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,
37 from .commonprotocols import RtmpIE
38 from .brightcove import (
46 from .nbc import NBCSportsVPlayerIE
47 from .ooyala import OoyalaIE
48 from .rutv import RUTVIE
49 from .tvc import TVCIE
50 from .sportbox import SportBoxEmbedIE
51 from .smotri import SmotriIE
52 from .myvi import MyviIE
53 from .condenast import CondeNastIE
54 from .udn import UDNEmbedIE
55 from .senateisvp import SenateISVPIE
56 from .svt import SVTIE
57 from .pornhub import PornHubIE
58 from .xhamster import XHamsterEmbedIE
59 from .tnaflix import TNAFlixNetworkEmbedIE
60 from .drtuber import DrTuberIE
61 from .redtube import RedTubeIE
62 from .tube8 import Tube8IE
63 from .vimeo import VimeoIE
64 from .dailymotion import DailymotionIE
65 from .dailymail import DailyMailIE
66 from .onionstudios import OnionStudiosIE
67 from .viewlift import ViewLiftEmbedIE
68 from .mtv import MTVServicesEmbeddedIE
69 from .pladform import PladformIE
70 from .videomore import VideomoreIE
71 from .webcaster import WebcasterFeedIE
72 from .googledrive import GoogleDriveIE
73 from .jwplatform import JWPlatformIE
74 from .digiteka import DigitekaIE
75 from .arkena import ArkenaIE
76 from .instagram import InstagramIE
77 from .liveleak import LiveLeakIE
78 from .threeqsdn import ThreeQSDNIE
79 from .theplatform import ThePlatformIE
80 from .vessel import VesselIE
81 from .kaltura import KalturaIE
82 from .eagleplatform import EaglePlatformIE
83 from .facebook import FacebookIE
84 from .soundcloud import SoundcloudIE
85 from .tunein import TuneInBaseIE
86 from .vbox7 import Vbox7IE
87 from .dbtv import DBTVIE
88 from .piksel import PikselIE
89 from .videa import VideaIE
90 from .twentymin import TwentyMinutenIE
91 from .ustream import UstreamIE
92 from .openload import OpenloadIE
93 from .videopress import VideoPressIE
94 from .rutube import RutubeIE
95 from .limelight import LimelightBaseIE
96 from .anvato import AnvatoIE
97 from .washingtonpost import WashingtonPostIE
98 from .wistia import WistiaIE
99 from .mediaset import MediasetIE
100 from .joj import JojIE
101 from .megaphone import MegaphoneIE
102 from .vzaar import VzaarIE
103 from .channel9 import Channel9IE
104 from .vshare import VShareIE
105 from .mediasite import MediasiteIE
106 from .springboardplatform import SpringboardPlatformIE
107 from .yapfiles import YapFilesIE
108 from .vice import ViceIE
109 from .xfileshare import XFileShareIE
110 from .cloudflarestream import CloudflareStreamIE
113 class GenericIE(InfoExtractor):
114 IE_DESC = 'Generic downloader that works on some sites'
118 # Direct link to a video
120 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
121 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
126 'upload_date': '20100513',
129 # Direct link to media delivered compressed (until Accept-Encoding is *)
131 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
132 'md5': '128c42e68b13950268b648275386fc74',
134 'id': 'FictionJunction-Parallel_Hearts',
136 'title': 'FictionJunction-Parallel_Hearts',
137 'upload_date': '20140522',
139 'expected_warnings': [
140 'URL could be a direct video link, returning it as such.'
142 'skip': 'URL invalid',
144 # Direct download with broken HEAD
146 'url': 'http://ai-radio.org:8000/radio.opus',
153 'skip_download': True, # infinite live stream
155 'expected_warnings': [
156 r'501.*Not Implemented',
160 # Direct link with incorrect MIME type
162 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
163 'md5': '4ccbebe5f36706d85221f204d7eb5913',
165 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
166 'id': '5_Lennart_Poettering_-_Systemd',
168 'title': '5_Lennart_Poettering_-_Systemd',
169 'upload_date': '20141120',
171 'expected_warnings': [
172 'URL could be a direct video link, returning it as such.'
177 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
179 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
180 'title': 'Zero Punctuation',
181 'description': 're:.*groundbreaking video review series.*'
183 'playlist_mincount': 11,
185 # RSS feed with enclosure
187 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
189 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
191 'upload_date': '20150228',
192 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
195 # RSS feed with enclosures and unsupported link URLs
197 'url': 'http://www.hellointernet.fm/podcast?format=rss',
199 'id': 'http://www.hellointernet.fm/podcast?format=rss',
200 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
201 'title': 'Hello Internet',
203 'playlist_mincount': 100,
205 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
207 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
211 'title': 'Automatics, robotics and biocybernetics',
212 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
213 'upload_date': '20130627',
214 'formats': 'mincount:16',
215 'subtitles': 'mincount:1',
218 'force_generic_extractor': True,
219 'skip_download': True,
222 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
224 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
229 'formats': 'mincount:1',
232 'skip_download': True,
235 # SMIL from https://www.restudy.dk/video/play/id/1637
237 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
241 'title': 'video_1637',
242 'formats': 'mincount:3',
245 'skip_download': True,
248 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
250 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
252 'id': 'smil-service',
254 'title': 'smil-service',
255 'formats': 'mincount:1',
258 'skip_download': True,
261 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
263 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
267 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
268 'formats': 'mincount:3',
271 'skip_download': True,
274 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
276 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
278 'id': 'mZlp2ctYIUEB',
280 'title': 'Tikibad ontruimd wegens brand',
281 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
282 'thumbnail': r're:^https?://.*\.jpg$',
286 'skip_download': True,
289 # MPD from http://dash-mse-test.appspot.com/media.html
291 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
292 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
294 'id': 'car-20120827-manifest',
296 'title': 'car-20120827-manifest',
297 'formats': 'mincount:9',
298 'upload_date': '20130904',
301 'format': 'bestvideo',
304 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
306 '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',
311 'formats': 'mincount:8',
315 'skip_download': True,
317 'skip': 'video gone',
319 # m3u8 served with Content-Type: text/plain
321 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
326 'upload_date': '20140720',
327 'formats': 'mincount:11',
331 'skip_download': True,
333 'skip': 'video gone',
337 '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',
341 'upload_date': '20130224',
342 'uploader_id': 'TheVerge',
343 'description': r're:^Chris Ziegler takes a look at the\.*',
344 'uploader': 'The Verge',
345 'title': 'First Firefox OS phones side-by-side',
348 'skip_download': False,
352 # redirect in Refresh HTTP header
353 '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',
357 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
358 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
359 'upload_date': '20150917',
360 'uploader_id': 'brtvofficial',
361 'uploader': 'Boiler Room',
364 'skip_download': False,
368 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
369 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
371 'id': '13601338388002',
373 'uploader': 'www.hodiho.fr',
374 'title': 'R\u00e9gis plante sa Jeep',
377 # bandcamp page with custom domain
379 'add_ie': ['Bandcamp'],
380 'url': 'http://bronyrock.com/track/the-pony-mash',
384 'title': 'The Pony Mash',
385 'uploader': 'M_Pallante',
387 'skip': 'There is a limit of 200 free downloads / month for the test song',
390 # embedded brightcove video
391 # it also tests brightcove videos that need to set the 'Referer'
392 # in the http requests
393 'add_ie': ['BrightcoveLegacy'],
394 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
396 'id': '2765128793001',
398 'title': 'Le cours de bourse : l’analyse technique',
399 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
400 'uploader': 'BFM BUSINESS',
403 'skip_download': True,
407 # embedded with itemprop embedURL and video id spelled as `idVideo`
408 'add_id': ['BrightcoveLegacy'],
409 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
411 'id': '5255628253001',
413 'title': 'md5:37c519b1128915607601e75a87995fc0',
414 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
415 'uploader': 'BFM BUSINESS',
416 'uploader_id': '876450612001',
417 'timestamp': 1482255315,
418 'upload_date': '20161220',
421 'skip_download': True,
425 # https://github.com/rg3/youtube-dl/issues/2253
426 'url': 'http://bcove.me/i6nfkrc3',
427 'md5': '0ba9446db037002366bab3b3eb30c88c',
429 'id': '3101154703001',
431 'title': 'Still no power',
432 'uploader': 'thestar.com',
433 '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.',
435 'add_ie': ['BrightcoveLegacy'],
436 'skip': 'video gone',
439 'url': 'http://www.championat.com/video/football/v/87/87499.html',
440 'md5': 'fb973ecf6e4a78a67453647444222983',
442 'id': '3414141473001',
444 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
445 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
446 'uploader': 'Championat',
450 # https://github.com/rg3/youtube-dl/issues/3541
451 'add_ie': ['BrightcoveLegacy'],
452 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
454 'id': '3866516442001',
456 'title': 'Leer mij vrouwen kennen: Aflevering 1',
457 'description': 'Leer mij vrouwen kennen: Aflevering 1',
458 'uploader': 'SBS Broadcasting',
460 'skip': 'Restricted to Netherlands',
462 'skip_download': True, # m3u8 download
466 # Brightcove video in <iframe>
467 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
468 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
470 'id': '5360463607001',
472 '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',
473 '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。',
474 'uploader': 'United Nations',
475 'uploader_id': '1362235914001',
476 'timestamp': 1489593889,
477 'upload_date': '20170315',
479 'add_ie': ['BrightcoveLegacy'],
482 # Brightcove with alternative playerID key
483 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
485 'id': 'nmeth.2062_SV1',
486 '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',
490 'id': '2228375078001',
492 'title': 'nmeth.2062-sv1',
493 'description': 'nmeth.2062-sv1',
494 'timestamp': 1363357591,
495 'upload_date': '20130315',
496 'uploader': 'Nature Publishing Group',
497 'uploader_id': '1964492299001',
502 # Brightcove with UUID in videoPlayer
503 'url': 'http://www8.hp.com/cn/zh/home.html',
505 'id': '5255815316001',
507 'title': 'Sprocket Video - China',
508 'description': 'Sprocket Video - China',
509 'uploader': 'HP-Video Gallery',
510 'timestamp': 1482263210,
511 'upload_date': '20161220',
512 'uploader_id': '1107601872001',
515 'skip_download': True, # m3u8 download
517 'skip': 'video rotates...weekly?',
520 # Brightcove:new type [2].
521 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
522 'md5': '2b35148fcf48da41c9fb4591650784f3',
524 'id': '5348741021001',
526 'upload_date': '20170306',
527 'uploader_id': '4191638492001',
528 'timestamp': 1488769918,
529 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
534 # Alternative brightcove <video> attributes
535 '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/',
537 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
538 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
541 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
543 'id': '5311302538001',
545 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
546 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
547 'timestamp': 1486321708,
548 'upload_date': '20170205',
549 'uploader_id': '800000640001',
551 'only_matching': True,
555 # Brightcove with UUID in videoPlayer
556 'url': 'http://www8.hp.com/cn/zh/home.html',
558 'id': '5255815316001',
560 'title': 'Sprocket Video - China',
561 'description': 'Sprocket Video - China',
562 'uploader': 'HP-Video Gallery',
563 'timestamp': 1482263210,
564 'upload_date': '20161220',
565 'uploader_id': '1107601872001',
568 'skip_download': True, # m3u8 download
573 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
574 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
576 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
578 'title': '2cc213299525360.mov', # that's what we get
581 'add_ie': ['Ooyala'],
584 # ooyala video embedded with http://player.ooyala.com/iframe.js
585 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
587 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
589 'title': '"Steve Jobs: Man in the Machine" trailer',
590 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
594 'skip_download': True,
596 'skip': 'movie expired',
598 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
600 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
602 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
604 'title': 'Steampunk Fest Comes to Honesdale',
608 'skip_download': True,
613 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
617 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
618 'upload_date': '20140225',
619 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
620 'uploader': 'Tested',
621 'uploader_id': 'testedcom',
623 # No need to test YoutubeIE here
625 'skip_download': True,
630 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
634 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
635 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
637 # HEAD requests lead to endless 301, while GET is OK
638 'expected_warnings': ['301'],
642 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
646 'title': 'Охотское море стало целиком российским',
647 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
651 'skip_download': True,
656 '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/',
660 'title': 'Дошкольное воспитание',
665 'url': 'http://www.vestifinance.ru/articles/25753',
668 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
673 'title': 'Госзаказ. День 3',
679 'title': 'Госзаказ. День 2',
685 'title': 'Госзаказ. День 1',
691 'skip_download': True,
696 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
698 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
700 'title': 'Ужастики, русский трейлер (2015)',
701 'thumbnail': r're:^https?://.*\.jpg$',
707 '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',
710 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
712 'playlist_mincount': 7,
713 # This forum does not allow <iframe> syntaxes anymore
714 # Now HTML tags are displayed as-is
715 'skip': 'No videos on this page',
719 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
720 'md5': '65fdff94098e4a607385a60c5177c638',
724 'title': 'Hidden miracles of the natural world',
725 'uploader': 'Louie Schwartzberg',
726 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
729 # nowvideo embed hidden behind percent encoding
731 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
732 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
734 'id': '06e53103ca9aa',
736 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
737 'description': 'No description',
742 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
743 'md5': '7653032cbb25bf6c80d80f217055fa43',
745 'id': '048195-004_PLUS7-F',
748 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
749 'upload_date': '20140320',
752 'skip_download': 'Requires rtmpdump'
754 'skip': 'video gone',
758 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
762 'title': 'Alcaline, le concert avec Calogero',
763 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
764 'upload_date': '20150226',
765 'timestamp': 1424989860,
770 'skip_download': True,
772 'expected_warnings': [
778 'url': 'http://www.wired.com/2014/04/honda-asimo/',
779 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
781 'id': '53501be369702d3275860000',
783 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
788 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
789 'md5': '441aeeb82eb72c422c7f14ec533999cd',
791 'id': 'k2mm4bCdJ6CQ2i7c8o2',
793 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
794 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
796 'uploader_id': 'xgditw',
797 'upload_date': '20140425',
798 'timestamp': 1398441542,
800 'add_ie': ['Dailymotion'],
804 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
808 'title': 'Care worker punches elderly dementia patient in head 11 times',
809 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
811 'add_ie': ['DailyMail'],
813 'skip_download': True,
818 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
822 'title': 'The NBL Auction 2014',
823 'uploader': 'BADMINTON England',
824 'uploader_id': 'BADMINTONEvents',
825 'upload_date': '20140603',
826 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
828 'add_ie': ['Youtube'],
830 'skip_download': True,
835 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
836 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
838 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
840 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
841 'description': 'Two valets share their love for movie star Liam Neesons.',
842 'timestamp': 1349922600,
843 'upload_date': '20121011',
846 # YouTube embed via <data-embed-url="">
848 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
852 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
853 'uploader': 'Gameloft',
854 'uploader_id': 'gameloft',
855 'upload_date': '20140828',
856 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
859 'skip_download': True,
862 # YouTube <object> embed
864 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
865 'md5': '516718101ec834f74318df76259fb3cc',
869 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
870 'upload_date': '20080526',
871 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
872 'uploader': 'Christopher Sykes',
873 'uploader_id': 'ChristopherJSykes',
875 'add_ie': ['Youtube'],
879 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
881 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
883 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
884 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
889 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
891 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
892 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
898 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
903 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
904 'md5': '9d65602bf31c6e20014319c7d07fba27',
906 'id': '5123ea6d5e5a7',
909 'uploader': 'www.handjobhub.com',
910 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
913 # Multiple brightcove videos
914 # https://github.com/rg3/youtube-dl/issues/2283
916 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
918 'id': 'always-never',
919 'title': 'Always / Never - The New Yorker',
923 'extract_flat': False,
924 'skip_download': True,
929 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
930 'md5': '96f09a37e44da40dd083e12d9a683327',
934 'title': 'Ump changes call to ball',
935 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
937 'timestamp': 1401537900,
938 'upload_date': '20140531',
939 'thumbnail': r're:^https?://.*\.jpg$',
944 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
945 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
949 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
950 'description': 'a Paywall Videos video from Remilon',
952 'uploader': 'study.com',
953 'timestamp': 1459678540,
954 'upload_date': '20160403',
955 'filesize': 24687186,
959 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
960 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
964 'title': 'Conversation about Hexagonal Rails Part 1',
965 'description': 'a Martin Fowler video from ThoughtWorks',
967 'uploader': 'thoughtworks.wistia.com',
968 'timestamp': 1401832161,
969 'upload_date': '20140603',
972 # Wistia standard embed (async)
974 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
978 'title': 'Drip Brennan Dunn Workshop',
979 'description': 'a JV Webinars video from getdrip-1',
981 'timestamp': 1463607249,
982 'upload_date': '20160518',
985 'skip_download': True,
990 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
994 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
995 'uploader': 'Sophos Security',
996 'title': 'Chet Chat 171 - Oct 29, 2014',
997 'upload_date': '20141029',
1000 # Soundcloud multiple embeds
1002 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1005 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1007 'playlist_mincount': 7,
1009 # TuneIn station embed
1011 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1016 'location': 'Paris, France',
1021 'skip_download': True,
1026 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1030 'upload_date': '20141112',
1031 'title': 'Rosetta #CometLanding webcast HL 10',
1034 # Another Livestream embed, without 'new.' in URL
1036 'url': 'https://www.freespeech.org/',
1040 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1044 'skip_download': True,
1049 'url': 'https://skiplagged.com/',
1052 'title': 'Skiplagged: The smart way to find cheap flights',
1054 'playlist_mincount': 1,
1055 'add_ie': ['Youtube'],
1059 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1063 'upload_date': '20141126',
1064 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1069 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1071 'id': '730m_DandD_1901_512k',
1073 'uploader': 'www.abc.net.au',
1074 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1077 # embedded viddler video
1079 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1083 'uploader': 'deadspin',
1084 'title': 'WALL-TO-GORTAT',
1085 'timestamp': 1422285291,
1086 'upload_date': '20150126',
1088 'add_ie': ['Viddler'],
1092 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1096 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1097 'description': 'md5:601cb790edd05908957dae8aaa866465',
1098 'upload_date': '20150220',
1100 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1104 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1106 'id': 'Mrj4DVp2zeA',
1108 'upload_date': '20150212',
1109 'uploader': 'The National Archives UK',
1110 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1111 'uploader_id': 'NationalArchives08',
1112 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1117 'url': 'http://www.suffolk.edu/sjc/live.php',
1121 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1122 'uploader': 'www.suffolk.edu',
1125 'skip_download': True,
1127 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1131 'url': 'http://www.indiedb.com/games/king-machine/videos',
1135 'title': 'king machine trailer 1',
1136 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1137 'thumbnail': r're:^https?://.*\.jpg$',
1141 # JWPlayer config passed as variable
1142 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1146 'title': 'ARIELE | Tube Cup',
1147 'uploader': 'www.txxx.com',
1151 'skip_download': True,
1156 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1157 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1161 'upload_date': '20171122',
1162 'timestamp': 1511366290,
1163 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1165 'add_ie': [JWPlatformIE.ie_key()],
1168 # Video.js embed, multiple formats
1169 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1171 'id': 'yygqldloqIk',
1173 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1174 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1175 'upload_date': '20130314',
1176 'uploader': 'PROстое3D',
1177 'uploader_id': 'PROstoe3D',
1180 'skip_download': True,
1184 # Video.js embed, single format
1185 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1189 'title': 'Step 1 - Good Foundation',
1190 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1193 'skip_download': True,
1198 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1199 'playlist_mincount': 5,
1201 'id': 'aanslagen-kopenhagen',
1202 'title': 'Aanslagen Kopenhagen',
1207 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1211 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1214 # Kaltura embed (different embed code)
1216 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1220 'upload_date': '20150127',
1221 'uploader_id': 'PremierMedia',
1223 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1226 # Kaltura embed with single quotes
1228 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1233 'timestamp': 1355743100,
1234 'upload_date': '20121217',
1235 'uploader_id': 'cplapp@learn360.com',
1237 'add_ie': ['Kaltura'],
1240 # Kaltura embedded via quoted entry_id
1241 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1245 'title': '06_matthew_brender_raj_dutt',
1246 'timestamp': 1466638791,
1247 'upload_date': '20160622',
1249 'add_ie': ['Kaltura'],
1250 'expected_warnings': [
1251 'Could not send HEAD request'
1254 'skip_download': True,
1258 # Kaltura embedded, some fileExt broken (#11480)
1259 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1263 'title': 'Our "Standard Models" of particle physics and cosmology',
1264 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1265 'timestamp': 1321158993,
1266 'upload_date': '20111113',
1267 'uploader_id': 'kps1',
1269 'add_ie': ['Kaltura'],
1272 # Kaltura iframe embed
1273 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1274 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1278 'title': 'I. M. Pei: A Centennial Celebration',
1279 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1280 'upload_date': '20170403',
1281 'uploader_id': 'batchUser',
1282 'timestamp': 1491232186,
1284 'add_ie': ['Kaltura'],
1287 # Kaltura iframe embed, more sophisticated
1288 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1292 'title': 'lecture-05sep2017',
1293 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1294 'upload_date': '20170913',
1295 'uploader_id': 'eps2',
1296 'timestamp': 1505340777,
1299 'skip_download': True,
1301 'add_ie': ['Kaltura'],
1304 # meta twitter:player
1305 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1309 'title': 'Main Twerk (Video)',
1310 'upload_date': '20171208',
1311 'uploader_id': 'sebastian.salinas@thechive.com',
1312 'timestamp': 1512713057,
1315 'skip_download': True,
1317 'add_ie': ['Kaltura'],
1319 # referrer protected EaglePlatform embed
1321 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1325 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1326 'thumbnail': r're:^https?://.*\.jpg$',
1331 'skip_download': True,
1334 # ClipYou (EaglePlatform) embed (custom URL)
1336 'url': 'http://muz-tv.ru/play/7129/',
1337 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1341 'title': "'O Sole Mio",
1342 'thumbnail': r're:^https?://.*\.jpg$',
1347 'skip_download': True,
1349 'skip': 'This video is unavailable.',
1353 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1357 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1358 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1359 'thumbnail': r're:^https?://.*\.jpg$',
1363 'skip': 'HTTP Error 404: Not Found',
1367 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1371 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1372 'thumbnail': r're:^https?://.*\.png$',
1378 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1379 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1383 'title': 'Facebook Creates "On This Day" | Crunch Report',
1384 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1385 'timestamp': 1427237531,
1386 'uploader': 'Crunch Report',
1387 'upload_date': '20150324',
1391 'skip_download': True,
1396 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1400 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1405 # Crooks and Liars embed
1407 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1411 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1412 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1413 'timestamp': 1428207000,
1414 'upload_date': '20150405',
1415 'uploader': 'Heather',
1418 # Crooks and Liars external embed
1420 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1422 'id': 'MTE3MjUtMzQ2MzA',
1424 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1425 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1426 'timestamp': 1265032391,
1427 'upload_date': '20100201',
1428 'uploader': 'Heather',
1431 # NBC Sports vplayer embed
1433 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1435 'id': 'ln7x1qSThw4k',
1437 'title': "PFT Live: New leader in the 'new-look' defense",
1438 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1439 'uploader': 'NBCU-SPORTS',
1440 'upload_date': '20140107',
1441 'timestamp': 1389118457,
1443 'skip': 'Invalid Page URL',
1447 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1448 'md5': '1aa589c675898ae6d37a17913cf68d66',
1450 'id': 'x_dtl_oa_LettermanliftPR_160608',
1452 'title': 'David Letterman: A Preview',
1453 '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.',
1454 'upload_date': '20160609',
1455 'timestamp': 1465431544,
1456 'uploader': 'NBCU-NEWS',
1461 'url': 'https://video.udn.com/news/300346',
1462 'md5': 'fd2060e988c326991037b9aff9df21a6',
1466 'title': '中一中男師變性 全校師生力挺',
1467 'thumbnail': r're:^https?://.*\.jpg$',
1471 'skip_download': True,
1473 'expected_warnings': ['Failed to parse JSON Expecting value'],
1477 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1479 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1481 'description': 'Index/Match versus VLOOKUP.',
1482 'title': 'This is what separates the Excel masters from the wannabes',
1483 'duration': 191.933,
1487 'skip_download': True,
1490 # Brightcove URL in single quotes
1492 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1493 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1495 'id': '4255764656001',
1497 'title': 'SN Presents: Russell Martin, World Citizen',
1498 '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.',
1499 'uploader': 'Rogers Sportsnet',
1500 'uploader_id': '1704050871',
1501 'upload_date': '20150525',
1502 'timestamp': 1432570283,
1505 # OnionStudios embed
1507 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1511 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1512 'thumbnail': r're:^https?://.*\.jpe?g$',
1513 'uploader': 'ClickHole',
1514 'uploader_id': 'clickhole',
1519 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1521 'id': '74849a00-85a9-11e1-9660-123139220831',
1523 'title': '#whilewewatch',
1526 # AdobeTVVideo embed
1528 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1529 'md5': '43662b577c018ad707a63766462b1e87',
1533 'title': 'New experience with Acrobat DC',
1534 'description': 'New experience with Acrobat DC',
1535 'duration': 248.667,
1538 # BrightcoveInPageEmbed embed
1540 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1542 'id': '4238694884001',
1544 'title': 'Tabletop: Dread, Last Thoughts',
1545 'description': 'Tabletop: Dread, Last Thoughts',
1549 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1550 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1552 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1554 'id': '4785848093001',
1556 'title': 'The Cardinal Pell Interview',
1557 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1558 'uploader': 'GlobeCast Australia - GlobeStream',
1559 'uploader_id': '2733773828001',
1560 'upload_date': '20160304',
1561 'timestamp': 1457083087,
1565 'skip_download': True,
1569 # Brightcove embed with whitespace around attribute names
1570 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1572 'id': '3167554373001',
1574 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1575 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1576 'uploader_id': '1079349493',
1577 'upload_date': '20140207',
1578 'timestamp': 1391810548,
1581 'skip_download': True,
1584 # Another form of arte.tv embed
1586 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1587 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1589 'id': '030273-562_PLUS7-F',
1591 'title': 'ARTE Reportage - Nulle part, en France',
1592 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1593 'upload_date': '20160409',
1598 'url': 'http://www.wykop.pl/link/3088787/',
1599 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1601 'id': '874_1459135191',
1603 'title': 'Man shows poor quality of new apartment building',
1604 'description': 'The wall is like a sand pile.',
1605 'uploader': 'Lake8737',
1607 'add_ie': [LiveLeakIE.ie_key()],
1609 # Another LiveLeak embed pattern (#13336)
1611 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1613 'id': '2eb_1496309988',
1615 'title': 'Thief robs place where everyone was armed',
1616 'description': 'md5:694d73ee79e535953cf2488562288eee',
1617 'uploader': 'brazilwtf',
1619 'add_ie': [LiveLeakIE.ie_key()],
1621 # Duplicated embedded video URLs
1623 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1625 'id': '149298443_480_16c25b74_2',
1627 'title': 'vs. Blue Orange Spring Game',
1628 'uploader': 'www.hudl.com',
1631 # twitter:player:stream embed
1633 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1637 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1638 'uploader': 'www.rtl.be',
1642 'skip_download': True,
1645 # twitter:player embed
1647 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1648 'md5': 'a3e0df96369831de324f0778e126653c',
1650 'id': '4909620399001',
1652 'title': 'What Do Black Holes Sound Like?',
1653 'description': 'what do black holes sound like',
1654 'upload_date': '20160524',
1655 'uploader_id': '29913724001',
1656 'timestamp': 1464107587,
1657 'uploader': 'TheAtlantic',
1659 'add_ie': ['BrightcoveLegacy'],
1661 # Facebook <iframe> embed
1663 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1664 'md5': 'fbcde74f534176ecb015849146dd3aee',
1666 'id': '599637780109885',
1668 'title': 'Facebook video #599637780109885',
1671 # Facebook <iframe> embed, plugin video
1673 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1675 'id': '1754168231264132',
1677 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1678 'uploader': 'Tariq Ramadan (official)',
1679 'timestamp': 1496758379,
1680 'upload_date': '20170606',
1683 'skip_download': True,
1686 # Facebook API embed
1688 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1689 'md5': 'a47372ee61b39a7b90287094d447d94e',
1691 'id': '10153467542406923',
1693 'title': 'Facebook video #10153467542406923',
1696 # Wordpress "YouTube Video Importer" plugin
1698 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1699 'md5': 'd16797741b560b485194eddda8121b48',
1701 'id': 'HNTXWDXV9Is',
1703 'title': 'Blue Devils Drumline Stanford lot 2016',
1704 'upload_date': '20160627',
1705 'uploader_id': 'GENOCIDE8GENERAL10',
1706 'uploader': 'cylus cyrus',
1710 # video stored on custom kaltura server
1711 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1712 'md5': '537617d06e64dfed891fa1593c4b30cc',
1716 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1717 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1718 'uploader_id': 'videos.expansion@el-mundo.net',
1719 'upload_date': '20150429',
1720 'timestamp': 1430303472,
1722 'add_ie': ['Kaltura'],
1725 # Non-standard Vimeo embed
1726 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1727 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1731 'title': 'Understanding the web - Teaser',
1732 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1733 'upload_date': '20151214',
1734 'uploader': 'OpenClassrooms',
1735 'uploader_id': 'openclassrooms',
1737 'add_ie': ['Vimeo'],
1740 # generic vimeo embed that requires original URL passed as Referer
1741 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1742 'only_matching': True,
1745 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1746 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1748 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1750 'title': 'Big Buck Bunny',
1751 'description': 'Royalty free test video',
1752 'timestamp': 1432816365,
1753 'upload_date': '20150528',
1757 'skip_download': True,
1759 'add_ie': [ArkenaIE.ie_key()],
1762 '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/',
1766 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1769 'skip_download': True,
1771 'add_ie': [Vbox7IE.ie_key()],
1775 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1778 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1780 'playlist_mincount': 3,
1784 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1786 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1787 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1789 'playlist_mincount': 2,
1793 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1797 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1798 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1801 'skip_download': True,
1803 'add_ie': [TwentyMinutenIE.ie_key()],
1807 'url': 'https://en.support.wordpress.com/videopress/',
1811 'title': 'IMG_5786',
1812 'timestamp': 1435711927,
1813 'upload_date': '20150701',
1816 'skip_download': True,
1818 'add_ie': [VideoPressIE.ie_key()],
1822 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1824 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1826 'title': 'Магаззино: Казань 2',
1827 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1828 'uploader': 'Магаззино',
1829 'upload_date': '20170228',
1830 'uploader_id': '996642',
1833 'skip_download': True,
1835 'add_ie': [RutubeIE.ie_key()],
1838 # ThePlatform embedded with whitespaces in URLs
1839 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1840 'only_matching': True,
1843 # Senate ISVP iframe https
1844 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1845 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1847 'id': 'govtaff020316',
1849 'title': 'Integrated Senate Video Player',
1851 'add_ie': [SenateISVPIE.ie_key()],
1854 # Limelight embeds (1 channel embed + 4 media embeds)
1855 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1857 'id': 'FacilitatorTraining2017',
1858 'title': 'Facilitator Training 2017',
1860 'playlist_mincount': 5,
1863 # Limelight embed (LimelightPlayerUtil.embed)
1864 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1866 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1868 'title': '07448641',
1869 'timestamp': 1499890639,
1870 'upload_date': '20170712',
1873 'skip_download': True,
1875 'add_ie': ['LimelightMedia'],
1878 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1880 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1881 'title': 'Standoff with Walnut Creek murder suspect ends',
1882 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1884 'playlist_mincount': 4,
1887 # WashingtonPost embed
1888 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1890 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1892 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1893 '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.',
1894 'timestamp': 1455216756,
1895 'uploader': 'The Washington Post',
1896 'upload_date': '20160211',
1898 'add_ie': [WashingtonPostIE.ie_key()],
1902 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1906 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1909 'skip_download': True,
1911 'add_ie': [MediasetIE.ie_key()],
1915 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1917 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1918 'title': 'Slovenskom sa prehnala vlna silných búrok',
1920 'playlist_mincount': 5,
1921 'add_ie': [JojIE.ie_key()],
1924 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1925 'url': 'https://tvrain.ru/amp/418921/',
1926 'md5': 'cc00413936695987e8de148b67d14f1d',
1930 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1935 'url': 'http://help.vzaar.com/article/165-embedding-video',
1936 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1940 'title': 'Building A Business Online: Principal Chairs Q & A',
1944 # multiple HTML5 videos on one page
1945 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1947 'id': 'keyscenarios',
1948 'title': 'Rescue Kit 14 Free Edition - Getting started',
1950 'playlist_count': 4,
1954 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1955 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1958 'title': 'vl14062007715967',
1963 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1964 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1966 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1968 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1969 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1970 'timestamp': 1474354800,
1971 'upload_date': '20160920',
1975 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1979 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1980 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1981 'timestamp': 1516100691,
1982 'upload_date': '20180116',
1985 'skip_download': True,
1987 'add_ie': [SpringboardPlatformIE.ie_key()],
1990 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1992 'id': 'uPDB5I9wfp8',
1994 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1995 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1996 'upload_date': '20160219',
1997 'uploader': 'Pocoyo - Português (BR)',
1998 'uploader_id': 'PocoyoBrazil',
2000 'add_ie': [YoutubeIE.ie_key()],
2002 'skip_download': True,
2006 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2008 'id': 'vMDE4NzI1Mjgt690b',
2012 'add_ie': [YapFilesIE.ie_key()],
2014 'skip_download': True,
2018 # CloudflareStream embed
2019 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2021 'id': '31c9291ab41fac05471db4e73aa11717',
2023 'title': '31c9291ab41fac05471db4e73aa11717',
2025 'add_ie': [CloudflareStreamIE.ie_key()],
2027 'skip_download': True,
2031 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2032 'md5': 'b68d276de422ab07ee1d49388103f457',
2035 'title': 'Lock up and get excited',
2038 'skip': 'TODO: fix nested playlists processing in tests',
2041 # # TODO: find another test
2042 # # http://schema.org/VideoObject
2043 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2044 # 'md5': '888dcf08b7ea671381f00fab74692755',
2046 # 'id': 'nyvTSJMKId',
2048 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2049 # 'description': '#love for cats.',
2050 # 'timestamp': 1461244995,
2051 # 'upload_date': '20160421',
2054 # 'force_generic_extractor': True,
2059 def report_following_redirect(self, new_url):
2060 """Report information extraction."""
2061 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2063 def _extract_rss(self, url, video_id, doc):
2064 playlist_title = doc.find('./channel/title').text
2065 playlist_desc_el = doc.find('./channel/description')
2066 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2069 for it in doc.findall('./channel/item'):
2071 enclosure_nodes = it.findall('./enclosure')
2072 for e in enclosure_nodes:
2073 next_url = e.attrib.get('url')
2078 next_url = xpath_text(it, 'link', fatal=False)
2084 '_type': 'url_transparent',
2086 'title': it.find('title').text,
2090 '_type': 'playlist',
2092 'title': playlist_title,
2093 'description': playlist_desc,
2097 def _extract_camtasia(self, url, video_id, webpage):
2098 """ Returns None if no camtasia video can be found. """
2100 camtasia_cfg = self._search_regex(
2101 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2102 webpage, 'camtasia configuration file', default=None)
2103 if camtasia_cfg is None:
2106 title = self._html_search_meta('DC.title', webpage, fatal=True)
2108 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2109 camtasia_cfg = self._download_xml(
2110 camtasia_url, video_id,
2111 note='Downloading camtasia configuration',
2112 errnote='Failed to download camtasia configuration')
2113 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2116 for n in fileset_node.getchildren():
2117 url_n = n.find('./uri')
2122 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2123 'title': '%s - %s' % (title, n.tag),
2124 'url': compat_urlparse.urljoin(url, url_n.text),
2125 'duration': float_or_none(n.find('./duration').text),
2129 '_type': 'playlist',
2134 def _real_extract(self, url):
2135 if url.startswith('//'):
2138 'url': self.http_scheme() + url,
2141 parsed_url = compat_urlparse.urlparse(url)
2142 if not parsed_url.scheme:
2143 default_search = self._downloader.params.get('default_search')
2144 if default_search is None:
2145 default_search = 'fixup_error'
2147 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2149 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2150 return self.url_result('http://' + url)
2151 elif default_search != 'fixup_error':
2152 if default_search == 'auto_warning':
2153 if re.match(r'^(?:url|URL)$', url):
2154 raise ExtractorError(
2155 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2158 self._downloader.report_warning(
2159 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2160 return self.url_result('ytsearch:' + url)
2162 if default_search in ('error', 'fixup_error'):
2163 raise ExtractorError(
2164 '%r is not a valid URL. '
2165 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2166 % (url, url), expected=True)
2168 if ':' not in default_search:
2169 default_search += ':'
2170 return self.url_result(default_search + url)
2172 url, smuggled_data = unsmuggle_url(url)
2173 force_videoid = None
2174 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2175 if smuggled_data and 'force_videoid' in smuggled_data:
2176 force_videoid = smuggled_data['force_videoid']
2177 video_id = force_videoid
2179 video_id = self._generic_id(url)
2181 self.to_screen('%s: Requesting header' % video_id)
2183 head_req = HEADRequest(url)
2184 head_response = self._request_webpage(
2186 note=False, errnote='Could not send HEAD request to %s' % url,
2189 if head_response is not False:
2190 # Check for redirect
2191 new_url = compat_str(head_response.geturl())
2193 self.report_following_redirect(new_url)
2195 new_url = smuggle_url(
2196 new_url, {'force_videoid': force_videoid})
2197 return self.url_result(new_url)
2199 full_response = None
2200 if head_response is False:
2201 request = sanitized_Request(url)
2202 request.add_header('Accept-Encoding', '*')
2203 full_response = self._request_webpage(request, video_id)
2204 head_response = full_response
2208 'title': self._generic_title(url),
2209 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2212 # Check for direct link to a video
2213 content_type = head_response.headers.get('Content-Type', '').lower()
2214 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2216 format_id = compat_str(m.group('format_id'))
2217 if format_id.endswith('mpegurl'):
2218 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2219 elif format_id == 'f4m':
2220 formats = self._extract_f4m_formats(url, video_id)
2223 'format_id': format_id,
2225 'vcodec': 'none' if m.group('type') == 'audio' else None
2227 info_dict['direct'] = True
2228 self._sort_formats(formats)
2229 info_dict['formats'] = formats
2232 if not self._downloader.params.get('test', False) and not is_intentional:
2233 force = self._downloader.params.get('force_generic_extractor', False)
2234 self._downloader.report_warning(
2235 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2237 if not full_response:
2238 request = sanitized_Request(url)
2239 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2240 # making it impossible to download only chunk of the file (yet we need only 512kB to
2241 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2242 # that will always result in downloading the whole file that is not desirable.
2243 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2244 # to accept raw bytes and being able to download only a chunk.
2245 # It may probably better to solve this by checking Content-Type for application/octet-stream
2246 # after HEAD request finishes, but not sure if we can rely on this.
2247 request.add_header('Accept-Encoding', '*')
2248 full_response = self._request_webpage(request, video_id)
2250 first_bytes = full_response.read(512)
2252 # Is it an M3U playlist?
2253 if first_bytes.startswith(b'#EXTM3U'):
2254 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2255 self._sort_formats(info_dict['formats'])
2258 # Maybe it's a direct link to a video?
2259 # Be careful not to download the whole thing!
2260 if not is_html(first_bytes):
2261 self._downloader.report_warning(
2262 'URL could be a direct video link, returning it as such.')
2269 webpage = self._webpage_read_content(
2270 full_response, url, video_id, prefix=first_bytes)
2272 self.report_extraction(video_id)
2274 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2276 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2277 if doc.tag == 'rss':
2278 return self._extract_rss(url, video_id, doc)
2279 elif doc.tag == 'SmoothStreamingMedia':
2280 info_dict['formats'] = self._parse_ism_formats(doc, url)
2281 self._sort_formats(info_dict['formats'])
2283 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2284 smil = self._parse_smil(doc, url, video_id)
2285 self._sort_formats(smil['formats'])
2287 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2288 return self.playlist_result(
2290 doc, video_id, xspf_url=url,
2291 xspf_base_url=compat_str(full_response.geturl())),
2293 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2294 info_dict['formats'] = self._parse_mpd_formats(
2296 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2298 self._sort_formats(info_dict['formats'])
2300 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2301 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2302 self._sort_formats(info_dict['formats'])
2304 except compat_xml_parse_error:
2307 # Is it a Camtasia project?
2308 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2309 if camtasia_res is not None:
2312 # Sometimes embedded video player is hidden behind percent encoding
2313 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2314 # Unescaping the whole page allows to handle those cases in a generic way
2315 webpage = compat_urllib_parse_unquote(webpage)
2317 # it's tempting to parse this further, but you would
2318 # have to take into account all the variations like
2319 # Video Title - Site Name
2320 # Site Name | Video Title
2321 # Video Title - Tagline | Site Name
2322 # and so on and so forth; it's just not practical
2323 video_title = self._og_search_title(
2324 webpage, default=None) or self._html_search_regex(
2325 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2328 # Try to detect age limit automatically
2329 age_limit = self._rta_search(webpage)
2330 # And then there are the jokers who advertise that they use RTA,
2331 # but actually don't.
2332 AGE_LIMIT_MARKERS = [
2333 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2335 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2338 # video uploader is domain name
2339 video_uploader = self._search_regex(
2340 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2342 video_description = self._og_search_description(webpage, default=None)
2343 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2346 'title': video_title,
2347 'description': video_description,
2348 'thumbnail': video_thumbnail,
2349 'age_limit': age_limit,
2352 # Look for Brightcove Legacy Studio embeds
2353 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2357 'url': smuggle_url(bc_url, {'Referer': url}),
2358 'ie_key': 'BrightcoveLegacy'
2359 } for bc_url in bc_urls]
2362 '_type': 'playlist',
2363 'title': video_title,
2368 # Look for Brightcove New Studio embeds
2369 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2371 return self.playlist_from_matches(
2372 bc_urls, video_id, video_title,
2373 getter=lambda x: smuggle_url(x, {'referrer': url}),
2376 # Look for Nexx embeds
2377 nexx_urls = NexxIE._extract_urls(webpage)
2379 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2381 # Look for Nexx iFrame embeds
2382 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2384 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2386 # Look for ThePlatform embeds
2387 tp_urls = ThePlatformIE._extract_urls(webpage)
2389 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2391 # Look for Vessel embeds
2392 vessel_urls = VesselIE._extract_urls(webpage)
2394 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2396 # Look for embedded rtl.nl player
2397 matches = re.findall(
2398 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2401 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2403 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2405 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2407 vid_me_embed_url = self._search_regex(
2408 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2409 webpage, 'vid.me embed', default=None)
2410 if vid_me_embed_url is not None:
2411 return self.url_result(vid_me_embed_url, 'Vidme')
2413 # Look for YouTube embeds
2414 youtube_urls = YoutubeIE._extract_urls(webpage)
2416 return self.playlist_from_matches(
2417 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2419 matches = DailymotionIE._extract_urls(webpage)
2421 return self.playlist_from_matches(matches, video_id, video_title)
2423 # Look for embedded Dailymotion playlist player (#3822)
2425 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2427 playlists = re.findall(
2428 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2430 return self.playlist_from_matches(
2431 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2433 # Look for DailyMail embeds
2434 dailymail_urls = DailyMailIE._extract_urls(webpage)
2436 return self.playlist_from_matches(
2437 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2439 # Look for embedded Wistia player
2440 wistia_url = WistiaIE._extract_url(webpage)
2443 '_type': 'url_transparent',
2444 'url': self._proto_relative_url(wistia_url),
2445 'ie_key': WistiaIE.ie_key(),
2446 'uploader': video_uploader,
2449 # Look for SVT player
2450 svt_url = SVTIE._extract_url(webpage)
2452 return self.url_result(svt_url, 'SVT')
2454 # Look for Bandcamp pages with custom domain
2455 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2456 if mobj is not None:
2457 burl = unescapeHTML(mobj.group(1))
2458 # Don't set the extractor because it can be a track url or an album
2459 return self.url_result(burl)
2461 # Look for embedded Vevo player
2463 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2464 if mobj is not None:
2465 return self.url_result(mobj.group('url'))
2467 # Look for embedded Viddler player
2469 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2471 if mobj is not None:
2472 return self.url_result(mobj.group('url'))
2474 # Look for NYTimes player
2476 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2478 if mobj is not None:
2479 return self.url_result(mobj.group('url'))
2481 # Look for Libsyn player
2483 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2484 if mobj is not None:
2485 return self.url_result(mobj.group('url'))
2487 # Look for Ooyala videos
2488 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2489 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2490 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2491 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2492 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2493 if mobj is not None:
2494 embed_token = self._search_regex(
2495 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2496 webpage, 'ooyala embed token', default=None)
2497 return OoyalaIE._build_url_result(smuggle_url(
2500 'embed_token': embed_token,
2503 # Look for multiple Ooyala embeds on SBN network websites
2504 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2505 if mobj is not None:
2506 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2508 return self.playlist_from_matches(
2509 embeds, video_id, video_title,
2510 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2512 # Look for Aparat videos
2513 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2514 if mobj is not None:
2515 return self.url_result(mobj.group(1), 'Aparat')
2517 # Look for MPORA videos
2518 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2519 if mobj is not None:
2520 return self.url_result(mobj.group(1), 'Mpora')
2522 # Look for embedded NovaMov-based player
2524 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2525 (?P<url>http://(?:(?:embed|www)\.)?
2527 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2528 videoweed\.(?:es|com)|
2529 movshare\.(?:net|sx|ag)|
2530 divxstage\.(?:eu|net|ch|co|at|ag))
2531 /embed\.php.+?)\1''', webpage)
2532 if mobj is not None:
2533 return self.url_result(mobj.group('url'))
2535 # Look for embedded Facebook player
2536 facebook_urls = FacebookIE._extract_urls(webpage)
2538 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2540 # Look for embedded VK player
2541 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2542 if mobj is not None:
2543 return self.url_result(mobj.group('url'), 'VK')
2545 # Look for embedded Odnoklassniki player
2546 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2547 if mobj is not None:
2548 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2550 # Look for embedded ivi player
2551 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2552 if mobj is not None:
2553 return self.url_result(mobj.group('url'), 'Ivi')
2555 # Look for embedded Huffington Post player
2557 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2558 if mobj is not None:
2559 return self.url_result(mobj.group('url'), 'HuffPost')
2562 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2563 if mobj is not None:
2564 return self.url_result(mobj.group('url'))
2565 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2566 if mobj is not None:
2567 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2569 # Look for funnyordie embed
2570 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2572 return self.playlist_from_matches(
2573 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2575 # Look for BBC iPlayer embed
2576 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2578 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2580 # Look for embedded RUTV player
2581 rutv_url = RUTVIE._extract_url(webpage)
2583 return self.url_result(rutv_url, 'RUTV')
2585 # Look for embedded TVC player
2586 tvc_url = TVCIE._extract_url(webpage)
2588 return self.url_result(tvc_url, 'TVC')
2590 # Look for embedded SportBox player
2591 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2593 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2595 # Look for embedded XHamster player
2596 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2598 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2600 # Look for embedded TNAFlixNetwork player
2601 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2603 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2605 # Look for embedded PornHub player
2606 pornhub_urls = PornHubIE._extract_urls(webpage)
2608 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2610 # Look for embedded DrTuber player
2611 drtuber_urls = DrTuberIE._extract_urls(webpage)
2613 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2615 # Look for embedded RedTube player
2616 redtube_urls = RedTubeIE._extract_urls(webpage)
2618 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2620 # Look for embedded Tube8 player
2621 tube8_urls = Tube8IE._extract_urls(webpage)
2623 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2625 # Look for embedded Tvigle player
2627 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2628 if mobj is not None:
2629 return self.url_result(mobj.group('url'), 'Tvigle')
2631 # Look for embedded TED player
2633 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2634 if mobj is not None:
2635 return self.url_result(mobj.group('url'), 'TED')
2637 # Look for embedded Ustream videos
2638 ustream_url = UstreamIE._extract_url(webpage)
2640 return self.url_result(ustream_url, UstreamIE.ie_key())
2642 # Look for embedded arte.tv player
2644 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2646 if mobj is not None:
2647 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2649 # Look for embedded francetv player
2651 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2653 if mobj is not None:
2654 return self.url_result(mobj.group('url'))
2656 # Look for embedded smotri.com player
2657 smotri_url = SmotriIE._extract_url(webpage)
2659 return self.url_result(smotri_url, 'Smotri')
2661 # Look for embedded Myvi.ru player
2662 myvi_url = MyviIE._extract_url(webpage)
2664 return self.url_result(myvi_url)
2666 # Look for embedded soundcloud player
2667 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2669 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2671 # Look for tunein player
2672 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2674 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2676 # Look for embedded mtvservices player
2677 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2679 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2681 # Look for embedded yahoo player
2683 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2685 if mobj is not None:
2686 return self.url_result(mobj.group('url'), 'Yahoo')
2688 # Look for embedded sbs.com.au player
2692 <meta\s+property="og:video"\s+content=|
2695 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2697 if mobj is not None:
2698 return self.url_result(mobj.group('url'), 'SBS')
2700 # Look for embedded Cinchcast player
2702 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2704 if mobj is not None:
2705 return self.url_result(mobj.group('url'), 'Cinchcast')
2708 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2712 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2714 if mobj is not None:
2715 return self.url_result(mobj.group('url'), 'MLB')
2718 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2720 if mobj is not None:
2721 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2724 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2726 if mobj is not None:
2727 return self.url_result(mobj.group('url'), 'Livestream')
2729 # Look for Zapiks embed
2731 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2732 if mobj is not None:
2733 return self.url_result(mobj.group('url'), 'Zapiks')
2735 # Look for Kaltura embeds
2736 kaltura_url = KalturaIE._extract_url(webpage)
2738 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2740 # Look for EaglePlatform embeds
2741 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2742 if eagleplatform_url:
2743 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2745 # Look for ClipYou (uses EaglePlatform) embeds
2747 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2748 if mobj is not None:
2749 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2751 # Look for Pladform embeds
2752 pladform_url = PladformIE._extract_url(webpage)
2754 return self.url_result(pladform_url)
2756 # Look for Videomore embeds
2757 videomore_url = VideomoreIE._extract_url(webpage)
2759 return self.url_result(videomore_url)
2761 # Look for Webcaster embeds
2762 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2764 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2766 # Look for Playwire embeds
2768 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2769 if mobj is not None:
2770 return self.url_result(mobj.group('url'))
2772 # Look for 5min embeds
2774 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2775 if mobj is not None:
2776 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2778 # Look for Crooks and Liars embeds
2780 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2781 if mobj is not None:
2782 return self.url_result(mobj.group('url'))
2784 # Look for NBC Sports VPlayer embeds
2785 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2787 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2789 # Look for NBC News embeds
2790 nbc_news_embed_url = re.search(
2791 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2792 if nbc_news_embed_url:
2793 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2795 # Look for Google Drive embeds
2796 google_drive_url = GoogleDriveIE._extract_url(webpage)
2797 if google_drive_url:
2798 return self.url_result(google_drive_url, 'GoogleDrive')
2800 # Look for UDN embeds
2802 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2803 if mobj is not None:
2804 return self.url_result(
2805 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2807 # Look for Senate ISVP iframe
2808 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2810 return self.url_result(senate_isvp_url, 'SenateISVP')
2812 # Look for OnionStudios embeds
2813 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2814 if onionstudios_url:
2815 return self.url_result(onionstudios_url)
2817 # Look for ViewLift embeds
2818 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2820 return self.url_result(viewlift_url)
2822 # Look for JWPlatform embeds
2823 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2825 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2827 # Look for Digiteka embeds
2828 digiteka_url = DigitekaIE._extract_url(webpage)
2830 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2832 # Look for Arkena embeds
2833 arkena_url = ArkenaIE._extract_url(webpage)
2835 return self.url_result(arkena_url, ArkenaIE.ie_key())
2837 # Look for Piksel embeds
2838 piksel_url = PikselIE._extract_url(webpage)
2840 return self.url_result(piksel_url, PikselIE.ie_key())
2842 # Look for Limelight embeds
2843 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2845 return self.playlist_result(
2846 limelight_urls, video_id, video_title, video_description)
2848 # Look for Anvato embeds
2849 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2851 return self.playlist_result(
2852 anvato_urls, video_id, video_title, video_description)
2854 # Look for AdobeTVVideo embeds
2856 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2858 if mobj is not None:
2859 return self.url_result(
2860 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2863 # Look for Vine embeds
2865 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2867 if mobj is not None:
2868 return self.url_result(
2869 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2871 # Look for VODPlatform embeds
2873 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2875 if mobj is not None:
2876 return self.url_result(
2877 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2879 # Look for Mangomolo embeds
2881 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2883 video\?.*?\bid=(?P<video_id>\d+)|
2884 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2885 ).+?)\1''', webpage)
2886 if mobj is not None:
2888 '_type': 'url_transparent',
2889 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2890 'title': video_title,
2891 'description': video_description,
2892 'thumbnail': video_thumbnail,
2893 'uploader': video_uploader,
2895 video_id = mobj.group('video_id')
2898 'ie_key': 'MangomoloVideo',
2903 'ie_key': 'MangomoloLive',
2904 'id': mobj.group('channel_id'),
2908 # Look for Instagram embeds
2909 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2910 if instagram_embed_url is not None:
2911 return self.url_result(
2912 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2914 # Look for LiveLeak embeds
2915 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2917 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2919 # Look for 3Q SDN embeds
2920 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2923 '_type': 'url_transparent',
2924 'ie_key': ThreeQSDNIE.ie_key(),
2925 'url': self._proto_relative_url(threeqsdn_url),
2926 'title': video_title,
2927 'description': video_description,
2928 'thumbnail': video_thumbnail,
2929 'uploader': video_uploader,
2932 # Look for VBOX7 embeds
2933 vbox7_url = Vbox7IE._extract_url(webpage)
2935 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2937 # Look for DBTV embeds
2938 dbtv_urls = DBTVIE._extract_urls(webpage)
2940 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2942 # Look for Videa embeds
2943 videa_urls = VideaIE._extract_urls(webpage)
2945 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2947 # Look for 20 minuten embeds
2948 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2950 return self.playlist_from_matches(
2951 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2953 # Look for Openload embeds
2954 openload_urls = OpenloadIE._extract_urls(webpage)
2956 return self.playlist_from_matches(
2957 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2959 # Look for VideoPress embeds
2960 videopress_urls = VideoPressIE._extract_urls(webpage)
2962 return self.playlist_from_matches(
2963 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2965 # Look for Rutube embeds
2966 rutube_urls = RutubeIE._extract_urls(webpage)
2968 return self.playlist_from_matches(
2969 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2971 # Look for WashingtonPost embeds
2972 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2974 return self.playlist_from_matches(
2975 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2977 # Look for Mediaset embeds
2978 mediaset_urls = MediasetIE._extract_urls(webpage)
2980 return self.playlist_from_matches(
2981 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2983 # Look for JOJ.sk embeds
2984 joj_urls = JojIE._extract_urls(webpage)
2986 return self.playlist_from_matches(
2987 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2989 # Look for megaphone.fm embeds
2990 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2992 return self.playlist_from_matches(
2993 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2995 # Look for vzaar embeds
2996 vzaar_urls = VzaarIE._extract_urls(webpage)
2998 return self.playlist_from_matches(
2999 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3001 channel9_urls = Channel9IE._extract_urls(webpage)
3003 return self.playlist_from_matches(
3004 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3006 vshare_urls = VShareIE._extract_urls(webpage)
3008 return self.playlist_from_matches(
3009 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3011 # Look for Mediasite embeds
3012 mediasite_urls = MediasiteIE._extract_urls(webpage)
3015 self.url_result(smuggle_url(
3016 compat_urlparse.urljoin(url, mediasite_url),
3017 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3018 for mediasite_url in mediasite_urls]
3019 return self.playlist_result(entries, video_id, video_title)
3021 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3022 if springboardplatform_urls:
3023 return self.playlist_from_matches(
3024 springboardplatform_urls, video_id, video_title,
3025 ie=SpringboardPlatformIE.ie_key())
3027 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3029 return self.playlist_from_matches(
3030 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3032 vice_urls = ViceIE._extract_urls(webpage)
3034 return self.playlist_from_matches(
3035 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3037 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3039 return self.playlist_from_matches(
3040 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3042 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3043 if cloudflarestream_urls:
3044 return self.playlist_from_matches(
3045 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3047 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
3048 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3050 if sharevideos_urls:
3051 return self.playlist_from_matches(
3052 sharevideos_urls, video_id, video_title)
3054 # Look for HTML5 media
3055 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3057 if len(entries) == 1:
3060 'title': video_title,
3063 for num, entry in enumerate(entries, start=1):
3065 'id': '%s-%s' % (video_id, num),
3066 'title': '%s (%d)' % (video_title, num),
3068 for entry in entries:
3069 self._sort_formats(entry['formats'])
3070 return self.playlist_result(entries, video_id, video_title)
3072 jwplayer_data = self._find_jwplayer_data(
3073 webpage, video_id, transform_source=js_to_json)
3075 info = self._parse_jwplayer_data(
3076 jwplayer_data, video_id, require_title=False, base_url=url)
3077 return merge_dicts(info, info_dict)
3081 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3083 if mobj is not None:
3084 sources = self._parse_json(
3085 mobj.group(1), video_id, transform_source=js_to_json,
3087 if not isinstance(sources, list):
3090 for source in sources:
3091 src = source.get('src')
3092 if not src or not isinstance(src, compat_str):
3094 src = compat_urlparse.urljoin(url, src)
3095 src_type = source.get('type')
3096 if isinstance(src_type, compat_str):
3097 src_type = src_type.lower()
3098 ext = determine_ext(src).lower()
3099 if src_type == 'video/youtube':
3100 return self.url_result(src, YoutubeIE.ie_key())
3101 if src_type == 'application/dash+xml' or ext == 'mpd':
3102 formats.extend(self._extract_mpd_formats(
3103 src, video_id, mpd_id='dash', fatal=False))
3104 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3105 formats.extend(self._extract_m3u8_formats(
3106 src, video_id, 'mp4', entry_protocol='m3u8_native',
3107 m3u8_id='hls', fatal=False))
3111 'ext': (mimetype2ext(src_type) or
3112 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3115 self._sort_formats(formats)
3116 info_dict['formats'] = formats
3119 # Looking for http://schema.org/VideoObject
3120 json_ld = self._search_json_ld(
3121 webpage, video_id, default={}, expected_type='VideoObject')
3122 if json_ld.get('url'):
3123 return merge_dicts(json_ld, info_dict)
3125 def check_video(vurl):
3126 if YoutubeIE.suitable(vurl):
3128 if RtmpIE.suitable(vurl):
3130 vpath = compat_urlparse.urlparse(vurl).path
3131 vext = determine_ext(vpath)
3132 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3134 def filter_video(urls):
3135 return list(filter(check_video, urls))
3137 # Start with something easy: JW Player in SWFObject
3138 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3140 # Look for gorilla-vid style embedding
3141 found = filter_video(re.findall(r'''(?sx)
3145 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3148 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3150 # Broaden the search a little bit
3151 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3153 # Broaden the findall a little bit: JWPlayer JS loader
3154 found = filter_video(re.findall(
3155 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3158 found = filter_video(re.findall(r'''(?xs)
3159 flowplayer\("[^"]+",\s*
3161 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3162 ["']?url["']?\s*:\s*["']([^"']+)["']
3167 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3169 # Try to find twitter cards info
3170 # twitter:player:stream should be checked before twitter:player since
3171 # it is expected to contain a raw stream (see
3172 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3173 found = filter_video(re.findall(
3174 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3176 # We look for Open Graph info:
3177 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3178 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3179 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3180 if m_video_type is not None:
3181 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3183 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3185 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3186 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3189 # Look also in Refresh HTTP header
3190 refresh_header = head_response.headers.get('Refresh')
3192 # In python 2 response HTTP headers are bytestrings
3193 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3194 refresh_header = refresh_header.decode('iso-8859-1')
3195 found = re.search(REDIRECT_REGEX, refresh_header)
3197 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3199 self.report_following_redirect(new_url)
3208 # twitter:player is a https URL to iframe player that may or may not
3209 # be supported by youtube-dl thus this is checked the very last (see
3210 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3211 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3212 if embed_url and embed_url != url:
3213 return self.url_result(embed_url)
3216 raise UnsupportedError(url)
3219 for video_url in orderedSet(found):
3220 video_url = unescapeHTML(video_url)
3221 video_url = video_url.replace('\\/', '/')
3222 video_url = compat_urlparse.urljoin(url, video_url)
3223 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3225 # Sometimes, jwplayer extraction will result in a YouTube URL
3226 if YoutubeIE.suitable(video_url):
3227 entries.append(self.url_result(video_url, 'Youtube'))
3230 # here's a fun little line of code for you:
3231 video_id = os.path.splitext(video_id)[0]
3235 'uploader': video_uploader,
3236 'title': video_title,
3237 'age_limit': age_limit,
3240 if RtmpIE.suitable(video_url):
3241 entry_info_dict.update({
3242 '_type': 'url_transparent',
3243 'ie_key': RtmpIE.ie_key(),
3246 entries.append(entry_info_dict)
3249 ext = determine_ext(video_url)
3251 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3253 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3255 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3257 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3259 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3260 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3261 # Just matching .ism/manifest is not enough to be reliably sure
3262 # whether it's actually an ISM manifest or some other streaming
3263 # manifest since there are various streaming URL formats
3264 # possible (see [1]) as well as some other shenanigans like
3265 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3267 # Thus the most reasonable way to solve this is to delegate
3268 # to generic extractor in order to look into the contents of
3269 # the manifest itself.
3270 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3271 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3272 entry_info_dict = self.url_result(
3273 smuggle_url(video_url, {'to_generic': True}),
3276 entry_info_dict['url'] = video_url
3278 if entry_info_dict.get('formats'):
3279 self._sort_formats(entry_info_dict['formats'])
3281 entries.append(entry_info_dict)
3283 if len(entries) == 1:
3286 for num, e in enumerate(entries, start=1):
3287 # 'url' results don't have a title
3288 if e.get('title') is not None:
3289 e['title'] = '%s (%d)' % (e['title'], num)
3291 '_type': 'playlist',