren():
1918 url_n = n.find('./uri')
1923 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1924 'title': '%s - %s' % (title, n.tag),
1925 'url': compat_urlparse.urljoin(url, url_n.text),
1926 'duration': float_or_none(n.find('./duration').text),
1930 '_type': 'playlist',
1935 def _real_extract(self, url):
1936 if url.startswith('//'):
1939 'url': self.http_scheme() + url,
1942 parsed_url = compat_urlparse.urlparse(url)
1943 if not parsed_url.scheme:
1944 default_search = self._downloader.params.get('default_search')
1945 if default_search is None:
1946 default_search = 'fixup_error'
1948 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1950 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1951 return self.url_result('http://' + url)
1952 elif default_search != 'fixup_error':
1953 if default_search == 'auto_warning':
1954 if re.match(r'^(?:url|URL)$', url):
1955 raise ExtractorError(
1956 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1959 self._downloader.report_warning(
1960 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1961 return self.url_result('ytsearch:' + url)
1963 if default_search in ('error', 'fixup_error'):
1964 raise ExtractorError(
1965 '%r is not a valid URL. '
1966 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1967 % (url, url), expected=True)
1969 if ':' not in default_search:
1970 default_search += ':'
1971 return self.url_result(default_search + url)
1973 url, smuggled_data = unsmuggle_url(url)
1974 force_videoid = None
1975 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1976 if smuggled_data and 'force_videoid' in smuggled_data:
1977 force_videoid = smuggled_data['force_videoid']
1978 video_id = force_videoid
1980 video_id = self._generic_id(url)
1982 self.to_screen('%s: Requesting header' % video_id)
1984 head_req = HEADRequest(url)
1985 head_response = self._request_webpage(
1987 note=False, errnote='Could not send HEAD request to %s' % url,
1990 if head_response is not False:
1991 # Check for redirect
1992 new_url = head_response.geturl()
1994 self.report_following_redirect(new_url)
1996 new_url = smuggle_url(
1997 new_url, {'force_videoid': force_videoid})
1998 return self.url_result(new_url)
2000 full_response = None
2001 if head_response is False:
2002 request = sanitized_Request(url)
2003 request.add_header('Accept-Encoding', '*')
2004 full_response = self._request_webpage(request, video_id)
2005 head_response = full_response
2009 'title': self._generic_title(url),
2010 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2013 # Check for direct link to a video
2014 content_type = head_response.headers.get('Content-Type', '').lower()
2015 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2017 format_id = compat_str(m.group('format_id'))
2018 if format_id.endswith('mpegurl'):
2019 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2020 elif format_id == 'f4m':
2021 formats = self._extract_f4m_formats(url, video_id)
2024 'format_id': format_id,
2026 'vcodec': 'none' if m.group('type') == 'audio' else None
2028 info_dict['direct'] = True
2029 self._sort_formats(formats)
2030 info_dict['formats'] = formats
2033 if not self._downloader.params.get('test', False) and not is_intentional:
2034 force = self._downloader.params.get('force_generic_extractor', False)
2035 self._downloader.report_warning(
2036 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2038 if not full_response:
2039 request = sanitized_Request(url)
2040 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2041 # making it impossible to download only chunk of the file (yet we need only 512kB to
2042 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2043 # that will always result in downloading the whole file that is not desirable.
2044 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2045 # to accept raw bytes and being able to download only a chunk.
2046 # It may probably better to solve this by checking Content-Type for application/octet-stream
2047 # after HEAD request finishes, but not sure if we can rely on this.
2048 request.add_header('Accept-Encoding', '*')
2049 full_response = self._request_webpage(request, video_id)
2051 first_bytes = full_response.read(512)
2053 # Is it an M3U playlist?
2054 if first_bytes.startswith(b'#EXTM3U'):
2055 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2056 self._sort_formats(info_dict['formats'])
2059 # Maybe it's a direct link to a video?
2060 # Be careful not to download the whole thing!
2061 if not is_html(first_bytes):
2062 self._downloader.report_warning(
2063 'URL could be a direct video link, returning it as such.')
2070 webpage = self._webpage_read_content(
2071 full_response, url, video_id, prefix=first_bytes)
2073 self.report_extraction(video_id)
2075 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2077 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2078 if doc.tag == 'rss':
2079 return self._extract_rss(url, video_id, doc)
2080 elif doc.tag == 'SmoothStreamingMedia':
2081 info_dict['formats'] = self._parse_ism_formats(doc, url)
2082 self._sort_formats(info_dict['formats'])
2084 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2085 smil = self._parse_smil(doc, url, video_id)
2086 self._sort_formats(smil['formats'])
2088 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2089 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2090 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2091 info_dict['formats'] = self._parse_mpd_formats(
2093 mpd_base_url=full_response.geturl().rpartition('/')[0],
2095 self._sort_formats(info_dict['formats'])
2097 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2098 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2099 self._sort_formats(info_dict['formats'])
2101 except compat_xml_parse_error:
2104 # Is it a Camtasia project?
2105 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2106 if camtasia_res is not None:
2109 # Sometimes embedded video player is hidden behind percent encoding
2110 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2111 # Unescaping the whole page allows to handle those cases in a generic way
2112 webpage = compat_urllib_parse_unquote(webpage)
2114 # it's tempting to parse this further, but you would
2115 # have to take into account all the variations like
2116 # Video Title - Site Name
2117 # Site Name | Video Title
2118 # Video Title - Tagline | Site Name
2119 # and so on and so forth; it's just not practical
2120 video_title = self._og_search_title(
2121 webpage, default=None) or self._html_search_regex(
2122 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2125 # Try to detect age limit automatically
2126 age_limit = self._rta_search(webpage)
2127 # And then there are the jokers who advertise that they use RTA,
2128 # but actually don't.
2129 AGE_LIMIT_MARKERS = [
2130 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2132 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2135 # video uploader is domain name
2136 video_uploader = self._search_regex(
2137 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2139 video_description = self._og_search_description(webpage, default=None)
2140 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2143 'title': video_title,
2144 'description': video_description,
2145 'thumbnail': video_thumbnail,
2146 'age_limit': age_limit,
2149 # Look for Brightcove Legacy Studio embeds
2150 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2154 'url': smuggle_url(bc_url, {'Referer': url}),
2155 'ie_key': 'BrightcoveLegacy'
2156 } for bc_url in bc_urls]
2159 '_type': 'playlist',
2160 'title': video_title,
2165 # Look for Brightcove New Studio embeds
2166 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2168 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2170 # Look for Nexx embeds
2171 nexx_urls = NexxIE._extract_urls(webpage)
2173 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2175 # Look for Nexx iFrame embeds
2176 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2178 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2180 # Look for ThePlatform embeds
2181 tp_urls = ThePlatformIE._extract_urls(webpage)
2183 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2185 # Look for Vessel embeds
2186 vessel_urls = VesselIE._extract_urls(webpage)
2188 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2190 # Look for embedded rtl.nl player
2191 matches = re.findall(
2192 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2195 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2197 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2199 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2201 vid_me_embed_url = self._search_regex(
2202 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2203 webpage, 'vid.me embed', default=None)
2204 if vid_me_embed_url is not None:
2205 return self.url_result(vid_me_embed_url, 'Vidme')
2207 # Look for embedded YouTube player
2208 matches = re.findall(r'''(?x)
2218 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2222 return self.playlist_from_matches(
2223 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2225 # Look for lazyYT YouTube embed
2226 matches = re.findall(
2227 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2229 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2231 # Look for Wordpress "YouTube Video Importer" plugin
2232 matches = re.findall(r'''(?x)<div[^>]+
2233 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2234 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2236 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2238 matches = DailymotionIE._extract_urls(webpage)
2240 return self.playlist_from_matches(matches, video_id, video_title)
2242 # Look for embedded Dailymotion playlist player (#3822)
2244 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2246 playlists = re.findall(
2247 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2249 return self.playlist_from_matches(
2250 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2252 # Look for DailyMail embeds
2253 dailymail_urls = DailyMailIE._extract_urls(webpage)
2255 return self.playlist_from_matches(
2256 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2258 # Look for embedded Wistia player
2259 wistia_url = WistiaIE._extract_url(webpage)
2262 '_type': 'url_transparent',
2263 'url': self._proto_relative_url(wistia_url),
2264 'ie_key': WistiaIE.ie_key(),
2265 'uploader': video_uploader,
2268 # Look for SVT player
2269 svt_url = SVTIE._extract_url(webpage)
2271 return self.url_result(svt_url, 'SVT')
2273 # Look for Bandcamp pages with custom domain
2274 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2275 if mobj is not None:
2276 burl = unescapeHTML(mobj.group(1))
2277 # Don't set the extractor because it can be a track url or an album
2278 return self.url_result(burl)
2280 # Look for embedded Vevo player
2282 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2283 if mobj is not None:
2284 return self.url_result(mobj.group('url'))
2286 # Look for embedded Viddler player
2288 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2290 if mobj is not None:
2291 return self.url_result(mobj.group('url'))
2293 # Look for NYTimes player
2295 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2297 if mobj is not None:
2298 return self.url_result(mobj.group('url'))
2300 # Look for Libsyn player
2302 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2303 if mobj is not None:
2304 return self.url_result(mobj.group('url'))
2306 # Look for Ooyala videos
2307 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2308 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2309 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2310 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2311 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2312 if mobj is not None:
2313 embed_token = self._search_regex(
2314 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2315 webpage, 'ooyala embed token', default=None)
2316 return OoyalaIE._build_url_result(smuggle_url(
2319 'embed_token': embed_token,
2322 # Look for multiple Ooyala embeds on SBN network websites
2323 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2324 if mobj is not None:
2325 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2327 return self.playlist_from_matches(
2328 embeds, video_id, video_title,
2329 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2331 # Look for Aparat videos
2332 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2333 if mobj is not None:
2334 return self.url_result(mobj.group(1), 'Aparat')
2336 # Look for MPORA videos
2337 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2338 if mobj is not None:
2339 return self.url_result(mobj.group(1), 'Mpora')
2341 # Look for embedded NovaMov-based player
2343 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2344 (?P<url>http://(?:(?:embed|www)\.)?
2346 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2347 videoweed\.(?:es|com)|
2348 movshare\.(?:net|sx|ag)|
2349 divxstage\.(?:eu|net|ch|co|at|ag))
2350 /embed\.php.+?)\1''', webpage)
2351 if mobj is not None:
2352 return self.url_result(mobj.group('url'))
2354 # Look for embedded Facebook player
2355 facebook_urls = FacebookIE._extract_urls(webpage)
2357 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2359 # Look for embedded VK player
2360 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2361 if mobj is not None:
2362 return self.url_result(mobj.group('url'), 'VK')
2364 # Look for embedded Odnoklassniki player
2365 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2366 if mobj is not None:
2367 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2369 # Look for embedded ivi player
2370 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2371 if mobj is not None:
2372 return self.url_result(mobj.group('url'), 'Ivi')
2374 # Look for embedded Huffington Post player
2376 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2377 if mobj is not None:
2378 return self.url_result(mobj.group('url'), 'HuffPost')
2381 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2382 if mobj is not None:
2383 return self.url_result(mobj.group('url'))
2384 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2385 if mobj is not None:
2386 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2388 # Look for funnyordie embed
2389 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2391 return self.playlist_from_matches(
2392 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2394 # Look for BBC iPlayer embed
2395 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2397 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2399 # Look for embedded RUTV player
2400 rutv_url = RUTVIE._extract_url(webpage)
2402 return self.url_result(rutv_url, 'RUTV')
2404 # Look for embedded TVC player
2405 tvc_url = TVCIE._extract_url(webpage)
2407 return self.url_result(tvc_url, 'TVC')
2409 # Look for embedded SportBox player
2410 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2412 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2414 # Look for embedded XHamster player
2415 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2417 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2419 # Look for embedded TNAFlixNetwork player
2420 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2422 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2424 # Look for embedded PornHub player
2425 pornhub_urls = PornHubIE._extract_urls(webpage)
2427 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2429 # Look for embedded DrTuber player
2430 drtuber_urls = DrTuberIE._extract_urls(webpage)
2432 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2434 # Look for embedded RedTube player
2435 redtube_urls = RedTubeIE._extract_urls(webpage)
2437 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2439 # Look for embedded Tvigle player
2441 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2442 if mobj is not None:
2443 return self.url_result(mobj.group('url'), 'Tvigle')
2445 # Look for embedded TED player
2447 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2448 if mobj is not None:
2449 return self.url_result(mobj.group('url'), 'TED')
2451 # Look for embedded Ustream videos
2452 ustream_url = UstreamIE._extract_url(webpage)
2454 return self.url_result(ustream_url, UstreamIE.ie_key())
2456 # Look for embedded arte.tv player
2458 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2460 if mobj is not None:
2461 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2463 # Look for embedded francetv player
2465 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2467 if mobj is not None:
2468 return self.url_result(mobj.group('url'))
2470 # Look for embedded smotri.com player
2471 smotri_url = SmotriIE._extract_url(webpage)
2473 return self.url_result(smotri_url, 'Smotri')
2475 # Look for embedded Myvi.ru player
2476 myvi_url = MyviIE._extract_url(webpage)
2478 return self.url_result(myvi_url)
2480 # Look for embedded soundcloud player
2481 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2483 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2485 # Look for tunein player
2486 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2488 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2490 # Look for embedded mtvservices player
2491 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2493 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2495 # Look for embedded yahoo player
2497 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2499 if mobj is not None:
2500 return self.url_result(mobj.group('url'), 'Yahoo')
2502 # Look for embedded sbs.com.au player
2506 <meta\s+property="og:video"\s+content=|
2509 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2511 if mobj is not None:
2512 return self.url_result(mobj.group('url'), 'SBS')
2514 # Look for embedded Cinchcast player
2516 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2518 if mobj is not None:
2519 return self.url_result(mobj.group('url'), 'Cinchcast')
2522 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2526 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2528 if mobj is not None:
2529 return self.url_result(mobj.group('url'), 'MLB')
2532 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2534 if mobj is not None:
2535 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2538 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2540 if mobj is not None:
2541 return self.url_result(mobj.group('url'), 'Livestream')
2543 # Look for Zapiks embed
2545 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2546 if mobj is not None:
2547 return self.url_result(mobj.group('url'), 'Zapiks')
2549 # Look for Kaltura embeds
2550 kaltura_url = KalturaIE._extract_url(webpage)
2552 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2554 # Look for EaglePlatform embeds
2555 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2556 if eagleplatform_url:
2557 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2559 # Look for ClipYou (uses EaglePlatform) embeds
2561 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2562 if mobj is not None:
2563 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2565 # Look for Pladform embeds
2566 pladform_url = PladformIE._extract_url(webpage)
2568 return self.url_result(pladform_url)
2570 # Look for Videomore embeds
2571 videomore_url = VideomoreIE._extract_url(webpage)
2573 return self.url_result(videomore_url)
2575 # Look for Webcaster embeds
2576 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2578 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2580 # Look for Playwire embeds
2582 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2583 if mobj is not None:
2584 return self.url_result(mobj.group('url'))
2586 # Look for 5min embeds
2588 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2589 if mobj is not None:
2590 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2592 # Look for Crooks and Liars embeds
2594 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2595 if mobj is not None:
2596 return self.url_result(mobj.group('url'))
2598 # Look for NBC Sports VPlayer embeds
2599 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2601 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2603 # Look for NBC News embeds
2604 nbc_news_embed_url = re.search(
2605 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2606 if nbc_news_embed_url:
2607 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2609 # Look for Google Drive embeds
2610 google_drive_url = GoogleDriveIE._extract_url(webpage)
2611 if google_drive_url:
2612 return self.url_result(google_drive_url, 'GoogleDrive')
2614 # Look for UDN embeds
2616 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2617 if mobj is not None:
2618 return self.url_result(
2619 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2621 # Look for Senate ISVP iframe
2622 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2624 return self.url_result(senate_isvp_url, 'SenateISVP')
2626 # Look for Dailymotion Cloud videos
2627 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2629 return self.url_result(dmcloud_url, 'DailymotionCloud')
2631 # Look for OnionStudios embeds
2632 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2633 if onionstudios_url:
2634 return self.url_result(onionstudios_url)
2636 # Look for ViewLift embeds
2637 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2639 return self.url_result(viewlift_url)
2641 # Look for JWPlatform embeds
2642 jwplatform_url = JWPlatformIE._extract_url(webpage)
2644 return self.url_result(jwplatform_url, 'JWPlatform')
2646 # Look for Digiteka embeds
2647 digiteka_url = DigitekaIE._extract_url(webpage)
2649 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2651 # Look for Arkena embeds
2652 arkena_url = ArkenaIE._extract_url(webpage)
2654 return self.url_result(arkena_url, ArkenaIE.ie_key())
2656 # Look for Piksel embeds
2657 piksel_url = PikselIE._extract_url(webpage)
2659 return self.url_result(piksel_url, PikselIE.ie_key())
2661 # Look for Limelight embeds
2662 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2664 return self.playlist_result(
2665 limelight_urls, video_id, video_title, video_description)
2667 # Look for Anvato embeds
2668 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2670 return self.playlist_result(
2671 anvato_urls, video_id, video_title, video_description)
2673 # Look for AdobeTVVideo embeds
2675 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2677 if mobj is not None:
2678 return self.url_result(
2679 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2682 # Look for Vine embeds
2684 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2686 if mobj is not None:
2687 return self.url_result(
2688 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2690 # Look for VODPlatform embeds
2692 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2694 if mobj is not None:
2695 return self.url_result(
2696 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2698 # Look for Mangomolo embeds
2700 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2702 video\?.*?\bid=(?P<video_id>\d+)|
2703 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2704 ).+?)\1''', webpage)
2705 if mobj is not None:
2707 '_type': 'url_transparent',
2708 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2709 'title': video_title,
2710 'description': video_description,
2711 'thumbnail': video_thumbnail,
2712 'uploader': video_uploader,
2714 video_id = mobj.group('video_id')
2717 'ie_key': 'MangomoloVideo',
2722 'ie_key': 'MangomoloLive',
2723 'id': mobj.group('channel_id'),
2727 # Look for Instagram embeds
2728 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2729 if instagram_embed_url is not None:
2730 return self.url_result(
2731 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2733 # Look for LiveLeak embeds
2734 liveleak_url = LiveLeakIE._extract_url(webpage)
2736 return self.url_result(liveleak_url, 'LiveLeak')
2738 # Look for 3Q SDN embeds
2739 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2742 '_type': 'url_transparent',
2743 'ie_key': ThreeQSDNIE.ie_key(),
2744 'url': self._proto_relative_url(threeqsdn_url),
2745 'title': video_title,
2746 'description': video_description,
2747 'thumbnail': video_thumbnail,
2748 'uploader': video_uploader,
2751 # Look for VBOX7 embeds
2752 vbox7_url = Vbox7IE._extract_url(webpage)
2754 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2756 # Look for DBTV embeds
2757 dbtv_urls = DBTVIE._extract_urls(webpage)
2759 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2761 # Look for Videa embeds
2762 videa_urls = VideaIE._extract_urls(webpage)
2764 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2766 # Look for 20 minuten embeds
2767 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2769 return self.playlist_from_matches(
2770 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2772 # Look for Openload embeds
2773 openload_urls = OpenloadIE._extract_urls(webpage)
2775 return self.playlist_from_matches(
2776 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2778 # Look for VideoPress embeds
2779 videopress_urls = VideoPressIE._extract_urls(webpage)
2781 return self.playlist_from_matches(
2782 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2784 # Look for Rutube embeds
2785 rutube_urls = RutubeIE._extract_urls(webpage)
2787 return self.playlist_from_matches(
2788 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2790 # Look for WashingtonPost embeds
2791 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2793 return self.playlist_from_matches(
2794 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2796 # Look for Mediaset embeds
2797 mediaset_urls = MediasetIE._extract_urls(webpage)
2799 return self.playlist_from_matches(
2800 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2802 # Look for JOJ.sk embeds
2803 joj_urls = JojIE._extract_urls(webpage)
2805 return self.playlist_from_matches(
2806 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2808 # Look for megaphone.fm embeds
2809 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2811 return self.playlist_from_matches(
2812 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2814 def merge_dicts(dict1, dict2):
2816 for k, v in dict1.items():
2819 for k, v in dict2.items():
2822 if (k not in merged or
2823 (isinstance(v, compat_str) and v and
2824 isinstance(merged[k], compat_str) and
2829 # Looking for http://schema.org/VideoObject
2830 json_ld = self._search_json_ld(
2831 webpage, video_id, default={}, expected_type='VideoObject')
2832 if json_ld.get('url'):
2833 return merge_dicts(json_ld, info_dict)
2835 # Look for HTML5 media
2836 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2838 for entry in entries:
2841 'title': video_title,
2843 self._sort_formats(entry['formats'])
2844 return self.playlist_result(entries)
2846 jwplayer_data = self._find_jwplayer_data(
2847 webpage, video_id, transform_source=js_to_json)
2849 info = self._parse_jwplayer_data(
2850 jwplayer_data, video_id, require_title=False, base_url=url)
2851 return merge_dicts(info, info_dict)
2853 def check_video(vurl):
2854 if YoutubeIE.suitable(vurl):
2856 if RtmpIE.suitable(vurl):
2858 vpath = compat_urlparse.urlparse(vurl).path
2859 vext = determine_ext(vpath)
2860 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2862 def filter_video(urls):
2863 return list(filter(check_video, urls))
2865 # Start with something easy: JW Player in SWFObject
2866 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2868 # Look for gorilla-vid style embedding
2869 found = filter_video(re.findall(r'''(?sx)
2873 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2876 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2878 # Broaden the search a little bit
2879 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2881 # Broaden the findall a little bit: JWPlayer JS loader
2882 found = filter_video(re.findall(
2883 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2886 found = filter_video(re.findall(r'''(?xs)
2887 flowplayer\("[^"]+",\s*
2889 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2890 ["']?url["']?\s*:\s*["']([^"']+)["']
2895 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2897 # Try to find twitter cards info
2898 # twitter:player:stream should be checked before twitter:player since
2899 # it is expected to contain a raw stream (see
2900 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2901 found = filter_video(re.findall(
2902 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2904 # We look for Open Graph info:
2905 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2906 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2907 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2908 if m_video_type is not None:
2909 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2911 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2913 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2914 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2917 # Look also in Refresh HTTP header
2918 refresh_header = head_response.headers.get('Refresh')
2920 # In python 2 response HTTP headers are bytestrings
2921 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2922 refresh_header = refresh_header.decode('iso-8859-1')
2923 found = re.search(REDIRECT_REGEX, refresh_header)
2925 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2927 self.report_following_redirect(new_url)
2936 # twitter:player is a https URL to iframe player that may or may not
2937 # be supported by youtube-dl thus this is checked the very last (see
2938 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2939 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2941 return self.url_result(embed_url)
2944 raise UnsupportedError(url)
2947 for video_url in orderedSet(found):
2948 video_url = unescapeHTML(video_url)
2949 video_url = video_url.replace('\\/', '/')
2950 video_url = compat_urlparse.urljoin(url, video_url)
2951 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2953 # Sometimes, jwplayer extraction will result in a YouTube URL
2954 if YoutubeIE.suitable(video_url):
2955 entries.append(self.url_result(video_url, 'Youtube'))
2958 # here's a fun little line of code for you:
2959 video_id = os.path.splitext(video_id)[0]
2963 'uploader': video_uploader,
2964 'title': video_title,
2965 'age_limit': age_limit,
2968 if RtmpIE.suitable(video_url):
2969 entry_info_dict.update({
2970 '_type': 'url_transparent',
2971 'ie_key': RtmpIE.ie_key(),
2974 entries.append(entry_info_dict)
2977 ext = determine_ext(video_url)
2979 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2981 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2983 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2985 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2987 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2988 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2989 # Just matching .ism/manifest is not enough to be reliably sure
2990 # whether it's actually an ISM manifest or some other streaming
2991 # manifest since there are various streaming URL formats
2992 # possible (see [1]) as well as some other shenanigans like
2993 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2995 # Thus the most reasonable way to solve this is to delegate
2996 # to generic extractor in order to look into the contents of
2997 # the manifest itself.
2998 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2999 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3000 entry_info_dict = self.url_result(
3001 smuggle_url(video_url, {'to_generic': True}),
3004 entry_info_dict['url'] = video_url
3006 if entry_info_dict.get('formats'):
3007 self._sort_formats(entry_info_dict['formats'])
3009 entries.append(entry_info_dict)
3011 if len(entries) == 1:
3014 for num, e in enumerate(entries, start=1):
3015 # 'url' results don't have a title
3016 if e.get('title') is not None:
3017 e['title'] = '%s (%d)' % (e['title'], num)
3019 '_type': 'playlist',