]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/generic.py
[tvp] Fix embeds (#1401)
[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
56bb56f3 138from .tvp import TVPEmbedIE
9b122384 139
0838239e 140
9b122384 141class GenericIE(InfoExtractor):
79649588 142 IE_DESC = 'Generic downloader that works on some sites'
9b122384 143 _VALID_URL = r'.*'
79649588 144 IE_NAME = 'generic'
cfe50f04 145 _TESTS = [
c5fa81fe
S
146 # Direct link to a video
147 {
148 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
149 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
150 'info_dict': {
151 'id': 'trailer',
152 'ext': 'mp4',
153 'title': 'trailer',
154 'upload_date': '20100513',
155 }
156 },
c5138a7c 157 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
158 {
159 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
160 'md5': '128c42e68b13950268b648275386fc74',
161 'info_dict': {
162 'id': 'FictionJunction-Parallel_Hearts',
163 'ext': 'flac',
164 'title': 'FictionJunction-Parallel_Hearts',
165 'upload_date': '20140522',
166 },
167 'expected_warnings': [
168 'URL could be a direct video link, returning it as such.'
39efc6e3
YCH
169 ],
170 'skip': 'URL invalid',
c5fa81fe
S
171 },
172 # Direct download with broken HEAD
173 {
174 'url': 'http://ai-radio.org:8000/radio.opus',
175 'info_dict': {
176 'id': 'radio',
177 'ext': 'opus',
178 'title': 'radio',
179 },
180 'params': {
181 'skip_download': True, # infinite live stream
182 },
183 'expected_warnings': [
ef0e4e7b
YCH
184 r'501.*Not Implemented',
185 r'400.*Bad Request',
c5fa81fe
S
186 ],
187 },
188 # Direct link with incorrect MIME type
189 {
190 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
191 'md5': '4ccbebe5f36706d85221f204d7eb5913',
192 'info_dict': {
193 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
194 'id': '5_Lennart_Poettering_-_Systemd',
195 'ext': 'webm',
196 'title': '5_Lennart_Poettering_-_Systemd',
197 'upload_date': '20141120',
198 },
199 'expected_warnings': [
200 'URL could be a direct video link, returning it as such.'
201 ]
202 },
203 # RSS feed
204 {
205 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
206 'info_dict': {
207 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
208 'title': 'Zero Punctuation',
209 'description': 're:.*groundbreaking video review series.*'
210 },
211 'playlist_mincount': 11,
212 },
213 # RSS feed with enclosure
214 {
215 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
216 'info_dict': {
29f7c58a 217 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
218 'title': 'MSNBC Rachel Maddow (video)',
219 'description': 're:.*her unique approach to storytelling.*',
220 },
221 'playlist': [{
222 'info_dict': {
223 'ext': 'mov',
224 'id': 'pdv_maddow_netcast_mov-12-03-2020-223726',
225 'title': 'MSNBC Rachel Maddow (video) - 12-03-2020-223726',
226 'description': 're:.*her unique approach to storytelling.*',
227 'upload_date': '20201204',
228 },
229 }],
230 },
231 # RSS feed with item with description and thumbnails
232 {
233 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
234 'info_dict': {
235 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
236 'title': 're:.*100% Hydrogen.*',
237 'description': 're:.*In this episode.*',
238 },
239 'playlist': [{
240 'info_dict': {
241 'ext': 'm4a',
242 'id': 'c1c879525ce2cb640b344507e682c36d',
243 'title': 're:Hydrogen!',
244 'description': 're:.*In this episode we are going.*',
245 'timestamp': 1567977776,
246 'upload_date': '20190908',
247 'duration': 459,
248 'thumbnail': r're:^https?://.*\.jpg$',
249 'episode_number': 1,
250 'season_number': 1,
251 'age_limit': 0,
252 },
253 }],
254 'params': {
255 'skip_download': True,
256 },
c5fa81fe 257 },
01aec848
BG
258 # RSS feed with enclosures and unsupported link URLs
259 {
260 'url': 'http://www.hellointernet.fm/podcast?format=rss',
261 'info_dict': {
262 'id': 'http://www.hellointernet.fm/podcast?format=rss',
263 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
264 'title': 'Hello Internet',
265 },
266 'playlist_mincount': 100,
267 },
8765222d
S
268 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
269 {
270 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
271 'info_dict': {
272 'id': 'smil',
273 'ext': 'mp4',
274 'title': 'Automatics, robotics and biocybernetics',
275 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 276 'upload_date': '20130627',
8765222d
S
277 'formats': 'mincount:16',
278 'subtitles': 'mincount:1',
279 },
280 'params': {
281 'force_generic_extractor': True,
282 'skip_download': True,
283 },
284 },
285 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
286 {
287 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
288 'info_dict': {
289 'id': 'hds',
290 'ext': 'flv',
291 'title': 'hds',
292 'formats': 'mincount:1',
293 },
294 'params': {
295 'skip_download': True,
296 },
297 },
298 # SMIL from https://www.restudy.dk/video/play/id/1637
299 {
300 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
301 'info_dict': {
302 'id': 'video_1637',
303 'ext': 'flv',
304 'title': 'video_1637',
305 'formats': 'mincount:3',
306 },
307 'params': {
308 'skip_download': True,
309 },
310 },
311 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
312 {
313 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
314 'info_dict': {
315 'id': 'smil-service',
316 'ext': 'flv',
317 'title': 'smil-service',
318 'formats': 'mincount:1',
319 },
320 'params': {
321 'skip_download': True,
322 },
323 },
324 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
325 {
326 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
327 'info_dict': {
328 'id': '4719370',
329 'ext': 'mp4',
330 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
331 'formats': 'mincount:3',
332 },
333 'params': {
334 'skip_download': True,
335 },
336 },
1de5cd3b
S
337 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
338 {
339 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
340 'info_dict': {
341 'id': 'mZlp2ctYIUEB',
342 'ext': 'mp4',
343 'title': 'Tikibad ontruimd wegens brand',
344 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
ec85ded8 345 'thumbnail': r're:^https?://.*\.jpg$',
1de5cd3b
S
346 'duration': 33,
347 },
348 'params': {
349 'skip_download': True,
350 },
351 },
9d939cec
S
352 # MPD from http://dash-mse-test.appspot.com/media.html
353 {
354 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
355 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
356 'info_dict': {
357 'id': 'car-20120827-manifest',
358 'ext': 'mp4',
359 'title': 'car-20120827-manifest',
360 'formats': 'mincount:9',
0738187f 361 'upload_date': '20130904',
9d939cec 362 },
9d939cec 363 },
20938f76
S
364 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
365 {
366 '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',
367 'info_dict': {
368 'id': 'content',
369 'ext': 'mp4',
370 'title': 'content',
371 'formats': 'mincount:8',
372 },
373 'params': {
374 # m3u8 downloads
375 'skip_download': True,
39efc6e3
YCH
376 },
377 'skip': 'video gone',
20938f76 378 },
edd9b71c
S
379 # m3u8 served with Content-Type: text/plain
380 {
381 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
382 'info_dict': {
383 'id': 'index',
384 'ext': 'mp4',
385 'title': 'index',
386 'upload_date': '20140720',
387 'formats': 'mincount:11',
388 },
389 'params': {
390 # m3u8 downloads
391 'skip_download': True,
39efc6e3
YCH
392 },
393 'skip': 'video gone',
edd9b71c 394 },
c5fa81fe
S
395 # google redirect
396 {
397 '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',
398 'info_dict': {
399 'id': 'cmQHVoWB5FY',
400 'ext': 'mp4',
401 'upload_date': '20130224',
402 'uploader_id': 'TheVerge',
ec85ded8 403 'description': r're:^Chris Ziegler takes a look at the\.*',
c5fa81fe
S
404 'uploader': 'The Verge',
405 'title': 'First Firefox OS phones side-by-side',
406 },
407 'params': {
408 'skip_download': False,
409 }
410 },
6c91a5a7
S
411 {
412 # redirect in Refresh HTTP header
413 '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',
414 'info_dict': {
415 'id': 'pO8h3EaFRdo',
416 'ext': 'mp4',
417 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
418 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
419 'upload_date': '20150917',
420 'uploader_id': 'brtvofficial',
421 'uploader': 'Boiler Room',
422 },
423 'params': {
424 'skip_download': False,
425 },
426 },
cfe50f04 427 {
79649588 428 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 429 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 430 'info_dict': {
d360a146
S
431 'id': '13601338388002',
432 'ext': 'mp4',
79649588
PH
433 'uploader': 'www.hodiho.fr',
434 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
435 }
436 },
c19f7764
JMF
437 # bandcamp page with custom domain
438 {
79649588
PH
439 'add_ie': ['Bandcamp'],
440 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 441 'info_dict': {
fd50bf62
S
442 'id': '3235767654',
443 'ext': 'mp3',
79649588
PH
444 'title': 'The Pony Mash',
445 'uploader': 'M_Pallante',
c19f7764 446 },
79649588 447 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 448 },
eeb165e6 449 {
53a664ed
S
450 # embedded brightcove video
451 # it also tests brightcove videos that need to set the 'Referer'
452 # in the http requests
3b7d9aa4 453 'add_ie': ['BrightcoveLegacy'],
79649588
PH
454 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
455 'info_dict': {
456 'id': '2765128793001',
457 'ext': 'mp4',
458 'title': 'Le cours de bourse : l’analyse technique',
459 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
460 'uploader': 'BFM BUSINESS',
eeb165e6 461 },
79649588
PH
462 'params': {
463 'skip_download': True,
eeb165e6
JMF
464 },
465 },
53a664ed
S
466 {
467 # embedded with itemprop embedURL and video id spelled as `idVideo`
468 'add_id': ['BrightcoveLegacy'],
469 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
470 'info_dict': {
471 'id': '5255628253001',
472 'ext': 'mp4',
473 'title': 'md5:37c519b1128915607601e75a87995fc0',
474 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
475 'uploader': 'BFM BUSINESS',
476 'uploader_id': '876450612001',
477 'timestamp': 1482255315,
478 'upload_date': '20161220',
479 },
480 'params': {
481 'skip_download': True,
482 },
483 },
17ab4d3b 484 {
067aa17e 485 # https://github.com/ytdl-org/youtube-dl/issues/2253
17ab4d3b 486 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
487 'md5': '0ba9446db037002366bab3b3eb30c88c',
488 'info_dict': {
fd50bf62
S
489 'id': '3101154703001',
490 'ext': 'mp4',
17ab4d3b
PH
491 'title': 'Still no power',
492 'uploader': 'thestar.com',
493 '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.',
494 },
3b7d9aa4 495 'add_ie': ['BrightcoveLegacy'],
39efc6e3 496 'skip': 'video gone',
17ab4d3b 497 },
0479c625
S
498 {
499 'url': 'http://www.championat.com/video/football/v/87/87499.html',
500 'md5': 'fb973ecf6e4a78a67453647444222983',
501 'info_dict': {
502 'id': '3414141473001',
503 'ext': 'mp4',
504 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
505 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
506 'uploader': 'Championat',
507 },
508 },
bdf97017 509 {
067aa17e 510 # https://github.com/ytdl-org/youtube-dl/issues/3541
3b7d9aa4 511 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
512 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
513 'info_dict': {
514 'id': '3866516442001',
37aab278 515 'ext': 'mp4',
bdf97017
NJ
516 'title': 'Leer mij vrouwen kennen: Aflevering 1',
517 'description': 'Leer mij vrouwen kennen: Aflevering 1',
518 'uploader': 'SBS Broadcasting',
519 },
37aab278 520 'skip': 'Restricted to Netherlands',
bdf97017 521 'params': {
37aab278 522 'skip_download': True, # m3u8 download
bdf97017
NJ
523 },
524 },
06d0ad9a
YCH
525 {
526 # Brightcove video in <iframe>
527 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
528 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
529 'info_dict': {
530 'id': '5360463607001',
531 'ext': 'mp4',
532 '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',
533 '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。',
534 'uploader': 'United Nations',
535 'uploader_id': '1362235914001',
536 'timestamp': 1489593889,
537 'upload_date': '20170315',
538 },
539 'add_ie': ['BrightcoveLegacy'],
540 },
16e2c8f7
YCH
541 {
542 # Brightcove with alternative playerID key
543 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
544 'info_dict': {
545 'id': 'nmeth.2062_SV1',
546 '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',
547 },
548 'playlist': [{
549 'info_dict': {
550 'id': '2228375078001',
551 'ext': 'mp4',
552 'title': 'nmeth.2062-sv1',
553 'description': 'nmeth.2062-sv1',
554 'timestamp': 1363357591,
555 'upload_date': '20130315',
556 'uploader': 'Nature Publishing Group',
557 'uploader_id': '1964492299001',
558 },
559 }],
560 },
40158f55
JH
561 {
562 # Brightcove with UUID in videoPlayer
563 'url': 'http://www8.hp.com/cn/zh/home.html',
564 'info_dict': {
565 'id': '5255815316001',
566 'ext': 'mp4',
567 'title': 'Sprocket Video - China',
568 'description': 'Sprocket Video - China',
569 'uploader': 'HP-Video Gallery',
570 'timestamp': 1482263210,
571 'upload_date': '20161220',
572 'uploader_id': '1107601872001',
573 },
574 'params': {
575 'skip_download': True, # m3u8 download
576 },
577 'skip': 'video rotates...weekly?',
578 },
579 {
580 # Brightcove:new type [2].
581 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
582 'md5': '2b35148fcf48da41c9fb4591650784f3',
583 'info_dict': {
584 'id': '5348741021001',
585 'ext': 'mp4',
586 'upload_date': '20170306',
587 'uploader_id': '4191638492001',
588 'timestamp': 1488769918,
589 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
590
591 },
592 },
593 {
594 # Alternative brightcove <video> attributes
595 '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/',
596 'info_dict': {
597 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
598 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
599 },
600 'playlist': [{
601 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
602 'info_dict': {
603 'id': '5311302538001',
604 'ext': 'mp4',
605 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
606 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
607 'timestamp': 1486321708,
608 'upload_date': '20170205',
609 'uploader_id': '800000640001',
610 },
611 'only_matching': True,
612 }],
613 },
b68a812e
S
614 {
615 # Brightcove with UUID in videoPlayer
616 'url': 'http://www8.hp.com/cn/zh/home.html',
617 'info_dict': {
618 'id': '5255815316001',
619 'ext': 'mp4',
620 'title': 'Sprocket Video - China',
621 'description': 'Sprocket Video - China',
622 'uploader': 'HP-Video Gallery',
623 'timestamp': 1482263210,
624 'upload_date': '20161220',
625 'uploader_id': '1107601872001',
626 },
627 'params': {
628 'skip_download': True, # m3u8 download
629 },
630 },
c0d0b01f
JMF
631 # ooyala video
632 {
79649588 633 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 634 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
635 'info_dict': {
636 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
637 'ext': 'mp4',
3486df38 638 'title': '2cc213299525360.mov', # that's what we get
53e06b25 639 'duration': 238.231,
c0d0b01f 640 },
87830900 641 'add_ie': ['Ooyala'],
c0d0b01f 642 },
bf94d763
S
643 {
644 # ooyala video embedded with http://player.ooyala.com/iframe.js
645 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
646 'info_dict': {
647 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
648 'ext': 'mp4',
649 'title': '"Steve Jobs: Man in the Machine" trailer',
650 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 651 'duration': 135.427,
bf94d763
S
652 },
653 'params': {
654 'skip_download': True,
655 },
39efc6e3 656 'skip': 'movie expired',
bf94d763 657 },
198d4cb4
GR
658 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
659 {
660 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
661 'info_dict': {
662 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
663 'ext': 'mp4',
664 'title': 'Steampunk Fest Comes to Honesdale',
665 'duration': 43.276,
666 },
667 'params': {
668 'skip_download': True,
669 }
670 },
1b86cc41 671 # embed.ly video
672 {
673 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
674 'info_dict': {
675 'id': '9ODmcdjQcHQ',
676 'ext': 'mp4',
0a5bce56
PH
677 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
678 'upload_date': '20140225',
679 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
680 'uploader': 'Tested',
681 'uploader_id': 'testedcom',
1b86cc41 682 },
683 # No need to test YoutubeIE here
684 'params': {
685 'skip_download': True,
686 },
687 },
60cc4dc4
PH
688 # funnyordie embed
689 {
690 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
691 'info_dict': {
692 'id': '18e820ec3f',
693 'ext': 'mp4',
694 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
695 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 696 },
39efc6e3
YCH
697 # HEAD requests lead to endless 301, while GET is OK
698 'expected_warnings': ['301'],
60cc4dc4 699 },
93d020dd
S
700 # RUTV embed
701 {
702 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
703 'info_dict': {
704 'id': '776940',
705 'ext': 'mp4',
706 'title': 'Охотское море стало целиком российским',
707 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
708 },
709 'params': {
710 # m3u8 download
711 'skip_download': True,
712 },
aab74fa1 713 },
f37bdbe5
S
714 # TVC embed
715 {
716 '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/',
717 'info_dict': {
718 'id': '55304',
719 'ext': 'mp4',
720 'title': 'Дошкольное воспитание',
721 },
722 },
b827a601
S
723 # SportBox embed
724 {
725 'url': 'http://www.vestifinance.ru/articles/25753',
726 'info_dict': {
727 'id': '25753',
05d1e7aa 728 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
b827a601
S
729 },
730 'playlist': [{
731 'info_dict': {
732 'id': '370908',
733 'title': 'Госзаказ. День 3',
734 'ext': 'mp4',
735 }
736 }, {
737 'info_dict': {
738 'id': '370905',
739 'title': 'Госзаказ. День 2',
740 'ext': 'mp4',
741 }
742 }, {
743 'info_dict': {
744 'id': '370902',
745 'title': 'Госзаказ. День 1',
746 'ext': 'mp4',
747 }
748 }],
749 'params': {
750 # m3u8 download
751 'skip_download': True,
752 },
753 },
bf20b9c5
S
754 # Myvi.ru embed
755 {
756 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
757 'info_dict': {
758 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
759 'ext': 'mp4',
760 'title': 'Ужастики, русский трейлер (2015)',
ec85ded8 761 'thumbnail': r're:^https?://.*\.jpg$',
bf20b9c5
S
762 'duration': 153,
763 }
764 },
c76799c5
S
765 # XHamster embed
766 {
767 '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',
768 'info_dict': {
769 'id': 'showthread',
770 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
771 },
772 'playlist_mincount': 7,
39efc6e3
YCH
773 # This forum does not allow <iframe> syntaxes anymore
774 # Now HTML tags are displayed as-is
775 'skip': 'No videos on this page',
c76799c5 776 },
aab74fa1
PH
777 # Embedded TED video
778 {
779 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 780 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 781 'info_dict': {
a8eb5a8e 782 'id': '1969',
aab74fa1 783 'ext': 'mp4',
a8eb5a8e
PH
784 'title': 'Hidden miracles of the natural world',
785 'uploader': 'Louie Schwartzberg',
786 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 787 }
60cc4dc4 788 },
d95e35d6
S
789 # nowvideo embed hidden behind percent encoding
790 {
791 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
792 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
793 'info_dict': {
794 'id': '06e53103ca9aa',
795 'ext': 'flv',
796 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
797 'description': 'No description',
798 },
0f2a2ba1 799 },
893f8832
PH
800 # arte embed
801 {
802 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
803 'md5': '7653032cbb25bf6c80d80f217055fa43',
804 'info_dict': {
805 'id': '048195-004_PLUS7-F',
806 'ext': 'flv',
807 'title': 'X:enius',
808 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
809 'upload_date': '20140320',
810 },
811 'params': {
812 'skip_download': 'Requires rtmpdump'
39efc6e3
YCH
813 },
814 'skip': 'video gone',
893f8832 815 },
cbd55ade
S
816 # francetv embed
817 {
818 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
819 'info_dict': {
820 'id': 'EV_30231',
821 'ext': 'mp4',
822 'title': 'Alcaline, le concert avec Calogero',
823 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
824 'upload_date': '20150226',
825 'timestamp': 1424989860,
826 'duration': 5400,
827 },
828 'params': {
829 # m3u8 downloads
830 'skip_download': True,
831 },
832 'expected_warnings': [
833 'Forbidden'
834 ]
835 },
fa35cdad
PH
836 # Condé Nast embed
837 {
838 'url': 'http://www.wired.com/2014/04/honda-asimo/',
839 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
840 'info_dict': {
841 'id': '53501be369702d3275860000',
842 'ext': 'mp4',
843 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
844 }
ebd3c7b3
PH
845 },
846 # Dailymotion embed
847 {
848 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
849 'md5': '441aeeb82eb72c422c7f14ec533999cd',
850 'info_dict': {
851 'id': 'k2mm4bCdJ6CQ2i7c8o2',
852 'ext': 'mp4',
853 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 854 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 855 'uploader': 'Spi0n',
0738187f
YCH
856 'uploader_id': 'xgditw',
857 'upload_date': '20140425',
858 'timestamp': 1398441542,
ebd3c7b3
PH
859 },
860 'add_ie': ['Dailymotion'],
2b88feed 861 },
71a1db89
S
862 # DailyMail embed
863 {
864 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
865 'info_dict': {
866 'id': '1495629',
867 'ext': 'mp4',
868 'title': 'Care worker punches elderly dementia patient in head 11 times',
869 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
870 },
871 'add_ie': ['DailyMail'],
872 'params': {
873 'skip_download': True,
874 },
875 },
2b88feed
PH
876 # YouTube embed
877 {
878 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
879 'info_dict': {
880 'id': 'FXRb4ykk4S0',
881 'ext': 'mp4',
882 'title': 'The NBL Auction 2014',
883 'uploader': 'BADMINTON England',
884 'uploader_id': 'BADMINTONEvents',
885 'upload_date': '20140603',
886 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
887 },
888 'add_ie': ['Youtube'],
889 'params': {
890 'skip_download': True,
891 }
892 },
a0566bbf 893 # MTVServices embed
c5cd249e 894 {
1fa309da
YCH
895 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
896 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 897 'info_dict': {
1fa309da 898 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 899 'ext': 'mp4',
1fa309da
YCH
900 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
901 'description': 'Two valets share their love for movie star Liam Neesons.',
05d1e7aa
YCH
902 'timestamp': 1349922600,
903 'upload_date': '20121011',
c5cd249e
JMF
904 },
905 },
61013473 906 # YouTube embed via <data-embed-url="">
907 {
908 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 909 'info_dict': {
a8eb5a8e 910 'id': '4vAffPZIT44',
61013473 911 'ext': 'mp4',
a8eb5a8e 912 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
913 'uploader': 'Gameloft',
914 'uploader_id': 'gameloft',
a8eb5a8e
PH
915 'upload_date': '20140828',
916 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
917 },
918 'params': {
919 'skip_download': True,
61013473 920 }
c8e9a235 921 },
61568e50
JH
922 # YouTube <object> embed
923 {
924 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
925 'md5': '516718101ec834f74318df76259fb3cc',
926 'info_dict': {
927 'id': 'msN87y-iEx0',
928 'ext': 'webm',
929 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
930 'upload_date': '20080526',
931 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
932 'uploader': 'Christopher Sykes',
933 'uploader_id': 'ChristopherJSykes',
934 },
935 'add_ie': ['Youtube'],
936 },
c8e9a235
PH
937 # Camtasia studio
938 {
939 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
940 'playlist': [{
941 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
942 'info_dict': {
943 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
944 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
945 'ext': 'flv',
946 'duration': 2235.90,
947 }
948 }, {
949 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
950 'info_dict': {
951 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
952 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
953 'ext': 'flv',
954 'duration': 2235.93,
955 }
956 }],
957 'info_dict': {
958 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
959 }
4d805e06
PH
960 },
961 # Flowplayer
962 {
963 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
964 'md5': '9d65602bf31c6e20014319c7d07fba27',
965 'info_dict': {
966 'id': '5123ea6d5e5a7',
967 'ext': 'mp4',
968 'age_limit': 18,
969 'uploader': 'www.handjobhub.com',
d6d9186f 970 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 971 }
0990305d 972 },
22a6f150 973 # Multiple brightcove videos
067aa17e 974 # https://github.com/ytdl-org/youtube-dl/issues/2283
22a6f150
PH
975 {
976 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
977 'info_dict': {
978 'id': 'always-never',
979 'title': 'Always / Never - The New Yorker',
980 },
981 'playlist_count': 3,
982 'params': {
983 'extract_flat': False,
984 'skip_download': True,
985 }
1a94ff68
S
986 },
987 # MLB embed
988 {
989 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
990 'md5': '96f09a37e44da40dd083e12d9a683327',
991 'info_dict': {
992 'id': '33322633',
993 'ext': 'mp4',
994 'title': 'Ump changes call to ball',
995 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
996 'duration': 48,
997 'timestamp': 1401537900,
998 'upload_date': '20140531',
ec85ded8 999 'thumbnail': r're:^https?://.*\.jpg$',
1a94ff68
S
1000 },
1001 },
746c67d7
NJ
1002 # Wistia embed
1003 {
6c114b12
S
1004 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1005 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 1006 'info_dict': {
6c114b12 1007 'id': '6e2wtrbdaf',
746c67d7 1008 'ext': 'mov',
6c114b12
S
1009 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1010 'description': 'a Paywall Videos video from Remilon',
1011 'duration': 644.072,
1012 'uploader': 'study.com',
1013 'timestamp': 1459678540,
1014 'upload_date': '20160403',
1015 'filesize': 24687186,
746c67d7
NJ
1016 },
1017 },
52cffcb1 1018 {
1019 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1020 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1021 'info_dict': {
1022 'id': 'uxjb0lwrcz',
1023 'ext': 'mp4',
6c114b12 1024 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 1025 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 1026 'duration': 1715.0,
85d7b765 1027 'uploader': 'thoughtworks.wistia.com',
0738187f 1028 'timestamp': 1401832161,
6c114b12 1029 'upload_date': '20140603',
70b7e3fb 1030 },
52cffcb1 1031 },
7ded6545
S
1032 # Wistia standard embed (async)
1033 {
1034 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1035 'info_dict': {
1036 'id': '807fafadvk',
1037 'ext': 'mp4',
1038 'title': 'Drip Brennan Dunn Workshop',
1039 'description': 'a JV Webinars video from getdrip-1',
1040 'duration': 4986.95,
7ded6545 1041 'timestamp': 1463607249,
6c114b12 1042 'upload_date': '20160518',
7ded6545
S
1043 },
1044 'params': {
1045 'skip_download': True,
1046 }
1047 },
ac645ac7
PH
1048 # Soundcloud embed
1049 {
1050 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1051 'info_dict': {
1052 'id': '174391317',
1053 'ext': 'mp3',
1054 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1055 'uploader': 'Sophos Security',
1056 'title': 'Chet Chat 171 - Oct 29, 2014',
1057 'upload_date': '20141029',
1058 }
af63fed7 1059 },
db19df6c
S
1060 # Soundcloud multiple embeds
1061 {
1062 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1063 'info_dict': {
1064 'id': '52809',
1065 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1066 },
1067 'playlist_mincount': 7,
1068 },
027e2312
S
1069 # TuneIn station embed
1070 {
1071 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1072 'info_dict': {
1073 'id': '204146',
1074 'ext': 'mp3',
1075 'title': 'CNRV',
1076 'location': 'Paris, France',
1077 'is_live': True,
1078 },
1079 'params': {
1080 # Live stream
1081 'skip_download': True,
1082 },
1083 },
af63fed7
PH
1084 # Livestream embed
1085 {
1086 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1087 'info_dict': {
1088 'id': '67864563',
1089 'ext': 'flv',
1090 'upload_date': '20141112',
1091 'title': 'Rosetta #CometLanding webcast HL 10',
1092 }
1093 },
78d3b3e2
YCH
1094 # Another Livestream embed, without 'new.' in URL
1095 {
1096 'url': 'https://www.freespeech.org/',
1097 'info_dict': {
1098 'id': '123537347',
1099 'ext': 'mp4',
1100 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1101 },
1102 'params': {
1103 # Live stream
1104 'skip_download': True,
1105 },
1106 },
65f3a228
PH
1107 # LazyYT
1108 {
e8e4cc5a 1109 'url': 'https://skiplagged.com/',
65f3a228 1110 'info_dict': {
e8e4cc5a
JH
1111 'id': 'skiplagged',
1112 'title': 'Skiplagged: The smart way to find cheap flights',
65f3a228 1113 },
e8e4cc5a
JH
1114 'playlist_mincount': 1,
1115 'add_ie': ['Youtube'],
4e262a88 1116 },
42bdd9d0
PH
1117 # Cinchcast embed
1118 {
1119 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1120 'info_dict': {
1121 'id': '7141703',
1122 'ext': 'mp3',
1123 'upload_date': '20141126',
1124 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1125 }
1126 },
501f13fb
PH
1127 # Cinerama player
1128 {
1129 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1130 'info_dict': {
1131 'id': '730m_DandD_1901_512k',
1132 'ext': 'mp4',
1133 'uploader': 'www.abc.net.au',
1134 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1135 }
796df3c6
S
1136 },
1137 # embedded viddler video
1138 {
1139 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1140 'info_dict': {
1141 'id': '4d03aad9',
1142 'ext': 'mp4',
1143 'uploader': 'deadspin',
1144 'title': 'WALL-TO-GORTAT',
1145 'timestamp': 1422285291,
1146 'upload_date': '20150126',
1147 },
1148 'add_ie': ['Viddler'],
a0f71985 1149 },
2051acde
S
1150 # Libsyn embed
1151 {
1152 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1153 'info_dict': {
1154 'id': '3377616',
1155 'ext': 'mp3',
1156 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1157 'description': 'md5:601cb790edd05908957dae8aaa866465',
1158 'upload_date': '20150220',
1159 },
326fa4e6 1160 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
2051acde 1161 },
a0f71985
PH
1162 # jwplayer YouTube
1163 {
1164 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1165 'info_dict': {
1166 'id': 'Mrj4DVp2zeA',
1167 'ext': 'mp4',
f37e3f99 1168 'upload_date': '20150212',
a0f71985 1169 'uploader': 'The National Archives UK',
2637fadc 1170 'description': 'md5:8078af856dca76edc42910b61273dbbf',
a0f71985
PH
1171 'uploader_id': 'NationalArchives08',
1172 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1173 },
59b8ab58 1174 },
5620f840
S
1175 # jwplayer rtmp
1176 {
6899b1d9 1177 'url': 'http://www.suffolk.edu/sjc/live.php',
5620f840 1178 'info_dict': {
6899b1d9 1179 'id': 'live',
5620f840
S
1180 'ext': 'flv',
1181 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1182 'uploader': 'www.suffolk.edu',
1183 },
1184 'params': {
1185 'skip_download': True,
2637fadc 1186 },
6899b1d9 1187 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
5620f840 1188 },
5e7bbac3 1189 # jwplayer with only the json URL
1190 {
1191 'url': 'https://www.hollywoodreporter.com/news/general-news/dunkirk-team-reveals-what-christopher-nolan-said-oscar-win-meet-your-oscar-winner-1092454',
1192 'info_dict': {
1193 'id': 'TljWkvWH',
1194 'ext': 'mp4',
1195 'upload_date': '20180306',
1196 'title': 'md5:91eb1862f6526415214f62c00b453936',
1197 'description': 'md5:73048ae50ae953da10549d1d2fe9b3aa',
1198 'timestamp': 1520367225,
1199 },
1200 'params': {
1201 'skip_download': True,
1202 },
1203 },
a4a554a7
YCH
1204 # Complex jwplayer
1205 {
1206 'url': 'http://www.indiedb.com/games/king-machine/videos',
1207 'info_dict': {
1208 'id': 'videos',
1209 'ext': 'mp4',
1210 'title': 'king machine trailer 1',
2637fadc 1211 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
a4a554a7
YCH
1212 'thumbnail': r're:^https?://.*\.jpg$',
1213 },
1214 },
03486dbb
RU
1215 {
1216 # JWPlayer config passed as variable
1217 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1218 'info_dict': {
1219 'id': '3326530_hq',
1220 'ext': 'mp4',
1221 'title': 'ARIELE | Tube Cup',
1222 'uploader': 'www.txxx.com',
1223 'age_limit': 18,
1224 },
1225 'params': {
1226 'skip_download': True,
1227 }
1228 },
939be9ad
JH
1229 {
1230 # JWPlatform iframe
2fac2e91 1231 'url': 'https://www.covermagazine.co.uk/feature/2465255/business-protection-involved',
939be9ad 1232 'info_dict': {
2fac2e91 1233 'id': 'AG26UQXM',
939be9ad 1234 'ext': 'mp4',
2fac2e91
AG
1235 'upload_date': '20160719',
1236 'timestamp': 468923808,
1237 'title': '2016_05_18 Cover L&G Business Protection V1 FINAL.mp4',
939be9ad 1238 },
805f5bf7 1239 'add_ie': [JWPlatformIE.ie_key()],
939be9ad 1240 },
63d990d2 1241 {
c5b7014a 1242 # Video.js embed, multiple formats
63d990d2
S
1243 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1244 'info_dict': {
1245 'id': 'yygqldloqIk',
1246 'ext': 'mp4',
1247 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1248 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1249 'upload_date': '20130314',
1250 'uploader': 'PROстое3D',
1251 'uploader_id': 'PROstoe3D',
1252 },
1253 'params': {
1254 'skip_download': True,
1255 },
1256 },
c5b7014a
S
1257 {
1258 # Video.js embed, single format
1259 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1260 'info_dict': {
1261 'id': 'watch',
1262 'ext': 'mp4',
1263 'title': 'Step 1 - Good Foundation',
1264 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1265 },
1266 'params': {
1267 'skip_download': True,
1268 },
1269 },
59b8ab58
PH
1270 # rtl.nl embed
1271 {
1272 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1273 'playlist_mincount': 5,
1274 'info_dict': {
1275 'id': 'aanslagen-kopenhagen',
2637fadc 1276 'title': 'Aanslagen Kopenhagen',
59b8ab58 1277 }
255fca5e
S
1278 },
1279 # Zapiks embed
1280 {
1281 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1282 'info_dict': {
1283 'id': '118046',
1284 'ext': 'mp4',
1285 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1286 }
1287 },
66e568de
S
1288 # Kaltura embed (different embed code)
1289 {
1290 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1291 'info_dict': {
1292 'id': '1_a52wc67y',
1293 'ext': 'flv',
1294 'upload_date': '20150127',
1295 'uploader_id': 'PremierMedia',
1296 'timestamp': int,
1297 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1298 },
1299 },
87703231
YCH
1300 # Kaltura embed with single quotes
1301 {
1302 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1303 'info_dict': {
1304 'id': '0_izeg5utt',
1305 'ext': 'mp4',
1306 'title': '35871',
1307 'timestamp': 1355743100,
1308 'upload_date': '20121217',
e30991f9 1309 'uploader_id': 'cplapp@learn360.com',
87703231
YCH
1310 },
1311 'add_ie': ['Kaltura'],
1312 },
427cd050
S
1313 {
1314 # Kaltura embedded via quoted entry_id
1315 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1316 'info_dict': {
1317 'id': '0_utuok90b',
1318 'ext': 'mp4',
1319 'title': '06_matthew_brender_raj_dutt',
1320 'timestamp': 1466638791,
1321 'upload_date': '20160622',
1322 },
1323 'add_ie': ['Kaltura'],
1324 'expected_warnings': [
1325 'Could not send HEAD request'
1326 ],
1327 'params': {
1328 'skip_download': True,
1329 }
1330 },
8ab7e6c4
YCH
1331 {
1332 # Kaltura embedded, some fileExt broken (#11480)
1333 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1334 'info_dict': {
1335 'id': '1_sgtvehim',
1336 'ext': 'mp4',
1337 'title': 'Our "Standard Models" of particle physics and cosmology',
1338 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1339 'timestamp': 1321158993,
1340 'upload_date': '20111113',
1341 'uploader_id': 'kps1',
1342 },
1343 'add_ie': ['Kaltura'],
1344 },
a01825a5
JH
1345 {
1346 # Kaltura iframe embed
1347 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1348 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1349 'info_dict': {
1350 'id': '0_f2cfbpwy',
1351 'ext': 'mp4',
1352 'title': 'I. M. Pei: A Centennial Celebration',
1353 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1354 'upload_date': '20170403',
1355 'uploader_id': 'batchUser',
1356 'timestamp': 1491232186,
1357 },
1358 'add_ie': ['Kaltura'],
1359 },
c21692fa
S
1360 {
1361 # Kaltura iframe embed, more sophisticated
1362 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1363 'info_dict': {
1364 'id': '1_9gzouybz',
1365 'ext': 'mp4',
1366 'title': 'lecture-05sep2017',
1367 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1368 'upload_date': '20170913',
1369 'uploader_id': 'eps2',
1370 'timestamp': 1505340777,
1371 },
1372 'params': {
1373 'skip_download': True,
1374 },
1375 'add_ie': ['Kaltura'],
1376 },
e30991f9
S
1377 {
1378 # meta twitter:player
1379 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1380 'info_dict': {
1381 'id': '0_01b42zps',
1382 'ext': 'mp4',
1383 'title': 'Main Twerk (Video)',
1384 'upload_date': '20171208',
1385 'uploader_id': 'sebastian.salinas@thechive.com',
1386 'timestamp': 1512713057,
1387 },
1388 'params': {
1389 'skip_download': True,
1390 },
1391 'add_ie': ['Kaltura'],
1392 },
250b042c
S
1393 # referrer protected EaglePlatform embed
1394 {
1395 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1396 'info_dict': {
1397 'id': '582306',
1398 'ext': 'mp4',
1399 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1400 'thumbnail': r're:^https?://.*\.jpg$',
1401 'duration': 3382,
1402 'view_count': int,
1403 },
1404 'params': {
1405 'skip_download': True,
1406 },
135c9c42 1407 },
665e9452 1408 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1409 {
1410 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1411 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1412 'info_dict': {
1413 'id': '12820',
1414 'ext': 'mp4',
1415 'title': "'O Sole Mio",
ec85ded8 1416 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1417 'duration': 216,
1418 'view_count': int,
1419 },
250b042c
S
1420 'params': {
1421 'skip_download': True,
1422 },
2637fadc 1423 'skip': 'This video is unavailable.',
d47ae7f6 1424 },
f8388757
S
1425 # Pladform embed
1426 {
1427 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1428 'info_dict': {
1429 'id': '100183293',
1430 'ext': 'mp4',
62259846 1431 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1432 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1433 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1434 'duration': 694,
1435 'age_limit': 0,
1436 },
2637fadc 1437 'skip': 'HTTP Error 404: Not Found',
f8388757 1438 },
c798f15b
S
1439 # Playwire embed
1440 {
1441 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1442 'info_dict': {
1443 'id': '3519514',
1444 'ext': 'mp4',
1445 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1446 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1447 'duration': 45.115,
1448 },
1449 },
ad320e9b
NJ
1450 # 5min embed
1451 {
1452 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1453 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1454 'info_dict': {
1455 'id': '518726732',
1456 'ext': 'mp4',
1457 'title': 'Facebook Creates "On This Day" | Crunch Report',
2637fadc
RA
1458 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1459 'timestamp': 1427237531,
1460 'uploader': 'Crunch Report',
1461 'upload_date': '20150324',
1462 },
1463 'params': {
1464 # m3u8 download
1465 'skip_download': True,
ad320e9b
NJ
1466 },
1467 },
a4257017
S
1468 # Crooks and Liars embed
1469 {
1470 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1471 'info_dict': {
1472 'id': '8RUoRhRi',
1473 'ext': 'mp4',
1474 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1475 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1476 'timestamp': 1428207000,
1477 'upload_date': '20150405',
1478 'uploader': 'Heather',
1479 },
1480 },
1481 # Crooks and Liars external embed
1482 {
1483 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1484 'info_dict': {
1485 'id': 'MTE3MjUtMzQ2MzA',
1486 'ext': 'mp4',
1487 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1488 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1489 'timestamp': 1265032391,
1490 'upload_date': '20100201',
1491 'uploader': 'Heather',
1492 },
1493 },
facecb84 1494 # NBC Sports vplayer embed
a2edf2e7 1495 {
facecb84 1496 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1497 'info_dict': {
facecb84
S
1498 'id': 'ln7x1qSThw4k',
1499 'ext': 'flv',
1500 'title': "PFT Live: New leader in the 'new-look' defense",
1501 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1502 'uploader': 'NBCU-SPORTS',
1503 'upload_date': '20140107',
1504 'timestamp': 1389118457,
a2edf2e7 1505 },
2637fadc 1506 'skip': 'Invalid Page URL',
418c5cc3 1507 },
de3eb07e
YCH
1508 # NBC News embed
1509 {
1510 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1511 'md5': '1aa589c675898ae6d37a17913cf68d66',
1512 'info_dict': {
2637fadc 1513 'id': 'x_dtl_oa_LettermanliftPR_160608',
de3eb07e 1514 'ext': 'mp4',
2637fadc 1515 'title': 'David Letterman: A Preview',
de3eb07e 1516 '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
1517 'upload_date': '20160609',
1518 'timestamp': 1465431544,
1519 'uploader': 'NBCU-NEWS',
de3eb07e
YCH
1520 },
1521 },
418c5cc3
YCH
1522 # UDN embed
1523 {
811586eb 1524 'url': 'https://video.udn.com/news/300346',
01c58f84 1525 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1526 'info_dict': {
01c58f84 1527 'id': '300346',
418c5cc3 1528 'ext': 'mp4',
01c58f84 1529 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1530 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1531 },
1532 'params': {
1533 # m3u8 download
1534 'skip_download': True,
1535 },
2637fadc 1536 'expected_warnings': ['Failed to parse JSON Expecting value'],
edfcf7ab 1537 },
b26733ba
YCH
1538 # Brightcove URL in single quotes
1539 {
1540 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1541 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1542 'info_dict': {
1543 'id': '4255764656001',
1544 'ext': 'mp4',
1545 'title': 'SN Presents: Russell Martin, World Citizen',
1546 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1547 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1548 'uploader_id': '1704050871',
1549 'upload_date': '20150525',
1550 'timestamp': 1432570283,
b26733ba 1551 },
756f574e 1552 },
55adb63e 1553 # Kinja embed
8084be78
S
1554 {
1555 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1556 'info_dict': {
55adb63e 1557 'id': '106351',
8084be78
S
1558 'ext': 'mp4',
1559 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
55adb63e 1560 'description': 'Migrated from OnionStudios',
ec85ded8 1561 'thumbnail': r're:^https?://.*\.jpe?g$',
55adb63e
RA
1562 'uploader': 'clickhole',
1563 'upload_date': '20150527',
1564 'timestamp': 1432744860,
8084be78
S
1565 }
1566 },
b8c1cc1a
S
1567 # SnagFilms embed
1568 {
1569 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1570 'info_dict': {
1571 'id': '74849a00-85a9-11e1-9660-123139220831',
1572 'ext': 'mp4',
1573 'title': '#whilewewatch',
1574 }
1575 },
a5158f38
YCH
1576 # AdobeTVVideo embed
1577 {
1578 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1579 'md5': '43662b577c018ad707a63766462b1e87',
1580 'info_dict': {
1581 'id': '2456',
1582 'ext': 'mp4',
1583 'title': 'New experience with Acrobat DC',
1584 'description': 'New experience with Acrobat DC',
1585 'duration': 248.667,
1586 },
1f812580 1587 },
ed126900 1588 # BrightcoveInPageEmbed embed
1589 {
1590 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1591 'info_dict': {
1592 'id': '4238694884001',
1593 'ext': 'flv',
1594 'title': 'Tabletop: Dread, Last Thoughts',
1595 'description': 'Tabletop: Dread, Last Thoughts',
1596 'duration': 51690,
1597 },
750b9ff0 1598 },
d10fe835
YCH
1599 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1600 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1601 {
1602 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1603 'info_dict': {
1604 'id': '4785848093001',
1605 'ext': 'mp4',
1606 'title': 'The Cardinal Pell Interview',
1607 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1608 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1609 'uploader_id': '2733773828001',
1610 'upload_date': '20160304',
1611 'timestamp': 1457083087,
d10fe835
YCH
1612 },
1613 'params': {
1614 # m3u8 downloads
1615 'skip_download': True,
1616 },
1617 },
9edf47df
S
1618 {
1619 # Brightcove embed with whitespace around attribute names
1620 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1621 'info_dict': {
1622 'id': '3167554373001',
1623 'ext': 'mp4',
1624 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1625 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1626 'uploader_id': '1079349493',
1627 'upload_date': '20140207',
1628 'timestamp': 1391810548,
1629 },
1630 'params': {
1631 'skip_download': True,
1632 },
1633 },
134c207e
YCH
1634 # Another form of arte.tv embed
1635 {
1636 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1637 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1638 'info_dict': {
1639 'id': '030273-562_PLUS7-F',
1640 'ext': 'mp4',
1641 'title': 'ARTE Reportage - Nulle part, en France',
1642 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1643 'upload_date': '20160409',
1644 },
1645 },
4a120778
YCH
1646 # Duplicated embedded video URLs
1647 {
1648 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1649 'info_dict': {
1650 'id': '149298443_480_16c25b74_2',
1651 'ext': 'mp4',
1652 'title': 'vs. Blue Orange Spring Game',
1653 'uploader': 'www.hudl.com',
1654 },
1655 },
371ddb14
S
1656 # twitter:player:stream embed
1657 {
1658 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1659 'info_dict': {
1660 'id': 'master',
1661 'ext': 'mp4',
1662 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1663 'uploader': 'www.rtl.be',
1664 },
1665 'params': {
1666 # m3u8 downloads
1667 'skip_download': True,
1668 },
1669 },
32917907
RA
1670 # twitter:player embed
1671 {
1672 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1673 'md5': 'a3e0df96369831de324f0778e126653c',
1674 'info_dict': {
1675 'id': '4909620399001',
1676 'ext': 'mp4',
1677 'title': 'What Do Black Holes Sound Like?',
1678 'description': 'what do black holes sound like',
1679 'upload_date': '20160524',
1680 'uploader_id': '29913724001',
1681 'timestamp': 1464107587,
1682 'uploader': 'TheAtlantic',
1683 },
1684 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1685 },
1686 # Facebook <iframe> embed
1687 {
1688 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1689 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1690 'info_dict': {
1691 'id': '599637780109885',
1692 'ext': 'mp4',
1693 'title': 'Facebook video #599637780109885',
1694 },
1695 },
fd1c5fba
S
1696 # Facebook <iframe> embed, plugin video
1697 {
1698 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1699 'info_dict': {
1700 'id': '1754168231264132',
1701 'ext': 'mp4',
1702 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1703 'uploader': 'Tariq Ramadan (official)',
1704 'timestamp': 1496758379,
1705 'upload_date': '20170606',
1706 },
1707 'params': {
1708 'skip_download': True,
1709 },
1710 },
fd6ca382
YCH
1711 # Facebook API embed
1712 {
1713 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1714 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1715 'info_dict': {
1716 'id': '10153467542406923',
1717 'ext': 'mp4',
1718 'title': 'Facebook video #10153467542406923',
1719 },
7deef1ba
YCH
1720 },
1721 # Wordpress "YouTube Video Importer" plugin
1722 {
1723 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1724 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1725 'info_dict': {
1726 'id': 'HNTXWDXV9Is',
1727 'ext': 'mp4',
1728 'title': 'Blue Devils Drumline Stanford lot 2016',
1729 'upload_date': '20160627',
1730 'uploader_id': 'GENOCIDE8GENERAL10',
1731 'uploader': 'cylus cyrus',
1732 },
1733 },
81953d1a
RA
1734 {
1735 # video stored on custom kaltura server
1736 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1737 'md5': '537617d06e64dfed891fa1593c4b30cc',
1738 'info_dict': {
1739 'id': '0_1iotm5bh',
1740 'ext': 'mp4',
1741 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1742 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1743 'uploader_id': 'videos.expansion@el-mundo.net',
1744 'upload_date': '20150429',
1745 'timestamp': 1430303472,
1746 },
1747 'add_ie': ['Kaltura'],
1748 },
562de77f
S
1749 {
1750 # multiple kaltura embeds, nsfw
1751 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1752 'info_dict': {
1753 'id': 'kamila-avec-video-jaime-sadomie',
1754 'title': "Kamila avec vídeo “J'aime sadomie”",
1755 },
1756 'playlist_count': 8,
1757 },
c03adf90
YCH
1758 {
1759 # Non-standard Vimeo embed
1760 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1761 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1762 'info_dict': {
1763 'id': '148867247',
1764 'ext': 'mp4',
1765 'title': 'Understanding the web - Teaser',
1766 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1767 'upload_date': '20151214',
1768 'uploader': 'OpenClassrooms',
1769 'uploader_id': 'openclassrooms',
1770 },
1771 'add_ie': ['Vimeo'],
1772 },
a5ff05df
S
1773 {
1774 # generic vimeo embed that requires original URL passed as Referer
1775 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1776 'only_matching': True,
1777 },
1979969f
S
1778 {
1779 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1780 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1781 'info_dict': {
1782 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1783 'ext': 'mp4',
1784 'title': 'Big Buck Bunny',
1785 'description': 'Royalty free test video',
1786 'timestamp': 1432816365,
1787 'upload_date': '20150528',
1788 'is_live': False,
1789 },
1790 'params': {
1791 'skip_download': True,
1792 },
1793 'add_ie': [ArkenaIE.ie_key()],
1794 },
2a1321a2
S
1795 {
1796 '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/',
1797 'info_dict': {
1798 'id': '1c7141f46c',
1799 'ext': 'mp4',
1800 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1801 },
1802 'params': {
1803 'skip_download': True,
1804 },
1805 'add_ie': [Vbox7IE.ie_key()],
1806 },
b0c8f2e9
DR
1807 {
1808 # DBTV embeds
1809 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1810 'info_dict': {
1811 'id': '43254897',
1812 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1813 },
b0c8f2e9
DR
1814 'playlist_mincount': 3,
1815 },
e186a9ec
S
1816 {
1817 # Videa embeds
1818 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1819 'info_dict': {
1820 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1821 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1822 },
1823 'playlist_mincount': 2,
1824 },
b687c85e
S
1825 {
1826 # 20 minuten embed
1827 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1828 'info_dict': {
1829 'id': '523629',
1830 'ext': 'mp4',
1831 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1832 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1833 },
1834 'params': {
1835 'skip_download': True,
1836 },
1837 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1838 },
1839 {
1840 # VideoPress embed
1841 'url': 'https://en.support.wordpress.com/videopress/',
1842 'info_dict': {
1843 'id': 'OcobLTqC',
1844 'ext': 'm4v',
1845 'title': 'IMG_5786',
1846 'timestamp': 1435711927,
1847 'upload_date': '20150701',
1848 },
1849 'params': {
1850 'skip_download': True,
1851 },
1852 'add_ie': [VideoPressIE.ie_key()],
fef51645 1853 },
eb3079b6
S
1854 {
1855 # Rutube embed
1856 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1857 'info_dict': {
1858 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1859 'ext': 'flv',
1860 'title': 'Магаззино: Казань 2',
1861 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1862 'uploader': 'Магаззино',
1863 'upload_date': '20170228',
1864 'uploader_id': '996642',
1865 },
1866 'params': {
1867 'skip_download': True,
1868 },
1869 'add_ie': [RutubeIE.ie_key()],
1870 },
fef51645
YCH
1871 {
1872 # ThePlatform embedded with whitespaces in URLs
1873 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1874 'only_matching': True,
1875 },
97952bdb
JH
1876 {
1877 # Senate ISVP iframe https
1878 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1879 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1880 'info_dict': {
1881 'id': 'govtaff020316',
1882 'ext': 'mp4',
1883 'title': 'Integrated Senate Video Player',
1884 },
1885 'add_ie': [SenateISVPIE.ie_key()],
1886 },
ab87c260
S
1887 {
1888 # Limelight embeds (1 channel embed + 4 media embeds)
1889 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1890 'info_dict': {
1891 'id': 'FacilitatorTraining2017',
1892 'title': 'Facilitator Training 2017',
1893 },
1894 'playlist_mincount': 5,
1895 },
eb02940c
S
1896 {
1897 # Limelight embed (LimelightPlayerUtil.embed)
1898 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1899 'info_dict': {
1900 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1901 'ext': 'mp4',
1902 'title': '07448641',
1903 'timestamp': 1499890639,
1904 'upload_date': '20170712',
1905 },
1906 'params': {
1907 'skip_download': True,
1908 },
1909 'add_ie': ['LimelightMedia'],
1910 },
7986c3ab
S
1911 {
1912 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1913 'info_dict': {
1914 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1915 'title': 'Standoff with Walnut Creek murder suspect ends',
1916 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1917 },
1918 'playlist_mincount': 4,
1919 },
55719459
JH
1920 {
1921 # WashingtonPost embed
1922 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1923 'info_dict': {
1924 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1925 'ext': 'mp4',
1926 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1927 '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.',
1928 'timestamp': 1455216756,
1929 'uploader': 'The Washington Post',
1930 'upload_date': '20160211',
1931 },
1932 'add_ie': [WashingtonPostIE.ie_key()],
1933 },
2b8e6a68
S
1934 {
1935 # Mediaset embed
1936 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1937 'info_dict': {
1938 'id': '720642',
1939 'ext': 'mp4',
1940 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1941 },
1942 'params': {
1943 'skip_download': True,
1944 },
1945 'add_ie': [MediasetIE.ie_key()],
1946 },
73cf76a9
S
1947 {
1948 # JOJ.sk embeds
1949 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1950 'info_dict': {
1951 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1952 'title': 'Slovenskom sa prehnala vlna silných búrok',
1953 },
1954 'playlist_mincount': 5,
1955 'add_ie': [JojIE.ie_key()],
1956 },
4328ddf8
S
1957 {
1958 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1959 'url': 'https://tvrain.ru/amp/418921/',
1960 'md5': 'cc00413936695987e8de148b67d14f1d',
1961 'info_dict': {
1962 'id': '418921',
1963 'ext': 'mp4',
1964 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1965 },
1966 },
41918eaa 1967 {
1968 # vzaar embed
1663bd6e
S
1969 'url': 'http://help.vzaar.com/article/165-embedding-video',
1970 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1971 'info_dict': {
1663bd6e 1972 'id': '8707641',
41918eaa 1973 'ext': 'mp4',
1663bd6e 1974 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1975 },
1976 },
9ce1ac40 1977 {
1978 # multiple HTML5 videos on one page
1979 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1980 'info_dict': {
1981 'id': 'keyscenarios',
1982 'title': 'Rescue Kit 14 Free Edition - Getting started',
1983 },
1984 'playlist_count': 4,
0987f2dd
T
1985 },
1986 {
1987 # vshare embed
7a5c1cfe 1988 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
0987f2dd
T
1989 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1990 'info_dict': {
1991 'id': '0f64ce6',
1992 'title': 'vl14062007715967',
1993 'ext': 'mp4',
1994 }
2ca7ed41
S
1995 },
1996 {
1997 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1998 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1999 'info_dict': {
2000 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
2001 'ext': 'mp4',
2002 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
2003 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
2004 'timestamp': 1474354800,
2005 'upload_date': '20160920',
2006 }
7d540621
S
2007 },
2008 {
2009 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
2010 'info_dict': {
2011 'id': '1731611',
2012 'ext': 'mp4',
2013 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2014 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2015 'timestamp': 1516100691,
2016 'upload_date': '20180116',
2017 },
2018 'params': {
2019 'skip_download': True,
2020 },
2021 'add_ie': [SpringboardPlatformIE.ie_key()],
ea696249 2022 },
4c780fbd
S
2023 {
2024 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2025 'info_dict': {
2026 'id': 'vMDE4NzI1Mjgt690b',
2027 'ext': 'mp4',
2028 'title': 'Котята',
2029 },
2030 'add_ie': [YapFilesIE.ie_key()],
2031 'params': {
2032 'skip_download': True,
2033 },
1fc37ca3 2034 },
660a230b
S
2035 {
2036 # CloudflareStream embed
2037 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2038 'info_dict': {
2039 'id': '31c9291ab41fac05471db4e73aa11717',
2040 'ext': 'mp4',
2041 'title': '31c9291ab41fac05471db4e73aa11717',
2042 },
2043 'add_ie': [CloudflareStreamIE.ie_key()],
2044 'params': {
2045 'skip_download': True,
2046 },
2047 },
6bd499e8
S
2048 {
2049 # PeerTube embed
2050 'url': 'https://joinpeertube.org/fr/home/',
2051 'info_dict': {
2052 'id': 'home',
2053 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2054 },
2055 'playlist_count': 2,
2056 },
aee36ca8
S
2057 {
2058 # Indavideo embed
2059 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2060 'info_dict': {
2061 'id': '1693903',
2062 'ext': 'mp4',
2063 'title': 'Így kell otthon hamburgert sütni',
2064 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2065 'timestamp': 1426330212,
2066 'upload_date': '20150314',
2067 'uploader': 'StreetKitchen',
2068 'uploader_id': '546363',
2069 },
2070 'add_ie': [IndavideoEmbedIE.ie_key()],
2071 'params': {
2072 'skip_download': True,
2073 },
2074 },
cfd7f2a6
S
2075 {
2076 # APA embed via JWPlatform embed
2077 'url': 'http://www.vol.at/blue-man-group/5593454',
2078 'info_dict': {
2079 'id': 'jjv85FdZ',
2080 'ext': 'mp4',
2081 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2082 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2083 'thumbnail': r're:^https?://.*\.jpg$',
2084 'duration': 254,
2085 'timestamp': 1519211149,
2086 'upload_date': '20180221',
2087 },
2088 'params': {
2089 'skip_download': True,
2090 },
2091 },
1fc37ca3
SO
2092 {
2093 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2094 'md5': 'b68d276de422ab07ee1d49388103f457',
2095 'info_dict': {
2096 'id': '83645793',
2097 'title': 'Lock up and get excited',
1fc37ca3 2098 'ext': 'mp4'
d3431dcb
S
2099 },
2100 'skip': 'TODO: fix nested playlists processing in tests',
2101 },
9d1b2138
S
2102 {
2103 # Viqeo embeds
2104 'url': 'https://viqeo.tv/',
2105 'info_dict': {
2106 'id': 'viqeo',
2107 'title': 'All-new video platform',
2108 },
2109 'playlist_count': 6,
2110 },
d78657fd
BM
2111 {
2112 # Squarespace video embed, 2019-08-28
2113 'url': 'http://ootboxford.com',
2114 'info_dict': {
2115 'id': 'Tc7b_JGdZfw',
2116 'title': 'Out of the Blue, at Childish Things 10',
7cb51b5d
S
2117 'ext': 'mp4',
2118 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2119 'uploader_id': 'helendouglashouse',
2120 'uploader': 'Helen & Douglas House',
2121 'upload_date': '20140328',
d78657fd
BM
2122 },
2123 'params': {
2124 'skip_download': True,
2125 },
2126 },
29f7c58a 2127 # {
2128 # # Zype embed
2129 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2130 # 'info_dict': {
2131 # 'id': '5b400b834b32992a310622b9',
2132 # 'ext': 'mp4',
2133 # 'title': 'Smoky Barbecue Favorites',
2134 # 'thumbnail': r're:^https?://.*\.jpe?g',
2135 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2136 # 'upload_date': '20170909',
2137 # 'timestamp': 1504915200,
2138 # },
2139 # 'add_ie': [ZypeIE.ie_key()],
2140 # 'params': {
2141 # 'skip_download': True,
2142 # },
2143 # },
e0b6e988
S
2144 {
2145 # videojs embed
2146 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2147 'info_dict': {
2148 'id': 'shell',
2149 'ext': 'mp4',
2150 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2151 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2152 'thumbnail': r're:^https?://.*\.jpg$',
2153 },
2154 'params': {
2155 'skip_download': True,
2156 },
2157 'expected_warnings': ['Failed to download MPD manifest'],
2158 },
5e3da0d4
RA
2159 {
2160 # DailyMotion embed with DM.player
2161 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2162 'info_dict': {
2163 'id': 'k6aKkGHd9FJs4mtJN39',
2164 'ext': 'mp4',
2165 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2166 'description': 'This video is private.',
2167 'uploader_id': 'x1jf30l',
2168 'uploader': 'beIN SPORTS USA',
2169 'upload_date': '20190528',
2170 'timestamp': 1559062971,
2171 },
2172 'params': {
2173 'skip_download': True,
2174 },
2175 },
6e6b70d6
S
2176 # {
2177 # # TODO: find another test
2178 # # http://schema.org/VideoObject
2179 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2180 # 'md5': '888dcf08b7ea671381f00fab74692755',
2181 # 'info_dict': {
2182 # 'id': 'nyvTSJMKId',
2183 # 'ext': 'mp4',
2184 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2185 # 'description': '#love for cats.',
2186 # 'timestamp': 1461244995,
2187 # 'upload_date': '20160421',
2188 # },
2189 # 'params': {
2190 # 'force_generic_extractor': True,
2191 # },
29f7c58a 2192 # },
2193 {
2194 # VHX Embed
2195 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2196 'info_dict': {
2197 'id': '858208',
2198 'ext': 'mp4',
2199 'title': 'Untitled',
2200 'uploader_id': 'user80538407',
2201 'uploader': 'OTT Videos',
2202 },
2203 },
2204 {
2205 # ArcPublishing PoWa video player
2206 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2207 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2208 'info_dict': {
2209 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2210 'ext': 'mp4',
2211 'title': 'Senate candidates wave to voters on Anchorage streets',
2212 'description': 'md5:91f51a6511f090617353dc720318b20e',
2213 'timestamp': 1604378735,
2214 'upload_date': '20201103',
2215 'duration': 1581,
2216 },
2217 },
2181983a 2218 {
2219 # MyChannels SDK embed
2220 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2221 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2222 'md5': '90c0699c37006ef18e198c032d81739c',
2223 'info_dict': {
2224 'id': '194165',
2225 'ext': 'mp4',
2226 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2227 'timestamp': 1611740340,
2228 'upload_date': '20210127',
2229 'duration': 159,
2230 },
2231 },
bc2ca1bb 2232 {
2233 # Simplecast player embed
2234 'url': 'https://www.bio.org/podcast',
2235 'info_dict': {
2236 'id': 'podcast',
2237 'title': 'I AM BIO Podcast | BIO',
2238 },
2239 'playlist_mincount': 52,
2240 },
e4edeb62 2241 {
b73612a2 2242 # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
2243 'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
2244 'only_matching': True,
2245 }, {
e4edeb62 2246 # WimTv embed player
2247 'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
2248 'info_dict': {
2249 'id': 'wearefmi-pt-2-2021',
2250 'title': '#WEAREFMI – PT.2 – 2021 – MsMotorTV',
2251 },
2252 'playlist_count': 1,
a318f59d 2253 }, {
2254 # KVS Player
2255 'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
2256 'info_dict': {
2257 'id': '105',
2258 'display_id': 'kelis-4th-of-july',
2259 'ext': 'mp4',
2260 'title': 'Kelis - 4th Of July',
2261 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2262 },
2263 'params': {
2264 'skip_download': True,
2265 },
2266 }, {
2267 # KVS Player
2268 'url': 'https://www.kvs-demo.com/embed/105/',
2269 'info_dict': {
2270 'id': '105',
2271 'display_id': 'kelis-4th-of-july',
2272 'ext': 'mp4',
2273 'title': 'Kelis - 4th Of July / Embed Player',
2274 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2275 },
2276 'params': {
2277 'skip_download': True,
2278 },
2279 }, {
2280 # KVS Player
2281 'url': 'https://thisvid.com/videos/french-boy-pantsed/',
2282 'md5': '3397979512c682f6b85b3b04989df224',
2283 'info_dict': {
2284 'id': '2400174',
2285 'display_id': 'french-boy-pantsed',
2286 'ext': 'mp4',
2287 'title': 'French Boy Pantsed - ThisVid.com',
2288 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2289 }
2290 }, {
2291 # KVS Player
2292 'url': 'https://thisvid.com/embed/2400174/',
2293 'md5': '3397979512c682f6b85b3b04989df224',
2294 'info_dict': {
2295 'id': '2400174',
2296 'display_id': 'french-boy-pantsed',
2297 'ext': 'mp4',
2298 'title': 'French Boy Pantsed - ThisVid.com',
2299 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2300 }
2301 }, {
2302 # KVS Player
2303 'url': 'https://youix.com/video/leningrad-zoj/',
2304 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2305 'info_dict': {
2306 'id': '18485',
2307 'display_id': 'leningrad-zoj',
2308 'ext': 'mp4',
2309 'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
2310 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2311 }
2312 }, {
2313 # KVS Player
2314 'url': 'https://youix.com/embed/18485',
2315 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2316 'info_dict': {
2317 'id': '18485',
2318 'display_id': 'leningrad-zoj',
2319 'ext': 'mp4',
2320 'title': 'Ленинград - ЗОЖ',
2321 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2322 }
2323 }, {
2324 # KVS Player
2325 'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
2326 'md5': '94166bdb26b4cb1fb9214319a629fc51',
2327 'info_dict': {
2328 'id': '21217',
2329 'display_id': '40-nochey-40-nights-2016',
2330 'ext': 'mp4',
2331 'title': '40 ночей (2016) - BogMedia.org',
2332 'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
2333 }
e4edeb62 2334 },
cfe50f04 2335 ]
9b122384 2336
9b122384
PH
2337 def report_following_redirect(self, new_url):
2338 """Report information extraction."""
79649588 2339 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 2340
aa9369a2 2341 def report_detected(self, name):
2342 self._downloader.write_debug(f'Identified a {name}')
2343
4fc946b5
PH
2344 def _extract_rss(self, url, video_id, doc):
2345 playlist_title = doc.find('./channel/title').text
2346 playlist_desc_el = doc.find('./channel/description')
2347 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2348
29f7c58a 2349 NS_MAP = {
2350 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2351 }
2352
76c73715
PH
2353 entries = []
2354 for it in doc.findall('./channel/item'):
01aec848
BG
2355 next_url = None
2356 enclosure_nodes = it.findall('./enclosure')
2357 for e in enclosure_nodes:
2358 next_url = e.attrib.get('url')
2359 if next_url:
2360 break
2361
76c73715 2362 if not next_url:
01aec848 2363 next_url = xpath_text(it, 'link', fatal=False)
76c73715
PH
2364
2365 if not next_url:
2366 continue
2367
29f7c58a 2368 def itunes(key):
2369 return xpath_text(
2370 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2371 default=None)
2372
2373 duration = itunes('duration')
2374 explicit = (itunes('explicit') or '').lower()
2375 if explicit in ('true', 'yes'):
2376 age_limit = 18
2377 elif explicit in ('false', 'no'):
2378 age_limit = 0
2379 else:
2380 age_limit = None
2381
76c73715 2382 entries.append({
413c1f8e 2383 '_type': 'url_transparent',
76c73715
PH
2384 'url': next_url,
2385 'title': it.find('title').text,
29f7c58a 2386 'description': xpath_text(it, 'description', default=None),
2387 'timestamp': unified_timestamp(
2388 xpath_text(it, 'pubDate', default=None)),
2389 'duration': int_or_none(duration) or parse_duration(duration),
2390 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2391 'episode': itunes('title'),
2392 'episode_number': int_or_none(itunes('episode')),
2393 'season_number': int_or_none(itunes('season')),
2394 'age_limit': age_limit,
76c73715 2395 })
4fc946b5
PH
2396
2397 return {
2398 '_type': 'playlist',
2399 'id': url,
2400 'title': playlist_title,
2401 'description': playlist_desc,
2402 'entries': entries,
2403 }
2404
c8e9a235
PH
2405 def _extract_camtasia(self, url, video_id, webpage):
2406 """ Returns None if no camtasia video can be found. """
2407
2408 camtasia_cfg = self._search_regex(
2409 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2410 webpage, 'camtasia configuration file', default=None)
2411 if camtasia_cfg is None:
2412 return None
2413
2414 title = self._html_search_meta('DC.title', webpage, fatal=True)
2415
2416 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2417 camtasia_cfg = self._download_xml(
2418 camtasia_url, video_id,
2419 note='Downloading camtasia configuration',
2420 errnote='Failed to download camtasia configuration')
2421 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2422
2423 entries = []
2424 for n in fileset_node.getchildren():
2425 url_n = n.find('./uri')
2426 if url_n is None:
2427 continue
2428
2429 entries.append({
2430 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2431 'title': '%s - %s' % (title, n.tag),
2432 'url': compat_urlparse.urljoin(url, url_n.text),
2433 'duration': float_or_none(n.find('./duration').text),
2434 })
2435
2436 return {
2437 '_type': 'playlist',
2438 'entries': entries,
2439 'title': title,
2440 }
2441
a318f59d 2442 def _kvs_getrealurl(self, video_url, license_code):
2443 if not video_url.startswith('function/0/'):
2444 return video_url # not obfuscated
2445
2446 url_path, _, url_query = video_url.partition('?')
2447 urlparts = url_path.split('/')[2:]
2448 license = self._kvs_getlicensetoken(license_code)
2449 newmagic = urlparts[5][:32]
2450
2451 for o in range(len(newmagic) - 1, -1, -1):
2452 new = ''
2453 l = (o + sum([int(n) for n in license[o:]])) % 32
2454
2455 for i in range(0, len(newmagic)):
2456 if i == o:
2457 new += newmagic[l]
2458 elif i == l:
2459 new += newmagic[o]
2460 else:
2461 new += newmagic[i]
2462 newmagic = new
2463
2464 urlparts[5] = newmagic + urlparts[5][32:]
2465 return '/'.join(urlparts) + '?' + url_query
2466
2467 def _kvs_getlicensetoken(self, license):
2468 modlicense = license.replace('$', '').replace('0', '1')
2469 center = int(len(modlicense) / 2)
2470 fronthalf = int(modlicense[:center + 1])
2471 backhalf = int(modlicense[center:])
2472
2473 modlicense = str(4 * abs(fronthalf - backhalf))
2474 retval = ''
2475 for o in range(0, center + 1):
2476 for i in range(1, 5):
2477 retval += str((int(license[o + i]) + int(modlicense[o])) % 10)
2478 return retval
2479
9b122384 2480 def _real_extract(self, url):
ebd3c7b3 2481 if url.startswith('//'):
d226c560 2482 return self.url_result(self.http_scheme() + url)
ebd3c7b3 2483
a7130543
JMF
2484 parsed_url = compat_urlparse.urlparse(url)
2485 if not parsed_url.scheme:
a06916d9 2486 default_search = self.get_param('default_search')
04b4d394 2487 if default_search is None:
1f7ccb90 2488 default_search = 'fixup_error'
04b4d394 2489
1f7ccb90 2490 if default_search in ('auto', 'auto_warning', 'fixup_error'):
9c1da4a9 2491 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
6a39ee13 2492 self.report_warning('The url doesn\'t specify the protocol, trying with http')
04b4d394 2493 return self.url_result('http://' + url)
1f7ccb90 2494 elif default_search != 'fixup_error':
9c1fc022 2495 if default_search == 'auto_warning':
0e67ab0d
PH
2496 if re.match(r'^(?:url|URL)$', url):
2497 raise ExtractorError(
7a5c1cfe 2498 'Invalid URL: %r . Call yt-dlp like this: yt-dlp -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
0e67ab0d
PH
2499 expected=True)
2500 else:
6a39ee13 2501 self.report_warning(
7571c02c 2502 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2503 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2504
2505 if default_search in ('error', 'fixup_error'):
7571c02c 2506 raise ExtractorError(
b74e86f4 2507 '%r is not a valid URL. '
7a5c1cfe 2508 'Set --default-search "ytsearch" (or run yt-dlp "ytsearch:%s" ) to search YouTube'
b74e86f4 2509 % (url, url), expected=True)
04b4d394 2510 else:
f2f2c0c2
PH
2511 if ':' not in default_search:
2512 default_search += ':'
04b4d394 2513 return self.url_result(default_search + url)
4d54ef20
PH
2514
2515 url, smuggled_data = unsmuggle_url(url)
2516 force_videoid = None
d6e6a422 2517 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2518 if smuggled_data and 'force_videoid' in smuggled_data:
2519 force_videoid = smuggled_data['force_videoid']
2520 video_id = force_videoid
2521 else:
9dcd6fd3 2522 video_id = self._generic_id(url)
3d83a1ae 2523
79649588 2524 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2525
ebab4520 2526 head_req = HEADRequest(url)
23be51d8 2527 head_response = self._request_webpage(
ebab4520
PH
2528 head_req, video_id,
2529 note=False, errnote='Could not send HEAD request to %s' % url,
2530 fatal=False)
42393ce2 2531
23be51d8 2532 if head_response is not False:
42393ce2 2533 # Check for redirect
7947a1f7 2534 new_url = head_response.geturl()
42393ce2
PH
2535 if url != new_url:
2536 self.report_following_redirect(new_url)
4d54ef20
PH
2537 if force_videoid:
2538 new_url = smuggle_url(
2539 new_url, {'force_videoid': force_videoid})
cecaaf3f 2540 return self.url_result(new_url)
42393ce2 2541
23be51d8
PH
2542 full_response = None
2543 if head_response is False:
5c2266df 2544 request = sanitized_Request(url)
58bde34a
S
2545 request.add_header('Accept-Encoding', '*')
2546 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2547 head_response = full_response
2548
f930e0c7
S
2549 info_dict = {
2550 'id': video_id,
9dcd6fd3 2551 'title': self._generic_title(url),
29f7c58a 2552 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
f930e0c7
S
2553 }
2554
23be51d8 2555 # Check for direct link to a video
955737b2 2556 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2557 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2558 if m:
aa9369a2 2559 self.report_detected('direct video link')
4e363703 2560 format_id = compat_str(m.group('format_id'))
c26326c1 2561 subtitles = {}
f930e0c7 2562 if format_id.endswith('mpegurl'):
c26326c1 2563 formats, subtitles = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
f930e0c7
S
2564 elif format_id == 'f4m':
2565 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2566 else:
2567 formats = [{
4e363703 2568 'format_id': format_id,
eadc3ccd 2569 'url': url,
2570 'vcodec': 'none' if m.group('type') == 'audio' else None
2571 }]
de6c51e8 2572 info_dict['direct'] = True
19dbaeec 2573 self._sort_formats(formats)
de6c51e8 2574 info_dict['formats'] = formats
c26326c1 2575 info_dict['subtitles'] = subtitles
f930e0c7 2576 return info_dict
42393ce2 2577
a06916d9 2578 if not self.get_param('test', False) and not is_intentional:
2579 force = self.get_param('force_generic_extractor', False)
6a39ee13 2580 self.report_warning(
2fece970 2581 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2582
4e262a88 2583 if not full_response:
5c2266df 2584 request = sanitized_Request(url)
58bde34a
S
2585 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2586 # making it impossible to download only chunk of the file (yet we need only 512kB to
7a5c1cfe 2587 # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
58bde34a
S
2588 # that will always result in downloading the whole file that is not desirable.
2589 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2590 # to accept raw bytes and being able to download only a chunk.
2591 # It may probably better to solve this by checking Content-Type for application/octet-stream
2592 # after HEAD request finishes, but not sure if we can rely on this.
2593 request.add_header('Accept-Encoding', '*')
2594 full_response = self._request_webpage(request, video_id)
4e262a88 2595
5940862d
S
2596 first_bytes = full_response.read(512)
2597
2598 # Is it an M3U playlist?
0d769bcb 2599 if first_bytes.startswith(b'#EXTM3U'):
aa9369a2 2600 self.report_detected('M3U playlist')
da1c94ee 2601 info_dict['formats'], info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
19dbaeec 2602 self._sort_formats(info_dict['formats'])
5940862d
S
2603 return info_dict
2604
4e262a88
PH
2605 # Maybe it's a direct link to a video?
2606 # Be careful not to download the whole thing!
61ca9a80 2607 if not is_html(first_bytes):
6a39ee13 2608 self.report_warning(
4e262a88 2609 'URL could be a direct video link, returning it as such.')
f930e0c7 2610 info_dict.update({
4e262a88
PH
2611 'direct': True,
2612 'url': url,
f930e0c7
S
2613 })
2614 return info_dict
4e262a88
PH
2615
2616 webpage = self._webpage_read_content(
2617 full_response, url, video_id, prefix=first_bytes)
2618
2181983a 2619 if '<title>DPG Media Privacy Gate</title>' in webpage:
2620 webpage = self._download_webpage(url, video_id)
2621
9b122384 2622 self.report_extraction(video_id)
887c6acd 2623
1b840245 2624 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2625 try:
61241abb 2626 try:
2627 doc = compat_etree_fromstring(webpage)
2628 except compat_xml_parse_error:
2629 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5 2630 if doc.tag == 'rss':
aa9369a2 2631 self.report_detected('RSS feed')
4fc946b5 2632 return self._extract_rss(url, video_id, doc)
cc99a77a 2633 elif doc.tag == 'SmoothStreamingMedia':
7a450a3b 2634 info_dict['formats'], info_dict['subtitles'] = self._parse_ism_formats_and_subtitles(doc, url)
aa9369a2 2635 self.report_detected('ISM manifest')
cc99a77a
S
2636 self._sort_formats(info_dict['formats'])
2637 return info_dict
e5e8d20a 2638 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec 2639 smil = self._parse_smil(doc, url, video_id)
aa9369a2 2640 self.report_detected('SMIL file')
19dbaeec
S
2641 self._sort_formats(smil['formats'])
2642 return smil
729accb4 2643 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
aa9369a2 2644 self.report_detected('XSPF playlist')
96b8b9ab 2645 return self.playlist_result(
47a5cb77
S
2646 self._parse_xspf(
2647 doc, video_id, xspf_url=url,
7947a1f7 2648 xspf_base_url=full_response.geturl()),
96b8b9ab 2649 video_id)
1b840245 2650 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
7de27caf 2651 info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles(
d3f8b76b 2652 doc,
7947a1f7 2653 mpd_base_url=full_response.geturl().rpartition('/')[0],
86f4d14f 2654 mpd_url=url)
aa9369a2 2655 self.report_detected('DASH manifest')
19dbaeec 2656 self._sort_formats(info_dict['formats'])
f930e0c7
S
2657 return info_dict
2658 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2659 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
aa9369a2 2660 self.report_detected('F4M manifest')
19dbaeec 2661 self._sort_formats(info_dict['formats'])
f930e0c7 2662 return info_dict
f7300c5c 2663 except compat_xml_parse_error:
4fc946b5
PH
2664 pass
2665
c8e9a235
PH
2666 # Is it a Camtasia project?
2667 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2668 if camtasia_res is not None:
aa9369a2 2669 self.report_detected('Camtasia video')
c8e9a235
PH
2670 return camtasia_res
2671
14390730 2672 # Sometimes embedded video player is hidden behind percent encoding
067aa17e 2673 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
14390730 2674 # Unescaping the whole page allows to handle those cases in a generic way
29f7c58a 2675 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2676 # There probably should be a second run of generic extractor on unescaped webpage.
2677 # webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2678
7cb51b5d
S
2679 # Unescape squarespace embeds to be detected by generic extractor,
2680 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2681 webpage = re.sub(
2682 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2683 lambda x: unescapeHTML(x.group(0)), webpage)
d78657fd 2684
887c6acd
PH
2685 # it's tempting to parse this further, but you would
2686 # have to take into account all the variations like
2687 # Video Title - Site Name
2688 # Site Name | Video Title
2689 # Video Title - Tagline | Site Name
2690 # and so on and so forth; it's just not practical
6f41b2bc
S
2691 video_title = self._og_search_title(
2692 webpage, default=None) or self._html_search_regex(
79649588
PH
2693 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2694 default='video')
ef4fd848 2695
4d805e06
PH
2696 # Try to detect age limit automatically
2697 age_limit = self._rta_search(webpage)
2698 # And then there are the jokers who advertise that they use RTA,
2699 # but actually don't.
2700 AGE_LIMIT_MARKERS = [
197224b7 2701 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
4d805e06
PH
2702 ]
2703 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2704 age_limit = 18
2705
ef4fd848
PH
2706 # video uploader is domain name
2707 video_uploader = self._search_regex(
79649588 2708 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2709
6f41b2bc
S
2710 video_description = self._og_search_description(webpage, default=None)
2711 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2712
b311b0ea
S
2713 info_dict.update({
2714 'title': video_title,
2715 'description': video_description,
2716 'thumbnail': video_thumbnail,
2717 'age_limit': age_limit,
2718 })
2719
aa9369a2 2720 self._downloader.write_debug('Looking for video embeds')
2721
1f4b722b 2722 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2723 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2724 if bc_urls:
99877772
PH
2725 entries = [{
2726 '_type': 'url',
2727 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2728 'ie_key': 'BrightcoveLegacy'
99877772
PH
2729 } for bc_url in bc_urls]
2730
2731 return {
2732 '_type': 'playlist',
2733 'title': video_title,
2734 'id': video_id,
2735 'entries': entries,
2736 }
cfe50f04 2737
f6519f89 2738 # Look for Brightcove New Studio embeds
0254f93b 2739 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2740 if bc_urls:
5399ab3f
S
2741 return self.playlist_from_matches(
2742 bc_urls, video_id, video_title,
2743 getter=lambda x: smuggle_url(x, {'referrer': url}),
2744 ie='BrightcoveNew')
ed126900 2745
4e826cd9
S
2746 # Look for Nexx embeds
2747 nexx_urls = NexxIE._extract_urls(webpage)
2748 if nexx_urls:
2749 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2750
3f59b015
S
2751 # Look for Nexx iFrame embeds
2752 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2753 if nexx_embed_urls:
2754 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2755
4d8819d2
S
2756 # Look for ThePlatform embeds
2757 tp_urls = ThePlatformIE._extract_urls(webpage)
2758 if tp_urls:
46b18f23 2759 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2760
29f7c58a 2761 arc_urls = ArcPublishingIE._extract_urls(webpage)
2762 if arc_urls:
2763 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2764
2181983a 2765 mychannels_urls = MedialaanIE._extract_urls(webpage)
2766 if mychannels_urls:
2767 return self.playlist_from_matches(
2768 mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
2769
59b8ab58
PH
2770 # Look for embedded rtl.nl player
2771 matches = re.findall(
2637fadc 2772 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
59b8ab58
PH
2773 webpage)
2774 if matches:
46b18f23 2775 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2776
09b9c45e
S
2777 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2778 if vimeo_urls:
46b18f23 2779 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2780
29f7c58a 2781 vhx_url = VHXEmbedIE._extract_url(webpage)
2782 if vhx_url:
2783 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2784
df0c8151 2785 # Invidious Instances
2786 # https://github.com/yt-dlp/yt-dlp/issues/195
2787 # https://github.com/iv-org/invidious/pull/1730
2788 youtube_url = self._search_regex(
2789 r'<link rel="alternate" href="(https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2790 webpage, 'youtube link', default=None)
2791 if youtube_url:
2792 return self.url_result(youtube_url, YoutubeIE.ie_key())
2793
66c9fa36
S
2794 # Look for YouTube embeds
2795 youtube_urls = YoutubeIE._extract_urls(webpage)
2796 if youtube_urls:
46b18f23 2797 return self.playlist_from_matches(
66c9fa36 2798 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2799
ad213a1d 2800 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2801 if matches:
46b18f23 2802 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2803
8489578d
NJ
2804 # Look for embedded Dailymotion playlist player (#3822)
2805 m = re.search(
2806 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2807 if m:
2808 playlists = re.findall(
2809 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2810 if playlists:
46b18f23
JH
2811 return self.playlist_from_matches(
2812 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2813
71a1db89
S
2814 # Look for DailyMail embeds
2815 dailymail_urls = DailyMailIE._extract_urls(webpage)
2816 if dailymail_urls:
2817 return self.playlist_from_matches(
2818 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2819
be7dacf9
S
2820 # Look for Teachable embeds, must be before Wistia
2821 teachable_url = TeachableIE._extract_url(webpage, url)
2822 if teachable_url:
2823 return self.url_result(teachable_url)
2824
ef4fd848 2825 # Look for embedded Wistia player
fda6d237
S
2826 wistia_urls = WistiaIE._extract_urls(webpage)
2827 if wistia_urls:
2828 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2829 for entry in playlist['entries']:
2830 entry.update({
2831 '_type': 'url_transparent',
2832 'uploader': video_uploader,
2833 })
2834 return playlist
5f6a1245 2835
bab19a8e
S
2836 # Look for SVT player
2837 svt_url = SVTIE._extract_url(webpage)
2838 if svt_url:
2839 return self.url_result(svt_url, 'SVT')
2840
c19f7764
JMF
2841 # Look for Bandcamp pages with custom domain
2842 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2843 if mobj is not None:
2844 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2845 # Don't set the extractor because it can be a track url or an album
2846 return self.url_result(burl)
c19f7764 2847
f25571ff
PH
2848 # Look for embedded Vevo player
2849 mobj = re.search(
2850 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2851 if mobj is not None:
2852 return self.url_result(mobj.group('url'))
796df3c6
S
2853
2854 # Look for embedded Viddler player
cb454b33
S
2855 mobj = re.search(
2856 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2857 webpage)
796df3c6
S
2858 if mobj is not None:
2859 return self.url_result(mobj.group('url'))
f25571ff 2860
3378d67a
S
2861 # Look for NYTimes player
2862 mobj = re.search(
2863 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2864 webpage)
2865 if mobj is not None:
2866 return self.url_result(mobj.group('url'))
2867
cefdf970
S
2868 # Look for Libsyn player
2869 mobj = re.search(
2870 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2871 if mobj is not None:
2872 return self.url_result(mobj.group('url'))
2873
c0d0b01f 2874 # Look for Ooyala videos
3089bc74
S
2875 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2876 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2877 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2878 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2879 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2880 if mobj is not None:
9837cb75
RA
2881 embed_token = self._search_regex(
2882 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2883 webpage, 'ooyala embed token', default=None)
2884 return OoyalaIE._build_url_result(smuggle_url(
2885 mobj.group('ec'), {
2886 'domain': url,
2887 'embed_token': embed_token,
2888 }))
c0d0b01f 2889
f076b638 2890 # Look for multiple Ooyala embeds on SBN network websites
2891 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2892 if mobj is not None:
2893 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2894 if embeds:
46b18f23
JH
2895 return self.playlist_from_matches(
2896 embeds, video_id, video_title,
2897 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2898
aa94a6d3 2899 # Look for Aparat videos
48099643 2900 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2901 if mobj is not None:
2902 return self.url_result(mobj.group(1), 'Aparat')
2903
c93c2ab1 2904 # Look for MPORA videos
c3f51436 2905 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2906 if mobj is not None:
2907 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2908
9834872b 2909 # Look for embedded Facebook player
0646e34c
S
2910 facebook_urls = FacebookIE._extract_urls(webpage)
2911 if facebook_urls:
2912 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2913
ca97a56e
S
2914 # Look for embedded VK player
2915 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2916 if mobj is not None:
2917 return self.url_result(mobj.group('url'), 'VK')
2918
33d4fdab 2919 # Look for embedded Odnoklassniki player
416c3ca7
RA
2920 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2921 if odnoklassniki_url:
2922 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
33d4fdab 2923
b73612a2 2924 # Look for sibnet embedded player
2925 sibnet_urls = VKIE._extract_sibnet_urls(webpage)
2926 if sibnet_urls:
2927 return self.playlist_from_matches(sibnet_urls, video_id, video_title)
2928
0364fa8b
S
2929 # Look for embedded ivi player
2930 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2931 if mobj is not None:
2932 return self.url_result(mobj.group('url'), 'Ivi')
2933
db1f3888
PH
2934 # Look for embedded Huffington Post player
2935 mobj = re.search(
c3f51436 2936 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2937 if mobj is not None:
2938 return self.url_result(mobj.group('url'), 'HuffPost')
2939
1b86cc41 2940 # Look for embed.ly
2941 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2942 if mobj is not None:
2943 return self.url_result(mobj.group('url'))
2944 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2945 if mobj is not None:
f7e6f7fa 2946 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2947
60cc4dc4
PH
2948 # Look for funnyordie embed
2949 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2950 if matches:
46b18f23
JH
2951 return self.playlist_from_matches(
2952 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2953
bc2ca1bb 2954 # Look for Simplecast embeds
2955 simplecast_urls = SimplecastIE._extract_urls(webpage)
2956 if simplecast_urls:
2957 return self.playlist_from_matches(
2958 simplecast_urls, video_id, video_title)
2959
db546cf8
S
2960 # Look for BBC iPlayer embed
2961 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2962 if matches:
46b18f23 2963 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2964
93d020dd
S
2965 # Look for embedded RUTV player
2966 rutv_url = RUTVIE._extract_url(webpage)
2967 if rutv_url:
2968 return self.url_result(rutv_url, 'RUTV')
2969
494f20cb 2970 # Look for embedded TVC player
b8599718
S
2971 tvc_url = TVCIE._extract_url(webpage)
2972 if tvc_url:
2973 return self.url_result(tvc_url, 'TVC')
494f20cb 2974
d40a3b5b 2975 # Look for embedded SportBox player
476cf548 2976 sportbox_urls = SportBoxIE._extract_urls(webpage)
d40a3b5b 2977 if sportbox_urls:
476cf548 2978 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
d40a3b5b 2979
2bb5b6d0
S
2980 # Look for embedded XHamster player
2981 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2982 if xhamster_urls:
46b18f23 2983 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2984
2c9ca782
S
2985 # Look for embedded TNAFlixNetwork player
2986 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2987 if tnaflix_urls:
46b18f23 2988 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2989
b52c9ef1
S
2990 # Look for embedded PornHub player
2991 pornhub_urls = PornHubIE._extract_urls(webpage)
2992 if pornhub_urls:
46b18f23 2993 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2994
37e7a71c
S
2995 # Look for embedded DrTuber player
2996 drtuber_urls = DrTuberIE._extract_urls(webpage)
2997 if drtuber_urls:
46b18f23 2998 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2999
e28ed498
S
3000 # Look for embedded RedTube player
3001 redtube_urls = RedTubeIE._extract_urls(webpage)
3002 if redtube_urls:
46b18f23 3003 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 3004
06993715
S
3005 # Look for embedded Tube8 player
3006 tube8_urls = Tube8IE._extract_urls(webpage)
3007 if tube8_urls:
3008 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
3009
4e7b5bba
S
3010 # Look for embedded Mofosex player
3011 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
3012 if mofosex_urls:
3013 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
3014
8fae1a04
S
3015 # Look for embedded Spankwire player
3016 spankwire_urls = SpankwireIE._extract_urls(webpage)
3017 if spankwire_urls:
3018 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
3019
52c4c515
S
3020 # Look for embedded YouPorn player
3021 youporn_urls = YouPornIE._extract_urls(webpage)
3022 if youporn_urls:
3023 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
3024
9872d311
S
3025 # Look for embedded Tvigle player
3026 mobj = re.search(
3027 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
3028 if mobj is not None:
3029 return self.url_result(mobj.group('url'), 'Tvigle')
3030
7e2ede98
JMF
3031 # Look for embedded TED player
3032 mobj = re.search(
d7cc31b6 3033 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
3034 if mobj is not None:
3035 return self.url_result(mobj.group('url'), 'TED')
3036
5c386252 3037 # Look for embedded Ustream videos
d77ac737
YCH
3038 ustream_url = UstreamIE._extract_url(webpage)
3039 if ustream_url:
3040 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 3041
893f8832 3042 # Look for embedded arte.tv player
8bdd16b4 3043 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
3044 if arte_urls:
3045 return self.playlist_from_matches(arte_urls, video_id, video_title)
893f8832 3046
cbd55ade
S
3047 # Look for embedded francetv player
3048 mobj = re.search(
3049 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
3050 webpage)
3051 if mobj is not None:
3052 return self.url_result(mobj.group('url'))
3053
e6c2d9ad 3054 # Look for embedded Myvi.ru player
6dd94d3a 3055 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
3056 if myvi_url:
3057 return self.url_result(myvi_url)
3058
dfb1b146 3059 # Look for embedded soundcloud player
548c3957 3060 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
94aae015 3061 if soundcloud_urls:
548c3957 3062 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
20991253 3063
027e2312
S
3064 # Look for tunein player
3065 tunein_urls = TuneInBaseIE._extract_urls(webpage)
3066 if tunein_urls:
46b18f23 3067 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 3068
c5cd249e 3069 # Look for embedded mtvservices player
46fde8a1
S
3070 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
3071 if mtvservices_url:
3072 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 3073
49807b4a
S
3074 # Look for embedded yahoo player
3075 mobj = re.search(
3076 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
3077 webpage)
3078 if mobj is not None:
3079 return self.url_result(mobj.group('url'), 'Yahoo')
3080
2ef6fcb5
PH
3081 # Look for embedded sbs.com.au player
3082 mobj = re.search(
e98b8e79
PH
3083 r'''(?x)
3084 (?:
3085 <meta\s+property="og:video"\s+content=|
3086 <iframe[^>]+?src=
3087 )
3088 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
3089 webpage)
3090 if mobj is not None:
3091 return self.url_result(mobj.group('url'), 'SBS')
3092
42bdd9d0
PH
3093 # Look for embedded Cinchcast player
3094 mobj = re.search(
3095 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
3096 webpage)
3097 if mobj is not None:
3098 return self.url_result(mobj.group('url'), 'Cinchcast')
3099
1a94ff68 3100 mobj = re.search(
5263cdfc 3101 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 3102 webpage)
8001607e
YCH
3103 if not mobj:
3104 mobj = re.search(
1418a043 3105 r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
8001607e 3106 webpage)
1a94ff68
S
3107 if mobj is not None:
3108 return self.url_result(mobj.group('url'), 'MLB')
3109
1419fafd 3110 mobj = re.search(
dd467d33 3111 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
3112 webpage)
3113 if mobj is not None:
3114 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
3115
af63fed7 3116 mobj = re.search(
78d3b3e2 3117 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
3118 webpage)
3119 if mobj is not None:
3120 return self.url_result(mobj.group('url'), 'Livestream')
3121
255fca5e
S
3122 # Look for Zapiks embed
3123 mobj = re.search(
3124 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
3125 if mobj is not None:
3126 return self.url_result(mobj.group('url'), 'Zapiks')
3127
e3216b82 3128 # Look for Kaltura embeds
562de77f
S
3129 kaltura_urls = KalturaIE._extract_urls(webpage)
3130 if kaltura_urls:
3131 return self.playlist_from_matches(
3132 kaltura_urls, video_id, video_title,
3133 getter=lambda x: smuggle_url(x, {'source_url': url}),
3134 ie=KalturaIE.ie_key())
e3216b82 3135
665e9452 3136 # Look for EaglePlatform embeds
06a96da1
S
3137 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
3138 if eagleplatform_url:
665e9452 3139 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 3140
665e9452 3141 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
3142 mobj = re.search(
3143 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
3144 if mobj is not None:
3145 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
3146
f8388757 3147 # Look for Pladform embeds
45dad7ba
S
3148 pladform_url = PladformIE._extract_url(webpage)
3149 if pladform_url:
3150 return self.url_result(pladform_url)
f8388757 3151
ff18735c
S
3152 # Look for Videomore embeds
3153 videomore_url = VideomoreIE._extract_url(webpage)
3154 if videomore_url:
3155 return self.url_result(videomore_url)
3156
83f1481b
S
3157 # Look for Webcaster embeds
3158 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3159 if webcaster_url:
3160 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3161
2dcc114f
S
3162 # Look for Playwire embeds
3163 mobj = re.search(
3164 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
3165 if mobj is not None:
3166 return self.url_result(mobj.group('url'))
3167
ad320e9b
NJ
3168 # Look for 5min embeds
3169 mobj = re.search(
3170 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3171 if mobj is not None:
3172 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3173
18153f1b
S
3174 # Look for Crooks and Liars embeds
3175 mobj = re.search(
3176 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
3177 if mobj is not None:
3178 return self.url_result(mobj.group('url'))
3179
a2edf2e7
YCH
3180 # Look for NBC Sports VPlayer embeds
3181 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3182 if nbc_sports_url:
3183 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
3184
de3eb07e
YCH
3185 # Look for NBC News embeds
3186 nbc_news_embed_url = re.search(
3187 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3188 if nbc_news_embed_url:
3189 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3190
653789af 3191 # Look for Google Drive embeds
5b251628 3192 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 3193 if google_drive_url:
3194 return self.url_result(google_drive_url, 'GoogleDrive')
3195
418c5cc3
YCH
3196 # Look for UDN embeds
3197 mobj = re.search(
2637fadc 3198 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
3199 if mobj is not None:
3200 return self.url_result(
0a160363 3201 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 3202
2fe1b5bd
YCH
3203 # Look for Senate ISVP iframe
3204 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3205 if senate_isvp_url:
25c3a734 3206 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 3207
55adb63e
RA
3208 # Look for Kinja embeds
3209 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3210 if kinja_embed_urls:
3211 return self.playlist_from_matches(
3212 kinja_embed_urls, video_id, video_title)
3213
1ac1c4c2
S
3214 # Look for OnionStudios embeds
3215 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3216 if onionstudios_url:
3217 return self.url_result(onionstudios_url)
3218
67167920 3219 # Look for ViewLift embeds
3220 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3221 if viewlift_url:
3222 return self.url_result(viewlift_url)
eedd20ef 3223
7cb09524 3224 # Look for JWPlatform embeds
b0ead0e0
S
3225 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3226 if jwplatform_urls:
3227 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
7cb09524 3228
aecfcd4e
S
3229 # Look for Digiteka embeds
3230 digiteka_url = DigitekaIE._extract_url(webpage)
3231 if digiteka_url:
3232 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 3233
1979969f
S
3234 # Look for Arkena embeds
3235 arkena_url = ArkenaIE._extract_url(webpage)
3236 if arkena_url:
3237 return self.url_result(arkena_url, ArkenaIE.ie_key())
3238
b1c35797
RA
3239 # Look for Piksel embeds
3240 piksel_url = PikselIE._extract_url(webpage)
3241 if piksel_url:
3242 return self.url_result(piksel_url, PikselIE.ie_key())
3243
1bf996fa 3244 # Look for Limelight embeds
e5d39886
S
3245 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3246 if limelight_urls:
3247 return self.playlist_result(
3248 limelight_urls, video_id, video_title, video_description)
3249
7986c3ab
S
3250 # Look for Anvato embeds
3251 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3252 if anvato_urls:
3253 return self.playlist_result(
3254 anvato_urls, video_id, video_title, video_description)
3255
a5158f38
YCH
3256 # Look for AdobeTVVideo embeds
3257 mobj = re.search(
3258 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3259 webpage)
3260 if mobj is not None:
3261 return self.url_result(
3262 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3263 'AdobeTVVideo')
3264
088e1aac
YCH
3265 # Look for Vine embeds
3266 mobj = re.search(
3267 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3268 webpage)
3269 if mobj is not None:
3270 return self.url_result(
3271 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3272
217d5ae0
RA
3273 # Look for VODPlatform embeds
3274 mobj = re.search(
bd2c211f 3275 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
217d5ae0
RA
3276 webpage)
3277 if mobj is not None:
3278 return self.url_result(
93b84045 3279 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 3280
7d273a38
RA
3281 # Look for Mangomolo embeds
3282 mobj = re.search(
755541a4
RA
3283 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3284 (?:
3285 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3286 player\.mangomolo\.com/v1
3287 )/
7d273a38
RA
3288 (?:
3289 video\?.*?\bid=(?P<video_id>\d+)|
755541a4 3290 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
7d273a38
RA
3291 ).+?)\1''', webpage)
3292 if mobj is not None:
3293 info = {
3294 '_type': 'url_transparent',
3295 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3296 'title': video_title,
3297 'description': video_description,
3298 'thumbnail': video_thumbnail,
3299 'uploader': video_uploader,
3300 }
3301 video_id = mobj.group('video_id')
3302 if video_id:
3303 info.update({
3304 'ie_key': 'MangomoloVideo',
3305 'id': video_id,
3306 })
3307 else:
3308 info.update({
3309 'ie_key': 'MangomoloLive',
3310 'id': mobj.group('channel_id'),
3311 })
3312 return info
3313
5a51775a
YCH
3314 # Look for Instagram embeds
3315 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3316 if instagram_embed_url is not None:
11e60fca
S
3317 return self.url_result(
3318 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 3319
5d39176f
S
3320 # Look for 3Q SDN embeds
3321 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3322 if threeqsdn_url:
6f41b2bc
S
3323 return {
3324 '_type': 'url_transparent',
3325 'ie_key': ThreeQSDNIE.ie_key(),
3326 'url': self._proto_relative_url(threeqsdn_url),
3327 'title': video_title,
3328 'description': video_description,
3329 'thumbnail': video_thumbnail,
3330 'uploader': video_uploader,
3331 }
5d39176f 3332
2a1321a2
S
3333 # Look for VBOX7 embeds
3334 vbox7_url = Vbox7IE._extract_url(webpage)
3335 if vbox7_url:
3336 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3337
b0c8f2e9
DR
3338 # Look for DBTV embeds
3339 dbtv_urls = DBTVIE._extract_urls(webpage)
3340 if dbtv_urls:
46b18f23 3341 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 3342
e186a9ec
S
3343 # Look for Videa embeds
3344 videa_urls = VideaIE._extract_urls(webpage)
3345 if videa_urls:
46b18f23 3346 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 3347
b687c85e
S
3348 # Look for 20 minuten embeds
3349 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3350 if twentymin_urls:
46b18f23
JH
3351 return self.playlist_from_matches(
3352 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 3353
6ef3e65a
S
3354 # Look for VideoPress embeds
3355 videopress_urls = VideoPressIE._extract_urls(webpage)
3356 if videopress_urls:
46b18f23
JH
3357 return self.playlist_from_matches(
3358 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 3359
eb3079b6
S
3360 # Look for Rutube embeds
3361 rutube_urls = RutubeIE._extract_urls(webpage)
3362 if rutube_urls:
46b18f23 3363 return self.playlist_from_matches(
2583c0b5 3364 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 3365
55719459
JH
3366 # Look for WashingtonPost embeds
3367 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3368 if wapo_urls:
3369 return self.playlist_from_matches(
3370 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3371
5d29af3d 3372 # Look for Mediaset embeds
8fd12a08 3373 mediaset_urls = MediasetIE._extract_urls(self, webpage)
5d29af3d
S
3374 if mediaset_urls:
3375 return self.playlist_from_matches(
3376 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3377
73cf76a9
S
3378 # Look for JOJ.sk embeds
3379 joj_urls = JojIE._extract_urls(webpage)
3380 if joj_urls:
3381 return self.playlist_from_matches(
3382 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3383
24e966e8
PH
3384 # Look for megaphone.fm embeds
3385 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3386 if mpfn_urls:
3387 return self.playlist_from_matches(
3388 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3389
1663bd6e
S
3390 # Look for vzaar embeds
3391 vzaar_urls = VzaarIE._extract_urls(webpage)
3392 if vzaar_urls:
3393 return self.playlist_from_matches(
3394 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3395
26bae2d9
S
3396 channel9_urls = Channel9IE._extract_urls(webpage)
3397 if channel9_urls:
3398 return self.playlist_from_matches(
3399 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3400
0987f2dd
T
3401 vshare_urls = VShareIE._extract_urls(webpage)
3402 if vshare_urls:
3403 return self.playlist_from_matches(
3404 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3405
8056c854 3406 # Look for Mediasite embeds
2ca7ed41
S
3407 mediasite_urls = MediasiteIE._extract_urls(webpage)
3408 if mediasite_urls:
3409 entries = [
3410 self.url_result(smuggle_url(
3411 compat_urlparse.urljoin(url, mediasite_url),
3412 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3413 for mediasite_url in mediasite_urls]
3414 return self.playlist_result(entries, video_id, video_title)
8056c854 3415
7d540621
S
3416 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3417 if springboardplatform_urls:
3418 return self.playlist_from_matches(
3419 springboardplatform_urls, video_id, video_title,
3420 ie=SpringboardPlatformIE.ie_key())
3421
4c780fbd
S
3422 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3423 if yapfiles_urls:
3424 return self.playlist_from_matches(
3425 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3426
86c8cfc5
S
3427 vice_urls = ViceIE._extract_urls(webpage)
3428 if vice_urls:
3429 return self.playlist_from_matches(
3430 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3431
178ee883
S
3432 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3433 if xfileshare_urls:
3434 return self.playlist_from_matches(
3435 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3436
660a230b
S
3437 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3438 if cloudflarestream_urls:
3439 return self.playlist_from_matches(
3440 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3441
8b4b400a 3442 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
6bd499e8
S
3443 if peertube_urls:
3444 return self.playlist_from_matches(
3445 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3446
aee36ca8
S
3447 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3448 if indavideo_urls:
3449 return self.playlist_from_matches(
3450 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3451
cfd7f2a6
S
3452 apa_urls = APAIE._extract_urls(webpage)
3453 if apa_urls:
3454 return self.playlist_from_matches(
3455 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3456
f51f526b
S
3457 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3458 if foxnews_urls:
3459 return self.playlist_from_matches(
3460 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3461
2e4350ee 3462 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
d3431dcb
S
3463 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3464 webpage)]
3465 if sharevideos_urls:
3466 return self.playlist_from_matches(
3467 sharevideos_urls, video_id, video_title)
3468
9d1b2138
S
3469 viqeo_urls = ViqeoIE._extract_urls(webpage)
3470 if viqeo_urls:
3471 return self.playlist_from_matches(
3472 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
57c68ec4
S
3473
3474 expressen_urls = ExpressenIE._extract_urls(webpage)
3475 if expressen_urls:
3476 return self.playlist_from_matches(
3477 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
9d1b2138 3478
83852e57
S
3479 zype_urls = ZypeIE._extract_urls(webpage)
3480 if zype_urls:
3481 return self.playlist_from_matches(
3482 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3483
feee67ae 3484 gedi_urls = GediDigitalIE._extract_urls(webpage)
902784a2 3485 if gedi_urls:
3486 return self.playlist_from_matches(
feee67ae 3487 gedi_urls, video_id, video_title, ie=GediDigitalIE.ie_key())
902784a2 3488
feee67ae 3489 # Look for RCS media group embeds
a85e131b 3490 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3491 if rcs_urls:
3492 return self.playlist_from_matches(
3493 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3494
e4edeb62 3495 wimtv_urls = WimTVIE._extract_urls(webpage)
3496 if wimtv_urls:
3497 return self.playlist_from_matches(
3498 wimtv_urls, video_id, video_title, ie=WimTVIE.ie_key())
3499
097f1663 3500 bitchute_urls = BitChuteIE._extract_urls(webpage)
3501 if bitchute_urls:
3502 return self.playlist_from_matches(
3503 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3504
62852977 3505 rumble_urls = RumbleEmbedIE._extract_urls(webpage)
3506 if len(rumble_urls) == 1:
3507 return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
3508 if rumble_urls:
3509 return self.playlist_from_matches(
3510 rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
3511
56bb56f3
LL
3512 tvp_urls = TVPEmbedIE._extract_urls(webpage)
3513 if tvp_urls:
3514 return self.playlist_from_matches(tvp_urls, video_id, video_title, ie=TVPEmbedIE.ie_key())
3515
bd264412
YCH
3516 # Look for HTML5 media
3517 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3518 if entries:
aa9369a2 3519 self.report_detected('HTML5 media')
9ce1ac40 3520 if len(entries) == 1:
3521 entries[0].update({
bd264412
YCH
3522 'id': video_id,
3523 'title': video_title,
3524 })
9ce1ac40 3525 else:
3526 for num, entry in enumerate(entries, start=1):
3527 entry.update({
3528 'id': '%s-%s' % (video_id, num),
3529 'title': '%s (%d)' % (video_title, num),
3530 })
3531 for entry in entries:
bd264412 3532 self._sort_formats(entry['formats'])
9ce1ac40 3533 return self.playlist_result(entries, video_id, video_title)
bd264412 3534
c73e330e
RU
3535 jwplayer_data = self._find_jwplayer_data(
3536 webpage, video_id, transform_source=js_to_json)
3537 if jwplayer_data:
5e7bbac3 3538 if isinstance(jwplayer_data.get('playlist'), str):
aa9369a2 3539 self.report_detected('JW Player playlist')
5e7bbac3 3540 return {
3541 **info_dict,
3542 '_type': 'url',
3543 'ie_key': JWPlatformIE.ie_key(),
3544 'url': jwplayer_data['playlist'],
3545 }
3d08f63d
MYM
3546 try:
3547 info = self._parse_jwplayer_data(
3548 jwplayer_data, video_id, require_title=False, base_url=url)
aa9369a2 3549 self.report_detected('JW Player data')
3d08f63d
MYM
3550 return merge_dicts(info, info_dict)
3551 except ExtractorError:
067aa17e 3552 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3d08f63d 3553 pass
a4a554a7 3554
63d990d2
S
3555 # Video.js embed
3556 mobj = re.search(
c5b7014a 3557 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
3558 webpage)
3559 if mobj is not None:
3560 sources = self._parse_json(
3561 mobj.group(1), video_id, transform_source=js_to_json,
3562 fatal=False) or []
c5b7014a
S
3563 if not isinstance(sources, list):
3564 sources = [sources]
63d990d2 3565 formats = []
da1c94ee 3566 subtitles = {}
63d990d2 3567 for source in sources:
e0b6e988
S
3568 src = source.get('src')
3569 if not src or not isinstance(src, compat_str):
63d990d2
S
3570 continue
3571 src = compat_urlparse.urljoin(url, src)
3572 src_type = source.get('type')
3573 if isinstance(src_type, compat_str):
3574 src_type = src_type.lower()
3575 ext = determine_ext(src).lower()
3576 if src_type == 'video/youtube':
3577 return self.url_result(src, YoutubeIE.ie_key())
3578 if src_type == 'application/dash+xml' or ext == 'mpd':
da1c94ee
F
3579 fmts, subs = self._extract_mpd_formats_and_subtitles(
3580 src, video_id, mpd_id='dash', fatal=False)
3581 formats.extend(fmts)
3582 self._merge_subtitles(subs, target=subtitles)
63d990d2 3583 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
da1c94ee 3584 fmts, subs = self._extract_m3u8_formats_and_subtitles(
63d990d2 3585 src, video_id, 'mp4', entry_protocol='m3u8_native',
da1c94ee
F
3586 m3u8_id='hls', fatal=False)
3587 formats.extend(fmts)
3588 self._merge_subtitles(subs, target=subtitles)
63d990d2
S
3589 else:
3590 formats.append({
3591 'url': src,
3089bc74
S
3592 'ext': (mimetype2ext(src_type)
3593 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
b73612a2 3594 'http_headers': {
3595 'Referer': full_response.geturl(),
3596 },
63d990d2 3597 })
da1c94ee 3598 if formats or subtitles:
aa9369a2 3599 self.report_detected('video.js embed')
63d990d2
S
3600 self._sort_formats(formats)
3601 info_dict['formats'] = formats
da1c94ee 3602 info_dict['subtitles'] = subtitles
63d990d2
S
3603 return info_dict
3604
ff17be3a 3605 # Looking for http://schema.org/VideoObject
fa0b816e 3606 json_ld = self._search_json_ld(webpage, video_id, default={})
ff17be3a 3607 if json_ld.get('url'):
aa9369a2 3608 self.report_detected('JSON LD')
ff17be3a
S
3609 return merge_dicts(json_ld, info_dict)
3610
ced659bb 3611 def check_video(vurl):
a0f71985
PH
3612 if YoutubeIE.suitable(vurl):
3613 return True
b7a8c1bc
S
3614 if RtmpIE.suitable(vurl):
3615 return True
ced659bb
S
3616 vpath = compat_urlparse.urlparse(vurl).path
3617 vext = determine_ext(vpath)
0ee79a37 3618 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
3619
3620 def filter_video(urls):
3621 return list(filter(check_video, urls))
3622
9b122384 3623 # Start with something easy: JW Player in SWFObject
ced659bb 3624 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
aa9369a2 3625 if found:
3626 self.report_detected('JW Player in SFWObject')
3627 else:
d981cef6 3628 # Look for gorilla-vid style embedding
ced659bb 3629 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
3630 (?:
3631 jw_plugins|
3632 JWPlayerOptions|
3633 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3634 )
a0f71985
PH
3635 .*?
3636 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
aa9369a2 3637 if found:
3638 self.report_detected('JW Player embed')
a318f59d 3639 if not found:
3640 # Look for generic KVS player
3641 found = re.search(r'<script [^>]*?src="https://.+?/kt_player\.js\?v=(?P<ver>(?P<maj_ver>\d+)(\.\d+)+)".*?>', webpage)
3642 if found:
aa9369a2 3643 self.report_detected('KWS Player')
a318f59d 3644 if found.group('maj_ver') not in ['4', '5']:
3645 self.report_warning('Untested major version (%s) in player engine--Download may fail.' % found.group('ver'))
3646 flashvars = re.search(r'(?ms)<script.*?>.*?var\s+flashvars\s*=\s*(\{.*?\});.*?</script>', webpage)
3647 flashvars = self._parse_json(flashvars.group(1), video_id, transform_source=js_to_json)
3648
3649 # extract the part after the last / as the display_id from the
3650 # canonical URL.
3651 display_id = self._search_regex(
3652 r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
3653 r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
3654 webpage, 'display_id', fatal=False
3655 )
3656 title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
3657
3658 thumbnail = flashvars['preview_url']
3659 if thumbnail.startswith('//'):
3660 protocol, _, _ = url.partition('/')
3661 thumbnail = protocol + thumbnail
3662
3663 formats = []
3664 for key in ('video_url', 'video_alt_url', 'video_alt_url2'):
3665 if key in flashvars and '/get_file/' in flashvars[key]:
3666 next_format = {
3667 'url': self._kvs_getrealurl(flashvars[key], flashvars['license_code']),
3668 'format_id': flashvars.get(key + '_text', key),
3669 'ext': 'mp4',
3670 }
3671 height = re.search(r'%s_(\d+)p\.mp4(?:/[?].*)?$' % flashvars['video_id'], flashvars[key])
3672 if height:
3673 next_format['height'] = int(height.group(1))
3674 else:
3675 next_format['quality'] = 1
3676 formats.append(next_format)
3677 self._sort_formats(formats)
3678
3679 return {
3680 'id': flashvars['video_id'],
3681 'display_id': display_id,
3682 'title': title,
3683 'thumbnail': thumbnail,
3684 'formats': formats,
3685 }
b30b8698 3686 if not found:
9b122384 3687 # Broaden the search a little bit
ced659bb 3688 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
aa9369a2 3689 if found:
3690 self.report_detected('video file')
b30b8698
PH
3691 if not found:
3692 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 3693 found = filter_video(re.findall(
54a9328b 3694 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
aa9369a2 3695 if found:
3696 self.report_detected('JW Player JS loader')
4d805e06
PH
3697 if not found:
3698 # Flow player
ced659bb 3699 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
3700 flowplayer\("[^"]+",\s*
3701 \{[^}]+?\}\s*,
52585fd6 3702 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 3703 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 3704 ''', webpage))
aa9369a2 3705 if found:
3706 self.report_detected('Flow Player')
501f13fb
PH
3707 if not found:
3708 # Cinerama player
3709 found = re.findall(
3710 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
aa9369a2 3711 if found:
3712 self.report_detected('Cinerama player')
b30b8698 3713 if not found:
9b122384 3714 # Try to find twitter cards info
371ddb14
S
3715 # twitter:player:stream should be checked before twitter:player since
3716 # it is expected to contain a raw stream (see
3717 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3718 found = filter_video(re.findall(
3719 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
aa9369a2 3720 if found:
3721 self.report_detected('Twitter card')
b30b8698 3722 if not found:
9b122384
PH
3723 # We look for Open Graph info:
3724 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3725 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3726 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3727 if m_video_type is not None:
b73612a2 3728 found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
aa9369a2 3729 if found:
3730 self.report_detected('Open Graph video info')
b30b8698 3731 if not found:
ed9a25dd 3732 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3733 found = re.search(
89ef304b 3734 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3735 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3736 webpage)
84f81016
S
3737 if not found:
3738 # Look also in Refresh HTTP header
3739 refresh_header = head_response.headers.get('Refresh')
3740 if refresh_header:
6c91a5a7
S
3741 # In python 2 response HTTP headers are bytestrings
3742 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3743 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3744 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3745 if found:
b37317d8 3746 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3747 if new_url != url:
3748 self.report_following_redirect(new_url)
3749 return {
3750 '_type': 'url',
3751 'url': new_url,
3752 }
3753 else:
3754 found = None
371ddb14
S
3755
3756 if not found:
3757 # twitter:player is a https URL to iframe player that may or may not
7a5c1cfe 3758 # be supported by yt-dlp thus this is checked the very last (see
371ddb14
S
3759 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3760 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3761 if embed_url and embed_url != url:
aa9369a2 3762 self.report_detected('twitter:player iframe')
371ddb14
S
3763 return self.url_result(embed_url)
3764
b30b8698 3765 if not found:
416c7fcb 3766 raise UnsupportedError(url)
9b122384 3767
b30b8698 3768 entries = []
4a120778 3769 for video_url in orderedSet(found):
949b6497 3770 video_url = unescapeHTML(video_url)
6cc37c69 3771 video_url = video_url.replace('\\/', '/')
b30b8698 3772 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3773 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3774
b30b8698
PH
3775 # Sometimes, jwplayer extraction will result in a YouTube URL
3776 if YoutubeIE.suitable(video_url):
3777 entries.append(self.url_result(video_url, 'Youtube'))
3778 continue
9b122384 3779
b30b8698
PH
3780 # here's a fun little line of code for you:
3781 video_id = os.path.splitext(video_id)[0]
fc9713a1 3782
28602e74
YCH
3783 entry_info_dict = {
3784 'id': video_id,
3785 'uploader': video_uploader,
3786 'title': video_title,
3787 'age_limit': age_limit,
3788 }
3789
5620f840
S
3790 if RtmpIE.suitable(video_url):
3791 entry_info_dict.update({
3792 '_type': 'url_transparent',
3793 'ie_key': RtmpIE.ie_key(),
3794 'url': video_url,
3795 })
3796 entries.append(entry_info_dict)
3797 continue
3798
729accb4
S
3799 ext = determine_ext(video_url)
3800 if ext == 'smil':
da1c94ee 3801 entry_info_dict = {**self._extract_smil_info(video_url, video_id), **entry_info_dict}
729accb4
S
3802 elif ext == 'xspf':
3803 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0 3804 elif ext == 'm3u8':
da1c94ee 3805 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(video_url, video_id, ext='mp4')
79a35085 3806 elif ext == 'mpd':
da1c94ee 3807 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_mpd_formats_and_subtitles(video_url, video_id)
3f2f4a94
S
3808 elif ext == 'f4m':
3809 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3810 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3811 # Just matching .ism/manifest is not enough to be reliably sure
3812 # whether it's actually an ISM manifest or some other streaming
3813 # manifest since there are various streaming URL formats
3814 # possible (see [1]) as well as some other shenanigans like
3815 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3816 # so on.
3817 # Thus the most reasonable way to solve this is to delegate
3818 # to generic extractor in order to look into the contents of
3819 # the manifest itself.
3820 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3821 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3822 entry_info_dict = self.url_result(
3823 smuggle_url(video_url, {'to_generic': True}),
3824 GenericIE.ie_key())
d6fd958c 3825 else:
28602e74
YCH
3826 entry_info_dict['url'] = video_url
3827
19dbaeec
S
3828 if entry_info_dict.get('formats'):
3829 self._sort_formats(entry_info_dict['formats'])
3830
28602e74 3831 entries.append(entry_info_dict)
b30b8698
PH
3832
3833 if len(entries) == 1:
669f0e7c 3834 return entries[0]
b30b8698
PH
3835 else:
3836 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3837 # 'url' results don't have a title
3838 if e.get('title') is not None:
3839 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3840 return {
3841 '_type': 'playlist',
3842 'entries': entries,
3843 }