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
101 from .vzaar import VzaarIE
104 class GenericIE(InfoExtractor):
105 IE_DESC = 'Generic downloader that works on some sites'
109 # Direct link to a video
111 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
112 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
117 'upload_date': '20100513',
120 # Direct link to media delivered compressed (until Accept-Encoding is *)
122 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
123 'md5': '128c42e68b13950268b648275386fc74',
125 'id': 'FictionJunction-Parallel_Hearts',
127 'title': 'FictionJunction-Parallel_Hearts',
128 'upload_date': '20140522',
130 'expected_warnings': [
131 'URL could be a direct video link, returning it as such.'
133 'skip': 'URL invalid',
135 # Direct download with broken HEAD
137 'url': 'http://ai-radio.org:8000/radio.opus',
144 'skip_download': True, # infinite live stream
146 'expected_warnings': [
147 r'501.*Not Implemented',
151 # Direct link with incorrect MIME type
153 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
154 'md5': '4ccbebe5f36706d85221f204d7eb5913',
156 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
157 'id': '5_Lennart_Poettering_-_Systemd',
159 'title': '5_Lennart_Poettering_-_Systemd',
160 'upload_date': '20141120',
162 'expected_warnings': [
163 'URL could be a direct video link, returning it as such.'
168 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
170 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
171 'title': 'Zero Punctuation',
172 'description': 're:.*groundbreaking video review series.*'
174 'playlist_mincount': 11,
176 # RSS feed with enclosure
178 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
180 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
182 'upload_date': '20150228',
183 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
186 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
188 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
192 'title': 'Automatics, robotics and biocybernetics',
193 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
194 'upload_date': '20130627',
195 'formats': 'mincount:16',
196 'subtitles': 'mincount:1',
199 'force_generic_extractor': True,
200 'skip_download': True,
203 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
205 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
210 'formats': 'mincount:1',
213 'skip_download': True,
216 # SMIL from https://www.restudy.dk/video/play/id/1637
218 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
222 'title': 'video_1637',
223 'formats': 'mincount:3',
226 'skip_download': True,
229 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
231 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
233 'id': 'smil-service',
235 'title': 'smil-service',
236 'formats': 'mincount:1',
239 'skip_download': True,
242 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
244 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
248 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
249 'formats': 'mincount:3',
252 'skip_download': True,
255 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
257 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
259 'id': 'mZlp2ctYIUEB',
261 'title': 'Tikibad ontruimd wegens brand',
262 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
263 'thumbnail': r're:^https?://.*\.jpg$',
267 'skip_download': True,
270 # MPD from http://dash-mse-test.appspot.com/media.html
272 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
273 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
275 'id': 'car-20120827-manifest',
277 'title': 'car-20120827-manifest',
278 'formats': 'mincount:9',
279 'upload_date': '20130904',
282 'format': 'bestvideo',
285 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
287 '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',
292 'formats': 'mincount:8',
296 'skip_download': True,
298 'skip': 'video gone',
300 # m3u8 served with Content-Type: text/plain
302 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
307 'upload_date': '20140720',
308 'formats': 'mincount:11',
312 'skip_download': True,
314 'skip': 'video gone',
318 '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',
322 'upload_date': '20130224',
323 'uploader_id': 'TheVerge',
324 'description': r're:^Chris Ziegler takes a look at the\.*',
325 'uploader': 'The Verge',
326 'title': 'First Firefox OS phones side-by-side',
329 'skip_download': False,
333 # redirect in Refresh HTTP header
334 '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',
338 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
339 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
340 'upload_date': '20150917',
341 'uploader_id': 'brtvofficial',
342 'uploader': 'Boiler Room',
345 'skip_download': False,
349 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
350 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
352 'id': '13601338388002',
354 'uploader': 'www.hodiho.fr',
355 'title': 'R\u00e9gis plante sa Jeep',
358 # bandcamp page with custom domain
360 'add_ie': ['Bandcamp'],
361 'url': 'http://bronyrock.com/track/the-pony-mash',
365 'title': 'The Pony Mash',
366 'uploader': 'M_Pallante',
368 'skip': 'There is a limit of 200 free downloads / month for the test song',
371 # embedded brightcove video
372 # it also tests brightcove videos that need to set the 'Referer'
373 # in the http requests
374 'add_ie': ['BrightcoveLegacy'],
375 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
377 'id': '2765128793001',
379 'title': 'Le cours de bourse : l’analyse technique',
380 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
381 'uploader': 'BFM BUSINESS',
384 'skip_download': True,
388 # embedded with itemprop embedURL and video id spelled as `idVideo`
389 'add_id': ['BrightcoveLegacy'],
390 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
392 'id': '5255628253001',
394 'title': 'md5:37c519b1128915607601e75a87995fc0',
395 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
396 'uploader': 'BFM BUSINESS',
397 'uploader_id': '876450612001',
398 'timestamp': 1482255315,
399 'upload_date': '20161220',
402 'skip_download': True,
406 # https://github.com/rg3/youtube-dl/issues/2253
407 'url': 'http://bcove.me/i6nfkrc3',
408 'md5': '0ba9446db037002366bab3b3eb30c88c',
410 'id': '3101154703001',
412 'title': 'Still no power',
413 'uploader': 'thestar.com',
414 '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.',
416 'add_ie': ['BrightcoveLegacy'],
417 'skip': 'video gone',
420 'url': 'http://www.championat.com/video/football/v/87/87499.html',
421 'md5': 'fb973ecf6e4a78a67453647444222983',
423 'id': '3414141473001',
425 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
426 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
427 'uploader': 'Championat',
431 # https://github.com/rg3/youtube-dl/issues/3541
432 'add_ie': ['BrightcoveLegacy'],
433 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
435 'id': '3866516442001',
437 'title': 'Leer mij vrouwen kennen: Aflevering 1',
438 'description': 'Leer mij vrouwen kennen: Aflevering 1',
439 'uploader': 'SBS Broadcasting',
441 'skip': 'Restricted to Netherlands',
443 'skip_download': True, # m3u8 download
447 # Brightcove video in <iframe>
448 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
449 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
451 'id': '5360463607001',
453 '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',
454 '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。',
455 'uploader': 'United Nations',
456 'uploader_id': '1362235914001',
457 'timestamp': 1489593889,
458 'upload_date': '20170315',
460 'add_ie': ['BrightcoveLegacy'],
463 # Brightcove with alternative playerID key
464 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
466 'id': 'nmeth.2062_SV1',
467 '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',
471 'id': '2228375078001',
473 'title': 'nmeth.2062-sv1',
474 'description': 'nmeth.2062-sv1',
475 'timestamp': 1363357591,
476 'upload_date': '20130315',
477 'uploader': 'Nature Publishing Group',
478 'uploader_id': '1964492299001',
483 # Brightcove with UUID in videoPlayer
484 'url': 'http://www8.hp.com/cn/zh/home.html',
486 'id': '5255815316001',
488 'title': 'Sprocket Video - China',
489 'description': 'Sprocket Video - China',
490 'uploader': 'HP-Video Gallery',
491 'timestamp': 1482263210,
492 'upload_date': '20161220',
493 'uploader_id': '1107601872001',
496 'skip_download': True, # m3u8 download
498 'skip': 'video rotates...weekly?',
501 # Brightcove:new type [2].
502 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
503 'md5': '2b35148fcf48da41c9fb4591650784f3',
505 'id': '5348741021001',
507 'upload_date': '20170306',
508 'uploader_id': '4191638492001',
509 'timestamp': 1488769918,
510 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
515 # Alternative brightcove <video> attributes
516 '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/',
518 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
519 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
522 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
524 'id': '5311302538001',
526 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
527 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
528 'timestamp': 1486321708,
529 'upload_date': '20170205',
530 'uploader_id': '800000640001',
532 'only_matching': True,
536 # Brightcove with UUID in videoPlayer
537 'url': 'http://www8.hp.com/cn/zh/home.html',
539 'id': '5255815316001',
541 'title': 'Sprocket Video - China',
542 'description': 'Sprocket Video - China',
543 'uploader': 'HP-Video Gallery',
544 'timestamp': 1482263210,
545 'upload_date': '20161220',
546 'uploader_id': '1107601872001',
549 'skip_download': True, # m3u8 download
554 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
555 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
557 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
559 'title': '2cc213299525360.mov', # that's what we get
562 'add_ie': ['Ooyala'],
565 # ooyala video embedded with http://player.ooyala.com/iframe.js
566 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
568 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
570 'title': '"Steve Jobs: Man in the Machine" trailer',
571 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
575 'skip_download': True,
577 'skip': 'movie expired',
579 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
581 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
583 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
585 'title': 'Steampunk Fest Comes to Honesdale',
589 'skip_download': True,
594 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
598 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
599 'upload_date': '20140225',
600 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
601 'uploader': 'Tested',
602 'uploader_id': 'testedcom',
604 # No need to test YoutubeIE here
606 'skip_download': True,
611 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
615 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
616 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
618 # HEAD requests lead to endless 301, while GET is OK
619 'expected_warnings': ['301'],
623 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
627 'title': 'Охотское море стало целиком российским',
628 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
632 'skip_download': True,
637 '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/',
641 'title': 'Дошкольное воспитание',
646 'url': 'http://www.vestifinance.ru/articles/25753',
649 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
654 'title': 'Госзаказ. День 3',
660 'title': 'Госзаказ. День 2',
666 'title': 'Госзаказ. День 1',
672 'skip_download': True,
677 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
679 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
681 'title': 'Ужастики, русский трейлер (2015)',
682 'thumbnail': r're:^https?://.*\.jpg$',
688 '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',
691 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
693 'playlist_mincount': 7,
694 # This forum does not allow <iframe> syntaxes anymore
695 # Now HTML tags are displayed as-is
696 'skip': 'No videos on this page',
700 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
701 'md5': '65fdff94098e4a607385a60c5177c638',
705 'title': 'Hidden miracles of the natural world',
706 'uploader': 'Louie Schwartzberg',
707 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
710 # nowvideo embed hidden behind percent encoding
712 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
713 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
715 'id': '06e53103ca9aa',
717 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
718 'description': 'No description',
723 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
724 'md5': '7653032cbb25bf6c80d80f217055fa43',
726 'id': '048195-004_PLUS7-F',
729 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
730 'upload_date': '20140320',
733 'skip_download': 'Requires rtmpdump'
735 'skip': 'video gone',
739 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
743 'title': 'Alcaline, le concert avec Calogero',
744 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
745 'upload_date': '20150226',
746 'timestamp': 1424989860,
751 'skip_download': True,
753 'expected_warnings': [
759 'url': 'http://www.wired.com/2014/04/honda-asimo/',
760 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
762 'id': '53501be369702d3275860000',
764 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
769 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
770 'md5': '441aeeb82eb72c422c7f14ec533999cd',
772 'id': 'k2mm4bCdJ6CQ2i7c8o2',
774 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
775 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
777 'uploader_id': 'xgditw',
778 'upload_date': '20140425',
779 'timestamp': 1398441542,
781 'add_ie': ['Dailymotion'],
785 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
789 'title': 'Care worker punches elderly dementia patient in head 11 times',
790 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
792 'add_ie': ['DailyMail'],
794 'skip_download': True,
799 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
803 'title': 'The NBL Auction 2014',
804 'uploader': 'BADMINTON England',
805 'uploader_id': 'BADMINTONEvents',
806 'upload_date': '20140603',
807 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
809 'add_ie': ['Youtube'],
811 'skip_download': True,
816 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
817 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
819 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
821 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
822 'description': 'Two valets share their love for movie star Liam Neesons.',
823 'timestamp': 1349922600,
824 'upload_date': '20121011',
827 # YouTube embed via <data-embed-url="">
829 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
833 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
834 'uploader': 'Gameloft',
835 'uploader_id': 'gameloft',
836 'upload_date': '20140828',
837 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
840 'skip_download': True,
843 # YouTube <object> embed
845 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
846 'md5': '516718101ec834f74318df76259fb3cc',
850 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
851 'upload_date': '20080526',
852 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
853 'uploader': 'Christopher Sykes',
854 'uploader_id': 'ChristopherJSykes',
856 'add_ie': ['Youtube'],
860 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
862 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
864 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
865 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
870 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
872 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
873 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
879 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
884 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
885 'md5': '9d65602bf31c6e20014319c7d07fba27',
887 'id': '5123ea6d5e5a7',
890 'uploader': 'www.handjobhub.com',
891 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
894 # Multiple brightcove videos
895 # https://github.com/rg3/youtube-dl/issues/2283
897 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
899 'id': 'always-never',
900 'title': 'Always / Never - The New Yorker',
904 'extract_flat': False,
905 'skip_download': True,
910 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
911 'md5': '96f09a37e44da40dd083e12d9a683327',
915 'title': 'Ump changes call to ball',
916 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
918 'timestamp': 1401537900,
919 'upload_date': '20140531',
920 'thumbnail': r're:^https?://.*\.jpg$',
925 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
926 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
930 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
931 'description': 'a Paywall Videos video from Remilon',
933 'uploader': 'study.com',
934 'timestamp': 1459678540,
935 'upload_date': '20160403',
936 'filesize': 24687186,
940 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
941 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
945 'title': 'Conversation about Hexagonal Rails Part 1',
946 'description': 'a Martin Fowler video from ThoughtWorks',
948 'uploader': 'thoughtworks.wistia.com',
949 'timestamp': 1401832161,
950 'upload_date': '20140603',
953 # Wistia standard embed (async)
955 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
959 'title': 'Drip Brennan Dunn Workshop',
960 'description': 'a JV Webinars video from getdrip-1',
962 'timestamp': 1463607249,
963 'upload_date': '20160518',
966 'skip_download': True,
971 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
975 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
976 'uploader': 'Sophos Security',
977 'title': 'Chet Chat 171 - Oct 29, 2014',
978 'upload_date': '20141029',
981 # Soundcloud multiple embeds
983 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
986 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
988 'playlist_mincount': 7,
990 # TuneIn station embed
992 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
997 'location': 'Paris, France',
1002 'skip_download': True,
1007 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1011 'upload_date': '20141112',
1012 'title': 'Rosetta #CometLanding webcast HL 10',
1015 # Another Livestream embed, without 'new.' in URL
1017 'url': 'https://www.freespeech.org/',
1021 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1025 'skip_download': True,
1030 'url': 'https://skiplagged.com/',
1033 'title': 'Skiplagged: The smart way to find cheap flights',
1035 'playlist_mincount': 1,
1036 'add_ie': ['Youtube'],
1040 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1044 'upload_date': '20141126',
1045 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1050 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1052 'id': '730m_DandD_1901_512k',
1054 'uploader': 'www.abc.net.au',
1055 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1058 # embedded viddler video
1060 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1064 'uploader': 'deadspin',
1065 'title': 'WALL-TO-GORTAT',
1066 'timestamp': 1422285291,
1067 'upload_date': '20150126',
1069 'add_ie': ['Viddler'],
1073 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1077 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1078 'description': 'md5:601cb790edd05908957dae8aaa866465',
1079 'upload_date': '20150220',
1081 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1085 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1087 'id': 'Mrj4DVp2zeA',
1089 'upload_date': '20150212',
1090 'uploader': 'The National Archives UK',
1091 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1092 'uploader_id': 'NationalArchives08',
1093 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1098 'url': 'http://www.suffolk.edu/sjc/',
1102 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1103 'uploader': 'www.suffolk.edu',
1106 'skip_download': True,
1111 'url': 'http://www.indiedb.com/games/king-machine/videos',
1115 'title': 'king machine trailer 1',
1116 'thumbnail': r're:^https?://.*\.jpg$',
1120 # JWPlayer config passed as variable
1121 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1125 'title': 'ARIELE | Tube Cup',
1126 'uploader': 'www.txxx.com',
1130 'skip_download': True,
1135 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1136 'playlist_mincount': 5,
1138 'id': 'aanslagen-kopenhagen',
1139 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1144 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1148 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1151 # Kaltura embed (different embed code)
1153 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1157 'upload_date': '20150127',
1158 'uploader_id': 'PremierMedia',
1160 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1163 # Kaltura embed with single quotes
1165 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1170 'timestamp': 1355743100,
1171 'upload_date': '20121217',
1172 'uploader_id': 'batchUser',
1174 'add_ie': ['Kaltura'],
1177 # Kaltura embedded via quoted entry_id
1178 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1182 'title': '06_matthew_brender_raj_dutt',
1183 'timestamp': 1466638791,
1184 'upload_date': '20160622',
1186 'add_ie': ['Kaltura'],
1187 'expected_warnings': [
1188 'Could not send HEAD request'
1191 'skip_download': True,
1195 # Kaltura embedded, some fileExt broken (#11480)
1196 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1200 'title': 'Our "Standard Models" of particle physics and cosmology',
1201 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1202 'timestamp': 1321158993,
1203 'upload_date': '20111113',
1204 'uploader_id': 'kps1',
1206 'add_ie': ['Kaltura'],
1209 # Kaltura iframe embed
1210 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1211 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1215 'title': 'I. M. Pei: A Centennial Celebration',
1216 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1217 'upload_date': '20170403',
1218 'uploader_id': 'batchUser',
1219 'timestamp': 1491232186,
1221 'add_ie': ['Kaltura'],
1223 # EaglePlatform embed (generic URL)
1225 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1226 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1230 'title': 'Навальный вышел на свободу',
1231 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1232 'thumbnail': r're:^https?://.*\.jpg$',
1238 'skip_download': True,
1241 # referrer protected EaglePlatform embed
1243 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1247 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1248 'thumbnail': r're:^https?://.*\.jpg$',
1253 'skip_download': True,
1256 # ClipYou (EaglePlatform) embed (custom URL)
1258 'url': 'http://muz-tv.ru/play/7129/',
1259 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1263 'title': "'O Sole Mio",
1264 'thumbnail': r're:^https?://.*\.jpg$',
1269 'skip_download': True,
1274 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1278 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1279 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1280 'thumbnail': r're:^https?://.*\.jpg$',
1287 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1291 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1292 'thumbnail': r're:^https?://.*\.png$',
1298 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1299 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1303 'title': 'Facebook Creates "On This Day" | Crunch Report',
1308 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1312 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1317 # Crooks and Liars embed
1319 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1323 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1324 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1325 'timestamp': 1428207000,
1326 'upload_date': '20150405',
1327 'uploader': 'Heather',
1330 # Crooks and Liars external embed
1332 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1334 'id': 'MTE3MjUtMzQ2MzA',
1336 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1337 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1338 'timestamp': 1265032391,
1339 'upload_date': '20100201',
1340 'uploader': 'Heather',
1343 # NBC Sports vplayer embed
1345 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1347 'id': 'ln7x1qSThw4k',
1349 'title': "PFT Live: New leader in the 'new-look' defense",
1350 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1351 'uploader': 'NBCU-SPORTS',
1352 'upload_date': '20140107',
1353 'timestamp': 1389118457,
1358 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1359 'md5': '1aa589c675898ae6d37a17913cf68d66',
1361 'id': '701714499682',
1363 'title': 'PREVIEW: On Assignment: David Letterman',
1364 '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.',
1369 'url': 'https://video.udn.com/news/300346',
1370 'md5': 'fd2060e988c326991037b9aff9df21a6',
1374 'title': '中一中男師變性 全校師生力挺',
1375 'thumbnail': r're:^https?://.*\.jpg$',
1379 'skip_download': True,
1384 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1386 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1388 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1389 'title': 'This is what separates the Excel masters from the wannabes',
1390 'duration': 191.933,
1394 'skip_download': True,
1397 # Brightcove URL in single quotes
1399 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1400 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1402 'id': '4255764656001',
1404 'title': 'SN Presents: Russell Martin, World Citizen',
1405 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1406 'uploader': 'Rogers Sportsnet',
1407 'uploader_id': '1704050871',
1408 'upload_date': '20150525',
1409 'timestamp': 1432570283,
1412 # Dailymotion Cloud video
1414 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1415 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1419 'title': 'Sauvons les abeilles ! - Le débat',
1420 'description': 'md5:d9082128b1c5277987825d684939ca26',
1421 'thumbnail': r're:^https?://.*\.jpe?g$',
1422 'timestamp': 1434970506,
1423 'upload_date': '20150622',
1424 'uploader': 'Public Sénat',
1425 'uploader_id': 'xa9gza',
1428 # OnionStudios embed
1430 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1434 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1435 'thumbnail': r're:^https?://.*\.jpe?g$',
1436 'uploader': 'ClickHole',
1437 'uploader_id': 'clickhole',
1442 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1444 'id': '74849a00-85a9-11e1-9660-123139220831',
1446 'title': '#whilewewatch',
1449 # AdobeTVVideo embed
1451 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1452 'md5': '43662b577c018ad707a63766462b1e87',
1456 'title': 'New experience with Acrobat DC',
1457 'description': 'New experience with Acrobat DC',
1458 'duration': 248.667,
1461 # BrightcoveInPageEmbed embed
1463 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1465 'id': '4238694884001',
1467 'title': 'Tabletop: Dread, Last Thoughts',
1468 'description': 'Tabletop: Dread, Last Thoughts',
1472 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1473 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1475 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1477 'id': '4785848093001',
1479 'title': 'The Cardinal Pell Interview',
1480 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1481 'uploader': 'GlobeCast Australia - GlobeStream',
1482 'uploader_id': '2733773828001',
1483 'upload_date': '20160304',
1484 'timestamp': 1457083087,
1488 'skip_download': True,
1492 # Brightcove embed with whitespace around attribute names
1493 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1495 'id': '3167554373001',
1497 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1498 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1499 'uploader_id': '1079349493',
1500 'upload_date': '20140207',
1501 'timestamp': 1391810548,
1504 'skip_download': True,
1507 # Another form of arte.tv embed
1509 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1510 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1512 'id': '030273-562_PLUS7-F',
1514 'title': 'ARTE Reportage - Nulle part, en France',
1515 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1516 'upload_date': '20160409',
1521 'url': 'http://www.wykop.pl/link/3088787/',
1522 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1524 'id': '874_1459135191',
1526 'title': 'Man shows poor quality of new apartment building',
1527 'description': 'The wall is like a sand pile.',
1528 'uploader': 'Lake8737',
1531 # Duplicated embedded video URLs
1533 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1535 'id': '149298443_480_16c25b74_2',
1537 'title': 'vs. Blue Orange Spring Game',
1538 'uploader': 'www.hudl.com',
1541 # twitter:player:stream embed
1543 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1547 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1548 'uploader': 'www.rtl.be',
1552 'skip_download': True,
1555 # twitter:player embed
1557 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1558 'md5': 'a3e0df96369831de324f0778e126653c',
1560 'id': '4909620399001',
1562 'title': 'What Do Black Holes Sound Like?',
1563 'description': 'what do black holes sound like',
1564 'upload_date': '20160524',
1565 'uploader_id': '29913724001',
1566 'timestamp': 1464107587,
1567 'uploader': 'TheAtlantic',
1569 'add_ie': ['BrightcoveLegacy'],
1573 'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
1577 'title': "Yesterday's Jam (OV)",
1578 'description': 'md5:09bc0984723fed34e2581624a84e05f0',
1579 'timestamp': 1492594816,
1580 'upload_date': '20170419',
1583 'format': 'bestvideo',
1584 'skip_download': True,
1587 # Facebook <iframe> embed
1589 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1590 'md5': 'fbcde74f534176ecb015849146dd3aee',
1592 'id': '599637780109885',
1594 'title': 'Facebook video #599637780109885',
1597 # Facebook <iframe> embed, plugin video
1599 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1601 'id': '1754168231264132',
1603 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1604 'uploader': 'Tariq Ramadan (official)',
1605 'timestamp': 1496758379,
1606 'upload_date': '20170606',
1609 'skip_download': True,
1612 # Facebook API embed
1614 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1615 'md5': 'a47372ee61b39a7b90287094d447d94e',
1617 'id': '10153467542406923',
1619 'title': 'Facebook video #10153467542406923',
1622 # Wordpress "YouTube Video Importer" plugin
1624 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1625 'md5': 'd16797741b560b485194eddda8121b48',
1627 'id': 'HNTXWDXV9Is',
1629 'title': 'Blue Devils Drumline Stanford lot 2016',
1630 'upload_date': '20160627',
1631 'uploader_id': 'GENOCIDE8GENERAL10',
1632 'uploader': 'cylus cyrus',
1636 # video stored on custom kaltura server
1637 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1638 'md5': '537617d06e64dfed891fa1593c4b30cc',
1642 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1643 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1644 'uploader_id': 'videos.expansion@el-mundo.net',
1645 'upload_date': '20150429',
1646 'timestamp': 1430303472,
1648 'add_ie': ['Kaltura'],
1651 # Non-standard Vimeo embed
1652 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1653 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1657 'title': 'Understanding the web - Teaser',
1658 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1659 'upload_date': '20151214',
1660 'uploader': 'OpenClassrooms',
1661 'uploader_id': 'openclassrooms',
1663 'add_ie': ['Vimeo'],
1666 # generic vimeo embed that requires original URL passed as Referer
1667 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1668 'only_matching': True,
1671 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1672 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1674 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1676 'title': 'Big Buck Bunny',
1677 'description': 'Royalty free test video',
1678 'timestamp': 1432816365,
1679 'upload_date': '20150528',
1683 'skip_download': True,
1685 'add_ie': [ArkenaIE.ie_key()],
1688 '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/',
1692 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1695 'skip_download': True,
1697 'add_ie': [Vbox7IE.ie_key()],
1701 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1704 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1706 'playlist_mincount': 3,
1710 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1712 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1713 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1715 'playlist_mincount': 2,
1719 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1723 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1724 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1727 'skip_download': True,
1729 'add_ie': [TwentyMinutenIE.ie_key()],
1733 'url': 'https://en.support.wordpress.com/videopress/',
1737 'title': 'IMG_5786',
1738 'timestamp': 1435711927,
1739 'upload_date': '20150701',
1742 'skip_download': True,
1744 'add_ie': [VideoPressIE.ie_key()],
1748 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1750 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1752 'title': 'Магаззино: Казань 2',
1753 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1754 'uploader': 'Магаззино',
1755 'upload_date': '20170228',
1756 'uploader_id': '996642',
1759 'skip_download': True,
1761 'add_ie': [RutubeIE.ie_key()],
1764 # ThePlatform embedded with whitespaces in URLs
1765 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1766 'only_matching': True,
1769 # Senate ISVP iframe https
1770 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1771 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1773 'id': 'govtaff020316',
1775 'title': 'Integrated Senate Video Player',
1777 'add_ie': [SenateISVPIE.ie_key()],
1780 # Limelight embeds (1 channel embed + 4 media embeds)
1781 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1783 'id': 'FacilitatorTraining2017',
1784 'title': 'Facilitator Training 2017',
1786 'playlist_mincount': 5,
1789 # Limelight embed (LimelightPlayerUtil.embed)
1790 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1792 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1794 'title': '07448641',
1795 'timestamp': 1499890639,
1796 'upload_date': '20170712',
1799 'skip_download': True,
1801 'add_ie': ['LimelightMedia'],
1804 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1806 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1807 'title': 'Standoff with Walnut Creek murder suspect ends',
1808 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1810 'playlist_mincount': 4,
1813 # WashingtonPost embed
1814 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1816 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1818 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1819 '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.',
1820 'timestamp': 1455216756,
1821 'uploader': 'The Washington Post',
1822 'upload_date': '20160211',
1824 'add_ie': [WashingtonPostIE.ie_key()],
1828 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1832 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1835 'skip_download': True,
1837 'add_ie': [MediasetIE.ie_key()],
1841 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1843 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1844 'title': 'Slovenskom sa prehnala vlna silných búrok',
1846 'playlist_mincount': 5,
1847 'add_ie': [JojIE.ie_key()],
1850 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1851 'url': 'https://tvrain.ru/amp/418921/',
1852 'md5': 'cc00413936695987e8de148b67d14f1d',
1856 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1861 'url': 'http://help.vzaar.com/article/165-embedding-video',
1862 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1866 'title': 'Building A Business Online: Principal Chairs Q & A',
1870 # # TODO: find another test
1871 # # http://schema.org/VideoObject
1872 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1873 # 'md5': '888dcf08b7ea671381f00fab74692755',
1875 # 'id': 'nyvTSJMKId',
1877 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1878 # 'description': '#love for cats.',
1879 # 'timestamp': 1461244995,
1880 # 'upload_date': '20160421',
1883 # 'force_generic_extractor': True,
1888 def report_following_redirect(self, new_url):
1889 """Report information extraction."""
1890 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1892 def _extract_rss(self, url, video_id, doc):
1893 playlist_title = doc.find('./channel/title').text
1894 playlist_desc_el = doc.find('./channel/description')
1895 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1898 for it in doc.findall('./channel/item'):
1899 next_url = xpath_text(it, 'link', fatal=False)
1901 enclosure_nodes = it.findall('./enclosure')
1902 for e in enclosure_nodes:
1903 next_url = e.attrib.get('url')
1911 '_type': 'url_transparent',
1913 'title': it.find('title').text,
1917 '_type': 'playlist',
1919 'title': playlist_title,
1920 'description': playlist_desc,
1924 def _extract_camtasia(self, url, video_id, webpage):
1925 """ Returns None if no camtasia video can be found. """
1927 camtasia_cfg = self._search_regex(
1928 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1929 webpage, 'camtasia configuration file', default=None)
1930 if camtasia_cfg is None:
1933 title = self._html_search_meta('DC.title', webpage, fatal=True)
1935 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1936 camtasia_cfg = self._download_xml(
1937 camtasia_url, video_id,
1938 note='Downloading camtasia configuration',
1939 errnote='Failed to download camtasia configuration')
1940 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1943 for n in fileset_node.getchildren():
1944 url_n = n.find('./uri')
1949 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1950 'title': '%s - %s' % (title, n.tag),
1951 'url': compat_urlparse.urljoin(url, url_n.text),
1952 'duration': float_or_none(n.find('./duration').text),
1956 '_type': 'playlist',
1961 def _real_extract(self, url):
1962 if url.startswith('//'):
1965 'url': self.http_scheme() + url,
1968 parsed_url = compat_urlparse.urlparse(url)
1969 if not parsed_url.scheme:
1970 default_search = self._downloader.params.get('default_search')
1971 if default_search is None:
1972 default_search = 'fixup_error'
1974 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1976 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1977 return self.url_result('http://' + url)
1978 elif default_search != 'fixup_error':
1979 if default_search == 'auto_warning':
1980 if re.match(r'^(?:url|URL)$', url):
1981 raise ExtractorError(
1982 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1985 self._downloader.report_warning(
1986 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1987 return self.url_result('ytsearch:' + url)
1989 if default_search in ('error', 'fixup_error'):
1990 raise ExtractorError(
1991 '%r is not a valid URL. '
1992 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1993 % (url, url), expected=True)
1995 if ':' not in default_search:
1996 default_search += ':'
1997 return self.url_result(default_search + url)
1999 url, smuggled_data = unsmuggle_url(url)
2000 force_videoid = None
2001 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2002 if smuggled_data and 'force_videoid' in smuggled_data:
2003 force_videoid = smuggled_data['force_videoid']
2004 video_id = force_videoid
2006 video_id = self._generic_id(url)
2008 self.to_screen('%s: Requesting header' % video_id)
2010 head_req = HEADRequest(url)
2011 head_response = self._request_webpage(
2013 note=False, errnote='Could not send HEAD request to %s' % url,
2016 if head_response is not False:
2017 # Check for redirect
2018 new_url = head_response.geturl()
2020 self.report_following_redirect(new_url)
2022 new_url = smuggle_url(
2023 new_url, {'force_videoid': force_videoid})
2024 return self.url_result(new_url)
2026 full_response = None
2027 if head_response is False:
2028 request = sanitized_Request(url)
2029 request.add_header('Accept-Encoding', '*')
2030 full_response = self._request_webpage(request, video_id)
2031 head_response = full_response
2035 'title': self._generic_title(url),
2036 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2039 # Check for direct link to a video
2040 content_type = head_response.headers.get('Content-Type', '').lower()
2041 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2043 format_id = compat_str(m.group('format_id'))
2044 if format_id.endswith('mpegurl'):
2045 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2046 elif format_id == 'f4m':
2047 formats = self._extract_f4m_formats(url, video_id)
2050 'format_id': format_id,
2052 'vcodec': 'none' if m.group('type') == 'audio' else None
2054 info_dict['direct'] = True
2055 self._sort_formats(formats)
2056 info_dict['formats'] = formats
2059 if not self._downloader.params.get('test', False) and not is_intentional:
2060 force = self._downloader.params.get('force_generic_extractor', False)
2061 self._downloader.report_warning(
2062 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2064 if not full_response:
2065 request = sanitized_Request(url)
2066 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2067 # making it impossible to download only chunk of the file (yet we need only 512kB to
2068 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2069 # that will always result in downloading the whole file that is not desirable.
2070 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2071 # to accept raw bytes and being able to download only a chunk.
2072 # It may probably better to solve this by checking Content-Type for application/octet-stream
2073 # after HEAD request finishes, but not sure if we can rely on this.
2074 request.add_header('Accept-Encoding', '*')
2075 full_response = self._request_webpage(request, video_id)
2077 first_bytes = full_response.read(512)
2079 # Is it an M3U playlist?
2080 if first_bytes.startswith(b'#EXTM3U'):
2081 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2082 self._sort_formats(info_dict['formats'])
2085 # Maybe it's a direct link to a video?
2086 # Be careful not to download the whole thing!
2087 if not is_html(first_bytes):
2088 self._downloader.report_warning(
2089 'URL could be a direct video link, returning it as such.')
2096 webpage = self._webpage_read_content(
2097 full_response, url, video_id, prefix=first_bytes)
2099 self.report_extraction(video_id)
2101 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2103 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2104 if doc.tag == 'rss':
2105 return self._extract_rss(url, video_id, doc)
2106 elif doc.tag == 'SmoothStreamingMedia':
2107 info_dict['formats'] = self._parse_ism_formats(doc, url)
2108 self._sort_formats(info_dict['formats'])
2110 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2111 smil = self._parse_smil(doc, url, video_id)
2112 self._sort_formats(smil['formats'])
2114 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2115 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2116 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2117 info_dict['formats'] = self._parse_mpd_formats(
2119 mpd_base_url=full_response.geturl().rpartition('/')[0],
2121 self._sort_formats(info_dict['formats'])
2123 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2124 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2125 self._sort_formats(info_dict['formats'])
2127 except compat_xml_parse_error:
2130 # Is it a Camtasia project?
2131 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2132 if camtasia_res is not None:
2135 # Sometimes embedded video player is hidden behind percent encoding
2136 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2137 # Unescaping the whole page allows to handle those cases in a generic way
2138 webpage = compat_urllib_parse_unquote(webpage)
2140 # it's tempting to parse this further, but you would
2141 # have to take into account all the variations like
2142 # Video Title - Site Name
2143 # Site Name | Video Title
2144 # Video Title - Tagline | Site Name
2145 # and so on and so forth; it's just not practical
2146 video_title = self._og_search_title(
2147 webpage, default=None) or self._html_search_regex(
2148 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2151 # Try to detect age limit automatically
2152 age_limit = self._rta_search(webpage)
2153 # And then there are the jokers who advertise that they use RTA,
2154 # but actually don't.
2155 AGE_LIMIT_MARKERS = [
2156 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2158 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2161 # video uploader is domain name
2162 video_uploader = self._search_regex(
2163 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2165 video_description = self._og_search_description(webpage, default=None)
2166 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2169 'title': video_title,
2170 'description': video_description,
2171 'thumbnail': video_thumbnail,
2172 'age_limit': age_limit,
2175 # Look for Brightcove Legacy Studio embeds
2176 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2180 'url': smuggle_url(bc_url, {'Referer': url}),
2181 'ie_key': 'BrightcoveLegacy'
2182 } for bc_url in bc_urls]
2185 '_type': 'playlist',
2186 'title': video_title,
2191 # Look for Brightcove New Studio embeds
2192 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2194 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2196 # Look for Nexx embeds
2197 nexx_urls = NexxIE._extract_urls(webpage)
2199 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2201 # Look for Nexx iFrame embeds
2202 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2204 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2206 # Look for ThePlatform embeds
2207 tp_urls = ThePlatformIE._extract_urls(webpage)
2209 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2211 # Look for Vessel embeds
2212 vessel_urls = VesselIE._extract_urls(webpage)
2214 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2216 # Look for embedded rtl.nl player
2217 matches = re.findall(
2218 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2221 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2223 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2225 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2227 vid_me_embed_url = self._search_regex(
2228 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2229 webpage, 'vid.me embed', default=None)
2230 if vid_me_embed_url is not None:
2231 return self.url_result(vid_me_embed_url, 'Vidme')
2233 # Look for embedded YouTube player
2234 matches = re.findall(r'''(?x)
2244 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2248 return self.playlist_from_matches(
2249 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2251 # Look for lazyYT YouTube embed
2252 matches = re.findall(
2253 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2255 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2257 # Look for Wordpress "YouTube Video Importer" plugin
2258 matches = re.findall(r'''(?x)<div[^>]+
2259 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2260 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2262 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2264 matches = DailymotionIE._extract_urls(webpage)
2266 return self.playlist_from_matches(matches, video_id, video_title)
2268 # Look for embedded Dailymotion playlist player (#3822)
2270 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2272 playlists = re.findall(
2273 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2275 return self.playlist_from_matches(
2276 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2278 # Look for DailyMail embeds
2279 dailymail_urls = DailyMailIE._extract_urls(webpage)
2281 return self.playlist_from_matches(
2282 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2284 # Look for embedded Wistia player
2285 wistia_url = WistiaIE._extract_url(webpage)
2288 '_type': 'url_transparent',
2289 'url': self._proto_relative_url(wistia_url),
2290 'ie_key': WistiaIE.ie_key(),
2291 'uploader': video_uploader,
2294 # Look for SVT player
2295 svt_url = SVTIE._extract_url(webpage)
2297 return self.url_result(svt_url, 'SVT')
2299 # Look for Bandcamp pages with custom domain
2300 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2301 if mobj is not None:
2302 burl = unescapeHTML(mobj.group(1))
2303 # Don't set the extractor because it can be a track url or an album
2304 return self.url_result(burl)
2306 # Look for embedded Vevo player
2308 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2309 if mobj is not None:
2310 return self.url_result(mobj.group('url'))
2312 # Look for embedded Viddler player
2314 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2316 if mobj is not None:
2317 return self.url_result(mobj.group('url'))
2319 # Look for NYTimes player
2321 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2323 if mobj is not None:
2324 return self.url_result(mobj.group('url'))
2326 # Look for Libsyn player
2328 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2329 if mobj is not None:
2330 return self.url_result(mobj.group('url'))
2332 # Look for Ooyala videos
2333 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2334 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2335 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2336 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2337 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2338 if mobj is not None:
2339 embed_token = self._search_regex(
2340 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2341 webpage, 'ooyala embed token', default=None)
2342 return OoyalaIE._build_url_result(smuggle_url(
2345 'embed_token': embed_token,
2348 # Look for multiple Ooyala embeds on SBN network websites
2349 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2350 if mobj is not None:
2351 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2353 return self.playlist_from_matches(
2354 embeds, video_id, video_title,
2355 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2357 # Look for Aparat videos
2358 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2359 if mobj is not None:
2360 return self.url_result(mobj.group(1), 'Aparat')
2362 # Look for MPORA videos
2363 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2364 if mobj is not None:
2365 return self.url_result(mobj.group(1), 'Mpora')
2367 # Look for embedded NovaMov-based player
2369 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2370 (?P<url>http://(?:(?:embed|www)\.)?
2372 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2373 videoweed\.(?:es|com)|
2374 movshare\.(?:net|sx|ag)|
2375 divxstage\.(?:eu|net|ch|co|at|ag))
2376 /embed\.php.+?)\1''', webpage)
2377 if mobj is not None:
2378 return self.url_result(mobj.group('url'))
2380 # Look for embedded Facebook player
2381 facebook_urls = FacebookIE._extract_urls(webpage)
2383 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2385 # Look for embedded VK player
2386 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2387 if mobj is not None:
2388 return self.url_result(mobj.group('url'), 'VK')
2390 # Look for embedded Odnoklassniki player
2391 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2392 if mobj is not None:
2393 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2395 # Look for embedded ivi player
2396 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2397 if mobj is not None:
2398 return self.url_result(mobj.group('url'), 'Ivi')
2400 # Look for embedded Huffington Post player
2402 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2403 if mobj is not None:
2404 return self.url_result(mobj.group('url'), 'HuffPost')
2407 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2408 if mobj is not None:
2409 return self.url_result(mobj.group('url'))
2410 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2411 if mobj is not None:
2412 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2414 # Look for funnyordie embed
2415 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2417 return self.playlist_from_matches(
2418 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2420 # Look for BBC iPlayer embed
2421 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2423 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2425 # Look for embedded RUTV player
2426 rutv_url = RUTVIE._extract_url(webpage)
2428 return self.url_result(rutv_url, 'RUTV')
2430 # Look for embedded TVC player
2431 tvc_url = TVCIE._extract_url(webpage)
2433 return self.url_result(tvc_url, 'TVC')
2435 # Look for embedded SportBox player
2436 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2438 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2440 # Look for embedded XHamster player
2441 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2443 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2445 # Look for embedded TNAFlixNetwork player
2446 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2448 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2450 # Look for embedded PornHub player
2451 pornhub_urls = PornHubIE._extract_urls(webpage)
2453 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2455 # Look for embedded DrTuber player
2456 drtuber_urls = DrTuberIE._extract_urls(webpage)
2458 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2460 # Look for embedded RedTube player
2461 redtube_urls = RedTubeIE._extract_urls(webpage)
2463 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2465 # Look for embedded Tvigle player
2467 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2468 if mobj is not None:
2469 return self.url_result(mobj.group('url'), 'Tvigle')
2471 # Look for embedded TED player
2473 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2474 if mobj is not None:
2475 return self.url_result(mobj.group('url'), 'TED')
2477 # Look for embedded Ustream videos
2478 ustream_url = UstreamIE._extract_url(webpage)
2480 return self.url_result(ustream_url, UstreamIE.ie_key())
2482 # Look for embedded arte.tv player
2484 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2486 if mobj is not None:
2487 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2489 # Look for embedded francetv player
2491 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2493 if mobj is not None:
2494 return self.url_result(mobj.group('url'))
2496 # Look for embedded smotri.com player
2497 smotri_url = SmotriIE._extract_url(webpage)
2499 return self.url_result(smotri_url, 'Smotri')
2501 # Look for embedded Myvi.ru player
2502 myvi_url = MyviIE._extract_url(webpage)
2504 return self.url_result(myvi_url)
2506 # Look for embedded soundcloud player
2507 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2509 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2511 # Look for tunein player
2512 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2514 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2516 # Look for embedded mtvservices player
2517 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2519 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2521 # Look for embedded yahoo player
2523 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2525 if mobj is not None:
2526 return self.url_result(mobj.group('url'), 'Yahoo')
2528 # Look for embedded sbs.com.au player
2532 <meta\s+property="og:video"\s+content=|
2535 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2537 if mobj is not None:
2538 return self.url_result(mobj.group('url'), 'SBS')
2540 # Look for embedded Cinchcast player
2542 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2544 if mobj is not None:
2545 return self.url_result(mobj.group('url'), 'Cinchcast')
2548 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2552 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2554 if mobj is not None:
2555 return self.url_result(mobj.group('url'), 'MLB')
2558 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2560 if mobj is not None:
2561 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2564 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2566 if mobj is not None:
2567 return self.url_result(mobj.group('url'), 'Livestream')
2569 # Look for Zapiks embed
2571 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2572 if mobj is not None:
2573 return self.url_result(mobj.group('url'), 'Zapiks')
2575 # Look for Kaltura embeds
2576 kaltura_url = KalturaIE._extract_url(webpage)
2578 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2580 # Look for EaglePlatform embeds
2581 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2582 if eagleplatform_url:
2583 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2585 # Look for ClipYou (uses EaglePlatform) embeds
2587 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2588 if mobj is not None:
2589 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2591 # Look for Pladform embeds
2592 pladform_url = PladformIE._extract_url(webpage)
2594 return self.url_result(pladform_url)
2596 # Look for Videomore embeds
2597 videomore_url = VideomoreIE._extract_url(webpage)
2599 return self.url_result(videomore_url)
2601 # Look for Webcaster embeds
2602 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2604 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2606 # Look for Playwire embeds
2608 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2609 if mobj is not None:
2610 return self.url_result(mobj.group('url'))
2612 # Look for 5min embeds
2614 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2615 if mobj is not None:
2616 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2618 # Look for Crooks and Liars embeds
2620 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2621 if mobj is not None:
2622 return self.url_result(mobj.group('url'))
2624 # Look for NBC Sports VPlayer embeds
2625 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2627 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2629 # Look for NBC News embeds
2630 nbc_news_embed_url = re.search(
2631 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2632 if nbc_news_embed_url:
2633 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2635 # Look for Google Drive embeds
2636 google_drive_url = GoogleDriveIE._extract_url(webpage)
2637 if google_drive_url:
2638 return self.url_result(google_drive_url, 'GoogleDrive')
2640 # Look for UDN embeds
2642 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2643 if mobj is not None:
2644 return self.url_result(
2645 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2647 # Look for Senate ISVP iframe
2648 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2650 return self.url_result(senate_isvp_url, 'SenateISVP')
2652 # Look for Dailymotion Cloud videos
2653 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2655 return self.url_result(dmcloud_url, 'DailymotionCloud')
2657 # Look for OnionStudios embeds
2658 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2659 if onionstudios_url:
2660 return self.url_result(onionstudios_url)
2662 # Look for ViewLift embeds
2663 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2665 return self.url_result(viewlift_url)
2667 # Look for JWPlatform embeds
2668 jwplatform_url = JWPlatformIE._extract_url(webpage)
2670 return self.url_result(jwplatform_url, 'JWPlatform')
2672 # Look for Digiteka embeds
2673 digiteka_url = DigitekaIE._extract_url(webpage)
2675 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2677 # Look for Arkena embeds
2678 arkena_url = ArkenaIE._extract_url(webpage)
2680 return self.url_result(arkena_url, ArkenaIE.ie_key())
2682 # Look for Piksel embeds
2683 piksel_url = PikselIE._extract_url(webpage)
2685 return self.url_result(piksel_url, PikselIE.ie_key())
2687 # Look for Limelight embeds
2688 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2690 return self.playlist_result(
2691 limelight_urls, video_id, video_title, video_description)
2693 # Look for Anvato embeds
2694 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2696 return self.playlist_result(
2697 anvato_urls, video_id, video_title, video_description)
2699 # Look for AdobeTVVideo embeds
2701 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2703 if mobj is not None:
2704 return self.url_result(
2705 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2708 # Look for Vine embeds
2710 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2712 if mobj is not None:
2713 return self.url_result(
2714 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2716 # Look for VODPlatform embeds
2718 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2720 if mobj is not None:
2721 return self.url_result(
2722 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2724 # Look for Mangomolo embeds
2726 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2728 video\?.*?\bid=(?P<video_id>\d+)|
2729 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2730 ).+?)\1''', webpage)
2731 if mobj is not None:
2733 '_type': 'url_transparent',
2734 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2735 'title': video_title,
2736 'description': video_description,
2737 'thumbnail': video_thumbnail,
2738 'uploader': video_uploader,
2740 video_id = mobj.group('video_id')
2743 'ie_key': 'MangomoloVideo',
2748 'ie_key': 'MangomoloLive',
2749 'id': mobj.group('channel_id'),
2753 # Look for Instagram embeds
2754 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2755 if instagram_embed_url is not None:
2756 return self.url_result(
2757 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2759 # Look for LiveLeak embeds
2760 liveleak_url = LiveLeakIE._extract_url(webpage)
2762 return self.url_result(liveleak_url, 'LiveLeak')
2764 # Look for 3Q SDN embeds
2765 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2768 '_type': 'url_transparent',
2769 'ie_key': ThreeQSDNIE.ie_key(),
2770 'url': self._proto_relative_url(threeqsdn_url),
2771 'title': video_title,
2772 'description': video_description,
2773 'thumbnail': video_thumbnail,
2774 'uploader': video_uploader,
2777 # Look for VBOX7 embeds
2778 vbox7_url = Vbox7IE._extract_url(webpage)
2780 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2782 # Look for DBTV embeds
2783 dbtv_urls = DBTVIE._extract_urls(webpage)
2785 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2787 # Look for Videa embeds
2788 videa_urls = VideaIE._extract_urls(webpage)
2790 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2792 # Look for 20 minuten embeds
2793 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2795 return self.playlist_from_matches(
2796 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2798 # Look for Openload embeds
2799 openload_urls = OpenloadIE._extract_urls(webpage)
2801 return self.playlist_from_matches(
2802 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2804 # Look for VideoPress embeds
2805 videopress_urls = VideoPressIE._extract_urls(webpage)
2807 return self.playlist_from_matches(
2808 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2810 # Look for Rutube embeds
2811 rutube_urls = RutubeIE._extract_urls(webpage)
2813 return self.playlist_from_matches(
2814 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2816 # Look for WashingtonPost embeds
2817 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2819 return self.playlist_from_matches(
2820 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2822 # Look for Mediaset embeds
2823 mediaset_urls = MediasetIE._extract_urls(webpage)
2825 return self.playlist_from_matches(
2826 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2828 # Look for JOJ.sk embeds
2829 joj_urls = JojIE._extract_urls(webpage)
2831 return self.playlist_from_matches(
2832 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2834 # Look for megaphone.fm embeds
2835 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2837 return self.playlist_from_matches(
2838 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2840 # Look for vzaar embeds
2841 vzaar_urls = VzaarIE._extract_urls(webpage)
2843 return self.playlist_from_matches(
2844 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2846 def merge_dicts(dict1, dict2):
2848 for k, v in dict1.items():
2851 for k, v in dict2.items():
2854 if (k not in merged or
2855 (isinstance(v, compat_str) and v and
2856 isinstance(merged[k], compat_str) and
2861 # Looking for http://schema.org/VideoObject
2862 json_ld = self._search_json_ld(
2863 webpage, video_id, default={}, expected_type='VideoObject')
2864 if json_ld.get('url'):
2865 return merge_dicts(json_ld, info_dict)
2867 # Look for HTML5 media
2868 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2870 for entry in entries:
2873 'title': video_title,
2875 self._sort_formats(entry['formats'])
2876 return self.playlist_result(entries)
2878 jwplayer_data = self._find_jwplayer_data(
2879 webpage, video_id, transform_source=js_to_json)
2881 info = self._parse_jwplayer_data(
2882 jwplayer_data, video_id, require_title=False, base_url=url)
2883 return merge_dicts(info, info_dict)
2885 def check_video(vurl):
2886 if YoutubeIE.suitable(vurl):
2888 if RtmpIE.suitable(vurl):
2890 vpath = compat_urlparse.urlparse(vurl).path
2891 vext = determine_ext(vpath)
2892 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2894 def filter_video(urls):
2895 return list(filter(check_video, urls))
2897 # Start with something easy: JW Player in SWFObject
2898 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2900 # Look for gorilla-vid style embedding
2901 found = filter_video(re.findall(r'''(?sx)
2905 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2908 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2910 # Broaden the search a little bit
2911 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2913 # Broaden the findall a little bit: JWPlayer JS loader
2914 found = filter_video(re.findall(
2915 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2918 found = filter_video(re.findall(r'''(?xs)
2919 flowplayer\("[^"]+",\s*
2921 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2922 ["']?url["']?\s*:\s*["']([^"']+)["']
2927 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2929 # Try to find twitter cards info
2930 # twitter:player:stream should be checked before twitter:player since
2931 # it is expected to contain a raw stream (see
2932 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2933 found = filter_video(re.findall(
2934 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2936 # We look for Open Graph info:
2937 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2938 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2939 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2940 if m_video_type is not None:
2941 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2943 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2945 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2946 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2949 # Look also in Refresh HTTP header
2950 refresh_header = head_response.headers.get('Refresh')
2952 # In python 2 response HTTP headers are bytestrings
2953 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2954 refresh_header = refresh_header.decode('iso-8859-1')
2955 found = re.search(REDIRECT_REGEX, refresh_header)
2957 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2959 self.report_following_redirect(new_url)
2968 # twitter:player is a https URL to iframe player that may or may not
2969 # be supported by youtube-dl thus this is checked the very last (see
2970 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2971 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2973 return self.url_result(embed_url)
2976 raise UnsupportedError(url)
2979 for video_url in orderedSet(found):
2980 video_url = unescapeHTML(video_url)
2981 video_url = video_url.replace('\\/', '/')
2982 video_url = compat_urlparse.urljoin(url, video_url)
2983 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2985 # Sometimes, jwplayer extraction will result in a YouTube URL
2986 if YoutubeIE.suitable(video_url):
2987 entries.append(self.url_result(video_url, 'Youtube'))
2990 # here's a fun little line of code for you:
2991 video_id = os.path.splitext(video_id)[0]
2995 'uploader': video_uploader,
2996 'title': video_title,
2997 'age_limit': age_limit,
3000 if RtmpIE.suitable(video_url):
3001 entry_info_dict.update({
3002 '_type': 'url_transparent',
3003 'ie_key': RtmpIE.ie_key(),
3006 entries.append(entry_info_dict)
3009 ext = determine_ext(video_url)
3011 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3013 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3015 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3017 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3019 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3020 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3021 # Just matching .ism/manifest is not enough to be reliably sure
3022 # whether it's actually an ISM manifest or some other streaming
3023 # manifest since there are various streaming URL formats
3024 # possible (see [1]) as well as some other shenanigans like
3025 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3027 # Thus the most reasonable way to solve this is to delegate
3028 # to generic extractor in order to look into the contents of
3029 # the manifest itself.
3030 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3031 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3032 entry_info_dict = self.url_result(
3033 smuggle_url(video_url, {'to_generic': True}),
3036 entry_info_dict['url'] = video_url
3038 if entry_info_dict.get('formats'):
3039 self._sort_formats(entry_info_dict['formats'])
3041 entries.append(entry_info_dict)
3043 if len(entries) == 1:
3046 for num, e in enumerate(entries, start=1):
3047 # 'url' results don't have a title
3048 if e.get('title') is not None:
3049 e['title'] = '%s (%d)' % (e['title'], num)
3051 '_type': 'playlist',