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
,
42 from .commonprotocols
import RtmpIE
43 from .brightcove
import (
51 from .nbc
import NBCSportsVPlayerIE
52 from .ooyala
import OoyalaIE
53 from .rutv
import RUTVIE
54 from .tvc
import TVCIE
55 from .sportbox
import SportBoxIE
56 from .myvi
import MyviIE
57 from .condenast
import CondeNastIE
58 from .udn
import UDNEmbedIE
59 from .senateisvp
import SenateISVPIE
60 from .svt
import SVTIE
61 from .pornhub
import PornHubIE
62 from .xhamster
import XHamsterEmbedIE
63 from .tnaflix
import TNAFlixNetworkEmbedIE
64 from .drtuber
import DrTuberIE
65 from .redtube
import RedTubeIE
66 from .tube8
import Tube8IE
67 from .mofosex
import MofosexEmbedIE
68 from .spankwire
import SpankwireIE
69 from .youporn
import YouPornIE
74 from .dailymotion
import DailymotionIE
75 from .dailymail
import DailyMailIE
76 from .onionstudios
import OnionStudiosIE
77 from .viewlift
import ViewLiftEmbedIE
78 from .mtv
import MTVServicesEmbeddedIE
79 from .pladform
import PladformIE
80 from .videomore
import VideomoreIE
81 from .webcaster
import WebcasterFeedIE
82 from .googledrive
import GoogleDriveIE
83 from .jwplatform
import JWPlatformIE
84 from .digiteka
import DigitekaIE
85 from .arkena
import ArkenaIE
86 from .instagram
import InstagramIE
87 from .threeqsdn
import ThreeQSDNIE
88 from .theplatform
import ThePlatformIE
89 from .kaltura
import KalturaIE
90 from .eagleplatform
import EaglePlatformIE
91 from .facebook
import FacebookIE
92 from .soundcloud
import SoundcloudEmbedIE
93 from .tunein
import TuneInBaseIE
94 from .vbox7
import Vbox7IE
95 from .dbtv
import DBTVIE
96 from .piksel
import PikselIE
97 from .videa
import VideaIE
98 from .twentymin
import TwentyMinutenIE
99 from .ustream
import UstreamIE
100 from .arte
import ArteTVEmbedIE
101 from .videopress
import VideoPressIE
102 from .rutube
import RutubeIE
103 from .limelight
import LimelightBaseIE
104 from .anvato
import AnvatoIE
105 from .washingtonpost
import WashingtonPostIE
106 from .wistia
import WistiaIE
107 from .mediaset
import MediasetIE
108 from .joj
import JojIE
109 from .megaphone
import MegaphoneIE
110 from .vzaar
import VzaarIE
111 from .channel9
import Channel9IE
112 from .vshare
import VShareIE
113 from .mediasite
import MediasiteIE
114 from .springboardplatform
import SpringboardPlatformIE
115 from .yapfiles
import YapFilesIE
116 from .vice
import ViceIE
117 from .xfileshare
import XFileShareIE
118 from .cloudflarestream
import CloudflareStreamIE
119 from .peertube
import PeerTubeIE
120 from .teachable
import TeachableIE
121 from .indavideo
import IndavideoEmbedIE
122 from .apa
import APAIE
123 from .foxnews
import FoxNewsIE
124 from .viqeo
import ViqeoIE
125 from .expressen
import ExpressenIE
126 from .zype
import ZypeIE
127 from .odnoklassniki
import OdnoklassnikiIE
129 from .kinja
import KinjaEmbedIE
130 from .gedidigital
import GediDigitalIE
131 from .rcs
import RCSEmbedsIE
132 from .bitchute
import BitChuteIE
133 from .rumble
import RumbleEmbedIE
134 from .arcpublishing
import ArcPublishingIE
135 from .medialaan
import MedialaanIE
136 from .simplecast
import SimplecastIE
137 from .wimtv
import WimTVIE
140 class GenericIE(InfoExtractor
):
141 IE_DESC
= 'Generic downloader that works on some sites'
145 # Direct link to a video
147 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
148 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
153 'upload_date': '20100513',
156 # Direct link to media delivered compressed (until Accept-Encoding is *)
158 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
159 'md5': '128c42e68b13950268b648275386fc74',
161 'id': 'FictionJunction-Parallel_Hearts',
163 'title': 'FictionJunction-Parallel_Hearts',
164 'upload_date': '20140522',
166 'expected_warnings': [
167 'URL could be a direct video link, returning it as such.'
169 'skip': 'URL invalid',
171 # Direct download with broken HEAD
173 'url': 'http://ai-radio.org:8000/radio.opus',
180 'skip_download': True, # infinite live stream
182 'expected_warnings': [
183 r
'501.*Not Implemented',
187 # Direct link with incorrect MIME type
189 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
190 'md5': '4ccbebe5f36706d85221f204d7eb5913',
192 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
193 'id': '5_Lennart_Poettering_-_Systemd',
195 'title': '5_Lennart_Poettering_-_Systemd',
196 'upload_date': '20141120',
198 'expected_warnings': [
199 'URL could be a direct video link, returning it as such.'
204 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
206 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
207 'title': 'Zero Punctuation',
208 'description': 're:.*groundbreaking video review series.*'
210 'playlist_mincount': 11,
212 # RSS feed with enclosure
214 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
216 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
217 'title': 'MSNBC Rachel Maddow (video)',
218 'description': 're:.*her unique approach to storytelling.*',
223 'id': 'pdv_maddow_netcast_mov-12-03-2020-223726',
224 'title': 'MSNBC Rachel Maddow (video) - 12-03-2020-223726',
225 'description': 're:.*her unique approach to storytelling.*',
226 'upload_date': '20201204',
230 # RSS feed with item with description and thumbnails
232 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
234 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
235 'title': 're:.*100% Hydrogen.*',
236 'description': 're:.*In this episode.*',
241 'id': 'c1c879525ce2cb640b344507e682c36d',
242 'title': 're:Hydrogen!',
243 'description': 're:.*In this episode we are going.*',
244 'timestamp': 1567977776,
245 'upload_date': '20190908',
247 'thumbnail': r
're:^https?://.*\.jpg$',
254 'skip_download': True,
257 # RSS feed with enclosures and unsupported link URLs
259 'url': 'http://www.hellointernet.fm/podcast?format=rss',
261 'id': 'http://www.hellointernet.fm/podcast?format=rss',
262 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
263 'title': 'Hello Internet',
265 'playlist_mincount': 100,
267 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
269 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
273 'title': 'Automatics, robotics and biocybernetics',
274 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
275 'upload_date': '20130627',
276 'formats': 'mincount:16',
277 'subtitles': 'mincount:1',
280 'force_generic_extractor': True,
281 'skip_download': True,
284 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
286 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
291 'formats': 'mincount:1',
294 'skip_download': True,
297 # SMIL from https://www.restudy.dk/video/play/id/1637
299 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
303 'title': 'video_1637',
304 'formats': 'mincount:3',
307 'skip_download': True,
310 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
312 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
314 'id': 'smil-service',
316 'title': 'smil-service',
317 'formats': 'mincount:1',
320 'skip_download': True,
323 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
325 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
329 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
330 'formats': 'mincount:3',
333 'skip_download': True,
336 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
338 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
340 'id': 'mZlp2ctYIUEB',
342 'title': 'Tikibad ontruimd wegens brand',
343 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
344 'thumbnail': r
're:^https?://.*\.jpg$',
348 'skip_download': True,
351 # MPD from http://dash-mse-test.appspot.com/media.html
353 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
354 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
356 'id': 'car-20120827-manifest',
358 'title': 'car-20120827-manifest',
359 'formats': 'mincount:9',
360 'upload_date': '20130904',
363 'format': 'bestvideo',
366 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
368 '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',
373 'formats': 'mincount:8',
377 'skip_download': True,
379 'skip': 'video gone',
381 # m3u8 served with Content-Type: text/plain
383 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
388 'upload_date': '20140720',
389 'formats': 'mincount:11',
393 'skip_download': True,
395 'skip': 'video gone',
399 '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',
403 'upload_date': '20130224',
404 'uploader_id': 'TheVerge',
405 'description': r
're:^Chris Ziegler takes a look at the\.*',
406 'uploader': 'The Verge',
407 'title': 'First Firefox OS phones side-by-side',
410 'skip_download': False,
414 # redirect in Refresh HTTP header
415 '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',
419 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
420 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
421 'upload_date': '20150917',
422 'uploader_id': 'brtvofficial',
423 'uploader': 'Boiler Room',
426 'skip_download': False,
430 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
431 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
433 'id': '13601338388002',
435 'uploader': 'www.hodiho.fr',
436 'title': 'R\u00e9gis plante sa Jeep',
439 # bandcamp page with custom domain
441 'add_ie': ['Bandcamp'],
442 'url': 'http://bronyrock.com/track/the-pony-mash',
446 'title': 'The Pony Mash',
447 'uploader': 'M_Pallante',
449 'skip': 'There is a limit of 200 free downloads / month for the test song',
452 # embedded brightcove video
453 # it also tests brightcove videos that need to set the 'Referer'
454 # in the http requests
455 'add_ie': ['BrightcoveLegacy'],
456 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
458 'id': '2765128793001',
460 'title': 'Le cours de bourse : l’analyse technique',
461 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
462 'uploader': 'BFM BUSINESS',
465 'skip_download': True,
469 # embedded with itemprop embedURL and video id spelled as `idVideo`
470 'add_id': ['BrightcoveLegacy'],
471 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
473 'id': '5255628253001',
475 'title': 'md5:37c519b1128915607601e75a87995fc0',
476 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
477 'uploader': 'BFM BUSINESS',
478 'uploader_id': '876450612001',
479 'timestamp': 1482255315,
480 'upload_date': '20161220',
483 'skip_download': True,
487 # https://github.com/ytdl-org/youtube-dl/issues/2253
488 'url': 'http://bcove.me/i6nfkrc3',
489 'md5': '0ba9446db037002366bab3b3eb30c88c',
491 'id': '3101154703001',
493 'title': 'Still no power',
494 'uploader': 'thestar.com',
495 '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.',
497 'add_ie': ['BrightcoveLegacy'],
498 'skip': 'video gone',
501 'url': 'http://www.championat.com/video/football/v/87/87499.html',
502 'md5': 'fb973ecf6e4a78a67453647444222983',
504 'id': '3414141473001',
506 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
507 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
508 'uploader': 'Championat',
512 # https://github.com/ytdl-org/youtube-dl/issues/3541
513 'add_ie': ['BrightcoveLegacy'],
514 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
516 'id': '3866516442001',
518 'title': 'Leer mij vrouwen kennen: Aflevering 1',
519 'description': 'Leer mij vrouwen kennen: Aflevering 1',
520 'uploader': 'SBS Broadcasting',
522 'skip': 'Restricted to Netherlands',
524 'skip_download': True, # m3u8 download
528 # Brightcove video in <iframe>
529 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
530 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
532 'id': '5360463607001',
534 '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',
535 '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。',
536 'uploader': 'United Nations',
537 'uploader_id': '1362235914001',
538 'timestamp': 1489593889,
539 'upload_date': '20170315',
541 'add_ie': ['BrightcoveLegacy'],
544 # Brightcove with alternative playerID key
545 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
547 'id': 'nmeth.2062_SV1',
548 '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',
552 'id': '2228375078001',
554 'title': 'nmeth.2062-sv1',
555 'description': 'nmeth.2062-sv1',
556 'timestamp': 1363357591,
557 'upload_date': '20130315',
558 'uploader': 'Nature Publishing Group',
559 'uploader_id': '1964492299001',
564 # Brightcove with UUID in videoPlayer
565 'url': 'http://www8.hp.com/cn/zh/home.html',
567 'id': '5255815316001',
569 'title': 'Sprocket Video - China',
570 'description': 'Sprocket Video - China',
571 'uploader': 'HP-Video Gallery',
572 'timestamp': 1482263210,
573 'upload_date': '20161220',
574 'uploader_id': '1107601872001',
577 'skip_download': True, # m3u8 download
579 'skip': 'video rotates...weekly?',
582 # Brightcove:new type [2].
583 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
584 'md5': '2b35148fcf48da41c9fb4591650784f3',
586 'id': '5348741021001',
588 'upload_date': '20170306',
589 'uploader_id': '4191638492001',
590 'timestamp': 1488769918,
591 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
596 # Alternative brightcove <video> attributes
597 '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/',
599 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
600 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
603 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
605 'id': '5311302538001',
607 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
608 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
609 'timestamp': 1486321708,
610 'upload_date': '20170205',
611 'uploader_id': '800000640001',
613 'only_matching': True,
617 # Brightcove with UUID in videoPlayer
618 'url': 'http://www8.hp.com/cn/zh/home.html',
620 'id': '5255815316001',
622 'title': 'Sprocket Video - China',
623 'description': 'Sprocket Video - China',
624 'uploader': 'HP-Video Gallery',
625 'timestamp': 1482263210,
626 'upload_date': '20161220',
627 'uploader_id': '1107601872001',
630 'skip_download': True, # m3u8 download
635 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
636 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
638 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
640 'title': '2cc213299525360.mov', # that's what we get
643 'add_ie': ['Ooyala'],
646 # ooyala video embedded with http://player.ooyala.com/iframe.js
647 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
649 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
651 'title': '"Steve Jobs: Man in the Machine" trailer',
652 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
656 'skip_download': True,
658 'skip': 'movie expired',
660 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
662 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
664 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
666 'title': 'Steampunk Fest Comes to Honesdale',
670 'skip_download': True,
675 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
679 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
680 'upload_date': '20140225',
681 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
682 'uploader': 'Tested',
683 'uploader_id': 'testedcom',
685 # No need to test YoutubeIE here
687 'skip_download': True,
692 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
696 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
697 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
699 # HEAD requests lead to endless 301, while GET is OK
700 'expected_warnings': ['301'],
704 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
708 'title': 'Охотское море стало целиком российским',
709 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
713 'skip_download': True,
718 '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/',
722 'title': 'Дошкольное воспитание',
727 'url': 'http://www.vestifinance.ru/articles/25753',
730 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
735 'title': 'Госзаказ. День 3',
741 'title': 'Госзаказ. День 2',
747 'title': 'Госзаказ. День 1',
753 'skip_download': True,
758 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
760 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
762 'title': 'Ужастики, русский трейлер (2015)',
763 'thumbnail': r
're:^https?://.*\.jpg$',
769 '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',
772 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
774 'playlist_mincount': 7,
775 # This forum does not allow <iframe> syntaxes anymore
776 # Now HTML tags are displayed as-is
777 'skip': 'No videos on this page',
781 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
782 'md5': '65fdff94098e4a607385a60c5177c638',
786 'title': 'Hidden miracles of the natural world',
787 'uploader': 'Louie Schwartzberg',
788 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
791 # nowvideo embed hidden behind percent encoding
793 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
794 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
796 'id': '06e53103ca9aa',
798 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
799 'description': 'No description',
804 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
805 'md5': '7653032cbb25bf6c80d80f217055fa43',
807 'id': '048195-004_PLUS7-F',
810 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
811 'upload_date': '20140320',
814 'skip_download': 'Requires rtmpdump'
816 'skip': 'video gone',
820 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
824 'title': 'Alcaline, le concert avec Calogero',
825 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
826 'upload_date': '20150226',
827 'timestamp': 1424989860,
832 'skip_download': True,
834 'expected_warnings': [
840 'url': 'http://www.wired.com/2014/04/honda-asimo/',
841 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
843 'id': '53501be369702d3275860000',
845 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
850 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
851 'md5': '441aeeb82eb72c422c7f14ec533999cd',
853 'id': 'k2mm4bCdJ6CQ2i7c8o2',
855 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
856 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
858 'uploader_id': 'xgditw',
859 'upload_date': '20140425',
860 'timestamp': 1398441542,
862 'add_ie': ['Dailymotion'],
866 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
870 'title': 'Care worker punches elderly dementia patient in head 11 times',
871 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
873 'add_ie': ['DailyMail'],
875 'skip_download': True,
880 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
884 'title': 'The NBL Auction 2014',
885 'uploader': 'BADMINTON England',
886 'uploader_id': 'BADMINTONEvents',
887 'upload_date': '20140603',
888 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
890 'add_ie': ['Youtube'],
892 'skip_download': True,
897 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
898 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
900 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
902 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
903 'description': 'Two valets share their love for movie star Liam Neesons.',
904 'timestamp': 1349922600,
905 'upload_date': '20121011',
908 # YouTube embed via <data-embed-url="">
910 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
914 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
915 'uploader': 'Gameloft',
916 'uploader_id': 'gameloft',
917 'upload_date': '20140828',
918 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
921 'skip_download': True,
924 # YouTube <object> embed
926 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
927 'md5': '516718101ec834f74318df76259fb3cc',
931 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
932 'upload_date': '20080526',
933 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
934 'uploader': 'Christopher Sykes',
935 'uploader_id': 'ChristopherJSykes',
937 'add_ie': ['Youtube'],
941 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
943 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
945 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
946 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
951 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
953 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
954 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
960 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
965 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
966 'md5': '9d65602bf31c6e20014319c7d07fba27',
968 'id': '5123ea6d5e5a7',
971 'uploader': 'www.handjobhub.com',
972 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
975 # Multiple brightcove videos
976 # https://github.com/ytdl-org/youtube-dl/issues/2283
978 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
980 'id': 'always-never',
981 'title': 'Always / Never - The New Yorker',
985 'extract_flat': False,
986 'skip_download': True,
991 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
992 'md5': '96f09a37e44da40dd083e12d9a683327',
996 'title': 'Ump changes call to ball',
997 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
999 'timestamp': 1401537900,
1000 'upload_date': '20140531',
1001 'thumbnail': r
're:^https?://.*\.jpg$',
1006 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1007 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
1011 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1012 'description': 'a Paywall Videos video from Remilon',
1013 'duration': 644.072,
1014 'uploader': 'study.com',
1015 'timestamp': 1459678540,
1016 'upload_date': '20160403',
1017 'filesize': 24687186,
1021 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1022 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1026 'title': 'Conversation about Hexagonal Rails Part 1',
1027 'description': 'a Martin Fowler video from ThoughtWorks',
1029 'uploader': 'thoughtworks.wistia.com',
1030 'timestamp': 1401832161,
1031 'upload_date': '20140603',
1034 # Wistia standard embed (async)
1036 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1040 'title': 'Drip Brennan Dunn Workshop',
1041 'description': 'a JV Webinars video from getdrip-1',
1042 'duration': 4986.95,
1043 'timestamp': 1463607249,
1044 'upload_date': '20160518',
1047 'skip_download': True,
1052 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1056 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1057 'uploader': 'Sophos Security',
1058 'title': 'Chet Chat 171 - Oct 29, 2014',
1059 'upload_date': '20141029',
1062 # Soundcloud multiple embeds
1064 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1067 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1069 'playlist_mincount': 7,
1071 # TuneIn station embed
1073 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1078 'location': 'Paris, France',
1083 'skip_download': True,
1088 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1092 'upload_date': '20141112',
1093 'title': 'Rosetta #CometLanding webcast HL 10',
1096 # Another Livestream embed, without 'new.' in URL
1098 'url': 'https://www.freespeech.org/',
1102 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1106 'skip_download': True,
1111 'url': 'https://skiplagged.com/',
1114 'title': 'Skiplagged: The smart way to find cheap flights',
1116 'playlist_mincount': 1,
1117 'add_ie': ['Youtube'],
1121 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1125 'upload_date': '20141126',
1126 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1131 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1133 'id': '730m_DandD_1901_512k',
1135 'uploader': 'www.abc.net.au',
1136 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1139 # embedded viddler video
1141 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1145 'uploader': 'deadspin',
1146 'title': 'WALL-TO-GORTAT',
1147 'timestamp': 1422285291,
1148 'upload_date': '20150126',
1150 'add_ie': ['Viddler'],
1154 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1158 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1159 'description': 'md5:601cb790edd05908957dae8aaa866465',
1160 'upload_date': '20150220',
1162 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1166 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1168 'id': 'Mrj4DVp2zeA',
1170 'upload_date': '20150212',
1171 'uploader': 'The National Archives UK',
1172 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1173 'uploader_id': 'NationalArchives08',
1174 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1179 'url': 'http://www.suffolk.edu/sjc/live.php',
1183 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1184 'uploader': 'www.suffolk.edu',
1187 'skip_download': True,
1189 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1191 # jwplayer with only the json URL
1193 'url': 'https://www.hollywoodreporter.com/news/general-news/dunkirk-team-reveals-what-christopher-nolan-said-oscar-win-meet-your-oscar-winner-1092454',
1197 'upload_date': '20180306',
1198 'title': 'md5:91eb1862f6526415214f62c00b453936',
1199 'description': 'md5:73048ae50ae953da10549d1d2fe9b3aa',
1200 'timestamp': 1520367225,
1203 'skip_download': True,
1208 'url': 'http://www.indiedb.com/games/king-machine/videos',
1212 'title': 'king machine trailer 1',
1213 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1214 'thumbnail': r
're:^https?://.*\.jpg$',
1218 # JWPlayer config passed as variable
1219 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1223 'title': 'ARIELE | Tube Cup',
1224 'uploader': 'www.txxx.com',
1228 'skip_download': True,
1233 'url': 'https://www.covermagazine.co.uk/feature/2465255/business-protection-involved',
1237 'upload_date': '20160719',
1238 'timestamp': 468923808,
1239 'title': '2016_05_18 Cover L&G Business Protection V1 FINAL.mp4',
1241 'add_ie': [JWPlatformIE
.ie_key()],
1244 # Video.js embed, multiple formats
1245 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1247 'id': 'yygqldloqIk',
1249 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1250 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1251 'upload_date': '20130314',
1252 'uploader': 'PROстое3D',
1253 'uploader_id': 'PROstoe3D',
1256 'skip_download': True,
1260 # Video.js embed, single format
1261 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1265 'title': 'Step 1 - Good Foundation',
1266 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1269 'skip_download': True,
1274 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1275 'playlist_mincount': 5,
1277 'id': 'aanslagen-kopenhagen',
1278 'title': 'Aanslagen Kopenhagen',
1283 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1287 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1290 # Kaltura embed (different embed code)
1292 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1296 'upload_date': '20150127',
1297 'uploader_id': 'PremierMedia',
1299 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1302 # Kaltura embed with single quotes
1304 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1309 'timestamp': 1355743100,
1310 'upload_date': '20121217',
1311 'uploader_id': 'cplapp@learn360.com',
1313 'add_ie': ['Kaltura'],
1316 # Kaltura embedded via quoted entry_id
1317 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1321 'title': '06_matthew_brender_raj_dutt',
1322 'timestamp': 1466638791,
1323 'upload_date': '20160622',
1325 'add_ie': ['Kaltura'],
1326 'expected_warnings': [
1327 'Could not send HEAD request'
1330 'skip_download': True,
1334 # Kaltura embedded, some fileExt broken (#11480)
1335 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1339 'title': 'Our "Standard Models" of particle physics and cosmology',
1340 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1341 'timestamp': 1321158993,
1342 'upload_date': '20111113',
1343 'uploader_id': 'kps1',
1345 'add_ie': ['Kaltura'],
1348 # Kaltura iframe embed
1349 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1350 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1354 'title': 'I. M. Pei: A Centennial Celebration',
1355 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1356 'upload_date': '20170403',
1357 'uploader_id': 'batchUser',
1358 'timestamp': 1491232186,
1360 'add_ie': ['Kaltura'],
1363 # Kaltura iframe embed, more sophisticated
1364 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1368 'title': 'lecture-05sep2017',
1369 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1370 'upload_date': '20170913',
1371 'uploader_id': 'eps2',
1372 'timestamp': 1505340777,
1375 'skip_download': True,
1377 'add_ie': ['Kaltura'],
1380 # meta twitter:player
1381 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1385 'title': 'Main Twerk (Video)',
1386 'upload_date': '20171208',
1387 'uploader_id': 'sebastian.salinas@thechive.com',
1388 'timestamp': 1512713057,
1391 'skip_download': True,
1393 'add_ie': ['Kaltura'],
1395 # referrer protected EaglePlatform embed
1397 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1401 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1402 'thumbnail': r
're:^https?://.*\.jpg$',
1407 'skip_download': True,
1410 # ClipYou (EaglePlatform) embed (custom URL)
1412 'url': 'http://muz-tv.ru/play/7129/',
1413 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1417 'title': "'O Sole Mio",
1418 'thumbnail': r
're:^https?://.*\.jpg$',
1423 'skip_download': True,
1425 'skip': 'This video is unavailable.',
1429 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1433 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1434 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1435 'thumbnail': r
're:^https?://.*\.jpg$',
1439 'skip': 'HTTP Error 404: Not Found',
1443 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1447 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1448 'thumbnail': r
're:^https?://.*\.png$',
1454 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1455 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1459 'title': 'Facebook Creates "On This Day" | Crunch Report',
1460 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1461 'timestamp': 1427237531,
1462 'uploader': 'Crunch Report',
1463 'upload_date': '20150324',
1467 'skip_download': True,
1470 # Crooks and Liars embed
1472 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1476 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1477 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1478 'timestamp': 1428207000,
1479 'upload_date': '20150405',
1480 'uploader': 'Heather',
1483 # Crooks and Liars external embed
1485 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1487 'id': 'MTE3MjUtMzQ2MzA',
1489 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1490 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1491 'timestamp': 1265032391,
1492 'upload_date': '20100201',
1493 'uploader': 'Heather',
1496 # NBC Sports vplayer embed
1498 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1500 'id': 'ln7x1qSThw4k',
1502 'title': "PFT Live: New leader in the 'new-look' defense",
1503 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1504 'uploader': 'NBCU-SPORTS',
1505 'upload_date': '20140107',
1506 'timestamp': 1389118457,
1508 'skip': 'Invalid Page URL',
1512 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1513 'md5': '1aa589c675898ae6d37a17913cf68d66',
1515 'id': 'x_dtl_oa_LettermanliftPR_160608',
1517 'title': 'David Letterman: A Preview',
1518 '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.',
1519 'upload_date': '20160609',
1520 'timestamp': 1465431544,
1521 'uploader': 'NBCU-NEWS',
1526 'url': 'https://video.udn.com/news/300346',
1527 'md5': 'fd2060e988c326991037b9aff9df21a6',
1531 'title': '中一中男師變性 全校師生力挺',
1532 'thumbnail': r
're:^https?://.*\.jpg$',
1536 'skip_download': True,
1538 'expected_warnings': ['Failed to parse JSON Expecting value'],
1540 # Brightcove URL in single quotes
1542 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1543 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1545 'id': '4255764656001',
1547 'title': 'SN Presents: Russell Martin, World Citizen',
1548 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1549 'uploader': 'Rogers Sportsnet',
1550 'uploader_id': '1704050871',
1551 'upload_date': '20150525',
1552 'timestamp': 1432570283,
1557 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1561 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1562 'description': 'Migrated from OnionStudios',
1563 'thumbnail': r
're:^https?://.*\.jpe?g$',
1564 'uploader': 'clickhole',
1565 'upload_date': '20150527',
1566 'timestamp': 1432744860,
1571 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1573 'id': '74849a00-85a9-11e1-9660-123139220831',
1575 'title': '#whilewewatch',
1578 # AdobeTVVideo embed
1580 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1581 'md5': '43662b577c018ad707a63766462b1e87',
1585 'title': 'New experience with Acrobat DC',
1586 'description': 'New experience with Acrobat DC',
1587 'duration': 248.667,
1590 # BrightcoveInPageEmbed embed
1592 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1594 'id': '4238694884001',
1596 'title': 'Tabletop: Dread, Last Thoughts',
1597 'description': 'Tabletop: Dread, Last Thoughts',
1601 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1602 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1604 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1606 'id': '4785848093001',
1608 'title': 'The Cardinal Pell Interview',
1609 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1610 'uploader': 'GlobeCast Australia - GlobeStream',
1611 'uploader_id': '2733773828001',
1612 'upload_date': '20160304',
1613 'timestamp': 1457083087,
1617 'skip_download': True,
1621 # Brightcove embed with whitespace around attribute names
1622 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1624 'id': '3167554373001',
1626 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1627 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1628 'uploader_id': '1079349493',
1629 'upload_date': '20140207',
1630 'timestamp': 1391810548,
1633 'skip_download': True,
1636 # Another form of arte.tv embed
1638 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1639 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1641 'id': '030273-562_PLUS7-F',
1643 'title': 'ARTE Reportage - Nulle part, en France',
1644 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1645 'upload_date': '20160409',
1648 # Duplicated embedded video URLs
1650 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1652 'id': '149298443_480_16c25b74_2',
1654 'title': 'vs. Blue Orange Spring Game',
1655 'uploader': 'www.hudl.com',
1658 # twitter:player:stream embed
1660 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1664 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1665 'uploader': 'www.rtl.be',
1669 'skip_download': True,
1672 # twitter:player embed
1674 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1675 'md5': 'a3e0df96369831de324f0778e126653c',
1677 'id': '4909620399001',
1679 'title': 'What Do Black Holes Sound Like?',
1680 'description': 'what do black holes sound like',
1681 'upload_date': '20160524',
1682 'uploader_id': '29913724001',
1683 'timestamp': 1464107587,
1684 'uploader': 'TheAtlantic',
1686 'add_ie': ['BrightcoveLegacy'],
1688 # Facebook <iframe> embed
1690 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1691 'md5': 'fbcde74f534176ecb015849146dd3aee',
1693 'id': '599637780109885',
1695 'title': 'Facebook video #599637780109885',
1698 # Facebook <iframe> embed, plugin video
1700 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1702 'id': '1754168231264132',
1704 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1705 'uploader': 'Tariq Ramadan (official)',
1706 'timestamp': 1496758379,
1707 'upload_date': '20170606',
1710 'skip_download': True,
1713 # Facebook API embed
1715 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1716 'md5': 'a47372ee61b39a7b90287094d447d94e',
1718 'id': '10153467542406923',
1720 'title': 'Facebook video #10153467542406923',
1723 # Wordpress "YouTube Video Importer" plugin
1725 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1726 'md5': 'd16797741b560b485194eddda8121b48',
1728 'id': 'HNTXWDXV9Is',
1730 'title': 'Blue Devils Drumline Stanford lot 2016',
1731 'upload_date': '20160627',
1732 'uploader_id': 'GENOCIDE8GENERAL10',
1733 'uploader': 'cylus cyrus',
1737 # video stored on custom kaltura server
1738 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1739 'md5': '537617d06e64dfed891fa1593c4b30cc',
1743 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1744 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1745 'uploader_id': 'videos.expansion@el-mundo.net',
1746 'upload_date': '20150429',
1747 'timestamp': 1430303472,
1749 'add_ie': ['Kaltura'],
1752 # multiple kaltura embeds, nsfw
1753 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1755 'id': 'kamila-avec-video-jaime-sadomie',
1756 'title': "Kamila avec vídeo “J'aime sadomie”",
1758 'playlist_count': 8,
1761 # Non-standard Vimeo embed
1762 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1763 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1767 'title': 'Understanding the web - Teaser',
1768 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1769 'upload_date': '20151214',
1770 'uploader': 'OpenClassrooms',
1771 'uploader_id': 'openclassrooms',
1773 'add_ie': ['Vimeo'],
1776 # generic vimeo embed that requires original URL passed as Referer
1777 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1778 'only_matching': True,
1781 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1782 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1784 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1786 'title': 'Big Buck Bunny',
1787 'description': 'Royalty free test video',
1788 'timestamp': 1432816365,
1789 'upload_date': '20150528',
1793 'skip_download': True,
1795 'add_ie': [ArkenaIE
.ie_key()],
1798 '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/',
1802 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1805 'skip_download': True,
1807 'add_ie': [Vbox7IE
.ie_key()],
1811 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1814 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1816 'playlist_mincount': 3,
1820 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1822 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1823 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1825 'playlist_mincount': 2,
1829 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1833 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1834 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1837 'skip_download': True,
1839 'add_ie': [TwentyMinutenIE
.ie_key()],
1843 'url': 'https://en.support.wordpress.com/videopress/',
1847 'title': 'IMG_5786',
1848 'timestamp': 1435711927,
1849 'upload_date': '20150701',
1852 'skip_download': True,
1854 'add_ie': [VideoPressIE
.ie_key()],
1858 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1860 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1862 'title': 'Магаззино: Казань 2',
1863 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1864 'uploader': 'Магаззино',
1865 'upload_date': '20170228',
1866 'uploader_id': '996642',
1869 'skip_download': True,
1871 'add_ie': [RutubeIE
.ie_key()],
1874 # ThePlatform embedded with whitespaces in URLs
1875 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1876 'only_matching': True,
1879 # Senate ISVP iframe https
1880 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1881 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1883 'id': 'govtaff020316',
1885 'title': 'Integrated Senate Video Player',
1887 'add_ie': [SenateISVPIE
.ie_key()],
1890 # Limelight embeds (1 channel embed + 4 media embeds)
1891 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1893 'id': 'FacilitatorTraining2017',
1894 'title': 'Facilitator Training 2017',
1896 'playlist_mincount': 5,
1899 # Limelight embed (LimelightPlayerUtil.embed)
1900 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1902 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1904 'title': '07448641',
1905 'timestamp': 1499890639,
1906 'upload_date': '20170712',
1909 'skip_download': True,
1911 'add_ie': ['LimelightMedia'],
1914 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1916 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1917 'title': 'Standoff with Walnut Creek murder suspect ends',
1918 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1920 'playlist_mincount': 4,
1923 # WashingtonPost embed
1924 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1926 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1928 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1929 '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.',
1930 'timestamp': 1455216756,
1931 'uploader': 'The Washington Post',
1932 'upload_date': '20160211',
1934 'add_ie': [WashingtonPostIE
.ie_key()],
1938 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1942 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1945 'skip_download': True,
1947 'add_ie': [MediasetIE
.ie_key()],
1951 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1953 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1954 'title': 'Slovenskom sa prehnala vlna silných búrok',
1956 'playlist_mincount': 5,
1957 'add_ie': [JojIE
.ie_key()],
1960 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1961 'url': 'https://tvrain.ru/amp/418921/',
1962 'md5': 'cc00413936695987e8de148b67d14f1d',
1966 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1971 'url': 'http://help.vzaar.com/article/165-embedding-video',
1972 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1976 'title': 'Building A Business Online: Principal Chairs Q & A',
1980 # multiple HTML5 videos on one page
1981 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1983 'id': 'keyscenarios',
1984 'title': 'Rescue Kit 14 Free Edition - Getting started',
1986 'playlist_count': 4,
1990 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1991 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1994 'title': 'vl14062007715967',
1999 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
2000 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
2002 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
2004 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
2005 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
2006 'timestamp': 1474354800,
2007 'upload_date': '20160920',
2011 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
2015 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2016 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2017 'timestamp': 1516100691,
2018 'upload_date': '20180116',
2021 'skip_download': True,
2023 'add_ie': [SpringboardPlatformIE
.ie_key()],
2026 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2028 'id': 'vMDE4NzI1Mjgt690b',
2032 'add_ie': [YapFilesIE
.ie_key()],
2034 'skip_download': True,
2038 # CloudflareStream embed
2039 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2041 'id': '31c9291ab41fac05471db4e73aa11717',
2043 'title': '31c9291ab41fac05471db4e73aa11717',
2045 'add_ie': [CloudflareStreamIE
.ie_key()],
2047 'skip_download': True,
2052 'url': 'https://joinpeertube.org/fr/home/',
2055 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2057 'playlist_count': 2,
2061 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2065 'title': 'Így kell otthon hamburgert sütni',
2066 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2067 'timestamp': 1426330212,
2068 'upload_date': '20150314',
2069 'uploader': 'StreetKitchen',
2070 'uploader_id': '546363',
2072 'add_ie': [IndavideoEmbedIE
.ie_key()],
2074 'skip_download': True,
2078 # APA embed via JWPlatform embed
2079 'url': 'http://www.vol.at/blue-man-group/5593454',
2083 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2084 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2085 'thumbnail': r
're:^https?://.*\.jpg$',
2087 'timestamp': 1519211149,
2088 'upload_date': '20180221',
2091 'skip_download': True,
2095 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2096 'md5': 'b68d276de422ab07ee1d49388103f457',
2099 'title': 'Lock up and get excited',
2102 'skip': 'TODO: fix nested playlists processing in tests',
2106 'url': 'https://viqeo.tv/',
2109 'title': 'All-new video platform',
2111 'playlist_count': 6,
2114 # Squarespace video embed, 2019-08-28
2115 'url': 'http://ootboxford.com',
2117 'id': 'Tc7b_JGdZfw',
2118 'title': 'Out of the Blue, at Childish Things 10',
2120 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2121 'uploader_id': 'helendouglashouse',
2122 'uploader': 'Helen & Douglas House',
2123 'upload_date': '20140328',
2126 'skip_download': True,
2131 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2133 # 'id': '5b400b834b32992a310622b9',
2135 # 'title': 'Smoky Barbecue Favorites',
2136 # 'thumbnail': r're:^https?://.*\.jpe?g',
2137 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2138 # 'upload_date': '20170909',
2139 # 'timestamp': 1504915200,
2141 # 'add_ie': [ZypeIE.ie_key()],
2143 # 'skip_download': True,
2148 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2152 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2153 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2154 'thumbnail': r
're:^https?://.*\.jpg$',
2157 'skip_download': True,
2159 'expected_warnings': ['Failed to download MPD manifest'],
2162 # DailyMotion embed with DM.player
2163 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2165 'id': 'k6aKkGHd9FJs4mtJN39',
2167 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2168 'description': 'This video is private.',
2169 'uploader_id': 'x1jf30l',
2170 'uploader': 'beIN SPORTS USA',
2171 'upload_date': '20190528',
2172 'timestamp': 1559062971,
2175 'skip_download': True,
2179 # # TODO: find another test
2180 # # http://schema.org/VideoObject
2181 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2182 # 'md5': '888dcf08b7ea671381f00fab74692755',
2184 # 'id': 'nyvTSJMKId',
2186 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2187 # 'description': '#love for cats.',
2188 # 'timestamp': 1461244995,
2189 # 'upload_date': '20160421',
2192 # 'force_generic_extractor': True,
2197 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2201 'title': 'Untitled',
2202 'uploader_id': 'user80538407',
2203 'uploader': 'OTT Videos',
2207 # ArcPublishing PoWa video player
2208 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2209 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2211 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2213 'title': 'Senate candidates wave to voters on Anchorage streets',
2214 'description': 'md5:91f51a6511f090617353dc720318b20e',
2215 'timestamp': 1604378735,
2216 'upload_date': '20201103',
2221 # MyChannels SDK embed
2222 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2223 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2224 'md5': '90c0699c37006ef18e198c032d81739c',
2228 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2229 'timestamp': 1611740340,
2230 'upload_date': '20210127',
2235 # Simplecast player embed
2236 'url': 'https://www.bio.org/podcast',
2239 'title': 'I AM BIO Podcast | BIO',
2241 'playlist_mincount': 52,
2244 # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
2245 'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
2246 'only_matching': True,
2248 # WimTv embed player
2249 'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
2251 'id': 'wearefmi-pt-2-2021',
2252 'title': '#WEAREFMI – PT.2 – 2021 – MsMotorTV',
2254 'playlist_count': 1,
2257 'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
2260 'display_id': 'kelis-4th-of-july',
2262 'title': 'Kelis - 4th Of July',
2263 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2266 'skip_download': True,
2270 'url': 'https://www.kvs-demo.com/embed/105/',
2273 'display_id': 'kelis-4th-of-july',
2275 'title': 'Kelis - 4th Of July / Embed Player',
2276 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2279 'skip_download': True,
2283 'url': 'https://thisvid.com/videos/french-boy-pantsed/',
2284 'md5': '3397979512c682f6b85b3b04989df224',
2287 'display_id': 'french-boy-pantsed',
2289 'title': 'French Boy Pantsed - ThisVid.com',
2290 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2294 'url': 'https://thisvid.com/embed/2400174/',
2295 'md5': '3397979512c682f6b85b3b04989df224',
2298 'display_id': 'french-boy-pantsed',
2300 'title': 'French Boy Pantsed - ThisVid.com',
2301 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2305 'url': 'https://youix.com/video/leningrad-zoj/',
2306 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2309 'display_id': 'leningrad-zoj',
2311 'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
2312 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2316 'url': 'https://youix.com/embed/18485',
2317 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2320 'display_id': 'leningrad-zoj',
2322 'title': 'Ленинград - ЗОЖ',
2323 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2327 'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
2328 'md5': '94166bdb26b4cb1fb9214319a629fc51',
2331 'display_id': '40-nochey-40-nights-2016',
2333 'title': '40 ночей (2016) - BogMedia.org',
2334 'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
2339 def report_following_redirect(self
, new_url
):
2340 """Report information extraction."""
2341 self
._downloader
.to_screen('[redirect] Following redirect to %s' % new_url
)
2343 def _extract_rss(self
, url
, video_id
, doc
):
2344 playlist_title
= doc
.find('./channel/title').text
2345 playlist_desc_el
= doc
.find('./channel/description')
2346 playlist_desc
= None if playlist_desc_el
is None else playlist_desc_el
.text
2349 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2353 for it
in doc
.findall('./channel/item'):
2355 enclosure_nodes
= it
.findall('./enclosure')
2356 for e
in enclosure_nodes
:
2357 next_url
= e
.attrib
.get('url')
2362 next_url
= xpath_text(it
, 'link', fatal
=False)
2369 it
, xpath_with_ns('./itunes:%s' % key
, NS_MAP
),
2372 duration
= itunes('duration')
2373 explicit
= (itunes('explicit') or '').lower()
2374 if explicit
in ('true', 'yes'):
2376 elif explicit
in ('false', 'no'):
2382 '_type': 'url_transparent',
2384 'title': it
.find('title').text
,
2385 'description': xpath_text(it
, 'description', default
=None),
2386 'timestamp': unified_timestamp(
2387 xpath_text(it
, 'pubDate', default
=None)),
2388 'duration': int_or_none(duration
) or parse_duration(duration
),
2389 'thumbnail': url_or_none(xpath_attr(it
, xpath_with_ns('./itunes:image', NS_MAP
), 'href')),
2390 'episode': itunes('title'),
2391 'episode_number': int_or_none(itunes('episode')),
2392 'season_number': int_or_none(itunes('season')),
2393 'age_limit': age_limit
,
2397 '_type': 'playlist',
2399 'title': playlist_title
,
2400 'description': playlist_desc
,
2404 def _extract_camtasia(self
, url
, video_id
, webpage
):
2405 """ Returns None if no camtasia video can be found. """
2407 camtasia_cfg
= self
._search
_regex
(
2408 r
'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2409 webpage
, 'camtasia configuration file', default
=None)
2410 if camtasia_cfg
is None:
2413 title
= self
._html
_search
_meta
('DC.title', webpage
, fatal
=True)
2415 camtasia_url
= compat_urlparse
.urljoin(url
, camtasia_cfg
)
2416 camtasia_cfg
= self
._download
_xml
(
2417 camtasia_url
, video_id
,
2418 note
='Downloading camtasia configuration',
2419 errnote
='Failed to download camtasia configuration')
2420 fileset_node
= camtasia_cfg
.find('./playlist/array/fileset')
2423 for n
in fileset_node
.getchildren():
2424 url_n
= n
.find('./uri')
2429 'id': os
.path
.splitext(url_n
.text
.rpartition('/')[2])[0],
2430 'title': '%s - %s' % (title
, n
.tag
),
2431 'url': compat_urlparse
.urljoin(url
, url_n
.text
),
2432 'duration': float_or_none(n
.find('./duration').text
),
2436 '_type': 'playlist',
2441 def _kvs_getrealurl(self
, video_url
, license_code
):
2442 if not video_url
.startswith('function/0/'):
2443 return video_url
# not obfuscated
2445 url_path
, _
, url_query
= video_url
.partition('?')
2446 urlparts
= url_path
.split('/')[2:]
2447 license
= self
._kvs
_getlicensetoken
(license_code
)
2448 newmagic
= urlparts
[5][:32]
2450 for o
in range(len(newmagic
) - 1, -1, -1):
2452 l
= (o
+ sum([int(n
) for n
in license
[o
:]])) % 32
2454 for i
in range(0, len(newmagic
)):
2463 urlparts
[5] = newmagic
+ urlparts
[5][32:]
2464 return '/'.join(urlparts
) + '?' + url_query
2466 def _kvs_getlicensetoken(self
, license
):
2467 modlicense
= license
.replace('$', '').replace('0', '1')
2468 center
= int(len(modlicense
) / 2)
2469 fronthalf
= int(modlicense
[:center
+ 1])
2470 backhalf
= int(modlicense
[center
:])
2472 modlicense
= str(4 * abs(fronthalf
- backhalf
))
2474 for o
in range(0, center
+ 1):
2475 for i
in range(1, 5):
2476 retval
+= str((int(license
[o
+ i
]) + int(modlicense
[o
])) % 10)
2479 def _real_extract(self
, url
):
2480 if url
.startswith('//'):
2481 return self
.url_result(self
.http_scheme() + url
)
2483 parsed_url
= compat_urlparse
.urlparse(url
)
2484 if not parsed_url
.scheme
:
2485 default_search
= self
.get_param('default_search')
2486 if default_search
is None:
2487 default_search
= 'fixup_error'
2489 if default_search
in ('auto', 'auto_warning', 'fixup_error'):
2490 if re
.match(r
'^[^\s/]+\.[^\s/]+/', url
):
2491 self
.report_warning('The url doesn\'t specify the protocol, trying with http')
2492 return self
.url_result('http://' + url
)
2493 elif default_search
!= 'fixup_error':
2494 if default_search
== 'auto_warning':
2495 if re
.match(r
'^(?:url|URL)$', url
):
2496 raise ExtractorError(
2497 'Invalid URL: %r . Call yt-dlp like this: yt-dlp -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url
,
2500 self
.report_warning(
2501 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url
)
2502 return self
.url_result('ytsearch:' + url
)
2504 if default_search
in ('error', 'fixup_error'):
2505 raise ExtractorError(
2506 '%r is not a valid URL. '
2507 'Set --default-search "ytsearch" (or run yt-dlp "ytsearch:%s" ) to search YouTube'
2508 % (url
, url
), expected
=True)
2510 if ':' not in default_search
:
2511 default_search
+= ':'
2512 return self
.url_result(default_search
+ url
)
2514 url
, smuggled_data
= unsmuggle_url(url
)
2515 force_videoid
= None
2516 is_intentional
= smuggled_data
and smuggled_data
.get('to_generic')
2517 if smuggled_data
and 'force_videoid' in smuggled_data
:
2518 force_videoid
= smuggled_data
['force_videoid']
2519 video_id
= force_videoid
2521 video_id
= self
._generic
_id
(url
)
2523 self
.to_screen('%s: Requesting header' % video_id
)
2525 head_req
= HEADRequest(url
)
2526 head_response
= self
._request
_webpage
(
2528 note
=False, errnote
='Could not send HEAD request to %s' % url
,
2531 if head_response
is not False:
2532 # Check for redirect
2533 new_url
= head_response
.geturl()
2535 self
.report_following_redirect(new_url
)
2537 new_url
= smuggle_url(
2538 new_url
, {'force_videoid': force_videoid}
)
2539 return self
.url_result(new_url
)
2541 full_response
= None
2542 if head_response
is False:
2543 request
= sanitized_Request(url
)
2544 request
.add_header('Accept-Encoding', '*')
2545 full_response
= self
._request
_webpage
(request
, video_id
)
2546 head_response
= full_response
2550 'title': self
._generic
_title
(url
),
2551 'timestamp': unified_timestamp(head_response
.headers
.get('Last-Modified'))
2554 # Check for direct link to a video
2555 content_type
= head_response
.headers
.get('Content-Type', '').lower()
2556 m
= re
.match(r
'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type
)
2558 format_id
= compat_str(m
.group('format_id'))
2560 if format_id
.endswith('mpegurl'):
2561 formats
, subtitles
= self
._extract
_m
3u8_formats
_and
_subtitles
(url
, video_id
, 'mp4')
2562 elif format_id
== 'f4m':
2563 formats
= self
._extract
_f
4m
_formats
(url
, video_id
)
2566 'format_id': format_id
,
2568 'vcodec': 'none' if m
.group('type') == 'audio' else None
2570 info_dict
['direct'] = True
2571 self
._sort
_formats
(formats
)
2572 info_dict
['formats'] = formats
2573 info_dict
['subtitles'] = subtitles
2576 if not self
.get_param('test', False) and not is_intentional
:
2577 force
= self
.get_param('force_generic_extractor', False)
2578 self
.report_warning(
2579 '%s on generic information extractor.' % ('Forcing' if force
else 'Falling back'))
2581 if not full_response
:
2582 request
= sanitized_Request(url
)
2583 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2584 # making it impossible to download only chunk of the file (yet we need only 512kB to
2585 # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
2586 # that will always result in downloading the whole file that is not desirable.
2587 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2588 # to accept raw bytes and being able to download only a chunk.
2589 # It may probably better to solve this by checking Content-Type for application/octet-stream
2590 # after HEAD request finishes, but not sure if we can rely on this.
2591 request
.add_header('Accept-Encoding', '*')
2592 full_response
= self
._request
_webpage
(request
, video_id
)
2594 first_bytes
= full_response
.read(512)
2596 # Is it an M3U playlist?
2597 if first_bytes
.startswith(b
'#EXTM3U'):
2598 info_dict
['formats'], info_dict
['subtitles'] = self
._extract
_m
3u8_formats
_and
_subtitles
(url
, video_id
, 'mp4')
2599 self
._sort
_formats
(info_dict
['formats'])
2602 # Maybe it's a direct link to a video?
2603 # Be careful not to download the whole thing!
2604 if not is_html(first_bytes
):
2605 self
.report_warning(
2606 'URL could be a direct video link, returning it as such.')
2613 webpage
= self
._webpage
_read
_content
(
2614 full_response
, url
, video_id
, prefix
=first_bytes
)
2616 if '<title>DPG Media Privacy Gate</title>' in webpage
:
2617 webpage
= self
._download
_webpage
(url
, video_id
)
2619 self
.report_extraction(video_id
)
2621 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2624 doc
= compat_etree_fromstring(webpage
)
2625 except compat_xml_parse_error
:
2626 doc
= compat_etree_fromstring(webpage
.encode('utf-8'))
2627 if doc
.tag
== 'rss':
2628 return self
._extract
_rss
(url
, video_id
, doc
)
2629 elif doc
.tag
== 'SmoothStreamingMedia':
2630 info_dict
['formats'], info_dict
['subtitles'] = self
._parse
_ism
_formats
_and
_subtitles
(doc
, url
)
2631 self
._sort
_formats
(info_dict
['formats'])
2633 elif re
.match(r
'^(?:{[^}]+})?smil$', doc
.tag
):
2634 smil
= self
._parse
_smil
(doc
, url
, video_id
)
2635 self
._sort
_formats
(smil
['formats'])
2637 elif doc
.tag
== '{http://xspf.org/ns/0/}playlist':
2638 return self
.playlist_result(
2640 doc
, video_id
, xspf_url
=url
,
2641 xspf_base_url
=full_response
.geturl()),
2643 elif re
.match(r
'(?i)^(?:{[^}]+})?MPD$', doc
.tag
):
2644 info_dict
['formats'], info_dict
['subtitles'] = self
._parse
_mpd
_formats
_and
_subtitles
(
2646 mpd_base_url
=full_response
.geturl().rpartition('/')[0],
2648 self
._sort
_formats
(info_dict
['formats'])
2650 elif re
.match(r
'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc
.tag
):
2651 info_dict
['formats'] = self
._parse
_f
4m
_formats
(doc
, url
, video_id
)
2652 self
._sort
_formats
(info_dict
['formats'])
2654 except compat_xml_parse_error
:
2657 # Is it a Camtasia project?
2658 camtasia_res
= self
._extract
_camtasia
(url
, video_id
, webpage
)
2659 if camtasia_res
is not None:
2662 # Sometimes embedded video player is hidden behind percent encoding
2663 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2664 # Unescaping the whole page allows to handle those cases in a generic way
2665 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2666 # There probably should be a second run of generic extractor on unescaped webpage.
2667 # webpage = compat_urllib_parse_unquote(webpage)
2669 # Unescape squarespace embeds to be detected by generic extractor,
2670 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2672 r
'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2673 lambda x
: unescapeHTML(x
.group(0)), webpage
)
2675 # it's tempting to parse this further, but you would
2676 # have to take into account all the variations like
2677 # Video Title - Site Name
2678 # Site Name | Video Title
2679 # Video Title - Tagline | Site Name
2680 # and so on and so forth; it's just not practical
2681 video_title
= self
._og
_search
_title
(
2682 webpage
, default
=None) or self
._html
_search
_regex
(
2683 r
'(?s)<title>(.*?)</title>', webpage
, 'video title',
2686 # Try to detect age limit automatically
2687 age_limit
= self
._rta
_search
(webpage
)
2688 # And then there are the jokers who advertise that they use RTA,
2689 # but actually don't.
2690 AGE_LIMIT_MARKERS
= [
2691 r
'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2693 if any(re
.search(marker
, webpage
) for marker
in AGE_LIMIT_MARKERS
):
2696 # video uploader is domain name
2697 video_uploader
= self
._search
_regex
(
2698 r
'^(?:https?://)?([^/]*)/.*', url
, 'video uploader')
2700 video_description
= self
._og
_search
_description
(webpage
, default
=None)
2701 video_thumbnail
= self
._og
_search
_thumbnail
(webpage
, default
=None)
2704 'title': video_title
,
2705 'description': video_description
,
2706 'thumbnail': video_thumbnail
,
2707 'age_limit': age_limit
,
2710 # Look for Brightcove Legacy Studio embeds
2711 bc_urls
= BrightcoveLegacyIE
._extract
_brightcove
_urls
(webpage
)
2715 'url': smuggle_url(bc_url
, {'Referer': url}
),
2716 'ie_key': 'BrightcoveLegacy'
2717 } for bc_url
in bc_urls
]
2720 '_type': 'playlist',
2721 'title': video_title
,
2726 # Look for Brightcove New Studio embeds
2727 bc_urls
= BrightcoveNewIE
._extract
_urls
(self
, webpage
)
2729 return self
.playlist_from_matches(
2730 bc_urls
, video_id
, video_title
,
2731 getter
=lambda x
: smuggle_url(x
, {'referrer': url}
),
2734 # Look for Nexx embeds
2735 nexx_urls
= NexxIE
._extract
_urls
(webpage
)
2737 return self
.playlist_from_matches(nexx_urls
, video_id
, video_title
, ie
=NexxIE
.ie_key())
2739 # Look for Nexx iFrame embeds
2740 nexx_embed_urls
= NexxEmbedIE
._extract
_urls
(webpage
)
2742 return self
.playlist_from_matches(nexx_embed_urls
, video_id
, video_title
, ie
=NexxEmbedIE
.ie_key())
2744 # Look for ThePlatform embeds
2745 tp_urls
= ThePlatformIE
._extract
_urls
(webpage
)
2747 return self
.playlist_from_matches(tp_urls
, video_id
, video_title
, ie
='ThePlatform')
2749 arc_urls
= ArcPublishingIE
._extract
_urls
(webpage
)
2751 return self
.playlist_from_matches(arc_urls
, video_id
, video_title
, ie
=ArcPublishingIE
.ie_key())
2753 mychannels_urls
= MedialaanIE
._extract
_urls
(webpage
)
2755 return self
.playlist_from_matches(
2756 mychannels_urls
, video_id
, video_title
, ie
=MedialaanIE
.ie_key())
2758 # Look for embedded rtl.nl player
2759 matches
= re
.findall(
2760 r
'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2763 return self
.playlist_from_matches(matches
, video_id
, video_title
, ie
='RtlNl')
2765 vimeo_urls
= VimeoIE
._extract
_urls
(url
, webpage
)
2767 return self
.playlist_from_matches(vimeo_urls
, video_id
, video_title
, ie
=VimeoIE
.ie_key())
2769 vhx_url
= VHXEmbedIE
._extract
_url
(webpage
)
2771 return self
.url_result(vhx_url
, VHXEmbedIE
.ie_key())
2773 # Invidious Instances
2774 # https://github.com/yt-dlp/yt-dlp/issues/195
2775 # https://github.com/iv-org/invidious/pull/1730
2776 youtube_url
= self
._search
_regex
(
2777 r
'<link rel="alternate" href="(https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2778 webpage
, 'youtube link', default
=None)
2780 return self
.url_result(youtube_url
, YoutubeIE
.ie_key())
2782 # Look for YouTube embeds
2783 youtube_urls
= YoutubeIE
._extract
_urls
(webpage
)
2785 return self
.playlist_from_matches(
2786 youtube_urls
, video_id
, video_title
, ie
=YoutubeIE
.ie_key())
2788 matches
= DailymotionIE
._extract
_urls
(webpage
)
2790 return self
.playlist_from_matches(matches
, video_id
, video_title
)
2792 # Look for embedded Dailymotion playlist player (#3822)
2794 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?dailymotion\
.[a
-z
]{2,3}
/widget
/jukebox
\?.+?
)\
1', webpage)
2796 playlists = re.findall(
2797 r'list\
[\
]=/playlist
/([^
/]+)/', unescapeHTML(m.group('url
')))
2799 return self.playlist_from_matches(
2800 playlists, video_id, video_title, lambda p: '//dailymotion
.com
/playlist
/%s' % p)
2802 # Look for DailyMail embeds
2803 dailymail_urls = DailyMailIE._extract_urls(webpage)
2805 return self.playlist_from_matches(
2806 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2808 # Look for Teachable embeds, must be before Wistia
2809 teachable_url = TeachableIE._extract_url(webpage, url)
2811 return self.url_result(teachable_url)
2813 # Look for embedded Wistia player
2814 wistia_urls = WistiaIE._extract_urls(webpage)
2816 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2817 for entry in playlist['entries
']:
2819 '_type
': 'url_transparent
',
2820 'uploader
': video_uploader,
2824 # Look for SVT player
2825 svt_url = SVTIE._extract_url(webpage)
2827 return self.url_result(svt_url, 'SVT
')
2829 # Look for Bandcamp pages with custom domain
2830 mobj = re.search(r'<meta
property="og:url"[^
>]*?content
="(.*?bandcamp\.com.*?)"', webpage)
2831 if mobj is not None:
2832 burl = unescapeHTML(mobj.group(1))
2833 # Don't
set the extractor because it can be a track url
or an album
2834 return self
.url_result(burl
)
2836 # Look for embedded Vevo player
2838 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:cache\
.)?vevo\
.com
/.+?
)\
1', webpage)
2839 if mobj is not None:
2840 return self.url_result(mobj.group('url
'))
2842 # Look for embedded Viddler player
2844 r'<(?
:iframe
[^
>]+?src|param
[^
>]+?value
)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2846 if mobj is not None:
2847 return self.url_result(mobj.group('url'))
2849 # Look for NYTimes player
2851 r'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//graphics8\
.nytimes\
.com
/bcvideo
/[^
/]+/iframe
/embed\
.html
.+?
)\
1>',
2853 if mobj is not None:
2854 return self.url_result(mobj.group('url
'))
2856 # Look for Libsyn player
2858 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2859 if mobj is not None:
2860 return self.url_result(mobj.group('url'))
2862 # Look for Ooyala videos
2863 mobj = (re.search(r'player\.ooyala\.com/[^"?
]+[?
#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2864 or re
.search(r
'OO\.Player\.create\([\'"].*?[\'"],\s
*[\'"](?P<ec>.{32})[\'"]', webpage)
2865 or re.search(r'OO\
.Player\
.create\
.apply\
(\s
*OO\
.Player\s
*,\s
*op\
(\s
*\
[\s
*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P
<ec
>.{32}
)[\'"]', webpage)
2866 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P
<ec
>.{32}
)[\'"]\)', webpage)
2867 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P
<ec
>.{32}
)[\'"]', webpage))
2868 if mobj is not None:
2869 embed_token = self._search_regex(
2870 r'embedToken[\'"]?\s
*:\s
*[\'"]([^\'"]+)',
2871 webpage, 'ooyala embed token
', default=None)
2872 return OoyalaIE._build_url_result(smuggle_url(
2875 'embed_token
': embed_token,
2878 # Look for multiple Ooyala embeds on SBN network websites
2879 mobj = re.search(r'SBN\
.VideoLinkset\
.entryGroup\
((\
[.*?\
])', webpage)
2880 if mobj is not None:
2881 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2883 return self.playlist_from_matches(
2884 embeds, video_id, video_title,
2885 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id
'], {'domain': url})), ie='Ooyala
')
2887 # Look for Aparat videos
2888 mobj = re.search(r'<iframe
.*?src
="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2889 if mobj is not None:
2890 return self.url_result(mobj.group(1), 'Aparat')
2892 # Look for MPORA videos
2893 mobj = re.search(r'<iframe .*?src="(http
://mpora\
.(?
:com|de
)/videos
/[^
"]+)"', webpage)
2894 if mobj is not None:
2895 return self.url_result(mobj.group(1), 'Mpora
')
2897 # Look for embedded Facebook player
2898 facebook_urls = FacebookIE._extract_urls(webpage)
2900 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2902 # Look for embedded VK player
2903 mobj = re.search(r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2904 if mobj is not None:
2905 return self.url_result(mobj.group('url'), 'VK')
2907 # Look for embedded Odnoklassniki player
2908 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2909 if odnoklassniki_url:
2910 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2912 # Look for sibnet embedded player
2913 sibnet_urls = VKIE._extract_sibnet_urls(webpage)
2915 return self.playlist_from_matches(sibnet_urls, video_id, video_title)
2917 # Look for embedded ivi player
2918 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P
<url
>https?
://(?
:www\
.)?ivi\
.ru
/video
/player
.+?
)\
1', webpage)
2919 if mobj is not None:
2920 return self.url_result(mobj.group('url
'), 'Ivi
')
2922 # Look for embedded Huffington Post player
2924 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2925 if mobj is not None:
2926 return self.url_result(mobj.group('url'), 'HuffPost')
2929 mobj = re.search(r'class=["\']embedly
-card
["\'][^>]href=["\'](?P
<url
>[^
"\']+)', webpage)
2930 if mobj is not None:
2931 return self.url_result(mobj.group('url'))
2932 mobj = re.search(r'class=["\']embedly
-embed
["\'][^>]src=["\'][^
"\']*url=(?P<url>[^&]+)', webpage)
2933 if mobj is not None:
2934 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2936 # Look for funnyordie embed
2937 matches = re.findall(r'<iframe[^>]+?src="(https?
://(?
:www\
.)?funnyordie\
.com
/embed
/[^
"]+)"', webpage)
2939 return self.playlist_from_matches(
2940 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie
')
2942 # Look for Simplecast embeds
2943 simplecast_urls = SimplecastIE._extract_urls(webpage)
2945 return self.playlist_from_matches(
2946 simplecast_urls, video_id, video_title)
2948 # Look for BBC iPlayer embed
2949 matches = re.findall(r'setPlaylist\
("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\
)', webpage)
2951 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk
')
2953 # Look for embedded RUTV player
2954 rutv_url = RUTVIE._extract_url(webpage)
2956 return self.url_result(rutv_url, 'RUTV
')
2958 # Look for embedded TVC player
2959 tvc_url = TVCIE._extract_url(webpage)
2961 return self.url_result(tvc_url, 'TVC
')
2963 # Look for embedded SportBox player
2964 sportbox_urls = SportBoxIE._extract_urls(webpage)
2966 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2968 # Look for embedded XHamster player
2969 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2971 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed
')
2973 # Look for embedded TNAFlixNetwork player
2974 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2976 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2978 # Look for embedded PornHub player
2979 pornhub_urls = PornHubIE._extract_urls(webpage)
2981 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2983 # Look for embedded DrTuber player
2984 drtuber_urls = DrTuberIE._extract_urls(webpage)
2986 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2988 # Look for embedded RedTube player
2989 redtube_urls = RedTubeIE._extract_urls(webpage)
2991 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2993 # Look for embedded Tube8 player
2994 tube8_urls = Tube8IE._extract_urls(webpage)
2996 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2998 # Look for embedded Mofosex player
2999 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
3001 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
3003 # Look for embedded Spankwire player
3004 spankwire_urls = SpankwireIE._extract_urls(webpage)
3006 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
3008 # Look for embedded YouPorn player
3009 youporn_urls = YouPornIE._extract_urls(webpage)
3011 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
3013 # Look for embedded Tvigle player
3015 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
3016 if mobj is not None:
3017 return self.url_result(mobj.group('url'), 'Tvigle')
3019 # Look for embedded TED player
3021 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://embed(?
:-ssl
)?\
.ted\
.com
/.+?
)\
1', webpage)
3022 if mobj is not None:
3023 return self.url_result(mobj.group('url
'), 'TED
')
3025 # Look for embedded Ustream videos
3026 ustream_url = UstreamIE._extract_url(webpage)
3028 return self.url_result(ustream_url, UstreamIE.ie_key())
3030 # Look for embedded arte.tv player
3031 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
3033 return self.playlist_from_matches(arte_urls, video_id, video_title)
3035 # Look for embedded francetv player
3037 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
3039 if mobj is not None:
3040 return self.url_result(mobj.group('url'))
3042 # Look for embedded Myvi.ru player
3043 myvi_url = MyviIE._extract_url(webpage)
3045 return self.url_result(myvi_url)
3047 # Look for embedded soundcloud player
3048 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
3050 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
3052 # Look for tunein player
3053 tunein_urls = TuneInBaseIE._extract_urls(webpage)
3055 return self.playlist_from_matches(tunein_urls, video_id, video_title)
3057 # Look for embedded mtvservices player
3058 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
3060 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
3062 # Look for embedded yahoo player
3064 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://(?
:screen|movies
)\
.yahoo\
.com
/.+?\
.html
\?format
=embed
)\
1',
3066 if mobj is not None:
3067 return self.url_result(mobj.group('url
'), 'Yahoo
')
3069 # Look for embedded sbs.com.au player
3073 <meta\s+property="og:video"\s+content=|
3076 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
3078 if mobj is not None:
3079 return self.url_result(mobj.group('url
'), 'SBS
')
3081 # Look for embedded Cinchcast player
3083 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
3085 if mobj is not None:
3086 return self.url_result(mobj.group('url'), 'Cinchcast')
3089 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://m(?
:lb
)?\
.mlb\
.com
/shared
/video
/embed
/embed\
.html
\?.+?
)\
1',
3093 r'data
-video
-link
=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
3095 if mobj is not None:
3096 return self.url_result(mobj.group('url
'), 'MLB
')
3099 r'<(?
:iframe|script
)[^
>]+?src
=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
3101 if mobj is not None:
3102 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
3105 r'<iframe[^>]+src="(?P
<url
>https?
://(?
:new\
.)?livestream\
.com
/[^
"]+/player[^"]+)"',
3107 if mobj is not None:
3108 return self.url_result(mobj.group('url'), 'Livestream')
3110 # Look for Zapiks embed
3112 r'<iframe[^>]+src="(?P
<url
>https?
://(?
:www\
.)?zapiks\
.fr
/index\
.php
\?.+?
)"', webpage)
3113 if mobj is not None:
3114 return self.url_result(mobj.group('url'), 'Zapiks')
3116 # Look for Kaltura embeds
3117 kaltura_urls = KalturaIE._extract_urls(webpage)
3119 return self.playlist_from_matches(
3120 kaltura_urls, video_id, video_title,
3121 getter=lambda x: smuggle_url(x, {'source_url': url}),
3122 ie=KalturaIE.ie_key())
3124 # Look for EaglePlatform embeds
3125 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
3126 if eagleplatform_url:
3127 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
3129 # Look for ClipYou (uses EaglePlatform) embeds
3131 r'<iframe[^>]+src="https?
://(?P
<host
>media\
.clipyou\
.ru
)/index
/player
\?.*\brecord
_id
=(?P
<id>\d
+).*"', webpage)
3132 if mobj is not None:
3133 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
3135 # Look for Pladform embeds
3136 pladform_url = PladformIE._extract_url(webpage)
3138 return self.url_result(pladform_url)
3140 # Look for Videomore embeds
3141 videomore_url = VideomoreIE._extract_url(webpage)
3143 return self.url_result(videomore_url)
3145 # Look for Webcaster embeds
3146 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3148 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3150 # Look for Playwire embeds
3152 r'<script[^>]+data-config=(["\'])(?P
<url
>(?
:https?
:)?
//config\
.playwire\
.com
/.+?
)\
1', webpage)
3153 if mobj is not None:
3154 return self.url_result(mobj.group('url
'))
3156 # Look for 5min embeds
3158 r'<meta
[^
>]+property="og:video"[^
>]+content
="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3159 if mobj is not None:
3160 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3162 # Look for Crooks and Liars embeds
3164 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P
<url
>(?
:https?
:)?
//embed\
.crooksandliars\
.com
/(?
:embed|v
)/.+?
)\
1', webpage)
3165 if mobj is not None:
3166 return self.url_result(mobj.group('url
'))
3168 # Look for NBC Sports VPlayer embeds
3169 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3171 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer
')
3173 # Look for NBC News embeds
3174 nbc_news_embed_url = re.search(
3175 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\
1', webpage)
3176 if nbc_news_embed_url:
3177 return self.url_result(nbc_news_embed_url.group('url
'), 'NBCNews
')
3179 # Look for Google Drive embeds
3180 google_drive_url = GoogleDriveIE._extract_url(webpage)
3181 if google_drive_url:
3182 return self.url_result(google_drive_url, 'GoogleDrive
')
3184 # Look for UDN embeds
3186 r'<iframe
[^
>]+src
="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
3187 if mobj is not None:
3188 return self.url_result(
3189 compat_urlparse.urljoin(url, mobj.group('url
')), 'UDNEmbed
')
3191 # Look for Senate ISVP iframe
3192 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3194 return self.url_result(senate_isvp_url, 'SenateISVP
')
3196 # Look for Kinja embeds
3197 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3198 if kinja_embed_urls:
3199 return self.playlist_from_matches(
3200 kinja_embed_urls, video_id, video_title)
3202 # Look for OnionStudios embeds
3203 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3204 if onionstudios_url:
3205 return self.url_result(onionstudios_url)
3207 # Look for ViewLift embeds
3208 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3210 return self.url_result(viewlift_url)
3212 # Look for JWPlatform embeds
3213 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3215 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
3217 # Look for Digiteka embeds
3218 digiteka_url = DigitekaIE._extract_url(webpage)
3220 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
3222 # Look for Arkena embeds
3223 arkena_url = ArkenaIE._extract_url(webpage)
3225 return self.url_result(arkena_url, ArkenaIE.ie_key())
3227 # Look for Piksel embeds
3228 piksel_url = PikselIE._extract_url(webpage)
3230 return self.url_result(piksel_url, PikselIE.ie_key())
3232 # Look for Limelight embeds
3233 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3235 return self.playlist_result(
3236 limelight_urls, video_id, video_title, video_description)
3238 # Look for Anvato embeds
3239 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3241 return self.playlist_result(
3242 anvato_urls, video_id, video_title, video_description)
3244 # Look for AdobeTVVideo embeds
3246 r'<iframe
[^
>]+src
=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3248 if mobj is not None:
3249 return self.url_result(
3250 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3253 # Look for Vine embeds
3255 r'<iframe[^>]+src=[\'"]((?
:https?
:)?
//(?
:www\
.)?vine\
.co
/v
/[^
/]+/embed
/(?
:simple|postcard
))',
3257 if mobj is not None:
3258 return self.url_result(
3259 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine
')
3261 # Look for VODPlatform embeds
3263 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
3265 if mobj is not None:
3266 return self.url_result(
3267 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
3269 # Look for Mangomolo embeds
3271 r'''(?x)<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//
3273 admin\
.mangomolo\
.com
/analytics
/index\
.php
/customers
/embed|
3274 player\
.mangomolo\
.com
/v1
3277 video
\?.*?
\bid
=(?P
<video_id
>\d
+)|
3278 (?
:index|live
)\?.*?
\bchannelid
=(?P
<channel_id
>(?
:[A
-Za
-z0
-9+/=]|
%2B|
%2F|
%3D
)+)
3279 ).+?
)\
1''', webpage)
3280 if mobj is not None:
3282 '_type': 'url_transparent',
3283 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3284 'title': video_title,
3285 'description': video_description,
3286 'thumbnail': video_thumbnail,
3287 'uploader': video_uploader,
3289 video_id = mobj.group('video_id')
3292 'ie_key': 'MangomoloVideo',
3297 'ie_key': 'MangomoloLive',
3298 'id': mobj.group('channel_id'),
3302 # Look for Instagram embeds
3303 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3304 if instagram_embed_url is not None:
3305 return self.url_result(
3306 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3308 # Look for 3Q SDN embeds
3309 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3312 '_type': 'url_transparent',
3313 'ie_key': ThreeQSDNIE.ie_key(),
3314 'url': self._proto_relative_url(threeqsdn_url),
3315 'title': video_title,
3316 'description': video_description,
3317 'thumbnail': video_thumbnail,
3318 'uploader': video_uploader,
3321 # Look for VBOX7 embeds
3322 vbox7_url = Vbox7IE._extract_url(webpage)
3324 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3326 # Look for DBTV embeds
3327 dbtv_urls = DBTVIE._extract_urls(webpage)
3329 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3331 # Look for Videa embeds
3332 videa_urls = VideaIE._extract_urls(webpage)
3334 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3336 # Look for 20 minuten embeds
3337 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3339 return self.playlist_from_matches(
3340 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3342 # Look for VideoPress embeds
3343 videopress_urls = VideoPressIE._extract_urls(webpage)
3345 return self.playlist_from_matches(
3346 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3348 # Look for Rutube embeds
3349 rutube_urls = RutubeIE._extract_urls(webpage)
3351 return self.playlist_from_matches(
3352 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3354 # Look for WashingtonPost embeds
3355 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3357 return self.playlist_from_matches(
3358 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3360 # Look for Mediaset embeds
3361 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3363 return self.playlist_from_matches(
3364 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3366 # Look for JOJ.sk embeds
3367 joj_urls = JojIE._extract_urls(webpage)
3369 return self.playlist_from_matches(
3370 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3372 # Look for megaphone.fm embeds
3373 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3375 return self.playlist_from_matches(
3376 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3378 # Look for vzaar embeds
3379 vzaar_urls = VzaarIE._extract_urls(webpage)
3381 return self.playlist_from_matches(
3382 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3384 channel9_urls = Channel9IE._extract_urls(webpage)
3386 return self.playlist_from_matches(
3387 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3389 vshare_urls = VShareIE._extract_urls(webpage)
3391 return self.playlist_from_matches(
3392 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3394 # Look for Mediasite embeds
3395 mediasite_urls = MediasiteIE._extract_urls(webpage)
3398 self.url_result(smuggle_url(
3399 compat_urlparse.urljoin(url, mediasite_url),
3400 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3401 for mediasite_url in mediasite_urls]
3402 return self.playlist_result(entries, video_id, video_title)
3404 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3405 if springboardplatform_urls:
3406 return self.playlist_from_matches(
3407 springboardplatform_urls, video_id, video_title,
3408 ie=SpringboardPlatformIE.ie_key())
3410 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3412 return self.playlist_from_matches(
3413 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3415 vice_urls = ViceIE._extract_urls(webpage)
3417 return self.playlist_from_matches(
3418 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3420 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3422 return self.playlist_from_matches(
3423 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3425 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3426 if cloudflarestream_urls:
3427 return self.playlist_from_matches(
3428 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3430 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3432 return self.playlist_from_matches(
3433 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3435 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3437 return self.playlist_from_matches(
3438 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3440 apa_urls = APAIE._extract_urls(webpage)
3442 return self.playlist_from_matches(
3443 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3445 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3447 return self.playlist_from_matches(
3448 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3450 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3451 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3453 if sharevideos_urls:
3454 return self.playlist_from_matches(
3455 sharevideos_urls, video_id, video_title)
3457 viqeo_urls = ViqeoIE._extract_urls(webpage)
3459 return self.playlist_from_matches(
3460 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3462 expressen_urls = ExpressenIE._extract_urls(webpage)
3464 return self.playlist_from_matches(
3465 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3467 zype_urls = ZypeIE._extract_urls(webpage)
3469 return self.playlist_from_matches(
3470 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3472 gedi_urls = GediDigitalIE._extract_urls(webpage)
3474 return self.playlist_from_matches(
3475 gedi_urls, video_id, video_title, ie=GediDigitalIE.ie_key())
3477 # Look for RCS media group embeds
3478 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3480 return self.playlist_from_matches(
3481 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3483 wimtv_urls = WimTVIE._extract_urls(webpage)
3485 return self.playlist_from_matches(
3486 wimtv_urls, video_id, video_title, ie=WimTVIE.ie_key())
3488 bitchute_urls = BitChuteIE._extract_urls(webpage)
3490 return self.playlist_from_matches(
3491 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3493 rumble_urls = RumbleEmbedIE._extract_urls(webpage)
3494 if len(rumble_urls) == 1:
3495 return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
3497 return self.playlist_from_matches(
3498 rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
3500 # Look for HTML5 media
3501 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3503 if len(entries) == 1:
3506 'title': video_title,
3509 for num, entry in enumerate(entries, start=1):
3511 'id': '%s-%s' % (video_id, num),
3512 'title': '%s (%d)' % (video_title, num),
3514 for entry in entries:
3515 self._sort_formats(entry['formats'])
3516 return self.playlist_result(entries, video_id, video_title)
3518 jwplayer_data = self._find_jwplayer_data(
3519 webpage, video_id, transform_source=js_to_json)
3521 if isinstance(jwplayer_data.get('playlist'), str):
3525 'ie_key': JWPlatformIE.ie_key(),
3526 'url': jwplayer_data['playlist'],
3529 info = self._parse_jwplayer_data(
3530 jwplayer_data, video_id, require_title=False, base_url=url)
3531 return merge_dicts(info, info_dict)
3532 except ExtractorError:
3533 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3538 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3540 if mobj is not None:
3541 sources = self._parse_json(
3542 mobj.group(1), video_id, transform_source=js_to_json,
3544 if not isinstance(sources, list):
3548 for source in sources:
3549 src = source.get('src')
3550 if not src or not isinstance(src, compat_str):
3552 src = compat_urlparse.urljoin(url, src)
3553 src_type = source.get('type')
3554 if isinstance(src_type, compat_str):
3555 src_type = src_type.lower()
3556 ext = determine_ext(src).lower()
3557 if src_type == 'video/youtube':
3558 return self.url_result(src, YoutubeIE.ie_key())
3559 if src_type == 'application/dash+xml' or ext == 'mpd':
3560 fmts, subs = self._extract_mpd_formats_and_subtitles(
3561 src, video_id, mpd_id='dash', fatal=False)
3562 formats.extend(fmts)
3563 self._merge_subtitles(subs, target=subtitles)
3564 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3565 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3566 src, video_id, 'mp4', entry_protocol='m3u8_native',
3567 m3u8_id='hls', fatal=False)
3568 formats.extend(fmts)
3569 self._merge_subtitles(subs, target=subtitles)
3573 'ext': (mimetype2ext(src_type)
3574 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3576 'Referer': full_response.geturl(),
3579 if formats or subtitles:
3580 self._sort_formats(formats)
3581 info_dict['formats'] = formats
3582 info_dict['subtitles'] = subtitles
3585 # Looking for http://schema.org/VideoObject
3586 json_ld = self._search_json_ld(webpage, video_id, default={})
3587 if json_ld.get('url'):
3588 return merge_dicts(json_ld, info_dict)
3590 def check_video(vurl):
3591 if YoutubeIE.suitable(vurl):
3593 if RtmpIE.suitable(vurl):
3595 vpath = compat_urlparse.urlparse(vurl).path
3596 vext = determine_ext(vpath)
3597 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3599 def filter_video(urls):
3600 return list(filter(check_video, urls))
3602 # Start with something easy: JW Player in SWFObject
3603 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3605 # Look for gorilla-vid style embedding
3606 found = filter_video(re.findall(r'''(?sx
)
3610 jwplayer\s
*\
(\s
*["'][^'"]+["']\s*\)\s*\.setup
3613 ['"]?
file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3615 # Look for generic KVS player
3616 found = re.search(r'<script
[^
>]*?src
="https://.+?/kt_player\.js\?v=(?P<ver>(?P<maj_ver>\d+)(\.\d+)+)".*?
>', webpage)
3618 if found.group('maj_ver
') not in ['4', '5']:
3619 self.report_warning('Untested major
version (%s) in player engine
--Download may fail
.' % found.group('ver
'))
3620 flashvars = re.search(r'(?ms
)<script
.*?
>.*?var\s
+flashvars\s
*=\s
*(\{.*?\}
);.*?
</script
>', webpage)
3621 flashvars = self._parse_json(flashvars.group(1), video_id, transform_source=js_to_json)
3623 # extract the part after the last / as the display_id from the
3625 display_id = self._search_regex(
3626 r'(?
:<link href
="https?://[^"]+/(.+?
)/?
" rel="canonical
"\s*/?>'
3627 r'|<link rel="canonical
" href="https?
://[^
"]+/(.+?)/?"\s
*/?
>)',
3628 webpage, 'display_id
', fatal=False
3630 title = self._html_search_regex(r'<(?
:h1|title
)>(?
:Video
: )?
(.+?
)</(?
:h1|title
)>', webpage, 'title
')
3632 thumbnail = flashvars['preview_url
']
3633 if thumbnail.startswith('//'):
3634 protocol, _, _ = url.partition('/')
3635 thumbnail = protocol + thumbnail
3638 for key in ('video_url
', 'video_alt_url
', 'video_alt_url2
'):
3639 if key in flashvars and '/get_file
/' in flashvars[key]:
3641 'url
': self._kvs_getrealurl(flashvars[key], flashvars['license_code
']),
3642 'format_id
': flashvars.get(key + '_text
', key),
3645 height = re.search(r'%s_(\d
+)p\
.mp4(?
:/[?
].*)?$
' % flashvars['video_id
'], flashvars[key])
3647 next_format['height
'] = int(height.group(1))
3649 next_format['quality
'] = 1
3650 formats.append(next_format)
3651 self._sort_formats(formats)
3654 'id': flashvars['video_id
'],
3655 'display_id
': display_id,
3657 'thumbnail
': thumbnail,
3661 # Broaden the search a little bit
3662 found = filter_video(re.findall(r'[^A
-Za
-z0
-9]?
(?
:file|source
)=(http
[^
\'"&]*)', webpage))
3664 # Broaden the findall a little bit: JWPlayer JS loader
3665 found = filter_video(re.findall(
3666 r'[^A-Za-z0-9]?(?:file|video_url)["\']?
:\s
*["\'](http(?![^\'"]+\
.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3669 found = filter_video(re.findall(r'''(?xs)
3670 flowplayer\("[^
"]+",\s
*
3672 \s
*\{[^}
]+?
["']?clip["']?\s*:\s*\{\s*
3673 ["']?url
["']?\s*:\s*["']([^"']+)["']
3678 r"cinerama\
.embedPlayer\
(\s
*\'[^
']+\',\s*'([^
']+)'", webpage)
3680 # Try to find twitter cards info
3681 # twitter:player:stream should be checked before twitter:player since
3682 # it is expected to contain a raw stream (see
3683 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3684 found = filter_video(re.findall(
3685 r'<meta (?:property|name)="twitter
:player
:stream
" (?:content|value)="(.+?
)"', webpage))
3687 # We look for Open Graph info:
3688 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3689 m_video_type = re.findall(r'<meta.*?property="og
:video
:type".*?content="video
/(.*?
)"', webpage)
3690 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3691 if m_video_type is not None:
3692 found = filter_video(re.findall(r'<meta.*?property="og
:(?
:video|audio
)".*?content="(.*?
)"', webpage))
3694 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3696 r'(?i
)<meta\s
+(?
=(?
:[a
-z
-]+="[^"]+"\s+)*http-equiv="refresh
")'
3697 r'(?:[a-z-]+="[^
"]+"\s
+)*?content
="%s' % REDIRECT_REGEX,
3700 # Look also in Refresh HTTP header
3701 refresh_header = head_response.headers.get('Refresh')
3703 # In python 2 response HTTP headers are bytestrings
3704 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3705 refresh_header = refresh_header.decode('iso-8859-1')
3706 found = re.search(REDIRECT_REGEX, refresh_header)
3708 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3710 self.report_following_redirect(new_url)
3719 # twitter:player is a https URL to iframe player that may or may not
3720 # be supported by yt-dlp thus this is checked the very last (see
3721 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3722 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3723 if embed_url and embed_url != url:
3724 return self.url_result(embed_url)
3727 raise UnsupportedError(url)
3730 for video_url in orderedSet(found):
3731 video_url = unescapeHTML(video_url)
3732 video_url = video_url.replace('\\/', '/')
3733 video_url = compat_urlparse.urljoin(url, video_url)
3734 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3736 # Sometimes, jwplayer extraction will result in a YouTube URL
3737 if YoutubeIE.suitable(video_url):
3738 entries.append(self.url_result(video_url, 'Youtube'))
3741 # here's a fun little line of code for you:
3742 video_id = os.path.splitext(video_id)[0]
3746 'uploader': video_uploader,
3747 'title': video_title,
3748 'age_limit': age_limit,
3751 if RtmpIE.suitable(video_url):
3752 entry_info_dict.update({
3753 '_type': 'url_transparent',
3754 'ie_key': RtmpIE.ie_key(),
3757 entries.append(entry_info_dict)
3760 ext = determine_ext(video_url)
3762 entry_info_dict = {**self._extract_smil_info(video_url, video_id), **entry_info_dict}
3764 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3766 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(video_url, video_id, ext='mp4')
3768 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_mpd_formats_and_subtitles(video_url, video_id)
3770 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3771 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3772 # Just matching .ism/manifest is not enough to be reliably sure
3773 # whether it's actually an ISM manifest or some other streaming
3774 # manifest since there are various streaming URL formats
3775 # possible (see [1]) as well as some other shenanigans like
3776 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3778 # Thus the most reasonable way to solve this is to delegate
3779 # to generic extractor in order to look into the contents of
3780 # the manifest itself.
3781 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3782 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3783 entry_info_dict = self.url_result(
3784 smuggle_url(video_url, {'to_generic': True}),
3787 entry_info_dict['url'] = video_url
3789 if entry_info_dict.get('formats'):
3790 self._sort_formats(entry_info_dict['formats'])
3792 entries.append(entry_info_dict)
3794 if len(entries) == 1:
3797 for num, e in enumerate(entries, start=1):
3798 # 'url' results don't have a title
3799 if e.get('title') is not None:
3800 e['title'] = '%s (%d)' % (e['title'], num)
3802 '_type': 'playlist',