]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/generic.py
[adobepass] Add MSO Sling TV (#596)
[yt-dlp.git] / yt_dlp / extractor / generic.py
CommitLineData
dcdb292f 1# coding: utf-8
cfe50f04 2
79649588
PH
3from __future__ import unicode_literals
4
9b122384
PH
5import os
6import re
6c91a5a7 7import sys
9b122384
PH
8
9from .common import InfoExtractor
fc9713a1 10from .youtube import YoutubeIE
8c25f81b 11from ..compat import (
f7854627 12 compat_etree_fromstring,
4e363703 13 compat_str,
1ddb9456 14 compat_urllib_parse_unquote,
a5caba1e 15 compat_urlparse,
f7300c5c 16 compat_xml_parse_error,
8c25f81b
PH
17)
18from ..utils import (
b759a0d4 19 determine_ext,
9b122384 20 ExtractorError,
c8e9a235 21 float_or_none,
aa94a6d3 22 HEADRequest,
c76eb41b 23 int_or_none,
61ca9a80 24 is_html,
a4a554a7 25 js_to_json,
63d990d2 26 KNOWN_EXTENSIONS,
6cc62232 27 merge_dicts,
63d990d2 28 mimetype2ext,
ed2d6a19 29 orderedSet,
c76eb41b 30 parse_duration,
5c2266df 31 sanitized_Request,
9d4660ca
PH
32 smuggle_url,
33 unescapeHTML,
29f7c58a 34 unified_timestamp,
4d54ef20 35 unsmuggle_url,
416c7fcb 36 UnsupportedError,
29f7c58a 37 url_or_none,
38 xpath_attr,
76c73715 39 xpath_text,
c76eb41b 40 xpath_with_ns,
9b122384 41)
b7a8c1bc 42from .commonprotocols import RtmpIE
ed126900 43from .brightcove import (
4fcaa4f4 44 BrightcoveLegacyIE,
5c17f0a6 45 BrightcoveNewIE,
ed126900 46)
3f59b015
S
47from .nexx import (
48 NexxIE,
49 NexxEmbedIE,
50)
a2edf2e7 51from .nbc import NBCSportsVPlayerIE
c0d0b01f 52from .ooyala import OoyalaIE
93d020dd 53from .rutv import RUTVIE
954c1d05 54from .tvc import TVCIE
476cf548 55from .sportbox import SportBoxIE
6dd94d3a 56from .myvi import MyviIE
1419fafd 57from .condenast import CondeNastIE
418c5cc3 58from .udn import UDNEmbedIE
2fe1b5bd 59from .senateisvp import SenateISVPIE
bab19a8e 60from .svt import SVTIE
65d161c4 61from .pornhub import PornHubIE
2bb5b6d0 62from .xhamster import XHamsterEmbedIE
2c9ca782 63from .tnaflix import TNAFlixNetworkEmbedIE
37e7a71c 64from .drtuber import DrTuberIE
e28ed498 65from .redtube import RedTubeIE
06993715 66from .tube8 import Tube8IE
4e7b5bba 67from .mofosex import MofosexEmbedIE
8fae1a04 68from .spankwire import SpankwireIE
52c4c515 69from .youporn import YouPornIE
29f7c58a 70from .vimeo import (
71 VimeoIE,
72 VHXEmbedIE,
73)
3c4fbfec 74from .dailymotion import DailymotionIE
71a1db89 75from .dailymail import DailyMailIE
1ac1c4c2 76from .onionstudios import OnionStudiosIE
67167920 77from .viewlift import ViewLiftEmbedIE
46fde8a1 78from .mtv import MTVServicesEmbeddedIE
45dad7ba 79from .pladform import PladformIE
ff18735c 80from .videomore import VideomoreIE
83f1481b 81from .webcaster import WebcasterFeedIE
5b251628 82from .googledrive import GoogleDriveIE
7cb09524 83from .jwplatform import JWPlatformIE
aecfcd4e 84from .digiteka import DigitekaIE
1979969f 85from .arkena import ArkenaIE
5a51775a 86from .instagram import InstagramIE
5d39176f 87from .threeqsdn import ThreeQSDNIE
4d8819d2 88from .theplatform import ThePlatformIE
c287f2bc 89from .kaltura import KalturaIE
06a96da1 90from .eagleplatform import EaglePlatformIE
fd6ca382 91from .facebook import FacebookIE
548c3957 92from .soundcloud import SoundcloudEmbedIE
027e2312 93from .tunein import TuneInBaseIE
2a1321a2 94from .vbox7 import Vbox7IE
b0c8f2e9 95from .dbtv import DBTVIE
b1c35797 96from .piksel import PikselIE
e186a9ec 97from .videa import VideaIE
b687c85e 98from .twentymin import TwentyMinutenIE
d77ac737 99from .ustream import UstreamIE
8bdd16b4 100from .arte import ArteTVEmbedIE
6ef3e65a 101from .videopress import VideoPressIE
eb3079b6 102from .rutube import RutubeIE
e5d39886 103from .limelight import LimelightBaseIE
7986c3ab 104from .anvato import AnvatoIE
55719459 105from .washingtonpost import WashingtonPostIE
58bb4402 106from .wistia import WistiaIE
5d29af3d 107from .mediaset import MediasetIE
73cf76a9 108from .joj import JojIE
24e966e8 109from .megaphone import MegaphoneIE
41918eaa 110from .vzaar import VzaarIE
26bae2d9 111from .channel9 import Channel9IE
0987f2dd 112from .vshare import VShareIE
2ca7ed41 113from .mediasite import MediasiteIE
7d540621 114from .springboardplatform import SpringboardPlatformIE
4c780fbd 115from .yapfiles import YapFilesIE
86c8cfc5 116from .vice import ViceIE
178ee883 117from .xfileshare import XFileShareIE
660a230b 118from .cloudflarestream import CloudflareStreamIE
6bd499e8 119from .peertube import PeerTubeIE
5ee7ae5c 120from .teachable import TeachableIE
aee36ca8 121from .indavideo import IndavideoEmbedIE
cfd7f2a6 122from .apa import APAIE
f51f526b 123from .foxnews import FoxNewsIE
9d1b2138 124from .viqeo import ViqeoIE
57c68ec4 125from .expressen import ExpressenIE
83852e57 126from .zype import ZypeIE
416c3ca7 127from .odnoklassniki import OdnoklassnikiIE
b73612a2 128from .vk import VKIE
55adb63e 129from .kinja import KinjaEmbedIE
feee67ae 130from .gedidigital import GediDigitalIE
a85e131b 131from .rcs import RCSEmbedsIE
097f1663 132from .bitchute import BitChuteIE
62852977 133from .rumble import RumbleEmbedIE
29f7c58a 134from .arcpublishing import ArcPublishingIE
2181983a 135from .medialaan import MedialaanIE
bc2ca1bb 136from .simplecast import SimplecastIE
e4edeb62 137from .wimtv import WimTVIE
9b122384 138
0838239e 139
9b122384 140class GenericIE(InfoExtractor):
79649588 141 IE_DESC = 'Generic downloader that works on some sites'
9b122384 142 _VALID_URL = r'.*'
79649588 143 IE_NAME = 'generic'
cfe50f04 144 _TESTS = [
c5fa81fe
S
145 # Direct link to a video
146 {
147 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
148 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
149 'info_dict': {
150 'id': 'trailer',
151 'ext': 'mp4',
152 'title': 'trailer',
153 'upload_date': '20100513',
154 }
155 },
c5138a7c 156 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
157 {
158 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
159 'md5': '128c42e68b13950268b648275386fc74',
160 'info_dict': {
161 'id': 'FictionJunction-Parallel_Hearts',
162 'ext': 'flac',
163 'title': 'FictionJunction-Parallel_Hearts',
164 'upload_date': '20140522',
165 },
166 'expected_warnings': [
167 'URL could be a direct video link, returning it as such.'
39efc6e3
YCH
168 ],
169 'skip': 'URL invalid',
c5fa81fe
S
170 },
171 # Direct download with broken HEAD
172 {
173 'url': 'http://ai-radio.org:8000/radio.opus',
174 'info_dict': {
175 'id': 'radio',
176 'ext': 'opus',
177 'title': 'radio',
178 },
179 'params': {
180 'skip_download': True, # infinite live stream
181 },
182 'expected_warnings': [
ef0e4e7b
YCH
183 r'501.*Not Implemented',
184 r'400.*Bad Request',
c5fa81fe
S
185 ],
186 },
187 # Direct link with incorrect MIME type
188 {
189 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
190 'md5': '4ccbebe5f36706d85221f204d7eb5913',
191 'info_dict': {
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',
194 'ext': 'webm',
195 'title': '5_Lennart_Poettering_-_Systemd',
196 'upload_date': '20141120',
197 },
198 'expected_warnings': [
199 'URL could be a direct video link, returning it as such.'
200 ]
201 },
202 # RSS feed
203 {
204 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
205 'info_dict': {
206 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
207 'title': 'Zero Punctuation',
208 'description': 're:.*groundbreaking video review series.*'
209 },
210 'playlist_mincount': 11,
211 },
212 # RSS feed with enclosure
213 {
214 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
215 'info_dict': {
29f7c58a 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.*',
219 },
220 'playlist': [{
221 'info_dict': {
222 'ext': 'mov',
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',
227 },
228 }],
229 },
230 # RSS feed with item with description and thumbnails
231 {
232 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
233 'info_dict': {
234 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
235 'title': 're:.*100% Hydrogen.*',
236 'description': 're:.*In this episode.*',
237 },
238 'playlist': [{
239 'info_dict': {
240 'ext': 'm4a',
241 'id': 'c1c879525ce2cb640b344507e682c36d',
242 'title': 're:Hydrogen!',
243 'description': 're:.*In this episode we are going.*',
244 'timestamp': 1567977776,
245 'upload_date': '20190908',
246 'duration': 459,
247 'thumbnail': r're:^https?://.*\.jpg$',
248 'episode_number': 1,
249 'season_number': 1,
250 'age_limit': 0,
251 },
252 }],
253 'params': {
254 'skip_download': True,
255 },
c5fa81fe 256 },
01aec848
BG
257 # RSS feed with enclosures and unsupported link URLs
258 {
259 'url': 'http://www.hellointernet.fm/podcast?format=rss',
260 'info_dict': {
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',
264 },
265 'playlist_mincount': 100,
266 },
8765222d
S
267 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
268 {
269 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
270 'info_dict': {
271 'id': 'smil',
272 'ext': 'mp4',
273 'title': 'Automatics, robotics and biocybernetics',
274 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 275 'upload_date': '20130627',
8765222d
S
276 'formats': 'mincount:16',
277 'subtitles': 'mincount:1',
278 },
279 'params': {
280 'force_generic_extractor': True,
281 'skip_download': True,
282 },
283 },
284 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
285 {
286 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
287 'info_dict': {
288 'id': 'hds',
289 'ext': 'flv',
290 'title': 'hds',
291 'formats': 'mincount:1',
292 },
293 'params': {
294 'skip_download': True,
295 },
296 },
297 # SMIL from https://www.restudy.dk/video/play/id/1637
298 {
299 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
300 'info_dict': {
301 'id': 'video_1637',
302 'ext': 'flv',
303 'title': 'video_1637',
304 'formats': 'mincount:3',
305 },
306 'params': {
307 'skip_download': True,
308 },
309 },
310 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
311 {
312 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
313 'info_dict': {
314 'id': 'smil-service',
315 'ext': 'flv',
316 'title': 'smil-service',
317 'formats': 'mincount:1',
318 },
319 'params': {
320 'skip_download': True,
321 },
322 },
323 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
324 {
325 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
326 'info_dict': {
327 'id': '4719370',
328 'ext': 'mp4',
329 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
330 'formats': 'mincount:3',
331 },
332 'params': {
333 'skip_download': True,
334 },
335 },
1de5cd3b
S
336 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
337 {
338 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
339 'info_dict': {
340 'id': 'mZlp2ctYIUEB',
341 'ext': 'mp4',
342 'title': 'Tikibad ontruimd wegens brand',
343 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
ec85ded8 344 'thumbnail': r're:^https?://.*\.jpg$',
1de5cd3b
S
345 'duration': 33,
346 },
347 'params': {
348 'skip_download': True,
349 },
350 },
9d939cec
S
351 # MPD from http://dash-mse-test.appspot.com/media.html
352 {
353 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
354 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
355 'info_dict': {
356 'id': 'car-20120827-manifest',
357 'ext': 'mp4',
358 'title': 'car-20120827-manifest',
359 'formats': 'mincount:9',
0738187f 360 'upload_date': '20130904',
9d939cec
S
361 },
362 'params': {
363 'format': 'bestvideo',
364 },
365 },
20938f76
S
366 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
367 {
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',
369 'info_dict': {
370 'id': 'content',
371 'ext': 'mp4',
372 'title': 'content',
373 'formats': 'mincount:8',
374 },
375 'params': {
376 # m3u8 downloads
377 'skip_download': True,
39efc6e3
YCH
378 },
379 'skip': 'video gone',
20938f76 380 },
edd9b71c
S
381 # m3u8 served with Content-Type: text/plain
382 {
383 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
384 'info_dict': {
385 'id': 'index',
386 'ext': 'mp4',
387 'title': 'index',
388 'upload_date': '20140720',
389 'formats': 'mincount:11',
390 },
391 'params': {
392 # m3u8 downloads
393 'skip_download': True,
39efc6e3
YCH
394 },
395 'skip': 'video gone',
edd9b71c 396 },
c5fa81fe
S
397 # google redirect
398 {
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',
400 'info_dict': {
401 'id': 'cmQHVoWB5FY',
402 'ext': 'mp4',
403 'upload_date': '20130224',
404 'uploader_id': 'TheVerge',
ec85ded8 405 'description': r're:^Chris Ziegler takes a look at the\.*',
c5fa81fe
S
406 'uploader': 'The Verge',
407 'title': 'First Firefox OS phones side-by-side',
408 },
409 'params': {
410 'skip_download': False,
411 }
412 },
6c91a5a7
S
413 {
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',
416 'info_dict': {
417 'id': 'pO8h3EaFRdo',
418 'ext': 'mp4',
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',
424 },
425 'params': {
426 'skip_download': False,
427 },
428 },
cfe50f04 429 {
79649588 430 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 431 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 432 'info_dict': {
d360a146
S
433 'id': '13601338388002',
434 'ext': 'mp4',
79649588
PH
435 'uploader': 'www.hodiho.fr',
436 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
437 }
438 },
c19f7764
JMF
439 # bandcamp page with custom domain
440 {
79649588
PH
441 'add_ie': ['Bandcamp'],
442 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 443 'info_dict': {
fd50bf62
S
444 'id': '3235767654',
445 'ext': 'mp3',
79649588
PH
446 'title': 'The Pony Mash',
447 'uploader': 'M_Pallante',
c19f7764 448 },
79649588 449 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 450 },
eeb165e6 451 {
53a664ed
S
452 # embedded brightcove video
453 # it also tests brightcove videos that need to set the 'Referer'
454 # in the http requests
3b7d9aa4 455 'add_ie': ['BrightcoveLegacy'],
79649588
PH
456 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
457 'info_dict': {
458 'id': '2765128793001',
459 'ext': 'mp4',
460 'title': 'Le cours de bourse : l’analyse technique',
461 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
462 'uploader': 'BFM BUSINESS',
eeb165e6 463 },
79649588
PH
464 'params': {
465 'skip_download': True,
eeb165e6
JMF
466 },
467 },
53a664ed
S
468 {
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/',
472 'info_dict': {
473 'id': '5255628253001',
474 'ext': 'mp4',
475 'title': 'md5:37c519b1128915607601e75a87995fc0',
476 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
477 'uploader': 'BFM BUSINESS',
478 'uploader_id': '876450612001',
479 'timestamp': 1482255315,
480 'upload_date': '20161220',
481 },
482 'params': {
483 'skip_download': True,
484 },
485 },
17ab4d3b 486 {
067aa17e 487 # https://github.com/ytdl-org/youtube-dl/issues/2253
17ab4d3b 488 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
489 'md5': '0ba9446db037002366bab3b3eb30c88c',
490 'info_dict': {
fd50bf62
S
491 'id': '3101154703001',
492 'ext': 'mp4',
17ab4d3b
PH
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.',
496 },
3b7d9aa4 497 'add_ie': ['BrightcoveLegacy'],
39efc6e3 498 'skip': 'video gone',
17ab4d3b 499 },
0479c625
S
500 {
501 'url': 'http://www.championat.com/video/football/v/87/87499.html',
502 'md5': 'fb973ecf6e4a78a67453647444222983',
503 'info_dict': {
504 'id': '3414141473001',
505 'ext': 'mp4',
506 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
507 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
508 'uploader': 'Championat',
509 },
510 },
bdf97017 511 {
067aa17e 512 # https://github.com/ytdl-org/youtube-dl/issues/3541
3b7d9aa4 513 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
514 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
515 'info_dict': {
516 'id': '3866516442001',
37aab278 517 'ext': 'mp4',
bdf97017
NJ
518 'title': 'Leer mij vrouwen kennen: Aflevering 1',
519 'description': 'Leer mij vrouwen kennen: Aflevering 1',
520 'uploader': 'SBS Broadcasting',
521 },
37aab278 522 'skip': 'Restricted to Netherlands',
bdf97017 523 'params': {
37aab278 524 'skip_download': True, # m3u8 download
bdf97017
NJ
525 },
526 },
06d0ad9a
YCH
527 {
528 # Brightcove video in <iframe>
529 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
530 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
531 'info_dict': {
532 'id': '5360463607001',
533 'ext': 'mp4',
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',
540 },
541 'add_ie': ['BrightcoveLegacy'],
542 },
16e2c8f7
YCH
543 {
544 # Brightcove with alternative playerID key
545 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
546 'info_dict': {
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',
549 },
550 'playlist': [{
551 'info_dict': {
552 'id': '2228375078001',
553 'ext': 'mp4',
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',
560 },
561 }],
562 },
40158f55
JH
563 {
564 # Brightcove with UUID in videoPlayer
565 'url': 'http://www8.hp.com/cn/zh/home.html',
566 'info_dict': {
567 'id': '5255815316001',
568 'ext': 'mp4',
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',
575 },
576 'params': {
577 'skip_download': True, # m3u8 download
578 },
579 'skip': 'video rotates...weekly?',
580 },
581 {
582 # Brightcove:new type [2].
583 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
584 'md5': '2b35148fcf48da41c9fb4591650784f3',
585 'info_dict': {
586 'id': '5348741021001',
587 'ext': 'mp4',
588 'upload_date': '20170306',
589 'uploader_id': '4191638492001',
590 'timestamp': 1488769918,
591 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
592
593 },
594 },
595 {
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/',
598 'info_dict': {
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",
601 },
602 'playlist': [{
603 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
604 'info_dict': {
605 'id': '5311302538001',
606 'ext': 'mp4',
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',
612 },
613 'only_matching': True,
614 }],
615 },
b68a812e
S
616 {
617 # Brightcove with UUID in videoPlayer
618 'url': 'http://www8.hp.com/cn/zh/home.html',
619 'info_dict': {
620 'id': '5255815316001',
621 'ext': 'mp4',
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',
628 },
629 'params': {
630 'skip_download': True, # m3u8 download
631 },
632 },
c0d0b01f
JMF
633 # ooyala video
634 {
79649588 635 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 636 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
637 'info_dict': {
638 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
639 'ext': 'mp4',
3486df38 640 'title': '2cc213299525360.mov', # that's what we get
53e06b25 641 'duration': 238.231,
c0d0b01f 642 },
87830900 643 'add_ie': ['Ooyala'],
c0d0b01f 644 },
bf94d763
S
645 {
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/',
648 'info_dict': {
649 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
650 'ext': 'mp4',
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."',
53e06b25 653 'duration': 135.427,
bf94d763
S
654 },
655 'params': {
656 'skip_download': True,
657 },
39efc6e3 658 'skip': 'movie expired',
bf94d763 659 },
198d4cb4
GR
660 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
661 {
662 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
663 'info_dict': {
664 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
665 'ext': 'mp4',
666 'title': 'Steampunk Fest Comes to Honesdale',
667 'duration': 43.276,
668 },
669 'params': {
670 'skip_download': True,
671 }
672 },
1b86cc41 673 # embed.ly video
674 {
675 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
676 'info_dict': {
677 'id': '9ODmcdjQcHQ',
678 'ext': 'mp4',
0a5bce56
PH
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',
1b86cc41 684 },
685 # No need to test YoutubeIE here
686 'params': {
687 'skip_download': True,
688 },
689 },
60cc4dc4
PH
690 # funnyordie embed
691 {
692 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
693 'info_dict': {
694 'id': '18e820ec3f',
695 'ext': 'mp4',
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.',
93d020dd 698 },
39efc6e3
YCH
699 # HEAD requests lead to endless 301, while GET is OK
700 'expected_warnings': ['301'],
60cc4dc4 701 },
93d020dd
S
702 # RUTV embed
703 {
704 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
705 'info_dict': {
706 'id': '776940',
707 'ext': 'mp4',
708 'title': 'Охотское море стало целиком российским',
709 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
710 },
711 'params': {
712 # m3u8 download
713 'skip_download': True,
714 },
aab74fa1 715 },
f37bdbe5
S
716 # TVC embed
717 {
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/',
719 'info_dict': {
720 'id': '55304',
721 'ext': 'mp4',
722 'title': 'Дошкольное воспитание',
723 },
724 },
b827a601
S
725 # SportBox embed
726 {
727 'url': 'http://www.vestifinance.ru/articles/25753',
728 'info_dict': {
729 'id': '25753',
05d1e7aa 730 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
b827a601
S
731 },
732 'playlist': [{
733 'info_dict': {
734 'id': '370908',
735 'title': 'Госзаказ. День 3',
736 'ext': 'mp4',
737 }
738 }, {
739 'info_dict': {
740 'id': '370905',
741 'title': 'Госзаказ. День 2',
742 'ext': 'mp4',
743 }
744 }, {
745 'info_dict': {
746 'id': '370902',
747 'title': 'Госзаказ. День 1',
748 'ext': 'mp4',
749 }
750 }],
751 'params': {
752 # m3u8 download
753 'skip_download': True,
754 },
755 },
bf20b9c5
S
756 # Myvi.ru embed
757 {
758 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
759 'info_dict': {
760 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
761 'ext': 'mp4',
762 'title': 'Ужастики, русский трейлер (2015)',
ec85ded8 763 'thumbnail': r're:^https?://.*\.jpg$',
bf20b9c5
S
764 'duration': 153,
765 }
766 },
c76799c5
S
767 # XHamster embed
768 {
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',
770 'info_dict': {
771 'id': 'showthread',
772 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
773 },
774 'playlist_mincount': 7,
39efc6e3
YCH
775 # This forum does not allow <iframe> syntaxes anymore
776 # Now HTML tags are displayed as-is
777 'skip': 'No videos on this page',
c76799c5 778 },
aab74fa1
PH
779 # Embedded TED video
780 {
781 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 782 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 783 'info_dict': {
a8eb5a8e 784 'id': '1969',
aab74fa1 785 'ext': 'mp4',
a8eb5a8e
PH
786 'title': 'Hidden miracles of the natural world',
787 'uploader': 'Louie Schwartzberg',
788 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 789 }
60cc4dc4 790 },
d95e35d6
S
791 # nowvideo embed hidden behind percent encoding
792 {
793 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
794 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
795 'info_dict': {
796 'id': '06e53103ca9aa',
797 'ext': 'flv',
798 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
799 'description': 'No description',
800 },
0f2a2ba1 801 },
893f8832
PH
802 # arte embed
803 {
804 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
805 'md5': '7653032cbb25bf6c80d80f217055fa43',
806 'info_dict': {
807 'id': '048195-004_PLUS7-F',
808 'ext': 'flv',
809 'title': 'X:enius',
810 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
811 'upload_date': '20140320',
812 },
813 'params': {
814 'skip_download': 'Requires rtmpdump'
39efc6e3
YCH
815 },
816 'skip': 'video gone',
893f8832 817 },
cbd55ade
S
818 # francetv embed
819 {
820 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
821 'info_dict': {
822 'id': 'EV_30231',
823 'ext': 'mp4',
824 'title': 'Alcaline, le concert avec Calogero',
825 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
826 'upload_date': '20150226',
827 'timestamp': 1424989860,
828 'duration': 5400,
829 },
830 'params': {
831 # m3u8 downloads
832 'skip_download': True,
833 },
834 'expected_warnings': [
835 'Forbidden'
836 ]
837 },
fa35cdad
PH
838 # Condé Nast embed
839 {
840 'url': 'http://www.wired.com/2014/04/honda-asimo/',
841 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
842 'info_dict': {
843 'id': '53501be369702d3275860000',
844 'ext': 'mp4',
845 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
846 }
ebd3c7b3
PH
847 },
848 # Dailymotion embed
849 {
850 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
851 'md5': '441aeeb82eb72c422c7f14ec533999cd',
852 'info_dict': {
853 'id': 'k2mm4bCdJ6CQ2i7c8o2',
854 'ext': 'mp4',
855 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 856 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 857 'uploader': 'Spi0n',
0738187f
YCH
858 'uploader_id': 'xgditw',
859 'upload_date': '20140425',
860 'timestamp': 1398441542,
ebd3c7b3
PH
861 },
862 'add_ie': ['Dailymotion'],
2b88feed 863 },
71a1db89
S
864 # DailyMail embed
865 {
866 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
867 'info_dict': {
868 'id': '1495629',
869 'ext': 'mp4',
870 'title': 'Care worker punches elderly dementia patient in head 11 times',
871 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
872 },
873 'add_ie': ['DailyMail'],
874 'params': {
875 'skip_download': True,
876 },
877 },
2b88feed
PH
878 # YouTube embed
879 {
880 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
881 'info_dict': {
882 'id': 'FXRb4ykk4S0',
883 'ext': 'mp4',
884 'title': 'The NBL Auction 2014',
885 'uploader': 'BADMINTON England',
886 'uploader_id': 'BADMINTONEvents',
887 'upload_date': '20140603',
888 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
889 },
890 'add_ie': ['Youtube'],
891 'params': {
892 'skip_download': True,
893 }
894 },
a0566bbf 895 # MTVServices embed
c5cd249e 896 {
1fa309da
YCH
897 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
898 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 899 'info_dict': {
1fa309da 900 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 901 'ext': 'mp4',
1fa309da
YCH
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.',
05d1e7aa
YCH
904 'timestamp': 1349922600,
905 'upload_date': '20121011',
c5cd249e
JMF
906 },
907 },
61013473 908 # YouTube embed via <data-embed-url="">
909 {
910 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 911 'info_dict': {
a8eb5a8e 912 'id': '4vAffPZIT44',
61013473 913 'ext': 'mp4',
a8eb5a8e 914 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
915 'uploader': 'Gameloft',
916 'uploader_id': 'gameloft',
a8eb5a8e
PH
917 'upload_date': '20140828',
918 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
919 },
920 'params': {
921 'skip_download': True,
61013473 922 }
c8e9a235 923 },
61568e50
JH
924 # YouTube <object> embed
925 {
926 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
927 'md5': '516718101ec834f74318df76259fb3cc',
928 'info_dict': {
929 'id': 'msN87y-iEx0',
930 'ext': 'webm',
931 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
932 'upload_date': '20080526',
933 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
934 'uploader': 'Christopher Sykes',
935 'uploader_id': 'ChristopherJSykes',
936 },
937 'add_ie': ['Youtube'],
938 },
c8e9a235
PH
939 # Camtasia studio
940 {
941 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
942 'playlist': [{
943 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
944 'info_dict': {
945 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
946 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
947 'ext': 'flv',
948 'duration': 2235.90,
949 }
950 }, {
951 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
952 'info_dict': {
953 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
954 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
955 'ext': 'flv',
956 'duration': 2235.93,
957 }
958 }],
959 'info_dict': {
960 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
961 }
4d805e06
PH
962 },
963 # Flowplayer
964 {
965 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
966 'md5': '9d65602bf31c6e20014319c7d07fba27',
967 'info_dict': {
968 'id': '5123ea6d5e5a7',
969 'ext': 'mp4',
970 'age_limit': 18,
971 'uploader': 'www.handjobhub.com',
d6d9186f 972 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 973 }
0990305d 974 },
22a6f150 975 # Multiple brightcove videos
067aa17e 976 # https://github.com/ytdl-org/youtube-dl/issues/2283
22a6f150
PH
977 {
978 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
979 'info_dict': {
980 'id': 'always-never',
981 'title': 'Always / Never - The New Yorker',
982 },
983 'playlist_count': 3,
984 'params': {
985 'extract_flat': False,
986 'skip_download': True,
987 }
1a94ff68
S
988 },
989 # MLB embed
990 {
991 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
992 'md5': '96f09a37e44da40dd083e12d9a683327',
993 'info_dict': {
994 'id': '33322633',
995 'ext': 'mp4',
996 'title': 'Ump changes call to ball',
997 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
998 'duration': 48,
999 'timestamp': 1401537900,
1000 'upload_date': '20140531',
ec85ded8 1001 'thumbnail': r're:^https?://.*\.jpg$',
1a94ff68
S
1002 },
1003 },
746c67d7
NJ
1004 # Wistia embed
1005 {
6c114b12
S
1006 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1007 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 1008 'info_dict': {
6c114b12 1009 'id': '6e2wtrbdaf',
746c67d7 1010 'ext': 'mov',
6c114b12
S
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,
746c67d7
NJ
1018 },
1019 },
52cffcb1 1020 {
1021 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1022 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1023 'info_dict': {
1024 'id': 'uxjb0lwrcz',
1025 'ext': 'mp4',
6c114b12 1026 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 1027 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 1028 'duration': 1715.0,
85d7b765 1029 'uploader': 'thoughtworks.wistia.com',
0738187f 1030 'timestamp': 1401832161,
6c114b12 1031 'upload_date': '20140603',
70b7e3fb 1032 },
52cffcb1 1033 },
7ded6545
S
1034 # Wistia standard embed (async)
1035 {
1036 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1037 'info_dict': {
1038 'id': '807fafadvk',
1039 'ext': 'mp4',
1040 'title': 'Drip Brennan Dunn Workshop',
1041 'description': 'a JV Webinars video from getdrip-1',
1042 'duration': 4986.95,
7ded6545 1043 'timestamp': 1463607249,
6c114b12 1044 'upload_date': '20160518',
7ded6545
S
1045 },
1046 'params': {
1047 'skip_download': True,
1048 }
1049 },
ac645ac7
PH
1050 # Soundcloud embed
1051 {
1052 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1053 'info_dict': {
1054 'id': '174391317',
1055 'ext': 'mp3',
1056 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1057 'uploader': 'Sophos Security',
1058 'title': 'Chet Chat 171 - Oct 29, 2014',
1059 'upload_date': '20141029',
1060 }
af63fed7 1061 },
db19df6c
S
1062 # Soundcloud multiple embeds
1063 {
1064 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1065 'info_dict': {
1066 'id': '52809',
1067 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1068 },
1069 'playlist_mincount': 7,
1070 },
027e2312
S
1071 # TuneIn station embed
1072 {
1073 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1074 'info_dict': {
1075 'id': '204146',
1076 'ext': 'mp3',
1077 'title': 'CNRV',
1078 'location': 'Paris, France',
1079 'is_live': True,
1080 },
1081 'params': {
1082 # Live stream
1083 'skip_download': True,
1084 },
1085 },
af63fed7
PH
1086 # Livestream embed
1087 {
1088 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1089 'info_dict': {
1090 'id': '67864563',
1091 'ext': 'flv',
1092 'upload_date': '20141112',
1093 'title': 'Rosetta #CometLanding webcast HL 10',
1094 }
1095 },
78d3b3e2
YCH
1096 # Another Livestream embed, without 'new.' in URL
1097 {
1098 'url': 'https://www.freespeech.org/',
1099 'info_dict': {
1100 'id': '123537347',
1101 'ext': 'mp4',
1102 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1103 },
1104 'params': {
1105 # Live stream
1106 'skip_download': True,
1107 },
1108 },
65f3a228
PH
1109 # LazyYT
1110 {
e8e4cc5a 1111 'url': 'https://skiplagged.com/',
65f3a228 1112 'info_dict': {
e8e4cc5a
JH
1113 'id': 'skiplagged',
1114 'title': 'Skiplagged: The smart way to find cheap flights',
65f3a228 1115 },
e8e4cc5a
JH
1116 'playlist_mincount': 1,
1117 'add_ie': ['Youtube'],
4e262a88 1118 },
42bdd9d0
PH
1119 # Cinchcast embed
1120 {
1121 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1122 'info_dict': {
1123 'id': '7141703',
1124 'ext': 'mp3',
1125 'upload_date': '20141126',
1126 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1127 }
1128 },
501f13fb
PH
1129 # Cinerama player
1130 {
1131 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1132 'info_dict': {
1133 'id': '730m_DandD_1901_512k',
1134 'ext': 'mp4',
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',
1137 }
796df3c6
S
1138 },
1139 # embedded viddler video
1140 {
1141 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1142 'info_dict': {
1143 'id': '4d03aad9',
1144 'ext': 'mp4',
1145 'uploader': 'deadspin',
1146 'title': 'WALL-TO-GORTAT',
1147 'timestamp': 1422285291,
1148 'upload_date': '20150126',
1149 },
1150 'add_ie': ['Viddler'],
a0f71985 1151 },
2051acde
S
1152 # Libsyn embed
1153 {
1154 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1155 'info_dict': {
1156 'id': '3377616',
1157 'ext': 'mp3',
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',
1161 },
326fa4e6 1162 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
2051acde 1163 },
a0f71985
PH
1164 # jwplayer YouTube
1165 {
1166 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1167 'info_dict': {
1168 'id': 'Mrj4DVp2zeA',
1169 'ext': 'mp4',
f37e3f99 1170 'upload_date': '20150212',
a0f71985 1171 'uploader': 'The National Archives UK',
2637fadc 1172 'description': 'md5:8078af856dca76edc42910b61273dbbf',
a0f71985
PH
1173 'uploader_id': 'NationalArchives08',
1174 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1175 },
59b8ab58 1176 },
5620f840
S
1177 # jwplayer rtmp
1178 {
6899b1d9 1179 'url': 'http://www.suffolk.edu/sjc/live.php',
5620f840 1180 'info_dict': {
6899b1d9 1181 'id': 'live',
5620f840
S
1182 'ext': 'flv',
1183 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1184 'uploader': 'www.suffolk.edu',
1185 },
1186 'params': {
1187 'skip_download': True,
2637fadc 1188 },
6899b1d9 1189 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
5620f840 1190 },
a4a554a7
YCH
1191 # Complex jwplayer
1192 {
1193 'url': 'http://www.indiedb.com/games/king-machine/videos',
1194 'info_dict': {
1195 'id': 'videos',
1196 'ext': 'mp4',
1197 'title': 'king machine trailer 1',
2637fadc 1198 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
a4a554a7
YCH
1199 'thumbnail': r're:^https?://.*\.jpg$',
1200 },
1201 },
03486dbb
RU
1202 {
1203 # JWPlayer config passed as variable
1204 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1205 'info_dict': {
1206 'id': '3326530_hq',
1207 'ext': 'mp4',
1208 'title': 'ARIELE | Tube Cup',
1209 'uploader': 'www.txxx.com',
1210 'age_limit': 18,
1211 },
1212 'params': {
1213 'skip_download': True,
1214 }
1215 },
939be9ad
JH
1216 {
1217 # JWPlatform iframe
1218 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1219 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1220 'info_dict': {
1221 'id': 'O0c5JcKT',
1222 'ext': 'mp4',
1223 'upload_date': '20171122',
1224 'timestamp': 1511366290,
1225 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1226 },
805f5bf7 1227 'add_ie': [JWPlatformIE.ie_key()],
939be9ad 1228 },
63d990d2 1229 {
c5b7014a 1230 # Video.js embed, multiple formats
63d990d2
S
1231 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1232 'info_dict': {
1233 'id': 'yygqldloqIk',
1234 'ext': 'mp4',
1235 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1236 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1237 'upload_date': '20130314',
1238 'uploader': 'PROстое3D',
1239 'uploader_id': 'PROstoe3D',
1240 },
1241 'params': {
1242 'skip_download': True,
1243 },
1244 },
c5b7014a
S
1245 {
1246 # Video.js embed, single format
1247 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1248 'info_dict': {
1249 'id': 'watch',
1250 'ext': 'mp4',
1251 'title': 'Step 1 - Good Foundation',
1252 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1253 },
1254 'params': {
1255 'skip_download': True,
1256 },
1257 },
59b8ab58
PH
1258 # rtl.nl embed
1259 {
1260 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1261 'playlist_mincount': 5,
1262 'info_dict': {
1263 'id': 'aanslagen-kopenhagen',
2637fadc 1264 'title': 'Aanslagen Kopenhagen',
59b8ab58 1265 }
255fca5e
S
1266 },
1267 # Zapiks embed
1268 {
1269 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1270 'info_dict': {
1271 'id': '118046',
1272 'ext': 'mp4',
1273 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1274 }
1275 },
66e568de
S
1276 # Kaltura embed (different embed code)
1277 {
1278 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1279 'info_dict': {
1280 'id': '1_a52wc67y',
1281 'ext': 'flv',
1282 'upload_date': '20150127',
1283 'uploader_id': 'PremierMedia',
1284 'timestamp': int,
1285 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1286 },
1287 },
87703231
YCH
1288 # Kaltura embed with single quotes
1289 {
1290 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1291 'info_dict': {
1292 'id': '0_izeg5utt',
1293 'ext': 'mp4',
1294 'title': '35871',
1295 'timestamp': 1355743100,
1296 'upload_date': '20121217',
e30991f9 1297 'uploader_id': 'cplapp@learn360.com',
87703231
YCH
1298 },
1299 'add_ie': ['Kaltura'],
1300 },
427cd050
S
1301 {
1302 # Kaltura embedded via quoted entry_id
1303 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1304 'info_dict': {
1305 'id': '0_utuok90b',
1306 'ext': 'mp4',
1307 'title': '06_matthew_brender_raj_dutt',
1308 'timestamp': 1466638791,
1309 'upload_date': '20160622',
1310 },
1311 'add_ie': ['Kaltura'],
1312 'expected_warnings': [
1313 'Could not send HEAD request'
1314 ],
1315 'params': {
1316 'skip_download': True,
1317 }
1318 },
8ab7e6c4
YCH
1319 {
1320 # Kaltura embedded, some fileExt broken (#11480)
1321 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1322 'info_dict': {
1323 'id': '1_sgtvehim',
1324 'ext': 'mp4',
1325 'title': 'Our "Standard Models" of particle physics and cosmology',
1326 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1327 'timestamp': 1321158993,
1328 'upload_date': '20111113',
1329 'uploader_id': 'kps1',
1330 },
1331 'add_ie': ['Kaltura'],
1332 },
a01825a5
JH
1333 {
1334 # Kaltura iframe embed
1335 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1336 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1337 'info_dict': {
1338 'id': '0_f2cfbpwy',
1339 'ext': 'mp4',
1340 'title': 'I. M. Pei: A Centennial Celebration',
1341 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1342 'upload_date': '20170403',
1343 'uploader_id': 'batchUser',
1344 'timestamp': 1491232186,
1345 },
1346 'add_ie': ['Kaltura'],
1347 },
c21692fa
S
1348 {
1349 # Kaltura iframe embed, more sophisticated
1350 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1351 'info_dict': {
1352 'id': '1_9gzouybz',
1353 'ext': 'mp4',
1354 'title': 'lecture-05sep2017',
1355 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1356 'upload_date': '20170913',
1357 'uploader_id': 'eps2',
1358 'timestamp': 1505340777,
1359 },
1360 'params': {
1361 'skip_download': True,
1362 },
1363 'add_ie': ['Kaltura'],
1364 },
e30991f9
S
1365 {
1366 # meta twitter:player
1367 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1368 'info_dict': {
1369 'id': '0_01b42zps',
1370 'ext': 'mp4',
1371 'title': 'Main Twerk (Video)',
1372 'upload_date': '20171208',
1373 'uploader_id': 'sebastian.salinas@thechive.com',
1374 'timestamp': 1512713057,
1375 },
1376 'params': {
1377 'skip_download': True,
1378 },
1379 'add_ie': ['Kaltura'],
1380 },
250b042c
S
1381 # referrer protected EaglePlatform embed
1382 {
1383 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1384 'info_dict': {
1385 'id': '582306',
1386 'ext': 'mp4',
1387 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1388 'thumbnail': r're:^https?://.*\.jpg$',
1389 'duration': 3382,
1390 'view_count': int,
1391 },
1392 'params': {
1393 'skip_download': True,
1394 },
135c9c42 1395 },
665e9452 1396 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1397 {
1398 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1399 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1400 'info_dict': {
1401 'id': '12820',
1402 'ext': 'mp4',
1403 'title': "'O Sole Mio",
ec85ded8 1404 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1405 'duration': 216,
1406 'view_count': int,
1407 },
250b042c
S
1408 'params': {
1409 'skip_download': True,
1410 },
2637fadc 1411 'skip': 'This video is unavailable.',
d47ae7f6 1412 },
f8388757
S
1413 # Pladform embed
1414 {
1415 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1416 'info_dict': {
1417 'id': '100183293',
1418 'ext': 'mp4',
62259846 1419 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1420 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1421 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1422 'duration': 694,
1423 'age_limit': 0,
1424 },
2637fadc 1425 'skip': 'HTTP Error 404: Not Found',
f8388757 1426 },
c798f15b
S
1427 # Playwire embed
1428 {
1429 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1430 'info_dict': {
1431 'id': '3519514',
1432 'ext': 'mp4',
1433 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1434 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1435 'duration': 45.115,
1436 },
1437 },
ad320e9b
NJ
1438 # 5min embed
1439 {
1440 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1441 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1442 'info_dict': {
1443 'id': '518726732',
1444 'ext': 'mp4',
1445 'title': 'Facebook Creates "On This Day" | Crunch Report',
2637fadc
RA
1446 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1447 'timestamp': 1427237531,
1448 'uploader': 'Crunch Report',
1449 'upload_date': '20150324',
1450 },
1451 'params': {
1452 # m3u8 download
1453 'skip_download': True,
ad320e9b
NJ
1454 },
1455 },
a4257017
S
1456 # Crooks and Liars embed
1457 {
1458 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1459 'info_dict': {
1460 'id': '8RUoRhRi',
1461 'ext': 'mp4',
1462 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1463 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1464 'timestamp': 1428207000,
1465 'upload_date': '20150405',
1466 'uploader': 'Heather',
1467 },
1468 },
1469 # Crooks and Liars external embed
1470 {
1471 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1472 'info_dict': {
1473 'id': 'MTE3MjUtMzQ2MzA',
1474 'ext': 'mp4',
1475 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1476 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1477 'timestamp': 1265032391,
1478 'upload_date': '20100201',
1479 'uploader': 'Heather',
1480 },
1481 },
facecb84 1482 # NBC Sports vplayer embed
a2edf2e7 1483 {
facecb84 1484 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1485 'info_dict': {
facecb84
S
1486 'id': 'ln7x1qSThw4k',
1487 'ext': 'flv',
1488 'title': "PFT Live: New leader in the 'new-look' defense",
1489 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1490 'uploader': 'NBCU-SPORTS',
1491 'upload_date': '20140107',
1492 'timestamp': 1389118457,
a2edf2e7 1493 },
2637fadc 1494 'skip': 'Invalid Page URL',
418c5cc3 1495 },
de3eb07e
YCH
1496 # NBC News embed
1497 {
1498 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1499 'md5': '1aa589c675898ae6d37a17913cf68d66',
1500 'info_dict': {
2637fadc 1501 'id': 'x_dtl_oa_LettermanliftPR_160608',
de3eb07e 1502 'ext': 'mp4',
2637fadc 1503 'title': 'David Letterman: A Preview',
de3eb07e 1504 '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.',
2637fadc
RA
1505 'upload_date': '20160609',
1506 'timestamp': 1465431544,
1507 'uploader': 'NBCU-NEWS',
de3eb07e
YCH
1508 },
1509 },
418c5cc3
YCH
1510 # UDN embed
1511 {
811586eb 1512 'url': 'https://video.udn.com/news/300346',
01c58f84 1513 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1514 'info_dict': {
01c58f84 1515 'id': '300346',
418c5cc3 1516 'ext': 'mp4',
01c58f84 1517 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1518 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1519 },
1520 'params': {
1521 # m3u8 download
1522 'skip_download': True,
1523 },
2637fadc 1524 'expected_warnings': ['Failed to parse JSON Expecting value'],
edfcf7ab 1525 },
b26733ba
YCH
1526 # Brightcove URL in single quotes
1527 {
1528 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1529 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1530 'info_dict': {
1531 'id': '4255764656001',
1532 'ext': 'mp4',
1533 'title': 'SN Presents: Russell Martin, World Citizen',
1534 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1535 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1536 'uploader_id': '1704050871',
1537 'upload_date': '20150525',
1538 'timestamp': 1432570283,
b26733ba 1539 },
756f574e 1540 },
55adb63e 1541 # Kinja embed
8084be78
S
1542 {
1543 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1544 'info_dict': {
55adb63e 1545 'id': '106351',
8084be78
S
1546 'ext': 'mp4',
1547 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
55adb63e 1548 'description': 'Migrated from OnionStudios',
ec85ded8 1549 'thumbnail': r're:^https?://.*\.jpe?g$',
55adb63e
RA
1550 'uploader': 'clickhole',
1551 'upload_date': '20150527',
1552 'timestamp': 1432744860,
8084be78
S
1553 }
1554 },
b8c1cc1a
S
1555 # SnagFilms embed
1556 {
1557 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1558 'info_dict': {
1559 'id': '74849a00-85a9-11e1-9660-123139220831',
1560 'ext': 'mp4',
1561 'title': '#whilewewatch',
1562 }
1563 },
a5158f38
YCH
1564 # AdobeTVVideo embed
1565 {
1566 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1567 'md5': '43662b577c018ad707a63766462b1e87',
1568 'info_dict': {
1569 'id': '2456',
1570 'ext': 'mp4',
1571 'title': 'New experience with Acrobat DC',
1572 'description': 'New experience with Acrobat DC',
1573 'duration': 248.667,
1574 },
1f812580 1575 },
ed126900 1576 # BrightcoveInPageEmbed embed
1577 {
1578 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1579 'info_dict': {
1580 'id': '4238694884001',
1581 'ext': 'flv',
1582 'title': 'Tabletop: Dread, Last Thoughts',
1583 'description': 'Tabletop: Dread, Last Thoughts',
1584 'duration': 51690,
1585 },
750b9ff0 1586 },
d10fe835
YCH
1587 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1588 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1589 {
1590 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1591 'info_dict': {
1592 'id': '4785848093001',
1593 'ext': 'mp4',
1594 'title': 'The Cardinal Pell Interview',
1595 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1596 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1597 'uploader_id': '2733773828001',
1598 'upload_date': '20160304',
1599 'timestamp': 1457083087,
d10fe835
YCH
1600 },
1601 'params': {
1602 # m3u8 downloads
1603 'skip_download': True,
1604 },
1605 },
9edf47df
S
1606 {
1607 # Brightcove embed with whitespace around attribute names
1608 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1609 'info_dict': {
1610 'id': '3167554373001',
1611 'ext': 'mp4',
1612 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1613 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1614 'uploader_id': '1079349493',
1615 'upload_date': '20140207',
1616 'timestamp': 1391810548,
1617 },
1618 'params': {
1619 'skip_download': True,
1620 },
1621 },
134c207e
YCH
1622 # Another form of arte.tv embed
1623 {
1624 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1625 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1626 'info_dict': {
1627 'id': '030273-562_PLUS7-F',
1628 'ext': 'mp4',
1629 'title': 'ARTE Reportage - Nulle part, en France',
1630 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1631 'upload_date': '20160409',
1632 },
1633 },
4a120778
YCH
1634 # Duplicated embedded video URLs
1635 {
1636 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1637 'info_dict': {
1638 'id': '149298443_480_16c25b74_2',
1639 'ext': 'mp4',
1640 'title': 'vs. Blue Orange Spring Game',
1641 'uploader': 'www.hudl.com',
1642 },
1643 },
371ddb14
S
1644 # twitter:player:stream embed
1645 {
1646 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1647 'info_dict': {
1648 'id': 'master',
1649 'ext': 'mp4',
1650 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1651 'uploader': 'www.rtl.be',
1652 },
1653 'params': {
1654 # m3u8 downloads
1655 'skip_download': True,
1656 },
1657 },
32917907
RA
1658 # twitter:player embed
1659 {
1660 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1661 'md5': 'a3e0df96369831de324f0778e126653c',
1662 'info_dict': {
1663 'id': '4909620399001',
1664 'ext': 'mp4',
1665 'title': 'What Do Black Holes Sound Like?',
1666 'description': 'what do black holes sound like',
1667 'upload_date': '20160524',
1668 'uploader_id': '29913724001',
1669 'timestamp': 1464107587,
1670 'uploader': 'TheAtlantic',
1671 },
1672 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1673 },
1674 # Facebook <iframe> embed
1675 {
1676 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1677 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1678 'info_dict': {
1679 'id': '599637780109885',
1680 'ext': 'mp4',
1681 'title': 'Facebook video #599637780109885',
1682 },
1683 },
fd1c5fba
S
1684 # Facebook <iframe> embed, plugin video
1685 {
1686 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1687 'info_dict': {
1688 'id': '1754168231264132',
1689 'ext': 'mp4',
1690 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1691 'uploader': 'Tariq Ramadan (official)',
1692 'timestamp': 1496758379,
1693 'upload_date': '20170606',
1694 },
1695 'params': {
1696 'skip_download': True,
1697 },
1698 },
fd6ca382
YCH
1699 # Facebook API embed
1700 {
1701 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1702 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1703 'info_dict': {
1704 'id': '10153467542406923',
1705 'ext': 'mp4',
1706 'title': 'Facebook video #10153467542406923',
1707 },
7deef1ba
YCH
1708 },
1709 # Wordpress "YouTube Video Importer" plugin
1710 {
1711 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1712 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1713 'info_dict': {
1714 'id': 'HNTXWDXV9Is',
1715 'ext': 'mp4',
1716 'title': 'Blue Devils Drumline Stanford lot 2016',
1717 'upload_date': '20160627',
1718 'uploader_id': 'GENOCIDE8GENERAL10',
1719 'uploader': 'cylus cyrus',
1720 },
1721 },
81953d1a
RA
1722 {
1723 # video stored on custom kaltura server
1724 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1725 'md5': '537617d06e64dfed891fa1593c4b30cc',
1726 'info_dict': {
1727 'id': '0_1iotm5bh',
1728 'ext': 'mp4',
1729 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1730 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1731 'uploader_id': 'videos.expansion@el-mundo.net',
1732 'upload_date': '20150429',
1733 'timestamp': 1430303472,
1734 },
1735 'add_ie': ['Kaltura'],
1736 },
562de77f
S
1737 {
1738 # multiple kaltura embeds, nsfw
1739 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1740 'info_dict': {
1741 'id': 'kamila-avec-video-jaime-sadomie',
1742 'title': "Kamila avec vídeo “J'aime sadomie”",
1743 },
1744 'playlist_count': 8,
1745 },
c03adf90
YCH
1746 {
1747 # Non-standard Vimeo embed
1748 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1749 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1750 'info_dict': {
1751 'id': '148867247',
1752 'ext': 'mp4',
1753 'title': 'Understanding the web - Teaser',
1754 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1755 'upload_date': '20151214',
1756 'uploader': 'OpenClassrooms',
1757 'uploader_id': 'openclassrooms',
1758 },
1759 'add_ie': ['Vimeo'],
1760 },
a5ff05df
S
1761 {
1762 # generic vimeo embed that requires original URL passed as Referer
1763 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1764 'only_matching': True,
1765 },
1979969f
S
1766 {
1767 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1768 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1769 'info_dict': {
1770 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1771 'ext': 'mp4',
1772 'title': 'Big Buck Bunny',
1773 'description': 'Royalty free test video',
1774 'timestamp': 1432816365,
1775 'upload_date': '20150528',
1776 'is_live': False,
1777 },
1778 'params': {
1779 'skip_download': True,
1780 },
1781 'add_ie': [ArkenaIE.ie_key()],
1782 },
2a1321a2
S
1783 {
1784 '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/',
1785 'info_dict': {
1786 'id': '1c7141f46c',
1787 'ext': 'mp4',
1788 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1789 },
1790 'params': {
1791 'skip_download': True,
1792 },
1793 'add_ie': [Vbox7IE.ie_key()],
1794 },
b0c8f2e9
DR
1795 {
1796 # DBTV embeds
1797 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1798 'info_dict': {
1799 'id': '43254897',
1800 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1801 },
b0c8f2e9
DR
1802 'playlist_mincount': 3,
1803 },
e186a9ec
S
1804 {
1805 # Videa embeds
1806 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1807 'info_dict': {
1808 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1809 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1810 },
1811 'playlist_mincount': 2,
1812 },
b687c85e
S
1813 {
1814 # 20 minuten embed
1815 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1816 'info_dict': {
1817 'id': '523629',
1818 'ext': 'mp4',
1819 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1820 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1821 },
1822 'params': {
1823 'skip_download': True,
1824 },
1825 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1826 },
1827 {
1828 # VideoPress embed
1829 'url': 'https://en.support.wordpress.com/videopress/',
1830 'info_dict': {
1831 'id': 'OcobLTqC',
1832 'ext': 'm4v',
1833 'title': 'IMG_5786',
1834 'timestamp': 1435711927,
1835 'upload_date': '20150701',
1836 },
1837 'params': {
1838 'skip_download': True,
1839 },
1840 'add_ie': [VideoPressIE.ie_key()],
fef51645 1841 },
eb3079b6
S
1842 {
1843 # Rutube embed
1844 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1845 'info_dict': {
1846 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1847 'ext': 'flv',
1848 'title': 'Магаззино: Казань 2',
1849 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1850 'uploader': 'Магаззино',
1851 'upload_date': '20170228',
1852 'uploader_id': '996642',
1853 },
1854 'params': {
1855 'skip_download': True,
1856 },
1857 'add_ie': [RutubeIE.ie_key()],
1858 },
fef51645
YCH
1859 {
1860 # ThePlatform embedded with whitespaces in URLs
1861 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1862 'only_matching': True,
1863 },
97952bdb
JH
1864 {
1865 # Senate ISVP iframe https
1866 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1867 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1868 'info_dict': {
1869 'id': 'govtaff020316',
1870 'ext': 'mp4',
1871 'title': 'Integrated Senate Video Player',
1872 },
1873 'add_ie': [SenateISVPIE.ie_key()],
1874 },
ab87c260
S
1875 {
1876 # Limelight embeds (1 channel embed + 4 media embeds)
1877 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1878 'info_dict': {
1879 'id': 'FacilitatorTraining2017',
1880 'title': 'Facilitator Training 2017',
1881 },
1882 'playlist_mincount': 5,
1883 },
eb02940c
S
1884 {
1885 # Limelight embed (LimelightPlayerUtil.embed)
1886 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1887 'info_dict': {
1888 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1889 'ext': 'mp4',
1890 'title': '07448641',
1891 'timestamp': 1499890639,
1892 'upload_date': '20170712',
1893 },
1894 'params': {
1895 'skip_download': True,
1896 },
1897 'add_ie': ['LimelightMedia'],
1898 },
7986c3ab
S
1899 {
1900 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1901 'info_dict': {
1902 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1903 'title': 'Standoff with Walnut Creek murder suspect ends',
1904 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1905 },
1906 'playlist_mincount': 4,
1907 },
55719459
JH
1908 {
1909 # WashingtonPost embed
1910 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1911 'info_dict': {
1912 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1913 'ext': 'mp4',
1914 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1915 '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.',
1916 'timestamp': 1455216756,
1917 'uploader': 'The Washington Post',
1918 'upload_date': '20160211',
1919 },
1920 'add_ie': [WashingtonPostIE.ie_key()],
1921 },
2b8e6a68
S
1922 {
1923 # Mediaset embed
1924 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1925 'info_dict': {
1926 'id': '720642',
1927 'ext': 'mp4',
1928 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1929 },
1930 'params': {
1931 'skip_download': True,
1932 },
1933 'add_ie': [MediasetIE.ie_key()],
1934 },
73cf76a9
S
1935 {
1936 # JOJ.sk embeds
1937 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1938 'info_dict': {
1939 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1940 'title': 'Slovenskom sa prehnala vlna silných búrok',
1941 },
1942 'playlist_mincount': 5,
1943 'add_ie': [JojIE.ie_key()],
1944 },
4328ddf8
S
1945 {
1946 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1947 'url': 'https://tvrain.ru/amp/418921/',
1948 'md5': 'cc00413936695987e8de148b67d14f1d',
1949 'info_dict': {
1950 'id': '418921',
1951 'ext': 'mp4',
1952 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1953 },
1954 },
41918eaa 1955 {
1956 # vzaar embed
1663bd6e
S
1957 'url': 'http://help.vzaar.com/article/165-embedding-video',
1958 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1959 'info_dict': {
1663bd6e 1960 'id': '8707641',
41918eaa 1961 'ext': 'mp4',
1663bd6e 1962 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1963 },
1964 },
9ce1ac40 1965 {
1966 # multiple HTML5 videos on one page
1967 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1968 'info_dict': {
1969 'id': 'keyscenarios',
1970 'title': 'Rescue Kit 14 Free Edition - Getting started',
1971 },
1972 'playlist_count': 4,
0987f2dd
T
1973 },
1974 {
1975 # vshare embed
7a5c1cfe 1976 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
0987f2dd
T
1977 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1978 'info_dict': {
1979 'id': '0f64ce6',
1980 'title': 'vl14062007715967',
1981 'ext': 'mp4',
1982 }
2ca7ed41
S
1983 },
1984 {
1985 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1986 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1987 'info_dict': {
1988 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1989 'ext': 'mp4',
1990 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1991 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1992 'timestamp': 1474354800,
1993 'upload_date': '20160920',
1994 }
7d540621
S
1995 },
1996 {
1997 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1998 'info_dict': {
1999 'id': '1731611',
2000 'ext': 'mp4',
2001 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2002 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2003 'timestamp': 1516100691,
2004 'upload_date': '20180116',
2005 },
2006 'params': {
2007 'skip_download': True,
2008 },
2009 'add_ie': [SpringboardPlatformIE.ie_key()],
ea696249 2010 },
4c780fbd
S
2011 {
2012 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2013 'info_dict': {
2014 'id': 'vMDE4NzI1Mjgt690b',
2015 'ext': 'mp4',
2016 'title': 'Котята',
2017 },
2018 'add_ie': [YapFilesIE.ie_key()],
2019 'params': {
2020 'skip_download': True,
2021 },
1fc37ca3 2022 },
660a230b
S
2023 {
2024 # CloudflareStream embed
2025 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2026 'info_dict': {
2027 'id': '31c9291ab41fac05471db4e73aa11717',
2028 'ext': 'mp4',
2029 'title': '31c9291ab41fac05471db4e73aa11717',
2030 },
2031 'add_ie': [CloudflareStreamIE.ie_key()],
2032 'params': {
2033 'skip_download': True,
2034 },
2035 },
6bd499e8
S
2036 {
2037 # PeerTube embed
2038 'url': 'https://joinpeertube.org/fr/home/',
2039 'info_dict': {
2040 'id': 'home',
2041 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2042 },
2043 'playlist_count': 2,
2044 },
aee36ca8
S
2045 {
2046 # Indavideo embed
2047 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2048 'info_dict': {
2049 'id': '1693903',
2050 'ext': 'mp4',
2051 'title': 'Így kell otthon hamburgert sütni',
2052 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2053 'timestamp': 1426330212,
2054 'upload_date': '20150314',
2055 'uploader': 'StreetKitchen',
2056 'uploader_id': '546363',
2057 },
2058 'add_ie': [IndavideoEmbedIE.ie_key()],
2059 'params': {
2060 'skip_download': True,
2061 },
2062 },
cfd7f2a6
S
2063 {
2064 # APA embed via JWPlatform embed
2065 'url': 'http://www.vol.at/blue-man-group/5593454',
2066 'info_dict': {
2067 'id': 'jjv85FdZ',
2068 'ext': 'mp4',
2069 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2070 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2071 'thumbnail': r're:^https?://.*\.jpg$',
2072 'duration': 254,
2073 'timestamp': 1519211149,
2074 'upload_date': '20180221',
2075 },
2076 'params': {
2077 'skip_download': True,
2078 },
2079 },
1fc37ca3
SO
2080 {
2081 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2082 'md5': 'b68d276de422ab07ee1d49388103f457',
2083 'info_dict': {
2084 'id': '83645793',
2085 'title': 'Lock up and get excited',
1fc37ca3 2086 'ext': 'mp4'
d3431dcb
S
2087 },
2088 'skip': 'TODO: fix nested playlists processing in tests',
2089 },
9d1b2138
S
2090 {
2091 # Viqeo embeds
2092 'url': 'https://viqeo.tv/',
2093 'info_dict': {
2094 'id': 'viqeo',
2095 'title': 'All-new video platform',
2096 },
2097 'playlist_count': 6,
2098 },
d78657fd
BM
2099 {
2100 # Squarespace video embed, 2019-08-28
2101 'url': 'http://ootboxford.com',
2102 'info_dict': {
2103 'id': 'Tc7b_JGdZfw',
2104 'title': 'Out of the Blue, at Childish Things 10',
7cb51b5d
S
2105 'ext': 'mp4',
2106 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2107 'uploader_id': 'helendouglashouse',
2108 'uploader': 'Helen & Douglas House',
2109 'upload_date': '20140328',
d78657fd
BM
2110 },
2111 'params': {
2112 'skip_download': True,
2113 },
2114 },
29f7c58a 2115 # {
2116 # # Zype embed
2117 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2118 # 'info_dict': {
2119 # 'id': '5b400b834b32992a310622b9',
2120 # 'ext': 'mp4',
2121 # 'title': 'Smoky Barbecue Favorites',
2122 # 'thumbnail': r're:^https?://.*\.jpe?g',
2123 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2124 # 'upload_date': '20170909',
2125 # 'timestamp': 1504915200,
2126 # },
2127 # 'add_ie': [ZypeIE.ie_key()],
2128 # 'params': {
2129 # 'skip_download': True,
2130 # },
2131 # },
e0b6e988
S
2132 {
2133 # videojs embed
2134 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2135 'info_dict': {
2136 'id': 'shell',
2137 'ext': 'mp4',
2138 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2139 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2140 'thumbnail': r're:^https?://.*\.jpg$',
2141 },
2142 'params': {
2143 'skip_download': True,
2144 },
2145 'expected_warnings': ['Failed to download MPD manifest'],
2146 },
5e3da0d4
RA
2147 {
2148 # DailyMotion embed with DM.player
2149 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2150 'info_dict': {
2151 'id': 'k6aKkGHd9FJs4mtJN39',
2152 'ext': 'mp4',
2153 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2154 'description': 'This video is private.',
2155 'uploader_id': 'x1jf30l',
2156 'uploader': 'beIN SPORTS USA',
2157 'upload_date': '20190528',
2158 'timestamp': 1559062971,
2159 },
2160 'params': {
2161 'skip_download': True,
2162 },
2163 },
6e6b70d6
S
2164 # {
2165 # # TODO: find another test
2166 # # http://schema.org/VideoObject
2167 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2168 # 'md5': '888dcf08b7ea671381f00fab74692755',
2169 # 'info_dict': {
2170 # 'id': 'nyvTSJMKId',
2171 # 'ext': 'mp4',
2172 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2173 # 'description': '#love for cats.',
2174 # 'timestamp': 1461244995,
2175 # 'upload_date': '20160421',
2176 # },
2177 # 'params': {
2178 # 'force_generic_extractor': True,
2179 # },
29f7c58a 2180 # },
2181 {
2182 # VHX Embed
2183 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2184 'info_dict': {
2185 'id': '858208',
2186 'ext': 'mp4',
2187 'title': 'Untitled',
2188 'uploader_id': 'user80538407',
2189 'uploader': 'OTT Videos',
2190 },
2191 },
2192 {
2193 # ArcPublishing PoWa video player
2194 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2195 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2196 'info_dict': {
2197 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2198 'ext': 'mp4',
2199 'title': 'Senate candidates wave to voters on Anchorage streets',
2200 'description': 'md5:91f51a6511f090617353dc720318b20e',
2201 'timestamp': 1604378735,
2202 'upload_date': '20201103',
2203 'duration': 1581,
2204 },
2205 },
2181983a 2206 {
2207 # MyChannels SDK embed
2208 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2209 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2210 'md5': '90c0699c37006ef18e198c032d81739c',
2211 'info_dict': {
2212 'id': '194165',
2213 'ext': 'mp4',
2214 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2215 'timestamp': 1611740340,
2216 'upload_date': '20210127',
2217 'duration': 159,
2218 },
2219 },
bc2ca1bb 2220 {
2221 # Simplecast player embed
2222 'url': 'https://www.bio.org/podcast',
2223 'info_dict': {
2224 'id': 'podcast',
2225 'title': 'I AM BIO Podcast | BIO',
2226 },
2227 'playlist_mincount': 52,
2228 },
e4edeb62 2229 {
b73612a2 2230 # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
2231 'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
2232 'only_matching': True,
2233 }, {
e4edeb62 2234 # WimTv embed player
2235 'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
2236 'info_dict': {
2237 'id': 'wearefmi-pt-2-2021',
2238 'title': '#WEAREFMI – PT.2 – 2021 – MsMotorTV',
2239 },
2240 'playlist_count': 1,
a318f59d 2241 }, {
2242 # KVS Player
2243 'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
2244 'info_dict': {
2245 'id': '105',
2246 'display_id': 'kelis-4th-of-july',
2247 'ext': 'mp4',
2248 'title': 'Kelis - 4th Of July',
2249 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2250 },
2251 'params': {
2252 'skip_download': True,
2253 },
2254 }, {
2255 # KVS Player
2256 'url': 'https://www.kvs-demo.com/embed/105/',
2257 'info_dict': {
2258 'id': '105',
2259 'display_id': 'kelis-4th-of-july',
2260 'ext': 'mp4',
2261 'title': 'Kelis - 4th Of July / Embed Player',
2262 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2263 },
2264 'params': {
2265 'skip_download': True,
2266 },
2267 }, {
2268 # KVS Player
2269 'url': 'https://thisvid.com/videos/french-boy-pantsed/',
2270 'md5': '3397979512c682f6b85b3b04989df224',
2271 'info_dict': {
2272 'id': '2400174',
2273 'display_id': 'french-boy-pantsed',
2274 'ext': 'mp4',
2275 'title': 'French Boy Pantsed - ThisVid.com',
2276 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2277 }
2278 }, {
2279 # KVS Player
2280 'url': 'https://thisvid.com/embed/2400174/',
2281 'md5': '3397979512c682f6b85b3b04989df224',
2282 'info_dict': {
2283 'id': '2400174',
2284 'display_id': 'french-boy-pantsed',
2285 'ext': 'mp4',
2286 'title': 'French Boy Pantsed - ThisVid.com',
2287 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2288 }
2289 }, {
2290 # KVS Player
2291 'url': 'https://youix.com/video/leningrad-zoj/',
2292 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2293 'info_dict': {
2294 'id': '18485',
2295 'display_id': 'leningrad-zoj',
2296 'ext': 'mp4',
2297 'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
2298 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2299 }
2300 }, {
2301 # KVS Player
2302 'url': 'https://youix.com/embed/18485',
2303 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2304 'info_dict': {
2305 'id': '18485',
2306 'display_id': 'leningrad-zoj',
2307 'ext': 'mp4',
2308 'title': 'Ленинград - ЗОЖ',
2309 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2310 }
2311 }, {
2312 # KVS Player
2313 'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
2314 'md5': '94166bdb26b4cb1fb9214319a629fc51',
2315 'info_dict': {
2316 'id': '21217',
2317 'display_id': '40-nochey-40-nights-2016',
2318 'ext': 'mp4',
2319 'title': '40 ночей (2016) - BogMedia.org',
2320 'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
2321 }
e4edeb62 2322 },
cfe50f04 2323 ]
9b122384 2324
9b122384
PH
2325 def report_following_redirect(self, new_url):
2326 """Report information extraction."""
79649588 2327 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 2328
4fc946b5
PH
2329 def _extract_rss(self, url, video_id, doc):
2330 playlist_title = doc.find('./channel/title').text
2331 playlist_desc_el = doc.find('./channel/description')
2332 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2333
29f7c58a 2334 NS_MAP = {
2335 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2336 }
2337
76c73715
PH
2338 entries = []
2339 for it in doc.findall('./channel/item'):
01aec848
BG
2340 next_url = None
2341 enclosure_nodes = it.findall('./enclosure')
2342 for e in enclosure_nodes:
2343 next_url = e.attrib.get('url')
2344 if next_url:
2345 break
2346
76c73715 2347 if not next_url:
01aec848 2348 next_url = xpath_text(it, 'link', fatal=False)
76c73715
PH
2349
2350 if not next_url:
2351 continue
2352
29f7c58a 2353 def itunes(key):
2354 return xpath_text(
2355 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2356 default=None)
2357
2358 duration = itunes('duration')
2359 explicit = (itunes('explicit') or '').lower()
2360 if explicit in ('true', 'yes'):
2361 age_limit = 18
2362 elif explicit in ('false', 'no'):
2363 age_limit = 0
2364 else:
2365 age_limit = None
2366
76c73715 2367 entries.append({
413c1f8e 2368 '_type': 'url_transparent',
76c73715
PH
2369 'url': next_url,
2370 'title': it.find('title').text,
29f7c58a 2371 'description': xpath_text(it, 'description', default=None),
2372 'timestamp': unified_timestamp(
2373 xpath_text(it, 'pubDate', default=None)),
2374 'duration': int_or_none(duration) or parse_duration(duration),
2375 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2376 'episode': itunes('title'),
2377 'episode_number': int_or_none(itunes('episode')),
2378 'season_number': int_or_none(itunes('season')),
2379 'age_limit': age_limit,
76c73715 2380 })
4fc946b5
PH
2381
2382 return {
2383 '_type': 'playlist',
2384 'id': url,
2385 'title': playlist_title,
2386 'description': playlist_desc,
2387 'entries': entries,
2388 }
2389
c8e9a235
PH
2390 def _extract_camtasia(self, url, video_id, webpage):
2391 """ Returns None if no camtasia video can be found. """
2392
2393 camtasia_cfg = self._search_regex(
2394 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2395 webpage, 'camtasia configuration file', default=None)
2396 if camtasia_cfg is None:
2397 return None
2398
2399 title = self._html_search_meta('DC.title', webpage, fatal=True)
2400
2401 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2402 camtasia_cfg = self._download_xml(
2403 camtasia_url, video_id,
2404 note='Downloading camtasia configuration',
2405 errnote='Failed to download camtasia configuration')
2406 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2407
2408 entries = []
2409 for n in fileset_node.getchildren():
2410 url_n = n.find('./uri')
2411 if url_n is None:
2412 continue
2413
2414 entries.append({
2415 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2416 'title': '%s - %s' % (title, n.tag),
2417 'url': compat_urlparse.urljoin(url, url_n.text),
2418 'duration': float_or_none(n.find('./duration').text),
2419 })
2420
2421 return {
2422 '_type': 'playlist',
2423 'entries': entries,
2424 'title': title,
2425 }
2426
a318f59d 2427 def _kvs_getrealurl(self, video_url, license_code):
2428 if not video_url.startswith('function/0/'):
2429 return video_url # not obfuscated
2430
2431 url_path, _, url_query = video_url.partition('?')
2432 urlparts = url_path.split('/')[2:]
2433 license = self._kvs_getlicensetoken(license_code)
2434 newmagic = urlparts[5][:32]
2435
2436 for o in range(len(newmagic) - 1, -1, -1):
2437 new = ''
2438 l = (o + sum([int(n) for n in license[o:]])) % 32
2439
2440 for i in range(0, len(newmagic)):
2441 if i == o:
2442 new += newmagic[l]
2443 elif i == l:
2444 new += newmagic[o]
2445 else:
2446 new += newmagic[i]
2447 newmagic = new
2448
2449 urlparts[5] = newmagic + urlparts[5][32:]
2450 return '/'.join(urlparts) + '?' + url_query
2451
2452 def _kvs_getlicensetoken(self, license):
2453 modlicense = license.replace('$', '').replace('0', '1')
2454 center = int(len(modlicense) / 2)
2455 fronthalf = int(modlicense[:center + 1])
2456 backhalf = int(modlicense[center:])
2457
2458 modlicense = str(4 * abs(fronthalf - backhalf))
2459 retval = ''
2460 for o in range(0, center + 1):
2461 for i in range(1, 5):
2462 retval += str((int(license[o + i]) + int(modlicense[o])) % 10)
2463 return retval
2464
9b122384 2465 def _real_extract(self, url):
ebd3c7b3 2466 if url.startswith('//'):
d226c560 2467 return self.url_result(self.http_scheme() + url)
ebd3c7b3 2468
a7130543
JMF
2469 parsed_url = compat_urlparse.urlparse(url)
2470 if not parsed_url.scheme:
a06916d9 2471 default_search = self.get_param('default_search')
04b4d394 2472 if default_search is None:
1f7ccb90 2473 default_search = 'fixup_error'
04b4d394 2474
1f7ccb90 2475 if default_search in ('auto', 'auto_warning', 'fixup_error'):
9c1da4a9 2476 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
6a39ee13 2477 self.report_warning('The url doesn\'t specify the protocol, trying with http')
04b4d394 2478 return self.url_result('http://' + url)
1f7ccb90 2479 elif default_search != 'fixup_error':
9c1fc022 2480 if default_search == 'auto_warning':
0e67ab0d
PH
2481 if re.match(r'^(?:url|URL)$', url):
2482 raise ExtractorError(
7a5c1cfe 2483 'Invalid URL: %r . Call yt-dlp like this: yt-dlp -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
0e67ab0d
PH
2484 expected=True)
2485 else:
6a39ee13 2486 self.report_warning(
7571c02c 2487 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2488 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2489
2490 if default_search in ('error', 'fixup_error'):
7571c02c 2491 raise ExtractorError(
b74e86f4 2492 '%r is not a valid URL. '
7a5c1cfe 2493 'Set --default-search "ytsearch" (or run yt-dlp "ytsearch:%s" ) to search YouTube'
b74e86f4 2494 % (url, url), expected=True)
04b4d394 2495 else:
f2f2c0c2
PH
2496 if ':' not in default_search:
2497 default_search += ':'
04b4d394 2498 return self.url_result(default_search + url)
4d54ef20
PH
2499
2500 url, smuggled_data = unsmuggle_url(url)
2501 force_videoid = None
d6e6a422 2502 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2503 if smuggled_data and 'force_videoid' in smuggled_data:
2504 force_videoid = smuggled_data['force_videoid']
2505 video_id = force_videoid
2506 else:
9dcd6fd3 2507 video_id = self._generic_id(url)
3d83a1ae 2508
79649588 2509 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2510
ebab4520 2511 head_req = HEADRequest(url)
23be51d8 2512 head_response = self._request_webpage(
ebab4520
PH
2513 head_req, video_id,
2514 note=False, errnote='Could not send HEAD request to %s' % url,
2515 fatal=False)
42393ce2 2516
23be51d8 2517 if head_response is not False:
42393ce2 2518 # Check for redirect
7947a1f7 2519 new_url = head_response.geturl()
42393ce2
PH
2520 if url != new_url:
2521 self.report_following_redirect(new_url)
4d54ef20
PH
2522 if force_videoid:
2523 new_url = smuggle_url(
2524 new_url, {'force_videoid': force_videoid})
cecaaf3f 2525 return self.url_result(new_url)
42393ce2 2526
23be51d8
PH
2527 full_response = None
2528 if head_response is False:
5c2266df 2529 request = sanitized_Request(url)
58bde34a
S
2530 request.add_header('Accept-Encoding', '*')
2531 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2532 head_response = full_response
2533
f930e0c7
S
2534 info_dict = {
2535 'id': video_id,
9dcd6fd3 2536 'title': self._generic_title(url),
29f7c58a 2537 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
f930e0c7
S
2538 }
2539
23be51d8 2540 # Check for direct link to a video
955737b2 2541 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2542 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2543 if m:
4e363703 2544 format_id = compat_str(m.group('format_id'))
c26326c1 2545 subtitles = {}
f930e0c7 2546 if format_id.endswith('mpegurl'):
c26326c1 2547 formats, subtitles = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
f930e0c7
S
2548 elif format_id == 'f4m':
2549 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2550 else:
2551 formats = [{
4e363703 2552 'format_id': format_id,
eadc3ccd 2553 'url': url,
2554 'vcodec': 'none' if m.group('type') == 'audio' else None
2555 }]
de6c51e8 2556 info_dict['direct'] = True
19dbaeec 2557 self._sort_formats(formats)
de6c51e8 2558 info_dict['formats'] = formats
c26326c1 2559 info_dict['subtitles'] = subtitles
f930e0c7 2560 return info_dict
42393ce2 2561
a06916d9 2562 if not self.get_param('test', False) and not is_intentional:
2563 force = self.get_param('force_generic_extractor', False)
6a39ee13 2564 self.report_warning(
2fece970 2565 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2566
4e262a88 2567 if not full_response:
5c2266df 2568 request = sanitized_Request(url)
58bde34a
S
2569 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2570 # making it impossible to download only chunk of the file (yet we need only 512kB to
7a5c1cfe 2571 # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
58bde34a
S
2572 # that will always result in downloading the whole file that is not desirable.
2573 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2574 # to accept raw bytes and being able to download only a chunk.
2575 # It may probably better to solve this by checking Content-Type for application/octet-stream
2576 # after HEAD request finishes, but not sure if we can rely on this.
2577 request.add_header('Accept-Encoding', '*')
2578 full_response = self._request_webpage(request, video_id)
4e262a88 2579
5940862d
S
2580 first_bytes = full_response.read(512)
2581
2582 # Is it an M3U playlist?
0d769bcb 2583 if first_bytes.startswith(b'#EXTM3U'):
da1c94ee 2584 info_dict['formats'], info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
19dbaeec 2585 self._sort_formats(info_dict['formats'])
5940862d
S
2586 return info_dict
2587
4e262a88
PH
2588 # Maybe it's a direct link to a video?
2589 # Be careful not to download the whole thing!
61ca9a80 2590 if not is_html(first_bytes):
6a39ee13 2591 self.report_warning(
4e262a88 2592 'URL could be a direct video link, returning it as such.')
f930e0c7 2593 info_dict.update({
4e262a88
PH
2594 'direct': True,
2595 'url': url,
f930e0c7
S
2596 })
2597 return info_dict
4e262a88
PH
2598
2599 webpage = self._webpage_read_content(
2600 full_response, url, video_id, prefix=first_bytes)
2601
2181983a 2602 if '<title>DPG Media Privacy Gate</title>' in webpage:
2603 webpage = self._download_webpage(url, video_id)
2604
9b122384 2605 self.report_extraction(video_id)
887c6acd 2606
1b840245 2607 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2608 try:
61241abb 2609 try:
2610 doc = compat_etree_fromstring(webpage)
2611 except compat_xml_parse_error:
2612 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
2613 if doc.tag == 'rss':
2614 return self._extract_rss(url, video_id, doc)
cc99a77a 2615 elif doc.tag == 'SmoothStreamingMedia':
7a450a3b 2616 info_dict['formats'], info_dict['subtitles'] = self._parse_ism_formats_and_subtitles(doc, url)
cc99a77a
S
2617 self._sort_formats(info_dict['formats'])
2618 return info_dict
e5e8d20a 2619 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
2620 smil = self._parse_smil(doc, url, video_id)
2621 self._sort_formats(smil['formats'])
2622 return smil
729accb4 2623 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
96b8b9ab 2624 return self.playlist_result(
47a5cb77
S
2625 self._parse_xspf(
2626 doc, video_id, xspf_url=url,
7947a1f7 2627 xspf_base_url=full_response.geturl()),
96b8b9ab 2628 video_id)
1b840245 2629 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
7de27caf 2630 info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles(
d3f8b76b 2631 doc,
7947a1f7 2632 mpd_base_url=full_response.geturl().rpartition('/')[0],
86f4d14f 2633 mpd_url=url)
19dbaeec 2634 self._sort_formats(info_dict['formats'])
f930e0c7
S
2635 return info_dict
2636 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2637 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 2638 self._sort_formats(info_dict['formats'])
f930e0c7 2639 return info_dict
f7300c5c 2640 except compat_xml_parse_error:
4fc946b5
PH
2641 pass
2642
c8e9a235
PH
2643 # Is it a Camtasia project?
2644 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2645 if camtasia_res is not None:
2646 return camtasia_res
2647
14390730 2648 # Sometimes embedded video player is hidden behind percent encoding
067aa17e 2649 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
14390730 2650 # Unescaping the whole page allows to handle those cases in a generic way
29f7c58a 2651 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2652 # There probably should be a second run of generic extractor on unescaped webpage.
2653 # webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2654
7cb51b5d
S
2655 # Unescape squarespace embeds to be detected by generic extractor,
2656 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2657 webpage = re.sub(
2658 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2659 lambda x: unescapeHTML(x.group(0)), webpage)
d78657fd 2660
887c6acd
PH
2661 # it's tempting to parse this further, but you would
2662 # have to take into account all the variations like
2663 # Video Title - Site Name
2664 # Site Name | Video Title
2665 # Video Title - Tagline | Site Name
2666 # and so on and so forth; it's just not practical
6f41b2bc
S
2667 video_title = self._og_search_title(
2668 webpage, default=None) or self._html_search_regex(
79649588
PH
2669 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2670 default='video')
ef4fd848 2671
4d805e06
PH
2672 # Try to detect age limit automatically
2673 age_limit = self._rta_search(webpage)
2674 # And then there are the jokers who advertise that they use RTA,
2675 # but actually don't.
2676 AGE_LIMIT_MARKERS = [
197224b7 2677 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
4d805e06
PH
2678 ]
2679 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2680 age_limit = 18
2681
ef4fd848
PH
2682 # video uploader is domain name
2683 video_uploader = self._search_regex(
79649588 2684 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2685
6f41b2bc
S
2686 video_description = self._og_search_description(webpage, default=None)
2687 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2688
b311b0ea
S
2689 info_dict.update({
2690 'title': video_title,
2691 'description': video_description,
2692 'thumbnail': video_thumbnail,
2693 'age_limit': age_limit,
2694 })
2695
1f4b722b 2696 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2697 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2698 if bc_urls:
99877772
PH
2699 entries = [{
2700 '_type': 'url',
2701 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2702 'ie_key': 'BrightcoveLegacy'
99877772
PH
2703 } for bc_url in bc_urls]
2704
2705 return {
2706 '_type': 'playlist',
2707 'title': video_title,
2708 'id': video_id,
2709 'entries': entries,
2710 }
cfe50f04 2711
f6519f89 2712 # Look for Brightcove New Studio embeds
0254f93b 2713 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2714 if bc_urls:
5399ab3f
S
2715 return self.playlist_from_matches(
2716 bc_urls, video_id, video_title,
2717 getter=lambda x: smuggle_url(x, {'referrer': url}),
2718 ie='BrightcoveNew')
ed126900 2719
4e826cd9
S
2720 # Look for Nexx embeds
2721 nexx_urls = NexxIE._extract_urls(webpage)
2722 if nexx_urls:
2723 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2724
3f59b015
S
2725 # Look for Nexx iFrame embeds
2726 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2727 if nexx_embed_urls:
2728 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2729
4d8819d2
S
2730 # Look for ThePlatform embeds
2731 tp_urls = ThePlatformIE._extract_urls(webpage)
2732 if tp_urls:
46b18f23 2733 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2734
29f7c58a 2735 arc_urls = ArcPublishingIE._extract_urls(webpage)
2736 if arc_urls:
2737 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2738
2181983a 2739 mychannels_urls = MedialaanIE._extract_urls(webpage)
2740 if mychannels_urls:
2741 return self.playlist_from_matches(
2742 mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
2743
59b8ab58
PH
2744 # Look for embedded rtl.nl player
2745 matches = re.findall(
2637fadc 2746 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
59b8ab58
PH
2747 webpage)
2748 if matches:
46b18f23 2749 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2750
09b9c45e
S
2751 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2752 if vimeo_urls:
46b18f23 2753 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2754
29f7c58a 2755 vhx_url = VHXEmbedIE._extract_url(webpage)
2756 if vhx_url:
2757 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2758
a1b85269
YCH
2759 vid_me_embed_url = self._search_regex(
2760 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2761 webpage, 'vid.me embed', default=None)
2762 if vid_me_embed_url is not None:
2763 return self.url_result(vid_me_embed_url, 'Vidme')
2764
df0c8151 2765 # Invidious Instances
2766 # https://github.com/yt-dlp/yt-dlp/issues/195
2767 # https://github.com/iv-org/invidious/pull/1730
2768 youtube_url = self._search_regex(
2769 r'<link rel="alternate" href="(https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2770 webpage, 'youtube link', default=None)
2771 if youtube_url:
2772 return self.url_result(youtube_url, YoutubeIE.ie_key())
2773
66c9fa36
S
2774 # Look for YouTube embeds
2775 youtube_urls = YoutubeIE._extract_urls(webpage)
2776 if youtube_urls:
46b18f23 2777 return self.playlist_from_matches(
66c9fa36 2778 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2779
ad213a1d 2780 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2781 if matches:
46b18f23 2782 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2783
8489578d
NJ
2784 # Look for embedded Dailymotion playlist player (#3822)
2785 m = re.search(
2786 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2787 if m:
2788 playlists = re.findall(
2789 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2790 if playlists:
46b18f23
JH
2791 return self.playlist_from_matches(
2792 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2793
71a1db89
S
2794 # Look for DailyMail embeds
2795 dailymail_urls = DailyMailIE._extract_urls(webpage)
2796 if dailymail_urls:
2797 return self.playlist_from_matches(
2798 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2799
be7dacf9
S
2800 # Look for Teachable embeds, must be before Wistia
2801 teachable_url = TeachableIE._extract_url(webpage, url)
2802 if teachable_url:
2803 return self.url_result(teachable_url)
2804
ef4fd848 2805 # Look for embedded Wistia player
fda6d237
S
2806 wistia_urls = WistiaIE._extract_urls(webpage)
2807 if wistia_urls:
2808 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2809 for entry in playlist['entries']:
2810 entry.update({
2811 '_type': 'url_transparent',
2812 'uploader': video_uploader,
2813 })
2814 return playlist
5f6a1245 2815
bab19a8e
S
2816 # Look for SVT player
2817 svt_url = SVTIE._extract_url(webpage)
2818 if svt_url:
2819 return self.url_result(svt_url, 'SVT')
2820
c19f7764
JMF
2821 # Look for Bandcamp pages with custom domain
2822 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2823 if mobj is not None:
2824 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2825 # Don't set the extractor because it can be a track url or an album
2826 return self.url_result(burl)
c19f7764 2827
f25571ff
PH
2828 # Look for embedded Vevo player
2829 mobj = re.search(
2830 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2831 if mobj is not None:
2832 return self.url_result(mobj.group('url'))
796df3c6
S
2833
2834 # Look for embedded Viddler player
cb454b33
S
2835 mobj = re.search(
2836 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2837 webpage)
796df3c6
S
2838 if mobj is not None:
2839 return self.url_result(mobj.group('url'))
f25571ff 2840
3378d67a
S
2841 # Look for NYTimes player
2842 mobj = re.search(
2843 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2844 webpage)
2845 if mobj is not None:
2846 return self.url_result(mobj.group('url'))
2847
cefdf970
S
2848 # Look for Libsyn player
2849 mobj = re.search(
2850 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2851 if mobj is not None:
2852 return self.url_result(mobj.group('url'))
2853
c0d0b01f 2854 # Look for Ooyala videos
3089bc74
S
2855 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2856 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2857 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2858 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2859 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2860 if mobj is not None:
9837cb75
RA
2861 embed_token = self._search_regex(
2862 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2863 webpage, 'ooyala embed token', default=None)
2864 return OoyalaIE._build_url_result(smuggle_url(
2865 mobj.group('ec'), {
2866 'domain': url,
2867 'embed_token': embed_token,
2868 }))
c0d0b01f 2869
f076b638 2870 # Look for multiple Ooyala embeds on SBN network websites
2871 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2872 if mobj is not None:
2873 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2874 if embeds:
46b18f23
JH
2875 return self.playlist_from_matches(
2876 embeds, video_id, video_title,
2877 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2878
aa94a6d3 2879 # Look for Aparat videos
48099643 2880 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2881 if mobj is not None:
2882 return self.url_result(mobj.group(1), 'Aparat')
2883
c93c2ab1 2884 # Look for MPORA videos
c3f51436 2885 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2886 if mobj is not None:
2887 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2888
9834872b 2889 # Look for embedded Facebook player
0646e34c
S
2890 facebook_urls = FacebookIE._extract_urls(webpage)
2891 if facebook_urls:
2892 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2893
ca97a56e
S
2894 # Look for embedded VK player
2895 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2896 if mobj is not None:
2897 return self.url_result(mobj.group('url'), 'VK')
2898
33d4fdab 2899 # Look for embedded Odnoklassniki player
416c3ca7
RA
2900 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2901 if odnoklassniki_url:
2902 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
33d4fdab 2903
b73612a2 2904 # Look for sibnet embedded player
2905 sibnet_urls = VKIE._extract_sibnet_urls(webpage)
2906 if sibnet_urls:
2907 return self.playlist_from_matches(sibnet_urls, video_id, video_title)
2908
0364fa8b
S
2909 # Look for embedded ivi player
2910 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2911 if mobj is not None:
2912 return self.url_result(mobj.group('url'), 'Ivi')
2913
db1f3888
PH
2914 # Look for embedded Huffington Post player
2915 mobj = re.search(
c3f51436 2916 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2917 if mobj is not None:
2918 return self.url_result(mobj.group('url'), 'HuffPost')
2919
1b86cc41 2920 # Look for embed.ly
2921 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2922 if mobj is not None:
2923 return self.url_result(mobj.group('url'))
2924 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2925 if mobj is not None:
f7e6f7fa 2926 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2927
60cc4dc4
PH
2928 # Look for funnyordie embed
2929 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2930 if matches:
46b18f23
JH
2931 return self.playlist_from_matches(
2932 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2933
bc2ca1bb 2934 # Look for Simplecast embeds
2935 simplecast_urls = SimplecastIE._extract_urls(webpage)
2936 if simplecast_urls:
2937 return self.playlist_from_matches(
2938 simplecast_urls, video_id, video_title)
2939
db546cf8
S
2940 # Look for BBC iPlayer embed
2941 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2942 if matches:
46b18f23 2943 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2944
93d020dd
S
2945 # Look for embedded RUTV player
2946 rutv_url = RUTVIE._extract_url(webpage)
2947 if rutv_url:
2948 return self.url_result(rutv_url, 'RUTV')
2949
494f20cb 2950 # Look for embedded TVC player
b8599718
S
2951 tvc_url = TVCIE._extract_url(webpage)
2952 if tvc_url:
2953 return self.url_result(tvc_url, 'TVC')
494f20cb 2954
d40a3b5b 2955 # Look for embedded SportBox player
476cf548 2956 sportbox_urls = SportBoxIE._extract_urls(webpage)
d40a3b5b 2957 if sportbox_urls:
476cf548 2958 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
d40a3b5b 2959
2bb5b6d0
S
2960 # Look for embedded XHamster player
2961 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2962 if xhamster_urls:
46b18f23 2963 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2964
2c9ca782
S
2965 # Look for embedded TNAFlixNetwork player
2966 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2967 if tnaflix_urls:
46b18f23 2968 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2969
b52c9ef1
S
2970 # Look for embedded PornHub player
2971 pornhub_urls = PornHubIE._extract_urls(webpage)
2972 if pornhub_urls:
46b18f23 2973 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2974
37e7a71c
S
2975 # Look for embedded DrTuber player
2976 drtuber_urls = DrTuberIE._extract_urls(webpage)
2977 if drtuber_urls:
46b18f23 2978 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2979
e28ed498
S
2980 # Look for embedded RedTube player
2981 redtube_urls = RedTubeIE._extract_urls(webpage)
2982 if redtube_urls:
46b18f23 2983 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 2984
06993715
S
2985 # Look for embedded Tube8 player
2986 tube8_urls = Tube8IE._extract_urls(webpage)
2987 if tube8_urls:
2988 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2989
4e7b5bba
S
2990 # Look for embedded Mofosex player
2991 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2992 if mofosex_urls:
2993 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2994
8fae1a04
S
2995 # Look for embedded Spankwire player
2996 spankwire_urls = SpankwireIE._extract_urls(webpage)
2997 if spankwire_urls:
2998 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2999
52c4c515
S
3000 # Look for embedded YouPorn player
3001 youporn_urls = YouPornIE._extract_urls(webpage)
3002 if youporn_urls:
3003 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
3004
9872d311
S
3005 # Look for embedded Tvigle player
3006 mobj = re.search(
3007 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
3008 if mobj is not None:
3009 return self.url_result(mobj.group('url'), 'Tvigle')
3010
7e2ede98
JMF
3011 # Look for embedded TED player
3012 mobj = re.search(
d7cc31b6 3013 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
3014 if mobj is not None:
3015 return self.url_result(mobj.group('url'), 'TED')
3016
5c386252 3017 # Look for embedded Ustream videos
d77ac737
YCH
3018 ustream_url = UstreamIE._extract_url(webpage)
3019 if ustream_url:
3020 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 3021
893f8832 3022 # Look for embedded arte.tv player
8bdd16b4 3023 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
3024 if arte_urls:
3025 return self.playlist_from_matches(arte_urls, video_id, video_title)
893f8832 3026
cbd55ade
S
3027 # Look for embedded francetv player
3028 mobj = re.search(
3029 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
3030 webpage)
3031 if mobj is not None:
3032 return self.url_result(mobj.group('url'))
3033
e6c2d9ad 3034 # Look for embedded Myvi.ru player
6dd94d3a 3035 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
3036 if myvi_url:
3037 return self.url_result(myvi_url)
3038
dfb1b146 3039 # Look for embedded soundcloud player
548c3957 3040 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
94aae015 3041 if soundcloud_urls:
548c3957 3042 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
20991253 3043
027e2312
S
3044 # Look for tunein player
3045 tunein_urls = TuneInBaseIE._extract_urls(webpage)
3046 if tunein_urls:
46b18f23 3047 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 3048
c5cd249e 3049 # Look for embedded mtvservices player
46fde8a1
S
3050 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
3051 if mtvservices_url:
3052 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 3053
49807b4a
S
3054 # Look for embedded yahoo player
3055 mobj = re.search(
3056 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
3057 webpage)
3058 if mobj is not None:
3059 return self.url_result(mobj.group('url'), 'Yahoo')
3060
2ef6fcb5
PH
3061 # Look for embedded sbs.com.au player
3062 mobj = re.search(
e98b8e79
PH
3063 r'''(?x)
3064 (?:
3065 <meta\s+property="og:video"\s+content=|
3066 <iframe[^>]+?src=
3067 )
3068 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
3069 webpage)
3070 if mobj is not None:
3071 return self.url_result(mobj.group('url'), 'SBS')
3072
42bdd9d0
PH
3073 # Look for embedded Cinchcast player
3074 mobj = re.search(
3075 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
3076 webpage)
3077 if mobj is not None:
3078 return self.url_result(mobj.group('url'), 'Cinchcast')
3079
1a94ff68 3080 mobj = re.search(
5263cdfc 3081 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 3082 webpage)
8001607e
YCH
3083 if not mobj:
3084 mobj = re.search(
1418a043 3085 r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
8001607e 3086 webpage)
1a94ff68
S
3087 if mobj is not None:
3088 return self.url_result(mobj.group('url'), 'MLB')
3089
1419fafd 3090 mobj = re.search(
dd467d33 3091 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
3092 webpage)
3093 if mobj is not None:
3094 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
3095
af63fed7 3096 mobj = re.search(
78d3b3e2 3097 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
3098 webpage)
3099 if mobj is not None:
3100 return self.url_result(mobj.group('url'), 'Livestream')
3101
255fca5e
S
3102 # Look for Zapiks embed
3103 mobj = re.search(
3104 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
3105 if mobj is not None:
3106 return self.url_result(mobj.group('url'), 'Zapiks')
3107
e3216b82 3108 # Look for Kaltura embeds
562de77f
S
3109 kaltura_urls = KalturaIE._extract_urls(webpage)
3110 if kaltura_urls:
3111 return self.playlist_from_matches(
3112 kaltura_urls, video_id, video_title,
3113 getter=lambda x: smuggle_url(x, {'source_url': url}),
3114 ie=KalturaIE.ie_key())
e3216b82 3115
665e9452 3116 # Look for EaglePlatform embeds
06a96da1
S
3117 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
3118 if eagleplatform_url:
665e9452 3119 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 3120
665e9452 3121 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
3122 mobj = re.search(
3123 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
3124 if mobj is not None:
3125 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
3126
f8388757 3127 # Look for Pladform embeds
45dad7ba
S
3128 pladform_url = PladformIE._extract_url(webpage)
3129 if pladform_url:
3130 return self.url_result(pladform_url)
f8388757 3131
ff18735c
S
3132 # Look for Videomore embeds
3133 videomore_url = VideomoreIE._extract_url(webpage)
3134 if videomore_url:
3135 return self.url_result(videomore_url)
3136
83f1481b
S
3137 # Look for Webcaster embeds
3138 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3139 if webcaster_url:
3140 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3141
2dcc114f
S
3142 # Look for Playwire embeds
3143 mobj = re.search(
3144 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
3145 if mobj is not None:
3146 return self.url_result(mobj.group('url'))
3147
ad320e9b
NJ
3148 # Look for 5min embeds
3149 mobj = re.search(
3150 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3151 if mobj is not None:
3152 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3153
18153f1b
S
3154 # Look for Crooks and Liars embeds
3155 mobj = re.search(
3156 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
3157 if mobj is not None:
3158 return self.url_result(mobj.group('url'))
3159
a2edf2e7
YCH
3160 # Look for NBC Sports VPlayer embeds
3161 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3162 if nbc_sports_url:
3163 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
3164
de3eb07e
YCH
3165 # Look for NBC News embeds
3166 nbc_news_embed_url = re.search(
3167 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3168 if nbc_news_embed_url:
3169 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3170
653789af 3171 # Look for Google Drive embeds
5b251628 3172 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 3173 if google_drive_url:
3174 return self.url_result(google_drive_url, 'GoogleDrive')
3175
418c5cc3
YCH
3176 # Look for UDN embeds
3177 mobj = re.search(
2637fadc 3178 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
3179 if mobj is not None:
3180 return self.url_result(
0a160363 3181 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 3182
2fe1b5bd
YCH
3183 # Look for Senate ISVP iframe
3184 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3185 if senate_isvp_url:
25c3a734 3186 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 3187
55adb63e
RA
3188 # Look for Kinja embeds
3189 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3190 if kinja_embed_urls:
3191 return self.playlist_from_matches(
3192 kinja_embed_urls, video_id, video_title)
3193
1ac1c4c2
S
3194 # Look for OnionStudios embeds
3195 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3196 if onionstudios_url:
3197 return self.url_result(onionstudios_url)
3198
67167920 3199 # Look for ViewLift embeds
3200 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3201 if viewlift_url:
3202 return self.url_result(viewlift_url)
eedd20ef 3203
7cb09524 3204 # Look for JWPlatform embeds
b0ead0e0
S
3205 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3206 if jwplatform_urls:
3207 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
7cb09524 3208
aecfcd4e
S
3209 # Look for Digiteka embeds
3210 digiteka_url = DigitekaIE._extract_url(webpage)
3211 if digiteka_url:
3212 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 3213
1979969f
S
3214 # Look for Arkena embeds
3215 arkena_url = ArkenaIE._extract_url(webpage)
3216 if arkena_url:
3217 return self.url_result(arkena_url, ArkenaIE.ie_key())
3218
b1c35797
RA
3219 # Look for Piksel embeds
3220 piksel_url = PikselIE._extract_url(webpage)
3221 if piksel_url:
3222 return self.url_result(piksel_url, PikselIE.ie_key())
3223
1bf996fa 3224 # Look for Limelight embeds
e5d39886
S
3225 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3226 if limelight_urls:
3227 return self.playlist_result(
3228 limelight_urls, video_id, video_title, video_description)
3229
7986c3ab
S
3230 # Look for Anvato embeds
3231 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3232 if anvato_urls:
3233 return self.playlist_result(
3234 anvato_urls, video_id, video_title, video_description)
3235
a5158f38
YCH
3236 # Look for AdobeTVVideo embeds
3237 mobj = re.search(
3238 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3239 webpage)
3240 if mobj is not None:
3241 return self.url_result(
3242 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3243 'AdobeTVVideo')
3244
088e1aac
YCH
3245 # Look for Vine embeds
3246 mobj = re.search(
3247 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3248 webpage)
3249 if mobj is not None:
3250 return self.url_result(
3251 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3252
217d5ae0
RA
3253 # Look for VODPlatform embeds
3254 mobj = re.search(
bd2c211f 3255 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
217d5ae0
RA
3256 webpage)
3257 if mobj is not None:
3258 return self.url_result(
93b84045 3259 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 3260
7d273a38
RA
3261 # Look for Mangomolo embeds
3262 mobj = re.search(
755541a4
RA
3263 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3264 (?:
3265 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3266 player\.mangomolo\.com/v1
3267 )/
7d273a38
RA
3268 (?:
3269 video\?.*?\bid=(?P<video_id>\d+)|
755541a4 3270 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
7d273a38
RA
3271 ).+?)\1''', webpage)
3272 if mobj is not None:
3273 info = {
3274 '_type': 'url_transparent',
3275 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3276 'title': video_title,
3277 'description': video_description,
3278 'thumbnail': video_thumbnail,
3279 'uploader': video_uploader,
3280 }
3281 video_id = mobj.group('video_id')
3282 if video_id:
3283 info.update({
3284 'ie_key': 'MangomoloVideo',
3285 'id': video_id,
3286 })
3287 else:
3288 info.update({
3289 'ie_key': 'MangomoloLive',
3290 'id': mobj.group('channel_id'),
3291 })
3292 return info
3293
5a51775a
YCH
3294 # Look for Instagram embeds
3295 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3296 if instagram_embed_url is not None:
11e60fca
S
3297 return self.url_result(
3298 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 3299
5d39176f
S
3300 # Look for 3Q SDN embeds
3301 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3302 if threeqsdn_url:
6f41b2bc
S
3303 return {
3304 '_type': 'url_transparent',
3305 'ie_key': ThreeQSDNIE.ie_key(),
3306 'url': self._proto_relative_url(threeqsdn_url),
3307 'title': video_title,
3308 'description': video_description,
3309 'thumbnail': video_thumbnail,
3310 'uploader': video_uploader,
3311 }
5d39176f 3312
2a1321a2
S
3313 # Look for VBOX7 embeds
3314 vbox7_url = Vbox7IE._extract_url(webpage)
3315 if vbox7_url:
3316 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3317
b0c8f2e9
DR
3318 # Look for DBTV embeds
3319 dbtv_urls = DBTVIE._extract_urls(webpage)
3320 if dbtv_urls:
46b18f23 3321 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 3322
e186a9ec
S
3323 # Look for Videa embeds
3324 videa_urls = VideaIE._extract_urls(webpage)
3325 if videa_urls:
46b18f23 3326 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 3327
b687c85e
S
3328 # Look for 20 minuten embeds
3329 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3330 if twentymin_urls:
46b18f23
JH
3331 return self.playlist_from_matches(
3332 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 3333
6ef3e65a
S
3334 # Look for VideoPress embeds
3335 videopress_urls = VideoPressIE._extract_urls(webpage)
3336 if videopress_urls:
46b18f23
JH
3337 return self.playlist_from_matches(
3338 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 3339
eb3079b6
S
3340 # Look for Rutube embeds
3341 rutube_urls = RutubeIE._extract_urls(webpage)
3342 if rutube_urls:
46b18f23 3343 return self.playlist_from_matches(
2583c0b5 3344 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 3345
55719459
JH
3346 # Look for WashingtonPost embeds
3347 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3348 if wapo_urls:
3349 return self.playlist_from_matches(
3350 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3351
5d29af3d 3352 # Look for Mediaset embeds
8fd12a08 3353 mediaset_urls = MediasetIE._extract_urls(self, webpage)
5d29af3d
S
3354 if mediaset_urls:
3355 return self.playlist_from_matches(
3356 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3357
73cf76a9
S
3358 # Look for JOJ.sk embeds
3359 joj_urls = JojIE._extract_urls(webpage)
3360 if joj_urls:
3361 return self.playlist_from_matches(
3362 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3363
24e966e8
PH
3364 # Look for megaphone.fm embeds
3365 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3366 if mpfn_urls:
3367 return self.playlist_from_matches(
3368 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3369
1663bd6e
S
3370 # Look for vzaar embeds
3371 vzaar_urls = VzaarIE._extract_urls(webpage)
3372 if vzaar_urls:
3373 return self.playlist_from_matches(
3374 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3375
26bae2d9
S
3376 channel9_urls = Channel9IE._extract_urls(webpage)
3377 if channel9_urls:
3378 return self.playlist_from_matches(
3379 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3380
0987f2dd
T
3381 vshare_urls = VShareIE._extract_urls(webpage)
3382 if vshare_urls:
3383 return self.playlist_from_matches(
3384 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3385
8056c854 3386 # Look for Mediasite embeds
2ca7ed41
S
3387 mediasite_urls = MediasiteIE._extract_urls(webpage)
3388 if mediasite_urls:
3389 entries = [
3390 self.url_result(smuggle_url(
3391 compat_urlparse.urljoin(url, mediasite_url),
3392 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3393 for mediasite_url in mediasite_urls]
3394 return self.playlist_result(entries, video_id, video_title)
8056c854 3395
7d540621
S
3396 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3397 if springboardplatform_urls:
3398 return self.playlist_from_matches(
3399 springboardplatform_urls, video_id, video_title,
3400 ie=SpringboardPlatformIE.ie_key())
3401
4c780fbd
S
3402 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3403 if yapfiles_urls:
3404 return self.playlist_from_matches(
3405 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3406
86c8cfc5
S
3407 vice_urls = ViceIE._extract_urls(webpage)
3408 if vice_urls:
3409 return self.playlist_from_matches(
3410 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3411
178ee883
S
3412 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3413 if xfileshare_urls:
3414 return self.playlist_from_matches(
3415 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3416
660a230b
S
3417 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3418 if cloudflarestream_urls:
3419 return self.playlist_from_matches(
3420 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3421
8b4b400a 3422 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
6bd499e8
S
3423 if peertube_urls:
3424 return self.playlist_from_matches(
3425 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3426
aee36ca8
S
3427 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3428 if indavideo_urls:
3429 return self.playlist_from_matches(
3430 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3431
cfd7f2a6
S
3432 apa_urls = APAIE._extract_urls(webpage)
3433 if apa_urls:
3434 return self.playlist_from_matches(
3435 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3436
f51f526b
S
3437 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3438 if foxnews_urls:
3439 return self.playlist_from_matches(
3440 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3441
2e4350ee 3442 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
d3431dcb
S
3443 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3444 webpage)]
3445 if sharevideos_urls:
3446 return self.playlist_from_matches(
3447 sharevideos_urls, video_id, video_title)
3448
9d1b2138
S
3449 viqeo_urls = ViqeoIE._extract_urls(webpage)
3450 if viqeo_urls:
3451 return self.playlist_from_matches(
3452 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
57c68ec4
S
3453
3454 expressen_urls = ExpressenIE._extract_urls(webpage)
3455 if expressen_urls:
3456 return self.playlist_from_matches(
3457 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
9d1b2138 3458
83852e57
S
3459 zype_urls = ZypeIE._extract_urls(webpage)
3460 if zype_urls:
3461 return self.playlist_from_matches(
3462 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3463
feee67ae 3464 gedi_urls = GediDigitalIE._extract_urls(webpage)
902784a2 3465 if gedi_urls:
3466 return self.playlist_from_matches(
feee67ae 3467 gedi_urls, video_id, video_title, ie=GediDigitalIE.ie_key())
902784a2 3468
feee67ae 3469 # Look for RCS media group embeds
a85e131b 3470 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3471 if rcs_urls:
3472 return self.playlist_from_matches(
3473 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3474
e4edeb62 3475 wimtv_urls = WimTVIE._extract_urls(webpage)
3476 if wimtv_urls:
3477 return self.playlist_from_matches(
3478 wimtv_urls, video_id, video_title, ie=WimTVIE.ie_key())
3479
097f1663 3480 bitchute_urls = BitChuteIE._extract_urls(webpage)
3481 if bitchute_urls:
3482 return self.playlist_from_matches(
3483 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3484
62852977 3485 rumble_urls = RumbleEmbedIE._extract_urls(webpage)
3486 if len(rumble_urls) == 1:
3487 return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
3488 if rumble_urls:
3489 return self.playlist_from_matches(
3490 rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
3491
bd264412
YCH
3492 # Look for HTML5 media
3493 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3494 if entries:
9ce1ac40 3495 if len(entries) == 1:
3496 entries[0].update({
bd264412
YCH
3497 'id': video_id,
3498 'title': video_title,
3499 })
9ce1ac40 3500 else:
3501 for num, entry in enumerate(entries, start=1):
3502 entry.update({
3503 'id': '%s-%s' % (video_id, num),
3504 'title': '%s (%d)' % (video_title, num),
3505 })
3506 for entry in entries:
bd264412 3507 self._sort_formats(entry['formats'])
9ce1ac40 3508 return self.playlist_result(entries, video_id, video_title)
bd264412 3509
c73e330e
RU
3510 jwplayer_data = self._find_jwplayer_data(
3511 webpage, video_id, transform_source=js_to_json)
3512 if jwplayer_data:
3d08f63d
MYM
3513 try:
3514 info = self._parse_jwplayer_data(
3515 jwplayer_data, video_id, require_title=False, base_url=url)
3516 return merge_dicts(info, info_dict)
3517 except ExtractorError:
067aa17e 3518 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3d08f63d 3519 pass
a4a554a7 3520
63d990d2
S
3521 # Video.js embed
3522 mobj = re.search(
c5b7014a 3523 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
3524 webpage)
3525 if mobj is not None:
3526 sources = self._parse_json(
3527 mobj.group(1), video_id, transform_source=js_to_json,
3528 fatal=False) or []
c5b7014a
S
3529 if not isinstance(sources, list):
3530 sources = [sources]
63d990d2 3531 formats = []
da1c94ee 3532 subtitles = {}
63d990d2 3533 for source in sources:
e0b6e988
S
3534 src = source.get('src')
3535 if not src or not isinstance(src, compat_str):
63d990d2
S
3536 continue
3537 src = compat_urlparse.urljoin(url, src)
3538 src_type = source.get('type')
3539 if isinstance(src_type, compat_str):
3540 src_type = src_type.lower()
3541 ext = determine_ext(src).lower()
3542 if src_type == 'video/youtube':
3543 return self.url_result(src, YoutubeIE.ie_key())
3544 if src_type == 'application/dash+xml' or ext == 'mpd':
da1c94ee
F
3545 fmts, subs = self._extract_mpd_formats_and_subtitles(
3546 src, video_id, mpd_id='dash', fatal=False)
3547 formats.extend(fmts)
3548 self._merge_subtitles(subs, target=subtitles)
63d990d2 3549 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
da1c94ee 3550 fmts, subs = self._extract_m3u8_formats_and_subtitles(
63d990d2 3551 src, video_id, 'mp4', entry_protocol='m3u8_native',
da1c94ee
F
3552 m3u8_id='hls', fatal=False)
3553 formats.extend(fmts)
3554 self._merge_subtitles(subs, target=subtitles)
63d990d2
S
3555 else:
3556 formats.append({
3557 'url': src,
3089bc74
S
3558 'ext': (mimetype2ext(src_type)
3559 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
b73612a2 3560 'http_headers': {
3561 'Referer': full_response.geturl(),
3562 },
63d990d2 3563 })
da1c94ee 3564 if formats or subtitles:
63d990d2
S
3565 self._sort_formats(formats)
3566 info_dict['formats'] = formats
da1c94ee 3567 info_dict['subtitles'] = subtitles
63d990d2
S
3568 return info_dict
3569
ff17be3a
S
3570 # Looking for http://schema.org/VideoObject
3571 json_ld = self._search_json_ld(
3572 webpage, video_id, default={}, expected_type='VideoObject')
3573 if json_ld.get('url'):
3574 return merge_dicts(json_ld, info_dict)
3575
ced659bb 3576 def check_video(vurl):
a0f71985
PH
3577 if YoutubeIE.suitable(vurl):
3578 return True
b7a8c1bc
S
3579 if RtmpIE.suitable(vurl):
3580 return True
ced659bb
S
3581 vpath = compat_urlparse.urlparse(vurl).path
3582 vext = determine_ext(vpath)
0ee79a37 3583 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
3584
3585 def filter_video(urls):
3586 return list(filter(check_video, urls))
3587
9b122384 3588 # Start with something easy: JW Player in SWFObject
ced659bb 3589 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 3590 if not found:
d981cef6 3591 # Look for gorilla-vid style embedding
ced659bb 3592 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
3593 (?:
3594 jw_plugins|
3595 JWPlayerOptions|
3596 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3597 )
a0f71985
PH
3598 .*?
3599 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
a318f59d 3600 if not found:
3601 # Look for generic KVS player
3602 found = re.search(r'<script [^>]*?src="https://.+?/kt_player\.js\?v=(?P<ver>(?P<maj_ver>\d+)(\.\d+)+)".*?>', webpage)
3603 if found:
3604 if found.group('maj_ver') not in ['4', '5']:
3605 self.report_warning('Untested major version (%s) in player engine--Download may fail.' % found.group('ver'))
3606 flashvars = re.search(r'(?ms)<script.*?>.*?var\s+flashvars\s*=\s*(\{.*?\});.*?</script>', webpage)
3607 flashvars = self._parse_json(flashvars.group(1), video_id, transform_source=js_to_json)
3608
3609 # extract the part after the last / as the display_id from the
3610 # canonical URL.
3611 display_id = self._search_regex(
3612 r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
3613 r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
3614 webpage, 'display_id', fatal=False
3615 )
3616 title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
3617
3618 thumbnail = flashvars['preview_url']
3619 if thumbnail.startswith('//'):
3620 protocol, _, _ = url.partition('/')
3621 thumbnail = protocol + thumbnail
3622
3623 formats = []
3624 for key in ('video_url', 'video_alt_url', 'video_alt_url2'):
3625 if key in flashvars and '/get_file/' in flashvars[key]:
3626 next_format = {
3627 'url': self._kvs_getrealurl(flashvars[key], flashvars['license_code']),
3628 'format_id': flashvars.get(key + '_text', key),
3629 'ext': 'mp4',
3630 }
3631 height = re.search(r'%s_(\d+)p\.mp4(?:/[?].*)?$' % flashvars['video_id'], flashvars[key])
3632 if height:
3633 next_format['height'] = int(height.group(1))
3634 else:
3635 next_format['quality'] = 1
3636 formats.append(next_format)
3637 self._sort_formats(formats)
3638
3639 return {
3640 'id': flashvars['video_id'],
3641 'display_id': display_id,
3642 'title': title,
3643 'thumbnail': thumbnail,
3644 'formats': formats,
3645 }
b30b8698 3646 if not found:
9b122384 3647 # Broaden the search a little bit
ced659bb 3648 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
3649 if not found:
3650 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 3651 found = filter_video(re.findall(
54a9328b 3652 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
3653 if not found:
3654 # Flow player
ced659bb 3655 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
3656 flowplayer\("[^"]+",\s*
3657 \{[^}]+?\}\s*,
52585fd6 3658 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 3659 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 3660 ''', webpage))
501f13fb
PH
3661 if not found:
3662 # Cinerama player
3663 found = re.findall(
3664 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 3665 if not found:
9b122384 3666 # Try to find twitter cards info
371ddb14
S
3667 # twitter:player:stream should be checked before twitter:player since
3668 # it is expected to contain a raw stream (see
3669 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3670 found = filter_video(re.findall(
3671 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 3672 if not found:
9b122384
PH
3673 # We look for Open Graph info:
3674 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3675 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3676 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3677 if m_video_type is not None:
b73612a2 3678 found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
b30b8698 3679 if not found:
ed9a25dd 3680 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3681 found = re.search(
89ef304b 3682 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3683 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3684 webpage)
84f81016
S
3685 if not found:
3686 # Look also in Refresh HTTP header
3687 refresh_header = head_response.headers.get('Refresh')
3688 if refresh_header:
6c91a5a7
S
3689 # In python 2 response HTTP headers are bytestrings
3690 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3691 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3692 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3693 if found:
b37317d8 3694 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3695 if new_url != url:
3696 self.report_following_redirect(new_url)
3697 return {
3698 '_type': 'url',
3699 'url': new_url,
3700 }
3701 else:
3702 found = None
371ddb14
S
3703
3704 if not found:
3705 # twitter:player is a https URL to iframe player that may or may not
7a5c1cfe 3706 # be supported by yt-dlp thus this is checked the very last (see
371ddb14
S
3707 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3708 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3709 if embed_url and embed_url != url:
371ddb14
S
3710 return self.url_result(embed_url)
3711
b30b8698 3712 if not found:
416c7fcb 3713 raise UnsupportedError(url)
9b122384 3714
b30b8698 3715 entries = []
4a120778 3716 for video_url in orderedSet(found):
949b6497 3717 video_url = unescapeHTML(video_url)
6cc37c69 3718 video_url = video_url.replace('\\/', '/')
b30b8698 3719 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3720 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3721
b30b8698
PH
3722 # Sometimes, jwplayer extraction will result in a YouTube URL
3723 if YoutubeIE.suitable(video_url):
3724 entries.append(self.url_result(video_url, 'Youtube'))
3725 continue
9b122384 3726
b30b8698
PH
3727 # here's a fun little line of code for you:
3728 video_id = os.path.splitext(video_id)[0]
fc9713a1 3729
28602e74
YCH
3730 entry_info_dict = {
3731 'id': video_id,
3732 'uploader': video_uploader,
3733 'title': video_title,
3734 'age_limit': age_limit,
3735 }
3736
5620f840
S
3737 if RtmpIE.suitable(video_url):
3738 entry_info_dict.update({
3739 '_type': 'url_transparent',
3740 'ie_key': RtmpIE.ie_key(),
3741 'url': video_url,
3742 })
3743 entries.append(entry_info_dict)
3744 continue
3745
729accb4
S
3746 ext = determine_ext(video_url)
3747 if ext == 'smil':
da1c94ee 3748 entry_info_dict = {**self._extract_smil_info(video_url, video_id), **entry_info_dict}
729accb4
S
3749 elif ext == 'xspf':
3750 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0 3751 elif ext == 'm3u8':
da1c94ee 3752 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(video_url, video_id, ext='mp4')
79a35085 3753 elif ext == 'mpd':
da1c94ee 3754 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_mpd_formats_and_subtitles(video_url, video_id)
3f2f4a94
S
3755 elif ext == 'f4m':
3756 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3757 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3758 # Just matching .ism/manifest is not enough to be reliably sure
3759 # whether it's actually an ISM manifest or some other streaming
3760 # manifest since there are various streaming URL formats
3761 # possible (see [1]) as well as some other shenanigans like
3762 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3763 # so on.
3764 # Thus the most reasonable way to solve this is to delegate
3765 # to generic extractor in order to look into the contents of
3766 # the manifest itself.
3767 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3768 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3769 entry_info_dict = self.url_result(
3770 smuggle_url(video_url, {'to_generic': True}),
3771 GenericIE.ie_key())
d6fd958c 3772 else:
28602e74
YCH
3773 entry_info_dict['url'] = video_url
3774
19dbaeec
S
3775 if entry_info_dict.get('formats'):
3776 self._sort_formats(entry_info_dict['formats'])
3777
28602e74 3778 entries.append(entry_info_dict)
b30b8698
PH
3779
3780 if len(entries) == 1:
669f0e7c 3781 return entries[0]
b30b8698
PH
3782 else:
3783 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3784 # 'url' results don't have a title
3785 if e.get('title') is not None:
3786 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3787 return {
3788 '_type': 'playlist',
3789 'entries': entries,
3790 }