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,
38 from .commonprotocols import RtmpIE
39 from .brightcove import (
47 from .nbc import NBCSportsVPlayerIE
48 from .ooyala import OoyalaIE
49 from .rutv import RUTVIE
50 from .tvc import TVCIE
51 from .sportbox import SportBoxEmbedIE
52 from .smotri import SmotriIE
53 from .myvi import MyviIE
54 from .condenast import CondeNastIE
55 from .udn import UDNEmbedIE
56 from .senateisvp import SenateISVPIE
57 from .svt import SVTIE
58 from .pornhub import PornHubIE
59 from .xhamster import XHamsterEmbedIE
60 from .tnaflix import TNAFlixNetworkEmbedIE
61 from .drtuber import DrTuberIE
62 from .redtube import RedTubeIE
63 from .tube8 import Tube8IE
64 from .vimeo import VimeoIE
65 from .dailymotion import DailymotionIE
66 from .dailymail import DailyMailIE
67 from .onionstudios import OnionStudiosIE
68 from .viewlift import ViewLiftEmbedIE
69 from .mtv import MTVServicesEmbeddedIE
70 from .pladform import PladformIE
71 from .videomore import VideomoreIE
72 from .webcaster import WebcasterFeedIE
73 from .googledrive import GoogleDriveIE
74 from .jwplatform import JWPlatformIE
75 from .digiteka import DigitekaIE
76 from .arkena import ArkenaIE
77 from .instagram import InstagramIE
78 from .liveleak import LiveLeakIE
79 from .threeqsdn import ThreeQSDNIE
80 from .theplatform import ThePlatformIE
81 from .vessel import VesselIE
82 from .kaltura import KalturaIE
83 from .eagleplatform import EaglePlatformIE
84 from .facebook import FacebookIE
85 from .soundcloud import SoundcloudIE
86 from .tunein import TuneInBaseIE
87 from .vbox7 import Vbox7IE
88 from .dbtv import DBTVIE
89 from .piksel import PikselIE
90 from .videa import VideaIE
91 from .twentymin import TwentyMinutenIE
92 from .ustream import UstreamIE
93 from .openload import OpenloadIE
94 from .videopress import VideoPressIE
95 from .rutube import RutubeIE
96 from .limelight import LimelightBaseIE
97 from .anvato import AnvatoIE
98 from .washingtonpost import WashingtonPostIE
99 from .wistia import WistiaIE
100 from .mediaset import MediasetIE
101 from .joj import JojIE
102 from .megaphone import MegaphoneIE
103 from .vzaar import VzaarIE
104 from .channel9 import Channel9IE
105 from .vshare import VShareIE
106 from .mediasite import MediasiteIE
107 from .springboardplatform import SpringboardPlatformIE
108 from .yapfiles import YapFilesIE
109 from .vice import ViceIE
110 from .xfileshare import XFileShareIE
111 from .cloudflarestream import CloudflareStreamIE
112 from .peertube import PeerTubeIE
113 from .indavideo import IndavideoEmbedIE
114 from .apa import APAIE
115 from .foxnews import FoxNewsIE
118 class GenericIE(InfoExtractor):
119 IE_DESC = 'Generic downloader that works on some sites'
123 # Direct link to a video
125 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
126 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
131 'upload_date': '20100513',
134 # Direct link to media delivered compressed (until Accept-Encoding is *)
136 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
137 'md5': '128c42e68b13950268b648275386fc74',
139 'id': 'FictionJunction-Parallel_Hearts',
141 'title': 'FictionJunction-Parallel_Hearts',
142 'upload_date': '20140522',
144 'expected_warnings': [
145 'URL could be a direct video link, returning it as such.'
147 'skip': 'URL invalid',
149 # Direct download with broken HEAD
151 'url': 'http://ai-radio.org:8000/radio.opus',
158 'skip_download': True, # infinite live stream
160 'expected_warnings': [
161 r'501.*Not Implemented',
165 # Direct link with incorrect MIME type
167 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
168 'md5': '4ccbebe5f36706d85221f204d7eb5913',
170 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
171 'id': '5_Lennart_Poettering_-_Systemd',
173 'title': '5_Lennart_Poettering_-_Systemd',
174 'upload_date': '20141120',
176 'expected_warnings': [
177 'URL could be a direct video link, returning it as such.'
182 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
184 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
185 'title': 'Zero Punctuation',
186 'description': 're:.*groundbreaking video review series.*'
188 'playlist_mincount': 11,
190 # RSS feed with enclosure
192 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
194 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
196 'upload_date': '20150228',
197 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
200 # RSS feed with enclosures and unsupported link URLs
202 'url': 'http://www.hellointernet.fm/podcast?format=rss',
204 'id': 'http://www.hellointernet.fm/podcast?format=rss',
205 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
206 'title': 'Hello Internet',
208 'playlist_mincount': 100,
210 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
212 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
216 'title': 'Automatics, robotics and biocybernetics',
217 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
218 'upload_date': '20130627',
219 'formats': 'mincount:16',
220 'subtitles': 'mincount:1',
223 'force_generic_extractor': True,
224 'skip_download': True,
227 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
229 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
234 'formats': 'mincount:1',
237 'skip_download': True,
240 # SMIL from https://www.restudy.dk/video/play/id/1637
242 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
246 'title': 'video_1637',
247 'formats': 'mincount:3',
250 'skip_download': True,
253 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
255 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
257 'id': 'smil-service',
259 'title': 'smil-service',
260 'formats': 'mincount:1',
263 'skip_download': True,
266 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
268 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
272 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
273 'formats': 'mincount:3',
276 'skip_download': True,
279 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
281 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
283 'id': 'mZlp2ctYIUEB',
285 'title': 'Tikibad ontruimd wegens brand',
286 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
287 'thumbnail': r're:^https?://.*\.jpg$',
291 'skip_download': True,
294 # MPD from http://dash-mse-test.appspot.com/media.html
296 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
297 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
299 'id': 'car-20120827-manifest',
301 'title': 'car-20120827-manifest',
302 'formats': 'mincount:9',
303 'upload_date': '20130904',
306 'format': 'bestvideo',
309 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
311 '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',
316 'formats': 'mincount:8',
320 'skip_download': True,
322 'skip': 'video gone',
324 # m3u8 served with Content-Type: text/plain
326 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
331 'upload_date': '20140720',
332 'formats': 'mincount:11',
336 'skip_download': True,
338 'skip': 'video gone',
342 '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',
346 'upload_date': '20130224',
347 'uploader_id': 'TheVerge',
348 'description': r're:^Chris Ziegler takes a look at the\.*',
349 'uploader': 'The Verge',
350 'title': 'First Firefox OS phones side-by-side',
353 'skip_download': False,
357 # redirect in Refresh HTTP header
358 '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',
362 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
363 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
364 'upload_date': '20150917',
365 'uploader_id': 'brtvofficial',
366 'uploader': 'Boiler Room',
369 'skip_download': False,
373 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
374 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
376 'id': '13601338388002',
378 'uploader': 'www.hodiho.fr',
379 'title': 'R\u00e9gis plante sa Jeep',
382 # bandcamp page with custom domain
384 'add_ie': ['Bandcamp'],
385 'url': 'http://bronyrock.com/track/the-pony-mash',
389 'title': 'The Pony Mash',
390 'uploader': 'M_Pallante',
392 'skip': 'There is a limit of 200 free downloads / month for the test song',
395 # embedded brightcove video
396 # it also tests brightcove videos that need to set the 'Referer'
397 # in the http requests
398 'add_ie': ['BrightcoveLegacy'],
399 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
401 'id': '2765128793001',
403 'title': 'Le cours de bourse : l’analyse technique',
404 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
405 'uploader': 'BFM BUSINESS',
408 'skip_download': True,
412 # embedded with itemprop embedURL and video id spelled as `idVideo`
413 'add_id': ['BrightcoveLegacy'],
414 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
416 'id': '5255628253001',
418 'title': 'md5:37c519b1128915607601e75a87995fc0',
419 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
420 'uploader': 'BFM BUSINESS',
421 'uploader_id': '876450612001',
422 'timestamp': 1482255315,
423 'upload_date': '20161220',
426 'skip_download': True,
430 # https://github.com/rg3/youtube-dl/issues/2253
431 'url': 'http://bcove.me/i6nfkrc3',
432 'md5': '0ba9446db037002366bab3b3eb30c88c',
434 'id': '3101154703001',
436 'title': 'Still no power',
437 'uploader': 'thestar.com',
438 '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.',
440 'add_ie': ['BrightcoveLegacy'],
441 'skip': 'video gone',
444 'url': 'http://www.championat.com/video/football/v/87/87499.html',
445 'md5': 'fb973ecf6e4a78a67453647444222983',
447 'id': '3414141473001',
449 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
450 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
451 'uploader': 'Championat',
455 # https://github.com/rg3/youtube-dl/issues/3541
456 'add_ie': ['BrightcoveLegacy'],
457 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
459 'id': '3866516442001',
461 'title': 'Leer mij vrouwen kennen: Aflevering 1',
462 'description': 'Leer mij vrouwen kennen: Aflevering 1',
463 'uploader': 'SBS Broadcasting',
465 'skip': 'Restricted to Netherlands',
467 'skip_download': True, # m3u8 download
471 # Brightcove video in <iframe>
472 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
473 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
475 'id': '5360463607001',
477 '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',
478 '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。',
479 'uploader': 'United Nations',
480 'uploader_id': '1362235914001',
481 'timestamp': 1489593889,
482 'upload_date': '20170315',
484 'add_ie': ['BrightcoveLegacy'],
487 # Brightcove with alternative playerID key
488 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
490 'id': 'nmeth.2062_SV1',
491 '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',
495 'id': '2228375078001',
497 'title': 'nmeth.2062-sv1',
498 'description': 'nmeth.2062-sv1',
499 'timestamp': 1363357591,
500 'upload_date': '20130315',
501 'uploader': 'Nature Publishing Group',
502 'uploader_id': '1964492299001',
507 # Brightcove with UUID in videoPlayer
508 'url': 'http://www8.hp.com/cn/zh/home.html',
510 'id': '5255815316001',
512 'title': 'Sprocket Video - China',
513 'description': 'Sprocket Video - China',
514 'uploader': 'HP-Video Gallery',
515 'timestamp': 1482263210,
516 'upload_date': '20161220',
517 'uploader_id': '1107601872001',
520 'skip_download': True, # m3u8 download
522 'skip': 'video rotates...weekly?',
525 # Brightcove:new type [2].
526 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
527 'md5': '2b35148fcf48da41c9fb4591650784f3',
529 'id': '5348741021001',
531 'upload_date': '20170306',
532 'uploader_id': '4191638492001',
533 'timestamp': 1488769918,
534 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
539 # Alternative brightcove <video> attributes
540 '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/',
542 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
543 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
546 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
548 'id': '5311302538001',
550 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
551 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
552 'timestamp': 1486321708,
553 'upload_date': '20170205',
554 'uploader_id': '800000640001',
556 'only_matching': True,
560 # Brightcove with UUID in videoPlayer
561 'url': 'http://www8.hp.com/cn/zh/home.html',
563 'id': '5255815316001',
565 'title': 'Sprocket Video - China',
566 'description': 'Sprocket Video - China',
567 'uploader': 'HP-Video Gallery',
568 'timestamp': 1482263210,
569 'upload_date': '20161220',
570 'uploader_id': '1107601872001',
573 'skip_download': True, # m3u8 download
578 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
579 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
581 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
583 'title': '2cc213299525360.mov', # that's what we get
586 'add_ie': ['Ooyala'],
589 # ooyala video embedded with http://player.ooyala.com/iframe.js
590 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
592 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
594 'title': '"Steve Jobs: Man in the Machine" trailer',
595 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
599 'skip_download': True,
601 'skip': 'movie expired',
603 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
605 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
607 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
609 'title': 'Steampunk Fest Comes to Honesdale',
613 'skip_download': True,
618 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
622 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
623 'upload_date': '20140225',
624 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
625 'uploader': 'Tested',
626 'uploader_id': 'testedcom',
628 # No need to test YoutubeIE here
630 'skip_download': True,
635 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
639 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
640 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
642 # HEAD requests lead to endless 301, while GET is OK
643 'expected_warnings': ['301'],
647 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
651 'title': 'Охотское море стало целиком российским',
652 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
656 'skip_download': True,
661 '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/',
665 'title': 'Дошкольное воспитание',
670 'url': 'http://www.vestifinance.ru/articles/25753',
673 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
678 'title': 'Госзаказ. День 3',
684 'title': 'Госзаказ. День 2',
690 'title': 'Госзаказ. День 1',
696 'skip_download': True,
701 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
703 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
705 'title': 'Ужастики, русский трейлер (2015)',
706 'thumbnail': r're:^https?://.*\.jpg$',
712 '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',
715 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
717 'playlist_mincount': 7,
718 # This forum does not allow <iframe> syntaxes anymore
719 # Now HTML tags are displayed as-is
720 'skip': 'No videos on this page',
724 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
725 'md5': '65fdff94098e4a607385a60c5177c638',
729 'title': 'Hidden miracles of the natural world',
730 'uploader': 'Louie Schwartzberg',
731 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
734 # nowvideo embed hidden behind percent encoding
736 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
737 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
739 'id': '06e53103ca9aa',
741 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
742 'description': 'No description',
747 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
748 'md5': '7653032cbb25bf6c80d80f217055fa43',
750 'id': '048195-004_PLUS7-F',
753 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
754 'upload_date': '20140320',
757 'skip_download': 'Requires rtmpdump'
759 'skip': 'video gone',
763 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
767 'title': 'Alcaline, le concert avec Calogero',
768 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
769 'upload_date': '20150226',
770 'timestamp': 1424989860,
775 'skip_download': True,
777 'expected_warnings': [
783 'url': 'http://www.wired.com/2014/04/honda-asimo/',
784 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
786 'id': '53501be369702d3275860000',
788 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
793 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
794 'md5': '441aeeb82eb72c422c7f14ec533999cd',
796 'id': 'k2mm4bCdJ6CQ2i7c8o2',
798 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
799 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
801 'uploader_id': 'xgditw',
802 'upload_date': '20140425',
803 'timestamp': 1398441542,
805 'add_ie': ['Dailymotion'],
809 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
813 'title': 'Care worker punches elderly dementia patient in head 11 times',
814 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
816 'add_ie': ['DailyMail'],
818 'skip_download': True,
823 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
827 'title': 'The NBL Auction 2014',
828 'uploader': 'BADMINTON England',
829 'uploader_id': 'BADMINTONEvents',
830 'upload_date': '20140603',
831 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
833 'add_ie': ['Youtube'],
835 'skip_download': True,
840 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
841 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
843 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
845 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
846 'description': 'Two valets share their love for movie star Liam Neesons.',
847 'timestamp': 1349922600,
848 'upload_date': '20121011',
851 # YouTube embed via <data-embed-url="">
853 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
857 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
858 'uploader': 'Gameloft',
859 'uploader_id': 'gameloft',
860 'upload_date': '20140828',
861 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
864 'skip_download': True,
867 # YouTube <object> embed
869 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
870 'md5': '516718101ec834f74318df76259fb3cc',
874 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
875 'upload_date': '20080526',
876 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
877 'uploader': 'Christopher Sykes',
878 'uploader_id': 'ChristopherJSykes',
880 'add_ie': ['Youtube'],
884 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
886 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
888 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
889 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
894 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
896 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
897 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
903 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
908 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
909 'md5': '9d65602bf31c6e20014319c7d07fba27',
911 'id': '5123ea6d5e5a7',
914 'uploader': 'www.handjobhub.com',
915 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
918 # Multiple brightcove videos
919 # https://github.com/rg3/youtube-dl/issues/2283
921 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
923 'id': 'always-never',
924 'title': 'Always / Never - The New Yorker',
928 'extract_flat': False,
929 'skip_download': True,
934 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
935 'md5': '96f09a37e44da40dd083e12d9a683327',
939 'title': 'Ump changes call to ball',
940 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
942 'timestamp': 1401537900,
943 'upload_date': '20140531',
944 'thumbnail': r're:^https?://.*\.jpg$',
949 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
950 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
954 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
955 'description': 'a Paywall Videos video from Remilon',
957 'uploader': 'study.com',
958 'timestamp': 1459678540,
959 'upload_date': '20160403',
960 'filesize': 24687186,
964 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
965 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
969 'title': 'Conversation about Hexagonal Rails Part 1',
970 'description': 'a Martin Fowler video from ThoughtWorks',
972 'uploader': 'thoughtworks.wistia.com',
973 'timestamp': 1401832161,
974 'upload_date': '20140603',
977 # Wistia standard embed (async)
979 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
983 'title': 'Drip Brennan Dunn Workshop',
984 'description': 'a JV Webinars video from getdrip-1',
986 'timestamp': 1463607249,
987 'upload_date': '20160518',
990 'skip_download': True,
995 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
999 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1000 'uploader': 'Sophos Security',
1001 'title': 'Chet Chat 171 - Oct 29, 2014',
1002 'upload_date': '20141029',
1005 # Soundcloud multiple embeds
1007 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1010 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1012 'playlist_mincount': 7,
1014 # TuneIn station embed
1016 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1021 'location': 'Paris, France',
1026 'skip_download': True,
1031 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1035 'upload_date': '20141112',
1036 'title': 'Rosetta #CometLanding webcast HL 10',
1039 # Another Livestream embed, without 'new.' in URL
1041 'url': 'https://www.freespeech.org/',
1045 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1049 'skip_download': True,
1054 'url': 'https://skiplagged.com/',
1057 'title': 'Skiplagged: The smart way to find cheap flights',
1059 'playlist_mincount': 1,
1060 'add_ie': ['Youtube'],
1064 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1068 'upload_date': '20141126',
1069 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1074 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1076 'id': '730m_DandD_1901_512k',
1078 'uploader': 'www.abc.net.au',
1079 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1082 # embedded viddler video
1084 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1088 'uploader': 'deadspin',
1089 'title': 'WALL-TO-GORTAT',
1090 'timestamp': 1422285291,
1091 'upload_date': '20150126',
1093 'add_ie': ['Viddler'],
1097 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1101 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1102 'description': 'md5:601cb790edd05908957dae8aaa866465',
1103 'upload_date': '20150220',
1105 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1109 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1111 'id': 'Mrj4DVp2zeA',
1113 'upload_date': '20150212',
1114 'uploader': 'The National Archives UK',
1115 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1116 'uploader_id': 'NationalArchives08',
1117 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1122 'url': 'http://www.suffolk.edu/sjc/live.php',
1126 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1127 'uploader': 'www.suffolk.edu',
1130 'skip_download': True,
1132 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1136 'url': 'http://www.indiedb.com/games/king-machine/videos',
1140 'title': 'king machine trailer 1',
1141 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1142 'thumbnail': r're:^https?://.*\.jpg$',
1146 # JWPlayer config passed as variable
1147 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1151 'title': 'ARIELE | Tube Cup',
1152 'uploader': 'www.txxx.com',
1156 'skip_download': True,
1161 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1162 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1166 'upload_date': '20171122',
1167 'timestamp': 1511366290,
1168 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1170 'add_ie': [JWPlatformIE.ie_key()],
1173 # Video.js embed, multiple formats
1174 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1176 'id': 'yygqldloqIk',
1178 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1179 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1180 'upload_date': '20130314',
1181 'uploader': 'PROстое3D',
1182 'uploader_id': 'PROstoe3D',
1185 'skip_download': True,
1189 # Video.js embed, single format
1190 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1194 'title': 'Step 1 - Good Foundation',
1195 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1198 'skip_download': True,
1203 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1204 'playlist_mincount': 5,
1206 'id': 'aanslagen-kopenhagen',
1207 'title': 'Aanslagen Kopenhagen',
1212 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1216 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1219 # Kaltura embed (different embed code)
1221 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1225 'upload_date': '20150127',
1226 'uploader_id': 'PremierMedia',
1228 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1231 # Kaltura embed with single quotes
1233 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1238 'timestamp': 1355743100,
1239 'upload_date': '20121217',
1240 'uploader_id': 'cplapp@learn360.com',
1242 'add_ie': ['Kaltura'],
1245 # Kaltura embedded via quoted entry_id
1246 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1250 'title': '06_matthew_brender_raj_dutt',
1251 'timestamp': 1466638791,
1252 'upload_date': '20160622',
1254 'add_ie': ['Kaltura'],
1255 'expected_warnings': [
1256 'Could not send HEAD request'
1259 'skip_download': True,
1263 # Kaltura embedded, some fileExt broken (#11480)
1264 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1268 'title': 'Our "Standard Models" of particle physics and cosmology',
1269 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1270 'timestamp': 1321158993,
1271 'upload_date': '20111113',
1272 'uploader_id': 'kps1',
1274 'add_ie': ['Kaltura'],
1277 # Kaltura iframe embed
1278 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1279 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1283 'title': 'I. M. Pei: A Centennial Celebration',
1284 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1285 'upload_date': '20170403',
1286 'uploader_id': 'batchUser',
1287 'timestamp': 1491232186,
1289 'add_ie': ['Kaltura'],
1292 # Kaltura iframe embed, more sophisticated
1293 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1297 'title': 'lecture-05sep2017',
1298 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1299 'upload_date': '20170913',
1300 'uploader_id': 'eps2',
1301 'timestamp': 1505340777,
1304 'skip_download': True,
1306 'add_ie': ['Kaltura'],
1309 # meta twitter:player
1310 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1314 'title': 'Main Twerk (Video)',
1315 'upload_date': '20171208',
1316 'uploader_id': 'sebastian.salinas@thechive.com',
1317 'timestamp': 1512713057,
1320 'skip_download': True,
1322 'add_ie': ['Kaltura'],
1324 # referrer protected EaglePlatform embed
1326 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1330 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1331 'thumbnail': r're:^https?://.*\.jpg$',
1336 'skip_download': True,
1339 # ClipYou (EaglePlatform) embed (custom URL)
1341 'url': 'http://muz-tv.ru/play/7129/',
1342 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1346 'title': "'O Sole Mio",
1347 'thumbnail': r're:^https?://.*\.jpg$',
1352 'skip_download': True,
1354 'skip': 'This video is unavailable.',
1358 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1362 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1363 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1364 'thumbnail': r're:^https?://.*\.jpg$',
1368 'skip': 'HTTP Error 404: Not Found',
1372 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1376 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1377 'thumbnail': r're:^https?://.*\.png$',
1383 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1384 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1388 'title': 'Facebook Creates "On This Day" | Crunch Report',
1389 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1390 'timestamp': 1427237531,
1391 'uploader': 'Crunch Report',
1392 'upload_date': '20150324',
1396 'skip_download': True,
1399 # Crooks and Liars embed
1401 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1405 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1406 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1407 'timestamp': 1428207000,
1408 'upload_date': '20150405',
1409 'uploader': 'Heather',
1412 # Crooks and Liars external embed
1414 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1416 'id': 'MTE3MjUtMzQ2MzA',
1418 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1419 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1420 'timestamp': 1265032391,
1421 'upload_date': '20100201',
1422 'uploader': 'Heather',
1425 # NBC Sports vplayer embed
1427 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1429 'id': 'ln7x1qSThw4k',
1431 'title': "PFT Live: New leader in the 'new-look' defense",
1432 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1433 'uploader': 'NBCU-SPORTS',
1434 'upload_date': '20140107',
1435 'timestamp': 1389118457,
1437 'skip': 'Invalid Page URL',
1441 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1442 'md5': '1aa589c675898ae6d37a17913cf68d66',
1444 'id': 'x_dtl_oa_LettermanliftPR_160608',
1446 'title': 'David Letterman: A Preview',
1447 '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.',
1448 'upload_date': '20160609',
1449 'timestamp': 1465431544,
1450 'uploader': 'NBCU-NEWS',
1455 'url': 'https://video.udn.com/news/300346',
1456 'md5': 'fd2060e988c326991037b9aff9df21a6',
1460 'title': '中一中男師變性 全校師生力挺',
1461 'thumbnail': r're:^https?://.*\.jpg$',
1465 'skip_download': True,
1467 'expected_warnings': ['Failed to parse JSON Expecting value'],
1469 # Brightcove URL in single quotes
1471 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1472 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1474 'id': '4255764656001',
1476 'title': 'SN Presents: Russell Martin, World Citizen',
1477 '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.',
1478 'uploader': 'Rogers Sportsnet',
1479 'uploader_id': '1704050871',
1480 'upload_date': '20150525',
1481 'timestamp': 1432570283,
1484 # OnionStudios embed
1486 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1490 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1491 'thumbnail': r're:^https?://.*\.jpe?g$',
1492 'uploader': 'ClickHole',
1493 'uploader_id': 'clickhole',
1498 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1500 'id': '74849a00-85a9-11e1-9660-123139220831',
1502 'title': '#whilewewatch',
1505 # AdobeTVVideo embed
1507 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1508 'md5': '43662b577c018ad707a63766462b1e87',
1512 'title': 'New experience with Acrobat DC',
1513 'description': 'New experience with Acrobat DC',
1514 'duration': 248.667,
1517 # BrightcoveInPageEmbed embed
1519 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1521 'id': '4238694884001',
1523 'title': 'Tabletop: Dread, Last Thoughts',
1524 'description': 'Tabletop: Dread, Last Thoughts',
1528 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1529 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1531 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1533 'id': '4785848093001',
1535 'title': 'The Cardinal Pell Interview',
1536 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1537 'uploader': 'GlobeCast Australia - GlobeStream',
1538 'uploader_id': '2733773828001',
1539 'upload_date': '20160304',
1540 'timestamp': 1457083087,
1544 'skip_download': True,
1548 # Brightcove embed with whitespace around attribute names
1549 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1551 'id': '3167554373001',
1553 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1554 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1555 'uploader_id': '1079349493',
1556 'upload_date': '20140207',
1557 'timestamp': 1391810548,
1560 'skip_download': True,
1563 # Another form of arte.tv embed
1565 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1566 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1568 'id': '030273-562_PLUS7-F',
1570 'title': 'ARTE Reportage - Nulle part, en France',
1571 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1572 'upload_date': '20160409',
1577 'url': 'http://www.wykop.pl/link/3088787/',
1578 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1580 'id': '874_1459135191',
1582 'title': 'Man shows poor quality of new apartment building',
1583 'description': 'The wall is like a sand pile.',
1584 'uploader': 'Lake8737',
1586 'add_ie': [LiveLeakIE.ie_key()],
1588 # Another LiveLeak embed pattern (#13336)
1590 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1592 'id': '2eb_1496309988',
1594 'title': 'Thief robs place where everyone was armed',
1595 'description': 'md5:694d73ee79e535953cf2488562288eee',
1596 'uploader': 'brazilwtf',
1598 'add_ie': [LiveLeakIE.ie_key()],
1600 # Duplicated embedded video URLs
1602 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1604 'id': '149298443_480_16c25b74_2',
1606 'title': 'vs. Blue Orange Spring Game',
1607 'uploader': 'www.hudl.com',
1610 # twitter:player:stream embed
1612 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1616 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1617 'uploader': 'www.rtl.be',
1621 'skip_download': True,
1624 # twitter:player embed
1626 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1627 'md5': 'a3e0df96369831de324f0778e126653c',
1629 'id': '4909620399001',
1631 'title': 'What Do Black Holes Sound Like?',
1632 'description': 'what do black holes sound like',
1633 'upload_date': '20160524',
1634 'uploader_id': '29913724001',
1635 'timestamp': 1464107587,
1636 'uploader': 'TheAtlantic',
1638 'add_ie': ['BrightcoveLegacy'],
1640 # Facebook <iframe> embed
1642 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1643 'md5': 'fbcde74f534176ecb015849146dd3aee',
1645 'id': '599637780109885',
1647 'title': 'Facebook video #599637780109885',
1650 # Facebook <iframe> embed, plugin video
1652 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1654 'id': '1754168231264132',
1656 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1657 'uploader': 'Tariq Ramadan (official)',
1658 'timestamp': 1496758379,
1659 'upload_date': '20170606',
1662 'skip_download': True,
1665 # Facebook API embed
1667 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1668 'md5': 'a47372ee61b39a7b90287094d447d94e',
1670 'id': '10153467542406923',
1672 'title': 'Facebook video #10153467542406923',
1675 # Wordpress "YouTube Video Importer" plugin
1677 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1678 'md5': 'd16797741b560b485194eddda8121b48',
1680 'id': 'HNTXWDXV9Is',
1682 'title': 'Blue Devils Drumline Stanford lot 2016',
1683 'upload_date': '20160627',
1684 'uploader_id': 'GENOCIDE8GENERAL10',
1685 'uploader': 'cylus cyrus',
1689 # video stored on custom kaltura server
1690 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1691 'md5': '537617d06e64dfed891fa1593c4b30cc',
1695 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1696 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1697 'uploader_id': 'videos.expansion@el-mundo.net',
1698 'upload_date': '20150429',
1699 'timestamp': 1430303472,
1701 'add_ie': ['Kaltura'],
1704 # Non-standard Vimeo embed
1705 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1706 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1710 'title': 'Understanding the web - Teaser',
1711 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1712 'upload_date': '20151214',
1713 'uploader': 'OpenClassrooms',
1714 'uploader_id': 'openclassrooms',
1716 'add_ie': ['Vimeo'],
1719 # generic vimeo embed that requires original URL passed as Referer
1720 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1721 'only_matching': True,
1724 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1725 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1727 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1729 'title': 'Big Buck Bunny',
1730 'description': 'Royalty free test video',
1731 'timestamp': 1432816365,
1732 'upload_date': '20150528',
1736 'skip_download': True,
1738 'add_ie': [ArkenaIE.ie_key()],
1741 '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/',
1745 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1748 'skip_download': True,
1750 'add_ie': [Vbox7IE.ie_key()],
1754 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1757 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1759 'playlist_mincount': 3,
1763 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1765 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1766 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1768 'playlist_mincount': 2,
1772 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1776 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1777 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1780 'skip_download': True,
1782 'add_ie': [TwentyMinutenIE.ie_key()],
1786 'url': 'https://en.support.wordpress.com/videopress/',
1790 'title': 'IMG_5786',
1791 'timestamp': 1435711927,
1792 'upload_date': '20150701',
1795 'skip_download': True,
1797 'add_ie': [VideoPressIE.ie_key()],
1801 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1803 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1805 'title': 'Магаззино: Казань 2',
1806 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1807 'uploader': 'Магаззино',
1808 'upload_date': '20170228',
1809 'uploader_id': '996642',
1812 'skip_download': True,
1814 'add_ie': [RutubeIE.ie_key()],
1817 # ThePlatform embedded with whitespaces in URLs
1818 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1819 'only_matching': True,
1822 # Senate ISVP iframe https
1823 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1824 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1826 'id': 'govtaff020316',
1828 'title': 'Integrated Senate Video Player',
1830 'add_ie': [SenateISVPIE.ie_key()],
1833 # Limelight embeds (1 channel embed + 4 media embeds)
1834 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1836 'id': 'FacilitatorTraining2017',
1837 'title': 'Facilitator Training 2017',
1839 'playlist_mincount': 5,
1842 # Limelight embed (LimelightPlayerUtil.embed)
1843 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1845 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1847 'title': '07448641',
1848 'timestamp': 1499890639,
1849 'upload_date': '20170712',
1852 'skip_download': True,
1854 'add_ie': ['LimelightMedia'],
1857 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1859 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1860 'title': 'Standoff with Walnut Creek murder suspect ends',
1861 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1863 'playlist_mincount': 4,
1866 # WashingtonPost embed
1867 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1869 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1871 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1872 '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.',
1873 'timestamp': 1455216756,
1874 'uploader': 'The Washington Post',
1875 'upload_date': '20160211',
1877 'add_ie': [WashingtonPostIE.ie_key()],
1881 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1885 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1888 'skip_download': True,
1890 'add_ie': [MediasetIE.ie_key()],
1894 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1896 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1897 'title': 'Slovenskom sa prehnala vlna silných búrok',
1899 'playlist_mincount': 5,
1900 'add_ie': [JojIE.ie_key()],
1903 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1904 'url': 'https://tvrain.ru/amp/418921/',
1905 'md5': 'cc00413936695987e8de148b67d14f1d',
1909 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1914 'url': 'http://help.vzaar.com/article/165-embedding-video',
1915 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1919 'title': 'Building A Business Online: Principal Chairs Q & A',
1923 # multiple HTML5 videos on one page
1924 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1926 'id': 'keyscenarios',
1927 'title': 'Rescue Kit 14 Free Edition - Getting started',
1929 'playlist_count': 4,
1933 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1934 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1937 'title': 'vl14062007715967',
1942 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1943 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1945 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1947 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1948 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1949 'timestamp': 1474354800,
1950 'upload_date': '20160920',
1954 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1958 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1959 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1960 'timestamp': 1516100691,
1961 'upload_date': '20180116',
1964 'skip_download': True,
1966 'add_ie': [SpringboardPlatformIE.ie_key()],
1969 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1971 'id': 'uPDB5I9wfp8',
1973 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1974 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1975 'upload_date': '20160219',
1976 'uploader': 'Pocoyo - Português (BR)',
1977 'uploader_id': 'PocoyoBrazil',
1979 'add_ie': [YoutubeIE.ie_key()],
1981 'skip_download': True,
1985 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1987 'id': 'vMDE4NzI1Mjgt690b',
1991 'add_ie': [YapFilesIE.ie_key()],
1993 'skip_download': True,
1997 # CloudflareStream embed
1998 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2000 'id': '31c9291ab41fac05471db4e73aa11717',
2002 'title': '31c9291ab41fac05471db4e73aa11717',
2004 'add_ie': [CloudflareStreamIE.ie_key()],
2006 'skip_download': True,
2011 'url': 'https://joinpeertube.org/fr/home/',
2014 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2016 'playlist_count': 2,
2020 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2024 'title': 'Így kell otthon hamburgert sütni',
2025 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2026 'timestamp': 1426330212,
2027 'upload_date': '20150314',
2028 'uploader': 'StreetKitchen',
2029 'uploader_id': '546363',
2031 'add_ie': [IndavideoEmbedIE.ie_key()],
2033 'skip_download': True,
2037 # APA embed via JWPlatform embed
2038 'url': 'http://www.vol.at/blue-man-group/5593454',
2042 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2043 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2044 'thumbnail': r're:^https?://.*\.jpg$',
2046 'timestamp': 1519211149,
2047 'upload_date': '20180221',
2050 'skip_download': True,
2054 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2055 'md5': 'b68d276de422ab07ee1d49388103f457',
2058 'title': 'Lock up and get excited',
2061 'skip': 'TODO: fix nested playlists processing in tests',
2064 # # TODO: find another test
2065 # # http://schema.org/VideoObject
2066 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2067 # 'md5': '888dcf08b7ea671381f00fab74692755',
2069 # 'id': 'nyvTSJMKId',
2071 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2072 # 'description': '#love for cats.',
2073 # 'timestamp': 1461244995,
2074 # 'upload_date': '20160421',
2077 # 'force_generic_extractor': True,
2082 def report_following_redirect(self, new_url):
2083 """Report information extraction."""
2084 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2086 def _extract_rss(self, url, video_id, doc):
2087 playlist_title = doc.find('./channel/title').text
2088 playlist_desc_el = doc.find('./channel/description')
2089 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2092 for it in doc.findall('./channel/item'):
2094 enclosure_nodes = it.findall('./enclosure')
2095 for e in enclosure_nodes:
2096 next_url = e.attrib.get('url')
2101 next_url = xpath_text(it, 'link', fatal=False)
2107 '_type': 'url_transparent',
2109 'title': it.find('title').text,
2113 '_type': 'playlist',
2115 'title': playlist_title,
2116 'description': playlist_desc,
2120 def _extract_camtasia(self, url, video_id, webpage):
2121 """ Returns None if no camtasia video can be found. """
2123 camtasia_cfg = self._search_regex(
2124 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2125 webpage, 'camtasia configuration file', default=None)
2126 if camtasia_cfg is None:
2129 title = self._html_search_meta('DC.title', webpage, fatal=True)
2131 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2132 camtasia_cfg = self._download_xml(
2133 camtasia_url, video_id,
2134 note='Downloading camtasia configuration',
2135 errnote='Failed to download camtasia configuration')
2136 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2139 for n in fileset_node.getchildren():
2140 url_n = n.find('./uri')
2145 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2146 'title': '%s - %s' % (title, n.tag),
2147 'url': compat_urlparse.urljoin(url, url_n.text),
2148 'duration': float_or_none(n.find('./duration').text),
2152 '_type': 'playlist',
2157 def _real_extract(self, url):
2158 if url.startswith('//'):
2161 'url': self.http_scheme() + url,
2164 parsed_url = compat_urlparse.urlparse(url)
2165 if not parsed_url.scheme:
2166 default_search = self._downloader.params.get('default_search')
2167 if default_search is None:
2168 default_search = 'fixup_error'
2170 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2172 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2173 return self.url_result('http://' + url)
2174 elif default_search != 'fixup_error':
2175 if default_search == 'auto_warning':
2176 if re.match(r'^(?:url|URL)$', url):
2177 raise ExtractorError(
2178 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2181 self._downloader.report_warning(
2182 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2183 return self.url_result('ytsearch:' + url)
2185 if default_search in ('error', 'fixup_error'):
2186 raise ExtractorError(
2187 '%r is not a valid URL. '
2188 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2189 % (url, url), expected=True)
2191 if ':' not in default_search:
2192 default_search += ':'
2193 return self.url_result(default_search + url)
2195 url, smuggled_data = unsmuggle_url(url)
2196 force_videoid = None
2197 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2198 if smuggled_data and 'force_videoid' in smuggled_data:
2199 force_videoid = smuggled_data['force_videoid']
2200 video_id = force_videoid
2202 video_id = self._generic_id(url)
2204 self.to_screen('%s: Requesting header' % video_id)
2206 head_req = HEADRequest(url)
2207 head_response = self._request_webpage(
2209 note=False, errnote='Could not send HEAD request to %s' % url,
2212 if head_response is not False:
2213 # Check for redirect
2214 new_url = compat_str(head_response.geturl())
2216 self.report_following_redirect(new_url)
2218 new_url = smuggle_url(
2219 new_url, {'force_videoid': force_videoid})
2220 return self.url_result(new_url)
2222 full_response = None
2223 if head_response is False:
2224 request = sanitized_Request(url)
2225 request.add_header('Accept-Encoding', '*')
2226 full_response = self._request_webpage(request, video_id)
2227 head_response = full_response
2231 'title': self._generic_title(url),
2232 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2235 # Check for direct link to a video
2236 content_type = head_response.headers.get('Content-Type', '').lower()
2237 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2239 format_id = compat_str(m.group('format_id'))
2240 if format_id.endswith('mpegurl'):
2241 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2242 elif format_id == 'f4m':
2243 formats = self._extract_f4m_formats(url, video_id)
2246 'format_id': format_id,
2248 'vcodec': 'none' if m.group('type') == 'audio' else None
2250 info_dict['direct'] = True
2251 self._sort_formats(formats)
2252 info_dict['formats'] = formats
2255 if not self._downloader.params.get('test', False) and not is_intentional:
2256 force = self._downloader.params.get('force_generic_extractor', False)
2257 self._downloader.report_warning(
2258 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2260 if not full_response:
2261 request = sanitized_Request(url)
2262 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2263 # making it impossible to download only chunk of the file (yet we need only 512kB to
2264 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2265 # that will always result in downloading the whole file that is not desirable.
2266 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2267 # to accept raw bytes and being able to download only a chunk.
2268 # It may probably better to solve this by checking Content-Type for application/octet-stream
2269 # after HEAD request finishes, but not sure if we can rely on this.
2270 request.add_header('Accept-Encoding', '*')
2271 full_response = self._request_webpage(request, video_id)
2273 first_bytes = full_response.read(512)
2275 # Is it an M3U playlist?
2276 if first_bytes.startswith(b'#EXTM3U'):
2277 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2278 self._sort_formats(info_dict['formats'])
2281 # Maybe it's a direct link to a video?
2282 # Be careful not to download the whole thing!
2283 if not is_html(first_bytes):
2284 self._downloader.report_warning(
2285 'URL could be a direct video link, returning it as such.')
2292 webpage = self._webpage_read_content(
2293 full_response, url, video_id, prefix=first_bytes)
2295 self.report_extraction(video_id)
2297 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2299 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2300 if doc.tag == 'rss':
2301 return self._extract_rss(url, video_id, doc)
2302 elif doc.tag == 'SmoothStreamingMedia':
2303 info_dict['formats'] = self._parse_ism_formats(doc, url)
2304 self._sort_formats(info_dict['formats'])
2306 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2307 smil = self._parse_smil(doc, url, video_id)
2308 self._sort_formats(smil['formats'])
2310 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2311 return self.playlist_result(
2313 doc, video_id, xspf_url=url,
2314 xspf_base_url=compat_str(full_response.geturl())),
2316 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2317 info_dict['formats'] = self._parse_mpd_formats(
2319 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2321 self._sort_formats(info_dict['formats'])
2323 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2324 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2325 self._sort_formats(info_dict['formats'])
2327 except compat_xml_parse_error:
2330 # Is it a Camtasia project?
2331 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2332 if camtasia_res is not None:
2335 # Sometimes embedded video player is hidden behind percent encoding
2336 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2337 # Unescaping the whole page allows to handle those cases in a generic way
2338 webpage = compat_urllib_parse_unquote(webpage)
2340 # it's tempting to parse this further, but you would
2341 # have to take into account all the variations like
2342 # Video Title - Site Name
2343 # Site Name | Video Title
2344 # Video Title - Tagline | Site Name
2345 # and so on and so forth; it's just not practical
2346 video_title = self._og_search_title(
2347 webpage, default=None) or self._html_search_regex(
2348 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2351 # Try to detect age limit automatically
2352 age_limit = self._rta_search(webpage)
2353 # And then there are the jokers who advertise that they use RTA,
2354 # but actually don't.
2355 AGE_LIMIT_MARKERS = [
2356 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2358 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2361 # video uploader is domain name
2362 video_uploader = self._search_regex(
2363 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2365 video_description = self._og_search_description(webpage, default=None)
2366 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2369 'title': video_title,
2370 'description': video_description,
2371 'thumbnail': video_thumbnail,
2372 'age_limit': age_limit,
2375 # Look for Brightcove Legacy Studio embeds
2376 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2380 'url': smuggle_url(bc_url, {'Referer': url}),
2381 'ie_key': 'BrightcoveLegacy'
2382 } for bc_url in bc_urls]
2385 '_type': 'playlist',
2386 'title': video_title,
2391 # Look for Brightcove New Studio embeds
2392 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2394 return self.playlist_from_matches(
2395 bc_urls, video_id, video_title,
2396 getter=lambda x: smuggle_url(x, {'referrer': url}),
2399 # Look for Nexx embeds
2400 nexx_urls = NexxIE._extract_urls(webpage)
2402 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2404 # Look for Nexx iFrame embeds
2405 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2407 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2409 # Look for ThePlatform embeds
2410 tp_urls = ThePlatformIE._extract_urls(webpage)
2412 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2414 # Look for Vessel embeds
2415 vessel_urls = VesselIE._extract_urls(webpage)
2417 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2419 # Look for embedded rtl.nl player
2420 matches = re.findall(
2421 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2424 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2426 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2428 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2430 vid_me_embed_url = self._search_regex(
2431 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2432 webpage, 'vid.me embed', default=None)
2433 if vid_me_embed_url is not None:
2434 return self.url_result(vid_me_embed_url, 'Vidme')
2436 # Look for YouTube embeds
2437 youtube_urls = YoutubeIE._extract_urls(webpage)
2439 return self.playlist_from_matches(
2440 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2442 matches = DailymotionIE._extract_urls(webpage)
2444 return self.playlist_from_matches(matches, video_id, video_title)
2446 # Look for embedded Dailymotion playlist player (#3822)
2448 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2450 playlists = re.findall(
2451 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2453 return self.playlist_from_matches(
2454 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2456 # Look for DailyMail embeds
2457 dailymail_urls = DailyMailIE._extract_urls(webpage)
2459 return self.playlist_from_matches(
2460 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2462 # Look for embedded Wistia player
2463 wistia_url = WistiaIE._extract_url(webpage)
2466 '_type': 'url_transparent',
2467 'url': self._proto_relative_url(wistia_url),
2468 'ie_key': WistiaIE.ie_key(),
2469 'uploader': video_uploader,
2472 # Look for SVT player
2473 svt_url = SVTIE._extract_url(webpage)
2475 return self.url_result(svt_url, 'SVT')
2477 # Look for Bandcamp pages with custom domain
2478 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2479 if mobj is not None:
2480 burl = unescapeHTML(mobj.group(1))
2481 # Don't set the extractor because it can be a track url or an album
2482 return self.url_result(burl)
2484 # Look for embedded Vevo player
2486 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2487 if mobj is not None:
2488 return self.url_result(mobj.group('url'))
2490 # Look for embedded Viddler player
2492 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2494 if mobj is not None:
2495 return self.url_result(mobj.group('url'))
2497 # Look for NYTimes player
2499 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2501 if mobj is not None:
2502 return self.url_result(mobj.group('url'))
2504 # Look for Libsyn player
2506 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2507 if mobj is not None:
2508 return self.url_result(mobj.group('url'))
2510 # Look for Ooyala videos
2511 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2512 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2513 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2514 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2515 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2516 if mobj is not None:
2517 embed_token = self._search_regex(
2518 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2519 webpage, 'ooyala embed token', default=None)
2520 return OoyalaIE._build_url_result(smuggle_url(
2523 'embed_token': embed_token,
2526 # Look for multiple Ooyala embeds on SBN network websites
2527 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2528 if mobj is not None:
2529 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2531 return self.playlist_from_matches(
2532 embeds, video_id, video_title,
2533 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2535 # Look for Aparat videos
2536 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2537 if mobj is not None:
2538 return self.url_result(mobj.group(1), 'Aparat')
2540 # Look for MPORA videos
2541 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2542 if mobj is not None:
2543 return self.url_result(mobj.group(1), 'Mpora')
2545 # Look for embedded NovaMov-based player
2547 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2548 (?P<url>http://(?:(?:embed|www)\.)?
2550 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2551 videoweed\.(?:es|com)|
2552 movshare\.(?:net|sx|ag)|
2553 divxstage\.(?:eu|net|ch|co|at|ag))
2554 /embed\.php.+?)\1''', webpage)
2555 if mobj is not None:
2556 return self.url_result(mobj.group('url'))
2558 # Look for embedded Facebook player
2559 facebook_urls = FacebookIE._extract_urls(webpage)
2561 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2563 # Look for embedded VK player
2564 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2565 if mobj is not None:
2566 return self.url_result(mobj.group('url'), 'VK')
2568 # Look for embedded Odnoklassniki player
2569 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2570 if mobj is not None:
2571 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2573 # Look for embedded ivi player
2574 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2575 if mobj is not None:
2576 return self.url_result(mobj.group('url'), 'Ivi')
2578 # Look for embedded Huffington Post player
2580 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2581 if mobj is not None:
2582 return self.url_result(mobj.group('url'), 'HuffPost')
2585 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2586 if mobj is not None:
2587 return self.url_result(mobj.group('url'))
2588 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2589 if mobj is not None:
2590 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2592 # Look for funnyordie embed
2593 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2595 return self.playlist_from_matches(
2596 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2598 # Look for BBC iPlayer embed
2599 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2601 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2603 # Look for embedded RUTV player
2604 rutv_url = RUTVIE._extract_url(webpage)
2606 return self.url_result(rutv_url, 'RUTV')
2608 # Look for embedded TVC player
2609 tvc_url = TVCIE._extract_url(webpage)
2611 return self.url_result(tvc_url, 'TVC')
2613 # Look for embedded SportBox player
2614 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2616 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2618 # Look for embedded XHamster player
2619 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2621 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2623 # Look for embedded TNAFlixNetwork player
2624 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2626 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2628 # Look for embedded PornHub player
2629 pornhub_urls = PornHubIE._extract_urls(webpage)
2631 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2633 # Look for embedded DrTuber player
2634 drtuber_urls = DrTuberIE._extract_urls(webpage)
2636 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2638 # Look for embedded RedTube player
2639 redtube_urls = RedTubeIE._extract_urls(webpage)
2641 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2643 # Look for embedded Tube8 player
2644 tube8_urls = Tube8IE._extract_urls(webpage)
2646 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2648 # Look for embedded Tvigle player
2650 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2651 if mobj is not None:
2652 return self.url_result(mobj.group('url'), 'Tvigle')
2654 # Look for embedded TED player
2656 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2657 if mobj is not None:
2658 return self.url_result(mobj.group('url'), 'TED')
2660 # Look for embedded Ustream videos
2661 ustream_url = UstreamIE._extract_url(webpage)
2663 return self.url_result(ustream_url, UstreamIE.ie_key())
2665 # Look for embedded arte.tv player
2667 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2669 if mobj is not None:
2670 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2672 # Look for embedded francetv player
2674 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2676 if mobj is not None:
2677 return self.url_result(mobj.group('url'))
2679 # Look for embedded smotri.com player
2680 smotri_url = SmotriIE._extract_url(webpage)
2682 return self.url_result(smotri_url, 'Smotri')
2684 # Look for embedded Myvi.ru player
2685 myvi_url = MyviIE._extract_url(webpage)
2687 return self.url_result(myvi_url)
2689 # Look for embedded soundcloud player
2690 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2692 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2694 # Look for tunein player
2695 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2697 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2699 # Look for embedded mtvservices player
2700 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2702 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2704 # Look for embedded yahoo player
2706 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2708 if mobj is not None:
2709 return self.url_result(mobj.group('url'), 'Yahoo')
2711 # Look for embedded sbs.com.au player
2715 <meta\s+property="og:video"\s+content=|
2718 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2720 if mobj is not None:
2721 return self.url_result(mobj.group('url'), 'SBS')
2723 # Look for embedded Cinchcast player
2725 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2727 if mobj is not None:
2728 return self.url_result(mobj.group('url'), 'Cinchcast')
2731 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2735 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2737 if mobj is not None:
2738 return self.url_result(mobj.group('url'), 'MLB')
2741 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2743 if mobj is not None:
2744 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2747 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2749 if mobj is not None:
2750 return self.url_result(mobj.group('url'), 'Livestream')
2752 # Look for Zapiks embed
2754 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2755 if mobj is not None:
2756 return self.url_result(mobj.group('url'), 'Zapiks')
2758 # Look for Kaltura embeds
2759 kaltura_url = KalturaIE._extract_url(webpage)
2761 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2763 # Look for EaglePlatform embeds
2764 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2765 if eagleplatform_url:
2766 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2768 # Look for ClipYou (uses EaglePlatform) embeds
2770 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2771 if mobj is not None:
2772 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2774 # Look for Pladform embeds
2775 pladform_url = PladformIE._extract_url(webpage)
2777 return self.url_result(pladform_url)
2779 # Look for Videomore embeds
2780 videomore_url = VideomoreIE._extract_url(webpage)
2782 return self.url_result(videomore_url)
2784 # Look for Webcaster embeds
2785 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2787 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2789 # Look for Playwire embeds
2791 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2792 if mobj is not None:
2793 return self.url_result(mobj.group('url'))
2795 # Look for 5min embeds
2797 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2798 if mobj is not None:
2799 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2801 # Look for Crooks and Liars embeds
2803 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2804 if mobj is not None:
2805 return self.url_result(mobj.group('url'))
2807 # Look for NBC Sports VPlayer embeds
2808 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2810 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2812 # Look for NBC News embeds
2813 nbc_news_embed_url = re.search(
2814 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2815 if nbc_news_embed_url:
2816 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2818 # Look for Google Drive embeds
2819 google_drive_url = GoogleDriveIE._extract_url(webpage)
2820 if google_drive_url:
2821 return self.url_result(google_drive_url, 'GoogleDrive')
2823 # Look for UDN embeds
2825 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2826 if mobj is not None:
2827 return self.url_result(
2828 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2830 # Look for Senate ISVP iframe
2831 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2833 return self.url_result(senate_isvp_url, 'SenateISVP')
2835 # Look for OnionStudios embeds
2836 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2837 if onionstudios_url:
2838 return self.url_result(onionstudios_url)
2840 # Look for ViewLift embeds
2841 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2843 return self.url_result(viewlift_url)
2845 # Look for JWPlatform embeds
2846 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2848 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2850 # Look for Digiteka embeds
2851 digiteka_url = DigitekaIE._extract_url(webpage)
2853 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2855 # Look for Arkena embeds
2856 arkena_url = ArkenaIE._extract_url(webpage)
2858 return self.url_result(arkena_url, ArkenaIE.ie_key())
2860 # Look for Piksel embeds
2861 piksel_url = PikselIE._extract_url(webpage)
2863 return self.url_result(piksel_url, PikselIE.ie_key())
2865 # Look for Limelight embeds
2866 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2868 return self.playlist_result(
2869 limelight_urls, video_id, video_title, video_description)
2871 # Look for Anvato embeds
2872 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2874 return self.playlist_result(
2875 anvato_urls, video_id, video_title, video_description)
2877 # Look for AdobeTVVideo embeds
2879 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2881 if mobj is not None:
2882 return self.url_result(
2883 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2886 # Look for Vine embeds
2888 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2890 if mobj is not None:
2891 return self.url_result(
2892 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2894 # Look for VODPlatform embeds
2896 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2898 if mobj is not None:
2899 return self.url_result(
2900 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2902 # Look for Mangomolo embeds
2904 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2906 video\?.*?\bid=(?P<video_id>\d+)|
2907 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2908 ).+?)\1''', webpage)
2909 if mobj is not None:
2911 '_type': 'url_transparent',
2912 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2913 'title': video_title,
2914 'description': video_description,
2915 'thumbnail': video_thumbnail,
2916 'uploader': video_uploader,
2918 video_id = mobj.group('video_id')
2921 'ie_key': 'MangomoloVideo',
2926 'ie_key': 'MangomoloLive',
2927 'id': mobj.group('channel_id'),
2931 # Look for Instagram embeds
2932 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2933 if instagram_embed_url is not None:
2934 return self.url_result(
2935 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2937 # Look for LiveLeak embeds
2938 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2940 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2942 # Look for 3Q SDN embeds
2943 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2946 '_type': 'url_transparent',
2947 'ie_key': ThreeQSDNIE.ie_key(),
2948 'url': self._proto_relative_url(threeqsdn_url),
2949 'title': video_title,
2950 'description': video_description,
2951 'thumbnail': video_thumbnail,
2952 'uploader': video_uploader,
2955 # Look for VBOX7 embeds
2956 vbox7_url = Vbox7IE._extract_url(webpage)
2958 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2960 # Look for DBTV embeds
2961 dbtv_urls = DBTVIE._extract_urls(webpage)
2963 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2965 # Look for Videa embeds
2966 videa_urls = VideaIE._extract_urls(webpage)
2968 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2970 # Look for 20 minuten embeds
2971 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2973 return self.playlist_from_matches(
2974 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2976 # Look for Openload embeds
2977 openload_urls = OpenloadIE._extract_urls(webpage)
2979 return self.playlist_from_matches(
2980 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2982 # Look for VideoPress embeds
2983 videopress_urls = VideoPressIE._extract_urls(webpage)
2985 return self.playlist_from_matches(
2986 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2988 # Look for Rutube embeds
2989 rutube_urls = RutubeIE._extract_urls(webpage)
2991 return self.playlist_from_matches(
2992 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2994 # Look for WashingtonPost embeds
2995 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2997 return self.playlist_from_matches(
2998 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3000 # Look for Mediaset embeds
3001 mediaset_urls = MediasetIE._extract_urls(webpage)
3003 return self.playlist_from_matches(
3004 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3006 # Look for JOJ.sk embeds
3007 joj_urls = JojIE._extract_urls(webpage)
3009 return self.playlist_from_matches(
3010 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3012 # Look for megaphone.fm embeds
3013 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3015 return self.playlist_from_matches(
3016 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3018 # Look for vzaar embeds
3019 vzaar_urls = VzaarIE._extract_urls(webpage)
3021 return self.playlist_from_matches(
3022 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3024 channel9_urls = Channel9IE._extract_urls(webpage)
3026 return self.playlist_from_matches(
3027 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3029 vshare_urls = VShareIE._extract_urls(webpage)
3031 return self.playlist_from_matches(
3032 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3034 # Look for Mediasite embeds
3035 mediasite_urls = MediasiteIE._extract_urls(webpage)
3038 self.url_result(smuggle_url(
3039 compat_urlparse.urljoin(url, mediasite_url),
3040 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3041 for mediasite_url in mediasite_urls]
3042 return self.playlist_result(entries, video_id, video_title)
3044 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3045 if springboardplatform_urls:
3046 return self.playlist_from_matches(
3047 springboardplatform_urls, video_id, video_title,
3048 ie=SpringboardPlatformIE.ie_key())
3050 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3052 return self.playlist_from_matches(
3053 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3055 vice_urls = ViceIE._extract_urls(webpage)
3057 return self.playlist_from_matches(
3058 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3060 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3062 return self.playlist_from_matches(
3063 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3065 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3066 if cloudflarestream_urls:
3067 return self.playlist_from_matches(
3068 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3070 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3072 return self.playlist_from_matches(
3073 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3075 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3077 return self.playlist_from_matches(
3078 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3080 apa_urls = APAIE._extract_urls(webpage)
3082 return self.playlist_from_matches(
3083 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3085 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3087 return self.playlist_from_matches(
3088 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3090 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
3091 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3093 if sharevideos_urls:
3094 return self.playlist_from_matches(
3095 sharevideos_urls, video_id, video_title)
3097 # Look for HTML5 media
3098 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3100 if len(entries) == 1:
3103 'title': video_title,
3106 for num, entry in enumerate(entries, start=1):
3108 'id': '%s-%s' % (video_id, num),
3109 'title': '%s (%d)' % (video_title, num),
3111 for entry in entries:
3112 self._sort_formats(entry['formats'])
3113 return self.playlist_result(entries, video_id, video_title)
3115 jwplayer_data = self._find_jwplayer_data(
3116 webpage, video_id, transform_source=js_to_json)
3118 info = self._parse_jwplayer_data(
3119 jwplayer_data, video_id, require_title=False, base_url=url)
3120 return merge_dicts(info, info_dict)
3124 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3126 if mobj is not None:
3127 sources = self._parse_json(
3128 mobj.group(1), video_id, transform_source=js_to_json,
3130 if not isinstance(sources, list):
3133 for source in sources:
3134 src = url_or_none(source.get('src'))
3137 src = compat_urlparse.urljoin(url, src)
3138 src_type = source.get('type')
3139 if isinstance(src_type, compat_str):
3140 src_type = src_type.lower()
3141 ext = determine_ext(src).lower()
3142 if src_type == 'video/youtube':
3143 return self.url_result(src, YoutubeIE.ie_key())
3144 if src_type == 'application/dash+xml' or ext == 'mpd':
3145 formats.extend(self._extract_mpd_formats(
3146 src, video_id, mpd_id='dash', fatal=False))
3147 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3148 formats.extend(self._extract_m3u8_formats(
3149 src, video_id, 'mp4', entry_protocol='m3u8_native',
3150 m3u8_id='hls', fatal=False))
3154 'ext': (mimetype2ext(src_type) or
3155 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3158 self._sort_formats(formats)
3159 info_dict['formats'] = formats
3162 # Looking for http://schema.org/VideoObject
3163 json_ld = self._search_json_ld(
3164 webpage, video_id, default={}, expected_type='VideoObject')
3165 if json_ld.get('url'):
3166 return merge_dicts(json_ld, info_dict)
3168 def check_video(vurl):
3169 if YoutubeIE.suitable(vurl):
3171 if RtmpIE.suitable(vurl):
3173 vpath = compat_urlparse.urlparse(vurl).path
3174 vext = determine_ext(vpath)
3175 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3177 def filter_video(urls):
3178 return list(filter(check_video, urls))
3180 # Start with something easy: JW Player in SWFObject
3181 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3183 # Look for gorilla-vid style embedding
3184 found = filter_video(re.findall(r'''(?sx)
3188 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3191 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3193 # Broaden the search a little bit
3194 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3196 # Broaden the findall a little bit: JWPlayer JS loader
3197 found = filter_video(re.findall(
3198 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3201 found = filter_video(re.findall(r'''(?xs)
3202 flowplayer\("[^"]+",\s*
3204 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3205 ["']?url["']?\s*:\s*["']([^"']+)["']
3210 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3212 # Try to find twitter cards info
3213 # twitter:player:stream should be checked before twitter:player since
3214 # it is expected to contain a raw stream (see
3215 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3216 found = filter_video(re.findall(
3217 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3219 # We look for Open Graph info:
3220 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3221 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3222 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3223 if m_video_type is not None:
3224 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3226 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3228 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3229 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3232 # Look also in Refresh HTTP header
3233 refresh_header = head_response.headers.get('Refresh')
3235 # In python 2 response HTTP headers are bytestrings
3236 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3237 refresh_header = refresh_header.decode('iso-8859-1')
3238 found = re.search(REDIRECT_REGEX, refresh_header)
3240 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3242 self.report_following_redirect(new_url)
3251 # twitter:player is a https URL to iframe player that may or may not
3252 # be supported by youtube-dl thus this is checked the very last (see
3253 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3254 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3255 if embed_url and embed_url != url:
3256 return self.url_result(embed_url)
3259 raise UnsupportedError(url)
3262 for video_url in orderedSet(found):
3263 video_url = unescapeHTML(video_url)
3264 video_url = video_url.replace('\\/', '/')
3265 video_url = compat_urlparse.urljoin(url, video_url)
3266 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3268 # Sometimes, jwplayer extraction will result in a YouTube URL
3269 if YoutubeIE.suitable(video_url):
3270 entries.append(self.url_result(video_url, 'Youtube'))
3273 # here's a fun little line of code for you:
3274 video_id = os.path.splitext(video_id)[0]
3278 'uploader': video_uploader,
3279 'title': video_title,
3280 'age_limit': age_limit,
3283 if RtmpIE.suitable(video_url):
3284 entry_info_dict.update({
3285 '_type': 'url_transparent',
3286 'ie_key': RtmpIE.ie_key(),
3289 entries.append(entry_info_dict)
3292 ext = determine_ext(video_url)
3294 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3296 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3298 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3300 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3302 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3303 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3304 # Just matching .ism/manifest is not enough to be reliably sure
3305 # whether it's actually an ISM manifest or some other streaming
3306 # manifest since there are various streaming URL formats
3307 # possible (see [1]) as well as some other shenanigans like
3308 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3310 # Thus the most reasonable way to solve this is to delegate
3311 # to generic extractor in order to look into the contents of
3312 # the manifest itself.
3313 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3314 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3315 entry_info_dict = self.url_result(
3316 smuggle_url(video_url, {'to_generic': True}),
3319 entry_info_dict['url'] = video_url
3321 if entry_info_dict.get('formats'):
3322 self._sort_formats(entry_info_dict['formats'])
3324 entries.append(entry_info_dict)
3326 if len(entries) == 1:
3329 for num, e in enumerate(entries, start=1):
3330 # 'url' results don't have a title
3331 if e.get('title') is not None:
3332 e['title'] = '%s (%d)' % (e['title'], num)
3334 '_type': 'playlist',