]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/generic.py
[cleanup] Minor improvements to error and debug messages
[yt-dlp.git] / yt_dlp / extractor / generic.py
CommitLineData
dcdb292f 1# coding: utf-8
cfe50f04 2
79649588
PH
3from __future__ import unicode_literals
4
9b122384
PH
5import os
6import re
6c91a5a7 7import sys
9b122384
PH
8
9from .common import InfoExtractor
fc9713a1 10from .youtube import YoutubeIE
8c25f81b 11from ..compat import (
f7854627 12 compat_etree_fromstring,
4e363703 13 compat_str,
1ddb9456 14 compat_urllib_parse_unquote,
a5caba1e 15 compat_urlparse,
f7300c5c 16 compat_xml_parse_error,
8c25f81b
PH
17)
18from ..utils import (
b759a0d4 19 determine_ext,
9b122384 20 ExtractorError,
c8e9a235 21 float_or_none,
aa94a6d3 22 HEADRequest,
c76eb41b 23 int_or_none,
61ca9a80 24 is_html,
a4a554a7 25 js_to_json,
63d990d2 26 KNOWN_EXTENSIONS,
6cc62232 27 merge_dicts,
63d990d2 28 mimetype2ext,
ed2d6a19 29 orderedSet,
c76eb41b 30 parse_duration,
5c2266df 31 sanitized_Request,
9d4660ca
PH
32 smuggle_url,
33 unescapeHTML,
29f7c58a 34 unified_timestamp,
4d54ef20 35 unsmuggle_url,
416c7fcb 36 UnsupportedError,
29f7c58a 37 url_or_none,
38 xpath_attr,
76c73715 39 xpath_text,
c76eb41b 40 xpath_with_ns,
9b122384 41)
b7a8c1bc 42from .commonprotocols import RtmpIE
ed126900 43from .brightcove import (
4fcaa4f4 44 BrightcoveLegacyIE,
5c17f0a6 45 BrightcoveNewIE,
ed126900 46)
3f59b015
S
47from .nexx import (
48 NexxIE,
49 NexxEmbedIE,
50)
a2edf2e7 51from .nbc import NBCSportsVPlayerIE
c0d0b01f 52from .ooyala import OoyalaIE
93d020dd 53from .rutv import RUTVIE
954c1d05 54from .tvc import TVCIE
476cf548 55from .sportbox import SportBoxIE
6dd94d3a 56from .myvi import MyviIE
1419fafd 57from .condenast import CondeNastIE
418c5cc3 58from .udn import UDNEmbedIE
2fe1b5bd 59from .senateisvp import SenateISVPIE
bab19a8e 60from .svt import SVTIE
65d161c4 61from .pornhub import PornHubIE
2bb5b6d0 62from .xhamster import XHamsterEmbedIE
2c9ca782 63from .tnaflix import TNAFlixNetworkEmbedIE
37e7a71c 64from .drtuber import DrTuberIE
e28ed498 65from .redtube import RedTubeIE
06993715 66from .tube8 import Tube8IE
4e7b5bba 67from .mofosex import MofosexEmbedIE
8fae1a04 68from .spankwire import SpankwireIE
52c4c515 69from .youporn import YouPornIE
29f7c58a 70from .vimeo import (
71 VimeoIE,
72 VHXEmbedIE,
73)
3c4fbfec 74from .dailymotion import DailymotionIE
71a1db89 75from .dailymail import DailyMailIE
1ac1c4c2 76from .onionstudios import OnionStudiosIE
67167920 77from .viewlift import ViewLiftEmbedIE
46fde8a1 78from .mtv import MTVServicesEmbeddedIE
45dad7ba 79from .pladform import PladformIE
ff18735c 80from .videomore import VideomoreIE
83f1481b 81from .webcaster import WebcasterFeedIE
5b251628 82from .googledrive import GoogleDriveIE
7cb09524 83from .jwplatform import JWPlatformIE
aecfcd4e 84from .digiteka import DigitekaIE
1979969f 85from .arkena import ArkenaIE
5a51775a 86from .instagram import InstagramIE
5d39176f 87from .threeqsdn import ThreeQSDNIE
4d8819d2 88from .theplatform import ThePlatformIE
c287f2bc 89from .kaltura import KalturaIE
06a96da1 90from .eagleplatform import EaglePlatformIE
fd6ca382 91from .facebook import FacebookIE
548c3957 92from .soundcloud import SoundcloudEmbedIE
027e2312 93from .tunein import TuneInBaseIE
2a1321a2 94from .vbox7 import Vbox7IE
b0c8f2e9 95from .dbtv import DBTVIE
b1c35797 96from .piksel import PikselIE
e186a9ec 97from .videa import VideaIE
b687c85e 98from .twentymin import TwentyMinutenIE
d77ac737 99from .ustream import UstreamIE
8bdd16b4 100from .arte import ArteTVEmbedIE
6ef3e65a 101from .videopress import VideoPressIE
eb3079b6 102from .rutube import RutubeIE
e5d39886 103from .limelight import LimelightBaseIE
7986c3ab 104from .anvato import AnvatoIE
55719459 105from .washingtonpost import WashingtonPostIE
58bb4402 106from .wistia import WistiaIE
5d29af3d 107from .mediaset import MediasetIE
73cf76a9 108from .joj import JojIE
24e966e8 109from .megaphone import MegaphoneIE
41918eaa 110from .vzaar import VzaarIE
26bae2d9 111from .channel9 import Channel9IE
0987f2dd 112from .vshare import VShareIE
2ca7ed41 113from .mediasite import MediasiteIE
7d540621 114from .springboardplatform import SpringboardPlatformIE
4c780fbd 115from .yapfiles import YapFilesIE
86c8cfc5 116from .vice import ViceIE
178ee883 117from .xfileshare import XFileShareIE
660a230b 118from .cloudflarestream import CloudflareStreamIE
6bd499e8 119from .peertube import PeerTubeIE
5ee7ae5c 120from .teachable import TeachableIE
aee36ca8 121from .indavideo import IndavideoEmbedIE
cfd7f2a6 122from .apa import APAIE
f51f526b 123from .foxnews import FoxNewsIE
9d1b2138 124from .viqeo import ViqeoIE
57c68ec4 125from .expressen import ExpressenIE
83852e57 126from .zype import ZypeIE
416c3ca7 127from .odnoklassniki import OdnoklassnikiIE
b73612a2 128from .vk import VKIE
55adb63e 129from .kinja import KinjaEmbedIE
feee67ae 130from .gedidigital import GediDigitalIE
a85e131b 131from .rcs import RCSEmbedsIE
097f1663 132from .bitchute import BitChuteIE
62852977 133from .rumble import RumbleEmbedIE
29f7c58a 134from .arcpublishing import ArcPublishingIE
2181983a 135from .medialaan import MedialaanIE
bc2ca1bb 136from .simplecast import SimplecastIE
e4edeb62 137from .wimtv import WimTVIE
9b122384 138
0838239e 139
9b122384 140class GenericIE(InfoExtractor):
79649588 141 IE_DESC = 'Generic downloader that works on some sites'
9b122384 142 _VALID_URL = r'.*'
79649588 143 IE_NAME = 'generic'
cfe50f04 144 _TESTS = [
c5fa81fe
S
145 # Direct link to a video
146 {
147 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
148 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
149 'info_dict': {
150 'id': 'trailer',
151 'ext': 'mp4',
152 'title': 'trailer',
153 'upload_date': '20100513',
154 }
155 },
c5138a7c 156 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
157 {
158 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
159 'md5': '128c42e68b13950268b648275386fc74',
160 'info_dict': {
161 'id': 'FictionJunction-Parallel_Hearts',
162 'ext': 'flac',
163 'title': 'FictionJunction-Parallel_Hearts',
164 'upload_date': '20140522',
165 },
166 'expected_warnings': [
167 'URL could be a direct video link, returning it as such.'
39efc6e3
YCH
168 ],
169 'skip': 'URL invalid',
c5fa81fe
S
170 },
171 # Direct download with broken HEAD
172 {
173 'url': 'http://ai-radio.org:8000/radio.opus',
174 'info_dict': {
175 'id': 'radio',
176 'ext': 'opus',
177 'title': 'radio',
178 },
179 'params': {
180 'skip_download': True, # infinite live stream
181 },
182 'expected_warnings': [
ef0e4e7b
YCH
183 r'501.*Not Implemented',
184 r'400.*Bad Request',
c5fa81fe
S
185 ],
186 },
187 # Direct link with incorrect MIME type
188 {
189 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
190 'md5': '4ccbebe5f36706d85221f204d7eb5913',
191 'info_dict': {
192 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
193 'id': '5_Lennart_Poettering_-_Systemd',
194 'ext': 'webm',
195 'title': '5_Lennart_Poettering_-_Systemd',
196 'upload_date': '20141120',
197 },
198 'expected_warnings': [
199 'URL could be a direct video link, returning it as such.'
200 ]
201 },
202 # RSS feed
203 {
204 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
205 'info_dict': {
206 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
207 'title': 'Zero Punctuation',
208 'description': 're:.*groundbreaking video review series.*'
209 },
210 'playlist_mincount': 11,
211 },
212 # RSS feed with enclosure
213 {
214 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
215 'info_dict': {
29f7c58a 216 'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
217 'title': 'MSNBC Rachel Maddow (video)',
218 'description': 're:.*her unique approach to storytelling.*',
219 },
220 'playlist': [{
221 'info_dict': {
222 'ext': 'mov',
223 'id': 'pdv_maddow_netcast_mov-12-03-2020-223726',
224 'title': 'MSNBC Rachel Maddow (video) - 12-03-2020-223726',
225 'description': 're:.*her unique approach to storytelling.*',
226 'upload_date': '20201204',
227 },
228 }],
229 },
230 # RSS feed with item with description and thumbnails
231 {
232 'url': 'https://anchor.fm/s/dd00e14/podcast/rss',
233 'info_dict': {
234 'id': 'https://anchor.fm/s/dd00e14/podcast/rss',
235 'title': 're:.*100% Hydrogen.*',
236 'description': 're:.*In this episode.*',
237 },
238 'playlist': [{
239 'info_dict': {
240 'ext': 'm4a',
241 'id': 'c1c879525ce2cb640b344507e682c36d',
242 'title': 're:Hydrogen!',
243 'description': 're:.*In this episode we are going.*',
244 'timestamp': 1567977776,
245 'upload_date': '20190908',
246 'duration': 459,
247 'thumbnail': r're:^https?://.*\.jpg$',
248 'episode_number': 1,
249 'season_number': 1,
250 'age_limit': 0,
251 },
252 }],
253 'params': {
254 'skip_download': True,
255 },
c5fa81fe 256 },
01aec848
BG
257 # RSS feed with enclosures and unsupported link URLs
258 {
259 'url': 'http://www.hellointernet.fm/podcast?format=rss',
260 'info_dict': {
261 'id': 'http://www.hellointernet.fm/podcast?format=rss',
262 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
263 'title': 'Hello Internet',
264 },
265 'playlist_mincount': 100,
266 },
8765222d
S
267 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
268 {
269 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
270 'info_dict': {
271 'id': 'smil',
272 'ext': 'mp4',
273 'title': 'Automatics, robotics and biocybernetics',
274 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 275 'upload_date': '20130627',
8765222d
S
276 'formats': 'mincount:16',
277 'subtitles': 'mincount:1',
278 },
279 'params': {
280 'force_generic_extractor': True,
281 'skip_download': True,
282 },
283 },
284 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
285 {
286 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
287 'info_dict': {
288 'id': 'hds',
289 'ext': 'flv',
290 'title': 'hds',
291 'formats': 'mincount:1',
292 },
293 'params': {
294 'skip_download': True,
295 },
296 },
297 # SMIL from https://www.restudy.dk/video/play/id/1637
298 {
299 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
300 'info_dict': {
301 'id': 'video_1637',
302 'ext': 'flv',
303 'title': 'video_1637',
304 'formats': 'mincount:3',
305 },
306 'params': {
307 'skip_download': True,
308 },
309 },
310 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
311 {
312 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
313 'info_dict': {
314 'id': 'smil-service',
315 'ext': 'flv',
316 'title': 'smil-service',
317 'formats': 'mincount:1',
318 },
319 'params': {
320 'skip_download': True,
321 },
322 },
323 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
324 {
325 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
326 'info_dict': {
327 'id': '4719370',
328 'ext': 'mp4',
329 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
330 'formats': 'mincount:3',
331 },
332 'params': {
333 'skip_download': True,
334 },
335 },
1de5cd3b
S
336 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
337 {
338 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
339 'info_dict': {
340 'id': 'mZlp2ctYIUEB',
341 'ext': 'mp4',
342 'title': 'Tikibad ontruimd wegens brand',
343 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
ec85ded8 344 'thumbnail': r're:^https?://.*\.jpg$',
1de5cd3b
S
345 'duration': 33,
346 },
347 'params': {
348 'skip_download': True,
349 },
350 },
9d939cec
S
351 # MPD from http://dash-mse-test.appspot.com/media.html
352 {
353 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
354 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
355 'info_dict': {
356 'id': 'car-20120827-manifest',
357 'ext': 'mp4',
358 'title': 'car-20120827-manifest',
359 'formats': 'mincount:9',
0738187f 360 'upload_date': '20130904',
9d939cec 361 },
9d939cec 362 },
20938f76
S
363 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
364 {
365 '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',
366 'info_dict': {
367 'id': 'content',
368 'ext': 'mp4',
369 'title': 'content',
370 'formats': 'mincount:8',
371 },
372 'params': {
373 # m3u8 downloads
374 'skip_download': True,
39efc6e3
YCH
375 },
376 'skip': 'video gone',
20938f76 377 },
edd9b71c
S
378 # m3u8 served with Content-Type: text/plain
379 {
380 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
381 'info_dict': {
382 'id': 'index',
383 'ext': 'mp4',
384 'title': 'index',
385 'upload_date': '20140720',
386 'formats': 'mincount:11',
387 },
388 'params': {
389 # m3u8 downloads
390 'skip_download': True,
39efc6e3
YCH
391 },
392 'skip': 'video gone',
edd9b71c 393 },
c5fa81fe
S
394 # google redirect
395 {
396 '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',
397 'info_dict': {
398 'id': 'cmQHVoWB5FY',
399 'ext': 'mp4',
400 'upload_date': '20130224',
401 'uploader_id': 'TheVerge',
ec85ded8 402 'description': r're:^Chris Ziegler takes a look at the\.*',
c5fa81fe
S
403 'uploader': 'The Verge',
404 'title': 'First Firefox OS phones side-by-side',
405 },
406 'params': {
407 'skip_download': False,
408 }
409 },
6c91a5a7
S
410 {
411 # redirect in Refresh HTTP header
412 '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',
413 'info_dict': {
414 'id': 'pO8h3EaFRdo',
415 'ext': 'mp4',
416 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
417 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
418 'upload_date': '20150917',
419 'uploader_id': 'brtvofficial',
420 'uploader': 'Boiler Room',
421 },
422 'params': {
423 'skip_download': False,
424 },
425 },
cfe50f04 426 {
79649588 427 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 428 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 429 'info_dict': {
d360a146
S
430 'id': '13601338388002',
431 'ext': 'mp4',
79649588
PH
432 'uploader': 'www.hodiho.fr',
433 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
434 }
435 },
c19f7764
JMF
436 # bandcamp page with custom domain
437 {
79649588
PH
438 'add_ie': ['Bandcamp'],
439 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 440 'info_dict': {
fd50bf62
S
441 'id': '3235767654',
442 'ext': 'mp3',
79649588
PH
443 'title': 'The Pony Mash',
444 'uploader': 'M_Pallante',
c19f7764 445 },
79649588 446 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 447 },
eeb165e6 448 {
53a664ed
S
449 # embedded brightcove video
450 # it also tests brightcove videos that need to set the 'Referer'
451 # in the http requests
3b7d9aa4 452 'add_ie': ['BrightcoveLegacy'],
79649588
PH
453 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
454 'info_dict': {
455 'id': '2765128793001',
456 'ext': 'mp4',
457 'title': 'Le cours de bourse : l’analyse technique',
458 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
459 'uploader': 'BFM BUSINESS',
eeb165e6 460 },
79649588
PH
461 'params': {
462 'skip_download': True,
eeb165e6
JMF
463 },
464 },
53a664ed
S
465 {
466 # embedded with itemprop embedURL and video id spelled as `idVideo`
467 'add_id': ['BrightcoveLegacy'],
468 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
469 'info_dict': {
470 'id': '5255628253001',
471 'ext': 'mp4',
472 'title': 'md5:37c519b1128915607601e75a87995fc0',
473 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
474 'uploader': 'BFM BUSINESS',
475 'uploader_id': '876450612001',
476 'timestamp': 1482255315,
477 'upload_date': '20161220',
478 },
479 'params': {
480 'skip_download': True,
481 },
482 },
17ab4d3b 483 {
067aa17e 484 # https://github.com/ytdl-org/youtube-dl/issues/2253
17ab4d3b 485 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
486 'md5': '0ba9446db037002366bab3b3eb30c88c',
487 'info_dict': {
fd50bf62
S
488 'id': '3101154703001',
489 'ext': 'mp4',
17ab4d3b
PH
490 'title': 'Still no power',
491 'uploader': 'thestar.com',
492 '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.',
493 },
3b7d9aa4 494 'add_ie': ['BrightcoveLegacy'],
39efc6e3 495 'skip': 'video gone',
17ab4d3b 496 },
0479c625
S
497 {
498 'url': 'http://www.championat.com/video/football/v/87/87499.html',
499 'md5': 'fb973ecf6e4a78a67453647444222983',
500 'info_dict': {
501 'id': '3414141473001',
502 'ext': 'mp4',
503 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
504 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
505 'uploader': 'Championat',
506 },
507 },
bdf97017 508 {
067aa17e 509 # https://github.com/ytdl-org/youtube-dl/issues/3541
3b7d9aa4 510 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
511 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
512 'info_dict': {
513 'id': '3866516442001',
37aab278 514 'ext': 'mp4',
bdf97017
NJ
515 'title': 'Leer mij vrouwen kennen: Aflevering 1',
516 'description': 'Leer mij vrouwen kennen: Aflevering 1',
517 'uploader': 'SBS Broadcasting',
518 },
37aab278 519 'skip': 'Restricted to Netherlands',
bdf97017 520 'params': {
37aab278 521 'skip_download': True, # m3u8 download
bdf97017
NJ
522 },
523 },
06d0ad9a
YCH
524 {
525 # Brightcove video in <iframe>
526 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
527 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
528 'info_dict': {
529 'id': '5360463607001',
530 'ext': 'mp4',
531 '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',
532 '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。',
533 'uploader': 'United Nations',
534 'uploader_id': '1362235914001',
535 'timestamp': 1489593889,
536 'upload_date': '20170315',
537 },
538 'add_ie': ['BrightcoveLegacy'],
539 },
16e2c8f7
YCH
540 {
541 # Brightcove with alternative playerID key
542 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
543 'info_dict': {
544 'id': 'nmeth.2062_SV1',
545 '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',
546 },
547 'playlist': [{
548 'info_dict': {
549 'id': '2228375078001',
550 'ext': 'mp4',
551 'title': 'nmeth.2062-sv1',
552 'description': 'nmeth.2062-sv1',
553 'timestamp': 1363357591,
554 'upload_date': '20130315',
555 'uploader': 'Nature Publishing Group',
556 'uploader_id': '1964492299001',
557 },
558 }],
559 },
40158f55
JH
560 {
561 # Brightcove with UUID in videoPlayer
562 'url': 'http://www8.hp.com/cn/zh/home.html',
563 'info_dict': {
564 'id': '5255815316001',
565 'ext': 'mp4',
566 'title': 'Sprocket Video - China',
567 'description': 'Sprocket Video - China',
568 'uploader': 'HP-Video Gallery',
569 'timestamp': 1482263210,
570 'upload_date': '20161220',
571 'uploader_id': '1107601872001',
572 },
573 'params': {
574 'skip_download': True, # m3u8 download
575 },
576 'skip': 'video rotates...weekly?',
577 },
578 {
579 # Brightcove:new type [2].
580 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
581 'md5': '2b35148fcf48da41c9fb4591650784f3',
582 'info_dict': {
583 'id': '5348741021001',
584 'ext': 'mp4',
585 'upload_date': '20170306',
586 'uploader_id': '4191638492001',
587 'timestamp': 1488769918,
588 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
589
590 },
591 },
592 {
593 # Alternative brightcove <video> attributes
594 '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/',
595 'info_dict': {
596 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
597 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
598 },
599 'playlist': [{
600 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
601 'info_dict': {
602 'id': '5311302538001',
603 'ext': 'mp4',
604 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
605 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
606 'timestamp': 1486321708,
607 'upload_date': '20170205',
608 'uploader_id': '800000640001',
609 },
610 'only_matching': True,
611 }],
612 },
b68a812e
S
613 {
614 # Brightcove with UUID in videoPlayer
615 'url': 'http://www8.hp.com/cn/zh/home.html',
616 'info_dict': {
617 'id': '5255815316001',
618 'ext': 'mp4',
619 'title': 'Sprocket Video - China',
620 'description': 'Sprocket Video - China',
621 'uploader': 'HP-Video Gallery',
622 'timestamp': 1482263210,
623 'upload_date': '20161220',
624 'uploader_id': '1107601872001',
625 },
626 'params': {
627 'skip_download': True, # m3u8 download
628 },
629 },
c0d0b01f
JMF
630 # ooyala video
631 {
79649588 632 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 633 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
634 'info_dict': {
635 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
636 'ext': 'mp4',
3486df38 637 'title': '2cc213299525360.mov', # that's what we get
53e06b25 638 'duration': 238.231,
c0d0b01f 639 },
87830900 640 'add_ie': ['Ooyala'],
c0d0b01f 641 },
bf94d763
S
642 {
643 # ooyala video embedded with http://player.ooyala.com/iframe.js
644 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
645 'info_dict': {
646 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
647 'ext': 'mp4',
648 'title': '"Steve Jobs: Man in the Machine" trailer',
649 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 650 'duration': 135.427,
bf94d763
S
651 },
652 'params': {
653 'skip_download': True,
654 },
39efc6e3 655 'skip': 'movie expired',
bf94d763 656 },
198d4cb4
GR
657 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
658 {
659 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
660 'info_dict': {
661 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
662 'ext': 'mp4',
663 'title': 'Steampunk Fest Comes to Honesdale',
664 'duration': 43.276,
665 },
666 'params': {
667 'skip_download': True,
668 }
669 },
1b86cc41 670 # embed.ly video
671 {
672 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
673 'info_dict': {
674 'id': '9ODmcdjQcHQ',
675 'ext': 'mp4',
0a5bce56
PH
676 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
677 'upload_date': '20140225',
678 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
679 'uploader': 'Tested',
680 'uploader_id': 'testedcom',
1b86cc41 681 },
682 # No need to test YoutubeIE here
683 'params': {
684 'skip_download': True,
685 },
686 },
60cc4dc4
PH
687 # funnyordie embed
688 {
689 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
690 'info_dict': {
691 'id': '18e820ec3f',
692 'ext': 'mp4',
693 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
694 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 695 },
39efc6e3
YCH
696 # HEAD requests lead to endless 301, while GET is OK
697 'expected_warnings': ['301'],
60cc4dc4 698 },
93d020dd
S
699 # RUTV embed
700 {
701 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
702 'info_dict': {
703 'id': '776940',
704 'ext': 'mp4',
705 'title': 'Охотское море стало целиком российским',
706 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
707 },
708 'params': {
709 # m3u8 download
710 'skip_download': True,
711 },
aab74fa1 712 },
f37bdbe5
S
713 # TVC embed
714 {
715 '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/',
716 'info_dict': {
717 'id': '55304',
718 'ext': 'mp4',
719 'title': 'Дошкольное воспитание',
720 },
721 },
b827a601
S
722 # SportBox embed
723 {
724 'url': 'http://www.vestifinance.ru/articles/25753',
725 'info_dict': {
726 'id': '25753',
05d1e7aa 727 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
b827a601
S
728 },
729 'playlist': [{
730 'info_dict': {
731 'id': '370908',
732 'title': 'Госзаказ. День 3',
733 'ext': 'mp4',
734 }
735 }, {
736 'info_dict': {
737 'id': '370905',
738 'title': 'Госзаказ. День 2',
739 'ext': 'mp4',
740 }
741 }, {
742 'info_dict': {
743 'id': '370902',
744 'title': 'Госзаказ. День 1',
745 'ext': 'mp4',
746 }
747 }],
748 'params': {
749 # m3u8 download
750 'skip_download': True,
751 },
752 },
bf20b9c5
S
753 # Myvi.ru embed
754 {
755 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
756 'info_dict': {
757 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
758 'ext': 'mp4',
759 'title': 'Ужастики, русский трейлер (2015)',
ec85ded8 760 'thumbnail': r're:^https?://.*\.jpg$',
bf20b9c5
S
761 'duration': 153,
762 }
763 },
c76799c5
S
764 # XHamster embed
765 {
766 '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',
767 'info_dict': {
768 'id': 'showthread',
769 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
770 },
771 'playlist_mincount': 7,
39efc6e3
YCH
772 # This forum does not allow <iframe> syntaxes anymore
773 # Now HTML tags are displayed as-is
774 'skip': 'No videos on this page',
c76799c5 775 },
aab74fa1
PH
776 # Embedded TED video
777 {
778 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 779 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 780 'info_dict': {
a8eb5a8e 781 'id': '1969',
aab74fa1 782 'ext': 'mp4',
a8eb5a8e
PH
783 'title': 'Hidden miracles of the natural world',
784 'uploader': 'Louie Schwartzberg',
785 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 786 }
60cc4dc4 787 },
d95e35d6
S
788 # nowvideo embed hidden behind percent encoding
789 {
790 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
791 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
792 'info_dict': {
793 'id': '06e53103ca9aa',
794 'ext': 'flv',
795 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
796 'description': 'No description',
797 },
0f2a2ba1 798 },
893f8832
PH
799 # arte embed
800 {
801 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
802 'md5': '7653032cbb25bf6c80d80f217055fa43',
803 'info_dict': {
804 'id': '048195-004_PLUS7-F',
805 'ext': 'flv',
806 'title': 'X:enius',
807 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
808 'upload_date': '20140320',
809 },
810 'params': {
811 'skip_download': 'Requires rtmpdump'
39efc6e3
YCH
812 },
813 'skip': 'video gone',
893f8832 814 },
cbd55ade
S
815 # francetv embed
816 {
817 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
818 'info_dict': {
819 'id': 'EV_30231',
820 'ext': 'mp4',
821 'title': 'Alcaline, le concert avec Calogero',
822 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
823 'upload_date': '20150226',
824 'timestamp': 1424989860,
825 'duration': 5400,
826 },
827 'params': {
828 # m3u8 downloads
829 'skip_download': True,
830 },
831 'expected_warnings': [
832 'Forbidden'
833 ]
834 },
fa35cdad
PH
835 # Condé Nast embed
836 {
837 'url': 'http://www.wired.com/2014/04/honda-asimo/',
838 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
839 'info_dict': {
840 'id': '53501be369702d3275860000',
841 'ext': 'mp4',
842 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
843 }
ebd3c7b3
PH
844 },
845 # Dailymotion embed
846 {
847 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
848 'md5': '441aeeb82eb72c422c7f14ec533999cd',
849 'info_dict': {
850 'id': 'k2mm4bCdJ6CQ2i7c8o2',
851 'ext': 'mp4',
852 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 853 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 854 'uploader': 'Spi0n',
0738187f
YCH
855 'uploader_id': 'xgditw',
856 'upload_date': '20140425',
857 'timestamp': 1398441542,
ebd3c7b3
PH
858 },
859 'add_ie': ['Dailymotion'],
2b88feed 860 },
71a1db89
S
861 # DailyMail embed
862 {
863 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
864 'info_dict': {
865 'id': '1495629',
866 'ext': 'mp4',
867 'title': 'Care worker punches elderly dementia patient in head 11 times',
868 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
869 },
870 'add_ie': ['DailyMail'],
871 'params': {
872 'skip_download': True,
873 },
874 },
2b88feed
PH
875 # YouTube embed
876 {
877 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
878 'info_dict': {
879 'id': 'FXRb4ykk4S0',
880 'ext': 'mp4',
881 'title': 'The NBL Auction 2014',
882 'uploader': 'BADMINTON England',
883 'uploader_id': 'BADMINTONEvents',
884 'upload_date': '20140603',
885 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
886 },
887 'add_ie': ['Youtube'],
888 'params': {
889 'skip_download': True,
890 }
891 },
a0566bbf 892 # MTVServices embed
c5cd249e 893 {
1fa309da
YCH
894 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
895 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 896 'info_dict': {
1fa309da 897 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 898 'ext': 'mp4',
1fa309da
YCH
899 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
900 'description': 'Two valets share their love for movie star Liam Neesons.',
05d1e7aa
YCH
901 'timestamp': 1349922600,
902 'upload_date': '20121011',
c5cd249e
JMF
903 },
904 },
61013473 905 # YouTube embed via <data-embed-url="">
906 {
907 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 908 'info_dict': {
a8eb5a8e 909 'id': '4vAffPZIT44',
61013473 910 'ext': 'mp4',
a8eb5a8e 911 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
912 'uploader': 'Gameloft',
913 'uploader_id': 'gameloft',
a8eb5a8e
PH
914 'upload_date': '20140828',
915 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
916 },
917 'params': {
918 'skip_download': True,
61013473 919 }
c8e9a235 920 },
61568e50
JH
921 # YouTube <object> embed
922 {
923 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
924 'md5': '516718101ec834f74318df76259fb3cc',
925 'info_dict': {
926 'id': 'msN87y-iEx0',
927 'ext': 'webm',
928 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
929 'upload_date': '20080526',
930 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
931 'uploader': 'Christopher Sykes',
932 'uploader_id': 'ChristopherJSykes',
933 },
934 'add_ie': ['Youtube'],
935 },
c8e9a235
PH
936 # Camtasia studio
937 {
938 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
939 'playlist': [{
940 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
941 'info_dict': {
942 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
943 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
944 'ext': 'flv',
945 'duration': 2235.90,
946 }
947 }, {
948 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
949 'info_dict': {
950 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
951 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
952 'ext': 'flv',
953 'duration': 2235.93,
954 }
955 }],
956 'info_dict': {
957 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
958 }
4d805e06
PH
959 },
960 # Flowplayer
961 {
962 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
963 'md5': '9d65602bf31c6e20014319c7d07fba27',
964 'info_dict': {
965 'id': '5123ea6d5e5a7',
966 'ext': 'mp4',
967 'age_limit': 18,
968 'uploader': 'www.handjobhub.com',
d6d9186f 969 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 970 }
0990305d 971 },
22a6f150 972 # Multiple brightcove videos
067aa17e 973 # https://github.com/ytdl-org/youtube-dl/issues/2283
22a6f150
PH
974 {
975 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
976 'info_dict': {
977 'id': 'always-never',
978 'title': 'Always / Never - The New Yorker',
979 },
980 'playlist_count': 3,
981 'params': {
982 'extract_flat': False,
983 'skip_download': True,
984 }
1a94ff68
S
985 },
986 # MLB embed
987 {
988 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
989 'md5': '96f09a37e44da40dd083e12d9a683327',
990 'info_dict': {
991 'id': '33322633',
992 'ext': 'mp4',
993 'title': 'Ump changes call to ball',
994 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
995 'duration': 48,
996 'timestamp': 1401537900,
997 'upload_date': '20140531',
ec85ded8 998 'thumbnail': r're:^https?://.*\.jpg$',
1a94ff68
S
999 },
1000 },
746c67d7
NJ
1001 # Wistia embed
1002 {
6c114b12
S
1003 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
1004 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 1005 'info_dict': {
6c114b12 1006 'id': '6e2wtrbdaf',
746c67d7 1007 'ext': 'mov',
6c114b12
S
1008 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
1009 'description': 'a Paywall Videos video from Remilon',
1010 'duration': 644.072,
1011 'uploader': 'study.com',
1012 'timestamp': 1459678540,
1013 'upload_date': '20160403',
1014 'filesize': 24687186,
746c67d7
NJ
1015 },
1016 },
52cffcb1 1017 {
1018 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
1019 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
1020 'info_dict': {
1021 'id': 'uxjb0lwrcz',
1022 'ext': 'mp4',
6c114b12 1023 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 1024 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 1025 'duration': 1715.0,
85d7b765 1026 'uploader': 'thoughtworks.wistia.com',
0738187f 1027 'timestamp': 1401832161,
6c114b12 1028 'upload_date': '20140603',
70b7e3fb 1029 },
52cffcb1 1030 },
7ded6545
S
1031 # Wistia standard embed (async)
1032 {
1033 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
1034 'info_dict': {
1035 'id': '807fafadvk',
1036 'ext': 'mp4',
1037 'title': 'Drip Brennan Dunn Workshop',
1038 'description': 'a JV Webinars video from getdrip-1',
1039 'duration': 4986.95,
7ded6545 1040 'timestamp': 1463607249,
6c114b12 1041 'upload_date': '20160518',
7ded6545
S
1042 },
1043 'params': {
1044 'skip_download': True,
1045 }
1046 },
ac645ac7
PH
1047 # Soundcloud embed
1048 {
1049 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1050 'info_dict': {
1051 'id': '174391317',
1052 'ext': 'mp3',
1053 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1054 'uploader': 'Sophos Security',
1055 'title': 'Chet Chat 171 - Oct 29, 2014',
1056 'upload_date': '20141029',
1057 }
af63fed7 1058 },
db19df6c
S
1059 # Soundcloud multiple embeds
1060 {
1061 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1062 'info_dict': {
1063 'id': '52809',
1064 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1065 },
1066 'playlist_mincount': 7,
1067 },
027e2312
S
1068 # TuneIn station embed
1069 {
1070 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1071 'info_dict': {
1072 'id': '204146',
1073 'ext': 'mp3',
1074 'title': 'CNRV',
1075 'location': 'Paris, France',
1076 'is_live': True,
1077 },
1078 'params': {
1079 # Live stream
1080 'skip_download': True,
1081 },
1082 },
af63fed7
PH
1083 # Livestream embed
1084 {
1085 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1086 'info_dict': {
1087 'id': '67864563',
1088 'ext': 'flv',
1089 'upload_date': '20141112',
1090 'title': 'Rosetta #CometLanding webcast HL 10',
1091 }
1092 },
78d3b3e2
YCH
1093 # Another Livestream embed, without 'new.' in URL
1094 {
1095 'url': 'https://www.freespeech.org/',
1096 'info_dict': {
1097 'id': '123537347',
1098 'ext': 'mp4',
1099 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1100 },
1101 'params': {
1102 # Live stream
1103 'skip_download': True,
1104 },
1105 },
65f3a228
PH
1106 # LazyYT
1107 {
e8e4cc5a 1108 'url': 'https://skiplagged.com/',
65f3a228 1109 'info_dict': {
e8e4cc5a
JH
1110 'id': 'skiplagged',
1111 'title': 'Skiplagged: The smart way to find cheap flights',
65f3a228 1112 },
e8e4cc5a
JH
1113 'playlist_mincount': 1,
1114 'add_ie': ['Youtube'],
4e262a88 1115 },
42bdd9d0
PH
1116 # Cinchcast embed
1117 {
1118 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1119 'info_dict': {
1120 'id': '7141703',
1121 'ext': 'mp3',
1122 'upload_date': '20141126',
1123 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1124 }
1125 },
501f13fb
PH
1126 # Cinerama player
1127 {
1128 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1129 'info_dict': {
1130 'id': '730m_DandD_1901_512k',
1131 'ext': 'mp4',
1132 'uploader': 'www.abc.net.au',
1133 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1134 }
796df3c6
S
1135 },
1136 # embedded viddler video
1137 {
1138 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1139 'info_dict': {
1140 'id': '4d03aad9',
1141 'ext': 'mp4',
1142 'uploader': 'deadspin',
1143 'title': 'WALL-TO-GORTAT',
1144 'timestamp': 1422285291,
1145 'upload_date': '20150126',
1146 },
1147 'add_ie': ['Viddler'],
a0f71985 1148 },
2051acde
S
1149 # Libsyn embed
1150 {
1151 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1152 'info_dict': {
1153 'id': '3377616',
1154 'ext': 'mp3',
1155 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1156 'description': 'md5:601cb790edd05908957dae8aaa866465',
1157 'upload_date': '20150220',
1158 },
326fa4e6 1159 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
2051acde 1160 },
a0f71985
PH
1161 # jwplayer YouTube
1162 {
1163 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1164 'info_dict': {
1165 'id': 'Mrj4DVp2zeA',
1166 'ext': 'mp4',
f37e3f99 1167 'upload_date': '20150212',
a0f71985 1168 'uploader': 'The National Archives UK',
2637fadc 1169 'description': 'md5:8078af856dca76edc42910b61273dbbf',
a0f71985
PH
1170 'uploader_id': 'NationalArchives08',
1171 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1172 },
59b8ab58 1173 },
5620f840
S
1174 # jwplayer rtmp
1175 {
6899b1d9 1176 'url': 'http://www.suffolk.edu/sjc/live.php',
5620f840 1177 'info_dict': {
6899b1d9 1178 'id': 'live',
5620f840
S
1179 'ext': 'flv',
1180 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1181 'uploader': 'www.suffolk.edu',
1182 },
1183 'params': {
1184 'skip_download': True,
2637fadc 1185 },
6899b1d9 1186 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
5620f840 1187 },
5e7bbac3 1188 # jwplayer with only the json URL
1189 {
1190 'url': 'https://www.hollywoodreporter.com/news/general-news/dunkirk-team-reveals-what-christopher-nolan-said-oscar-win-meet-your-oscar-winner-1092454',
1191 'info_dict': {
1192 'id': 'TljWkvWH',
1193 'ext': 'mp4',
1194 'upload_date': '20180306',
1195 'title': 'md5:91eb1862f6526415214f62c00b453936',
1196 'description': 'md5:73048ae50ae953da10549d1d2fe9b3aa',
1197 'timestamp': 1520367225,
1198 },
1199 'params': {
1200 'skip_download': True,
1201 },
1202 },
a4a554a7
YCH
1203 # Complex jwplayer
1204 {
1205 'url': 'http://www.indiedb.com/games/king-machine/videos',
1206 'info_dict': {
1207 'id': 'videos',
1208 'ext': 'mp4',
1209 'title': 'king machine trailer 1',
2637fadc 1210 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
a4a554a7
YCH
1211 'thumbnail': r're:^https?://.*\.jpg$',
1212 },
1213 },
03486dbb
RU
1214 {
1215 # JWPlayer config passed as variable
1216 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1217 'info_dict': {
1218 'id': '3326530_hq',
1219 'ext': 'mp4',
1220 'title': 'ARIELE | Tube Cup',
1221 'uploader': 'www.txxx.com',
1222 'age_limit': 18,
1223 },
1224 'params': {
1225 'skip_download': True,
1226 }
1227 },
939be9ad
JH
1228 {
1229 # JWPlatform iframe
2fac2e91 1230 'url': 'https://www.covermagazine.co.uk/feature/2465255/business-protection-involved',
939be9ad 1231 'info_dict': {
2fac2e91 1232 'id': 'AG26UQXM',
939be9ad 1233 'ext': 'mp4',
2fac2e91
AG
1234 'upload_date': '20160719',
1235 'timestamp': 468923808,
1236 'title': '2016_05_18 Cover L&G Business Protection V1 FINAL.mp4',
939be9ad 1237 },
805f5bf7 1238 'add_ie': [JWPlatformIE.ie_key()],
939be9ad 1239 },
63d990d2 1240 {
c5b7014a 1241 # Video.js embed, multiple formats
63d990d2
S
1242 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1243 'info_dict': {
1244 'id': 'yygqldloqIk',
1245 'ext': 'mp4',
1246 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1247 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1248 'upload_date': '20130314',
1249 'uploader': 'PROстое3D',
1250 'uploader_id': 'PROstoe3D',
1251 },
1252 'params': {
1253 'skip_download': True,
1254 },
1255 },
c5b7014a
S
1256 {
1257 # Video.js embed, single format
1258 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1259 'info_dict': {
1260 'id': 'watch',
1261 'ext': 'mp4',
1262 'title': 'Step 1 - Good Foundation',
1263 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1264 },
1265 'params': {
1266 'skip_download': True,
1267 },
1268 },
59b8ab58
PH
1269 # rtl.nl embed
1270 {
1271 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1272 'playlist_mincount': 5,
1273 'info_dict': {
1274 'id': 'aanslagen-kopenhagen',
2637fadc 1275 'title': 'Aanslagen Kopenhagen',
59b8ab58 1276 }
255fca5e
S
1277 },
1278 # Zapiks embed
1279 {
1280 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1281 'info_dict': {
1282 'id': '118046',
1283 'ext': 'mp4',
1284 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1285 }
1286 },
66e568de
S
1287 # Kaltura embed (different embed code)
1288 {
1289 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1290 'info_dict': {
1291 'id': '1_a52wc67y',
1292 'ext': 'flv',
1293 'upload_date': '20150127',
1294 'uploader_id': 'PremierMedia',
1295 'timestamp': int,
1296 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1297 },
1298 },
87703231
YCH
1299 # Kaltura embed with single quotes
1300 {
1301 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1302 'info_dict': {
1303 'id': '0_izeg5utt',
1304 'ext': 'mp4',
1305 'title': '35871',
1306 'timestamp': 1355743100,
1307 'upload_date': '20121217',
e30991f9 1308 'uploader_id': 'cplapp@learn360.com',
87703231
YCH
1309 },
1310 'add_ie': ['Kaltura'],
1311 },
427cd050
S
1312 {
1313 # Kaltura embedded via quoted entry_id
1314 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1315 'info_dict': {
1316 'id': '0_utuok90b',
1317 'ext': 'mp4',
1318 'title': '06_matthew_brender_raj_dutt',
1319 'timestamp': 1466638791,
1320 'upload_date': '20160622',
1321 },
1322 'add_ie': ['Kaltura'],
1323 'expected_warnings': [
1324 'Could not send HEAD request'
1325 ],
1326 'params': {
1327 'skip_download': True,
1328 }
1329 },
8ab7e6c4
YCH
1330 {
1331 # Kaltura embedded, some fileExt broken (#11480)
1332 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1333 'info_dict': {
1334 'id': '1_sgtvehim',
1335 'ext': 'mp4',
1336 'title': 'Our "Standard Models" of particle physics and cosmology',
1337 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1338 'timestamp': 1321158993,
1339 'upload_date': '20111113',
1340 'uploader_id': 'kps1',
1341 },
1342 'add_ie': ['Kaltura'],
1343 },
a01825a5
JH
1344 {
1345 # Kaltura iframe embed
1346 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1347 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1348 'info_dict': {
1349 'id': '0_f2cfbpwy',
1350 'ext': 'mp4',
1351 'title': 'I. M. Pei: A Centennial Celebration',
1352 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1353 'upload_date': '20170403',
1354 'uploader_id': 'batchUser',
1355 'timestamp': 1491232186,
1356 },
1357 'add_ie': ['Kaltura'],
1358 },
c21692fa
S
1359 {
1360 # Kaltura iframe embed, more sophisticated
1361 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1362 'info_dict': {
1363 'id': '1_9gzouybz',
1364 'ext': 'mp4',
1365 'title': 'lecture-05sep2017',
1366 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1367 'upload_date': '20170913',
1368 'uploader_id': 'eps2',
1369 'timestamp': 1505340777,
1370 },
1371 'params': {
1372 'skip_download': True,
1373 },
1374 'add_ie': ['Kaltura'],
1375 },
e30991f9
S
1376 {
1377 # meta twitter:player
1378 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1379 'info_dict': {
1380 'id': '0_01b42zps',
1381 'ext': 'mp4',
1382 'title': 'Main Twerk (Video)',
1383 'upload_date': '20171208',
1384 'uploader_id': 'sebastian.salinas@thechive.com',
1385 'timestamp': 1512713057,
1386 },
1387 'params': {
1388 'skip_download': True,
1389 },
1390 'add_ie': ['Kaltura'],
1391 },
250b042c
S
1392 # referrer protected EaglePlatform embed
1393 {
1394 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1395 'info_dict': {
1396 'id': '582306',
1397 'ext': 'mp4',
1398 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1399 'thumbnail': r're:^https?://.*\.jpg$',
1400 'duration': 3382,
1401 'view_count': int,
1402 },
1403 'params': {
1404 'skip_download': True,
1405 },
135c9c42 1406 },
665e9452 1407 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1408 {
1409 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1410 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1411 'info_dict': {
1412 'id': '12820',
1413 'ext': 'mp4',
1414 'title': "'O Sole Mio",
ec85ded8 1415 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1416 'duration': 216,
1417 'view_count': int,
1418 },
250b042c
S
1419 'params': {
1420 'skip_download': True,
1421 },
2637fadc 1422 'skip': 'This video is unavailable.',
d47ae7f6 1423 },
f8388757
S
1424 # Pladform embed
1425 {
1426 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1427 'info_dict': {
1428 'id': '100183293',
1429 'ext': 'mp4',
62259846 1430 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1431 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1432 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1433 'duration': 694,
1434 'age_limit': 0,
1435 },
2637fadc 1436 'skip': 'HTTP Error 404: Not Found',
f8388757 1437 },
c798f15b
S
1438 # Playwire embed
1439 {
1440 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1441 'info_dict': {
1442 'id': '3519514',
1443 'ext': 'mp4',
1444 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1445 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1446 'duration': 45.115,
1447 },
1448 },
ad320e9b
NJ
1449 # 5min embed
1450 {
1451 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1452 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1453 'info_dict': {
1454 'id': '518726732',
1455 'ext': 'mp4',
1456 'title': 'Facebook Creates "On This Day" | Crunch Report',
2637fadc
RA
1457 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1458 'timestamp': 1427237531,
1459 'uploader': 'Crunch Report',
1460 'upload_date': '20150324',
1461 },
1462 'params': {
1463 # m3u8 download
1464 'skip_download': True,
ad320e9b
NJ
1465 },
1466 },
a4257017
S
1467 # Crooks and Liars embed
1468 {
1469 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1470 'info_dict': {
1471 'id': '8RUoRhRi',
1472 'ext': 'mp4',
1473 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1474 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1475 'timestamp': 1428207000,
1476 'upload_date': '20150405',
1477 'uploader': 'Heather',
1478 },
1479 },
1480 # Crooks and Liars external embed
1481 {
1482 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1483 'info_dict': {
1484 'id': 'MTE3MjUtMzQ2MzA',
1485 'ext': 'mp4',
1486 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1487 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1488 'timestamp': 1265032391,
1489 'upload_date': '20100201',
1490 'uploader': 'Heather',
1491 },
1492 },
facecb84 1493 # NBC Sports vplayer embed
a2edf2e7 1494 {
facecb84 1495 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1496 'info_dict': {
facecb84
S
1497 'id': 'ln7x1qSThw4k',
1498 'ext': 'flv',
1499 'title': "PFT Live: New leader in the 'new-look' defense",
1500 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1501 'uploader': 'NBCU-SPORTS',
1502 'upload_date': '20140107',
1503 'timestamp': 1389118457,
a2edf2e7 1504 },
2637fadc 1505 'skip': 'Invalid Page URL',
418c5cc3 1506 },
de3eb07e
YCH
1507 # NBC News embed
1508 {
1509 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1510 'md5': '1aa589c675898ae6d37a17913cf68d66',
1511 'info_dict': {
2637fadc 1512 'id': 'x_dtl_oa_LettermanliftPR_160608',
de3eb07e 1513 'ext': 'mp4',
2637fadc 1514 'title': 'David Letterman: A Preview',
de3eb07e 1515 '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
1516 'upload_date': '20160609',
1517 'timestamp': 1465431544,
1518 'uploader': 'NBCU-NEWS',
de3eb07e
YCH
1519 },
1520 },
418c5cc3
YCH
1521 # UDN embed
1522 {
811586eb 1523 'url': 'https://video.udn.com/news/300346',
01c58f84 1524 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1525 'info_dict': {
01c58f84 1526 'id': '300346',
418c5cc3 1527 'ext': 'mp4',
01c58f84 1528 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1529 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1530 },
1531 'params': {
1532 # m3u8 download
1533 'skip_download': True,
1534 },
2637fadc 1535 'expected_warnings': ['Failed to parse JSON Expecting value'],
edfcf7ab 1536 },
b26733ba
YCH
1537 # Brightcove URL in single quotes
1538 {
1539 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1540 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1541 'info_dict': {
1542 'id': '4255764656001',
1543 'ext': 'mp4',
1544 'title': 'SN Presents: Russell Martin, World Citizen',
1545 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1546 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1547 'uploader_id': '1704050871',
1548 'upload_date': '20150525',
1549 'timestamp': 1432570283,
b26733ba 1550 },
756f574e 1551 },
55adb63e 1552 # Kinja embed
8084be78
S
1553 {
1554 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1555 'info_dict': {
55adb63e 1556 'id': '106351',
8084be78
S
1557 'ext': 'mp4',
1558 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
55adb63e 1559 'description': 'Migrated from OnionStudios',
ec85ded8 1560 'thumbnail': r're:^https?://.*\.jpe?g$',
55adb63e
RA
1561 'uploader': 'clickhole',
1562 'upload_date': '20150527',
1563 'timestamp': 1432744860,
8084be78
S
1564 }
1565 },
b8c1cc1a
S
1566 # SnagFilms embed
1567 {
1568 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1569 'info_dict': {
1570 'id': '74849a00-85a9-11e1-9660-123139220831',
1571 'ext': 'mp4',
1572 'title': '#whilewewatch',
1573 }
1574 },
a5158f38
YCH
1575 # AdobeTVVideo embed
1576 {
1577 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1578 'md5': '43662b577c018ad707a63766462b1e87',
1579 'info_dict': {
1580 'id': '2456',
1581 'ext': 'mp4',
1582 'title': 'New experience with Acrobat DC',
1583 'description': 'New experience with Acrobat DC',
1584 'duration': 248.667,
1585 },
1f812580 1586 },
ed126900 1587 # BrightcoveInPageEmbed embed
1588 {
1589 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1590 'info_dict': {
1591 'id': '4238694884001',
1592 'ext': 'flv',
1593 'title': 'Tabletop: Dread, Last Thoughts',
1594 'description': 'Tabletop: Dread, Last Thoughts',
1595 'duration': 51690,
1596 },
750b9ff0 1597 },
d10fe835
YCH
1598 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1599 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1600 {
1601 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1602 'info_dict': {
1603 'id': '4785848093001',
1604 'ext': 'mp4',
1605 'title': 'The Cardinal Pell Interview',
1606 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1607 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1608 'uploader_id': '2733773828001',
1609 'upload_date': '20160304',
1610 'timestamp': 1457083087,
d10fe835
YCH
1611 },
1612 'params': {
1613 # m3u8 downloads
1614 'skip_download': True,
1615 },
1616 },
9edf47df
S
1617 {
1618 # Brightcove embed with whitespace around attribute names
1619 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1620 'info_dict': {
1621 'id': '3167554373001',
1622 'ext': 'mp4',
1623 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1624 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1625 'uploader_id': '1079349493',
1626 'upload_date': '20140207',
1627 'timestamp': 1391810548,
1628 },
1629 'params': {
1630 'skip_download': True,
1631 },
1632 },
134c207e
YCH
1633 # Another form of arte.tv embed
1634 {
1635 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1636 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1637 'info_dict': {
1638 'id': '030273-562_PLUS7-F',
1639 'ext': 'mp4',
1640 'title': 'ARTE Reportage - Nulle part, en France',
1641 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1642 'upload_date': '20160409',
1643 },
1644 },
4a120778
YCH
1645 # Duplicated embedded video URLs
1646 {
1647 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1648 'info_dict': {
1649 'id': '149298443_480_16c25b74_2',
1650 'ext': 'mp4',
1651 'title': 'vs. Blue Orange Spring Game',
1652 'uploader': 'www.hudl.com',
1653 },
1654 },
371ddb14
S
1655 # twitter:player:stream embed
1656 {
1657 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1658 'info_dict': {
1659 'id': 'master',
1660 'ext': 'mp4',
1661 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1662 'uploader': 'www.rtl.be',
1663 },
1664 'params': {
1665 # m3u8 downloads
1666 'skip_download': True,
1667 },
1668 },
32917907
RA
1669 # twitter:player embed
1670 {
1671 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1672 'md5': 'a3e0df96369831de324f0778e126653c',
1673 'info_dict': {
1674 'id': '4909620399001',
1675 'ext': 'mp4',
1676 'title': 'What Do Black Holes Sound Like?',
1677 'description': 'what do black holes sound like',
1678 'upload_date': '20160524',
1679 'uploader_id': '29913724001',
1680 'timestamp': 1464107587,
1681 'uploader': 'TheAtlantic',
1682 },
1683 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1684 },
1685 # Facebook <iframe> embed
1686 {
1687 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1688 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1689 'info_dict': {
1690 'id': '599637780109885',
1691 'ext': 'mp4',
1692 'title': 'Facebook video #599637780109885',
1693 },
1694 },
fd1c5fba
S
1695 # Facebook <iframe> embed, plugin video
1696 {
1697 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1698 'info_dict': {
1699 'id': '1754168231264132',
1700 'ext': 'mp4',
1701 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1702 'uploader': 'Tariq Ramadan (official)',
1703 'timestamp': 1496758379,
1704 'upload_date': '20170606',
1705 },
1706 'params': {
1707 'skip_download': True,
1708 },
1709 },
fd6ca382
YCH
1710 # Facebook API embed
1711 {
1712 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1713 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1714 'info_dict': {
1715 'id': '10153467542406923',
1716 'ext': 'mp4',
1717 'title': 'Facebook video #10153467542406923',
1718 },
7deef1ba
YCH
1719 },
1720 # Wordpress "YouTube Video Importer" plugin
1721 {
1722 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1723 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1724 'info_dict': {
1725 'id': 'HNTXWDXV9Is',
1726 'ext': 'mp4',
1727 'title': 'Blue Devils Drumline Stanford lot 2016',
1728 'upload_date': '20160627',
1729 'uploader_id': 'GENOCIDE8GENERAL10',
1730 'uploader': 'cylus cyrus',
1731 },
1732 },
81953d1a
RA
1733 {
1734 # video stored on custom kaltura server
1735 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1736 'md5': '537617d06e64dfed891fa1593c4b30cc',
1737 'info_dict': {
1738 'id': '0_1iotm5bh',
1739 'ext': 'mp4',
1740 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1741 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1742 'uploader_id': 'videos.expansion@el-mundo.net',
1743 'upload_date': '20150429',
1744 'timestamp': 1430303472,
1745 },
1746 'add_ie': ['Kaltura'],
1747 },
562de77f
S
1748 {
1749 # multiple kaltura embeds, nsfw
1750 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1751 'info_dict': {
1752 'id': 'kamila-avec-video-jaime-sadomie',
1753 'title': "Kamila avec vídeo “J'aime sadomie”",
1754 },
1755 'playlist_count': 8,
1756 },
c03adf90
YCH
1757 {
1758 # Non-standard Vimeo embed
1759 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1760 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1761 'info_dict': {
1762 'id': '148867247',
1763 'ext': 'mp4',
1764 'title': 'Understanding the web - Teaser',
1765 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1766 'upload_date': '20151214',
1767 'uploader': 'OpenClassrooms',
1768 'uploader_id': 'openclassrooms',
1769 },
1770 'add_ie': ['Vimeo'],
1771 },
a5ff05df
S
1772 {
1773 # generic vimeo embed that requires original URL passed as Referer
1774 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1775 'only_matching': True,
1776 },
1979969f
S
1777 {
1778 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1779 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1780 'info_dict': {
1781 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1782 'ext': 'mp4',
1783 'title': 'Big Buck Bunny',
1784 'description': 'Royalty free test video',
1785 'timestamp': 1432816365,
1786 'upload_date': '20150528',
1787 'is_live': False,
1788 },
1789 'params': {
1790 'skip_download': True,
1791 },
1792 'add_ie': [ArkenaIE.ie_key()],
1793 },
2a1321a2
S
1794 {
1795 '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/',
1796 'info_dict': {
1797 'id': '1c7141f46c',
1798 'ext': 'mp4',
1799 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1800 },
1801 'params': {
1802 'skip_download': True,
1803 },
1804 'add_ie': [Vbox7IE.ie_key()],
1805 },
b0c8f2e9
DR
1806 {
1807 # DBTV embeds
1808 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1809 'info_dict': {
1810 'id': '43254897',
1811 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1812 },
b0c8f2e9
DR
1813 'playlist_mincount': 3,
1814 },
e186a9ec
S
1815 {
1816 # Videa embeds
1817 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1818 'info_dict': {
1819 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1820 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1821 },
1822 'playlist_mincount': 2,
1823 },
b687c85e
S
1824 {
1825 # 20 minuten embed
1826 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1827 'info_dict': {
1828 'id': '523629',
1829 'ext': 'mp4',
1830 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1831 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1832 },
1833 'params': {
1834 'skip_download': True,
1835 },
1836 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1837 },
1838 {
1839 # VideoPress embed
1840 'url': 'https://en.support.wordpress.com/videopress/',
1841 'info_dict': {
1842 'id': 'OcobLTqC',
1843 'ext': 'm4v',
1844 'title': 'IMG_5786',
1845 'timestamp': 1435711927,
1846 'upload_date': '20150701',
1847 },
1848 'params': {
1849 'skip_download': True,
1850 },
1851 'add_ie': [VideoPressIE.ie_key()],
fef51645 1852 },
eb3079b6
S
1853 {
1854 # Rutube embed
1855 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1856 'info_dict': {
1857 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1858 'ext': 'flv',
1859 'title': 'Магаззино: Казань 2',
1860 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1861 'uploader': 'Магаззино',
1862 'upload_date': '20170228',
1863 'uploader_id': '996642',
1864 },
1865 'params': {
1866 'skip_download': True,
1867 },
1868 'add_ie': [RutubeIE.ie_key()],
1869 },
fef51645
YCH
1870 {
1871 # ThePlatform embedded with whitespaces in URLs
1872 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1873 'only_matching': True,
1874 },
97952bdb
JH
1875 {
1876 # Senate ISVP iframe https
1877 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1878 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1879 'info_dict': {
1880 'id': 'govtaff020316',
1881 'ext': 'mp4',
1882 'title': 'Integrated Senate Video Player',
1883 },
1884 'add_ie': [SenateISVPIE.ie_key()],
1885 },
ab87c260
S
1886 {
1887 # Limelight embeds (1 channel embed + 4 media embeds)
1888 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1889 'info_dict': {
1890 'id': 'FacilitatorTraining2017',
1891 'title': 'Facilitator Training 2017',
1892 },
1893 'playlist_mincount': 5,
1894 },
eb02940c
S
1895 {
1896 # Limelight embed (LimelightPlayerUtil.embed)
1897 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1898 'info_dict': {
1899 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1900 'ext': 'mp4',
1901 'title': '07448641',
1902 'timestamp': 1499890639,
1903 'upload_date': '20170712',
1904 },
1905 'params': {
1906 'skip_download': True,
1907 },
1908 'add_ie': ['LimelightMedia'],
1909 },
7986c3ab
S
1910 {
1911 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1912 'info_dict': {
1913 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1914 'title': 'Standoff with Walnut Creek murder suspect ends',
1915 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1916 },
1917 'playlist_mincount': 4,
1918 },
55719459
JH
1919 {
1920 # WashingtonPost embed
1921 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1922 'info_dict': {
1923 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1924 'ext': 'mp4',
1925 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1926 '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.',
1927 'timestamp': 1455216756,
1928 'uploader': 'The Washington Post',
1929 'upload_date': '20160211',
1930 },
1931 'add_ie': [WashingtonPostIE.ie_key()],
1932 },
2b8e6a68
S
1933 {
1934 # Mediaset embed
1935 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1936 'info_dict': {
1937 'id': '720642',
1938 'ext': 'mp4',
1939 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1940 },
1941 'params': {
1942 'skip_download': True,
1943 },
1944 'add_ie': [MediasetIE.ie_key()],
1945 },
73cf76a9
S
1946 {
1947 # JOJ.sk embeds
1948 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1949 'info_dict': {
1950 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1951 'title': 'Slovenskom sa prehnala vlna silných búrok',
1952 },
1953 'playlist_mincount': 5,
1954 'add_ie': [JojIE.ie_key()],
1955 },
4328ddf8
S
1956 {
1957 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1958 'url': 'https://tvrain.ru/amp/418921/',
1959 'md5': 'cc00413936695987e8de148b67d14f1d',
1960 'info_dict': {
1961 'id': '418921',
1962 'ext': 'mp4',
1963 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1964 },
1965 },
41918eaa 1966 {
1967 # vzaar embed
1663bd6e
S
1968 'url': 'http://help.vzaar.com/article/165-embedding-video',
1969 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1970 'info_dict': {
1663bd6e 1971 'id': '8707641',
41918eaa 1972 'ext': 'mp4',
1663bd6e 1973 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1974 },
1975 },
9ce1ac40 1976 {
1977 # multiple HTML5 videos on one page
1978 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1979 'info_dict': {
1980 'id': 'keyscenarios',
1981 'title': 'Rescue Kit 14 Free Edition - Getting started',
1982 },
1983 'playlist_count': 4,
0987f2dd
T
1984 },
1985 {
1986 # vshare embed
7a5c1cfe 1987 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
0987f2dd
T
1988 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1989 'info_dict': {
1990 'id': '0f64ce6',
1991 'title': 'vl14062007715967',
1992 'ext': 'mp4',
1993 }
2ca7ed41
S
1994 },
1995 {
1996 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1997 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1998 'info_dict': {
1999 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
2000 'ext': 'mp4',
2001 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
2002 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
2003 'timestamp': 1474354800,
2004 'upload_date': '20160920',
2005 }
7d540621
S
2006 },
2007 {
2008 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
2009 'info_dict': {
2010 'id': '1731611',
2011 'ext': 'mp4',
2012 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
2013 'description': 'md5:eb5f23826a027ba95277d105f248b825',
2014 'timestamp': 1516100691,
2015 'upload_date': '20180116',
2016 },
2017 'params': {
2018 'skip_download': True,
2019 },
2020 'add_ie': [SpringboardPlatformIE.ie_key()],
ea696249 2021 },
4c780fbd
S
2022 {
2023 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2024 'info_dict': {
2025 'id': 'vMDE4NzI1Mjgt690b',
2026 'ext': 'mp4',
2027 'title': 'Котята',
2028 },
2029 'add_ie': [YapFilesIE.ie_key()],
2030 'params': {
2031 'skip_download': True,
2032 },
1fc37ca3 2033 },
660a230b
S
2034 {
2035 # CloudflareStream embed
2036 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2037 'info_dict': {
2038 'id': '31c9291ab41fac05471db4e73aa11717',
2039 'ext': 'mp4',
2040 'title': '31c9291ab41fac05471db4e73aa11717',
2041 },
2042 'add_ie': [CloudflareStreamIE.ie_key()],
2043 'params': {
2044 'skip_download': True,
2045 },
2046 },
6bd499e8
S
2047 {
2048 # PeerTube embed
2049 'url': 'https://joinpeertube.org/fr/home/',
2050 'info_dict': {
2051 'id': 'home',
2052 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2053 },
2054 'playlist_count': 2,
2055 },
aee36ca8
S
2056 {
2057 # Indavideo embed
2058 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2059 'info_dict': {
2060 'id': '1693903',
2061 'ext': 'mp4',
2062 'title': 'Így kell otthon hamburgert sütni',
2063 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2064 'timestamp': 1426330212,
2065 'upload_date': '20150314',
2066 'uploader': 'StreetKitchen',
2067 'uploader_id': '546363',
2068 },
2069 'add_ie': [IndavideoEmbedIE.ie_key()],
2070 'params': {
2071 'skip_download': True,
2072 },
2073 },
cfd7f2a6
S
2074 {
2075 # APA embed via JWPlatform embed
2076 'url': 'http://www.vol.at/blue-man-group/5593454',
2077 'info_dict': {
2078 'id': 'jjv85FdZ',
2079 'ext': 'mp4',
2080 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2081 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2082 'thumbnail': r're:^https?://.*\.jpg$',
2083 'duration': 254,
2084 'timestamp': 1519211149,
2085 'upload_date': '20180221',
2086 },
2087 'params': {
2088 'skip_download': True,
2089 },
2090 },
1fc37ca3
SO
2091 {
2092 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2093 'md5': 'b68d276de422ab07ee1d49388103f457',
2094 'info_dict': {
2095 'id': '83645793',
2096 'title': 'Lock up and get excited',
1fc37ca3 2097 'ext': 'mp4'
d3431dcb
S
2098 },
2099 'skip': 'TODO: fix nested playlists processing in tests',
2100 },
9d1b2138
S
2101 {
2102 # Viqeo embeds
2103 'url': 'https://viqeo.tv/',
2104 'info_dict': {
2105 'id': 'viqeo',
2106 'title': 'All-new video platform',
2107 },
2108 'playlist_count': 6,
2109 },
d78657fd
BM
2110 {
2111 # Squarespace video embed, 2019-08-28
2112 'url': 'http://ootboxford.com',
2113 'info_dict': {
2114 'id': 'Tc7b_JGdZfw',
2115 'title': 'Out of the Blue, at Childish Things 10',
7cb51b5d
S
2116 'ext': 'mp4',
2117 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2118 'uploader_id': 'helendouglashouse',
2119 'uploader': 'Helen & Douglas House',
2120 'upload_date': '20140328',
d78657fd
BM
2121 },
2122 'params': {
2123 'skip_download': True,
2124 },
2125 },
29f7c58a 2126 # {
2127 # # Zype embed
2128 # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2129 # 'info_dict': {
2130 # 'id': '5b400b834b32992a310622b9',
2131 # 'ext': 'mp4',
2132 # 'title': 'Smoky Barbecue Favorites',
2133 # 'thumbnail': r're:^https?://.*\.jpe?g',
2134 # 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2135 # 'upload_date': '20170909',
2136 # 'timestamp': 1504915200,
2137 # },
2138 # 'add_ie': [ZypeIE.ie_key()],
2139 # 'params': {
2140 # 'skip_download': True,
2141 # },
2142 # },
e0b6e988
S
2143 {
2144 # videojs embed
2145 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2146 'info_dict': {
2147 'id': 'shell',
2148 'ext': 'mp4',
2149 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2150 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2151 'thumbnail': r're:^https?://.*\.jpg$',
2152 },
2153 'params': {
2154 'skip_download': True,
2155 },
2156 'expected_warnings': ['Failed to download MPD manifest'],
2157 },
5e3da0d4
RA
2158 {
2159 # DailyMotion embed with DM.player
2160 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2161 'info_dict': {
2162 'id': 'k6aKkGHd9FJs4mtJN39',
2163 'ext': 'mp4',
2164 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2165 'description': 'This video is private.',
2166 'uploader_id': 'x1jf30l',
2167 'uploader': 'beIN SPORTS USA',
2168 'upload_date': '20190528',
2169 'timestamp': 1559062971,
2170 },
2171 'params': {
2172 'skip_download': True,
2173 },
2174 },
6e6b70d6
S
2175 # {
2176 # # TODO: find another test
2177 # # http://schema.org/VideoObject
2178 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2179 # 'md5': '888dcf08b7ea671381f00fab74692755',
2180 # 'info_dict': {
2181 # 'id': 'nyvTSJMKId',
2182 # 'ext': 'mp4',
2183 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2184 # 'description': '#love for cats.',
2185 # 'timestamp': 1461244995,
2186 # 'upload_date': '20160421',
2187 # },
2188 # 'params': {
2189 # 'force_generic_extractor': True,
2190 # },
29f7c58a 2191 # },
2192 {
2193 # VHX Embed
2194 'url': 'https://demo.vhx.tv/category-c/videos/file-example-mp4-480-1-5mg-copy',
2195 'info_dict': {
2196 'id': '858208',
2197 'ext': 'mp4',
2198 'title': 'Untitled',
2199 'uploader_id': 'user80538407',
2200 'uploader': 'OTT Videos',
2201 },
2202 },
2203 {
2204 # ArcPublishing PoWa video player
2205 'url': 'https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/',
2206 'md5': 'b03b2fac8680e1e5a7cc81a5c27e71b3',
2207 'info_dict': {
2208 'id': '8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
2209 'ext': 'mp4',
2210 'title': 'Senate candidates wave to voters on Anchorage streets',
2211 'description': 'md5:91f51a6511f090617353dc720318b20e',
2212 'timestamp': 1604378735,
2213 'upload_date': '20201103',
2214 'duration': 1581,
2215 },
2216 },
2181983a 2217 {
2218 # MyChannels SDK embed
2219 # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
2220 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
2221 'md5': '90c0699c37006ef18e198c032d81739c',
2222 'info_dict': {
2223 'id': '194165',
2224 'ext': 'mp4',
2225 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
2226 'timestamp': 1611740340,
2227 'upload_date': '20210127',
2228 'duration': 159,
2229 },
2230 },
bc2ca1bb 2231 {
2232 # Simplecast player embed
2233 'url': 'https://www.bio.org/podcast',
2234 'info_dict': {
2235 'id': 'podcast',
2236 'title': 'I AM BIO Podcast | BIO',
2237 },
2238 'playlist_mincount': 52,
2239 },
e4edeb62 2240 {
b73612a2 2241 # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
2242 'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
2243 'only_matching': True,
2244 }, {
e4edeb62 2245 # WimTv embed player
2246 'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
2247 'info_dict': {
2248 'id': 'wearefmi-pt-2-2021',
2249 'title': '#WEAREFMI – PT.2 – 2021 – MsMotorTV',
2250 },
2251 'playlist_count': 1,
a318f59d 2252 }, {
2253 # KVS Player
2254 'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
2255 'info_dict': {
2256 'id': '105',
2257 'display_id': 'kelis-4th-of-july',
2258 'ext': 'mp4',
2259 'title': 'Kelis - 4th Of July',
2260 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2261 },
2262 'params': {
2263 'skip_download': True,
2264 },
2265 }, {
2266 # KVS Player
2267 'url': 'https://www.kvs-demo.com/embed/105/',
2268 'info_dict': {
2269 'id': '105',
2270 'display_id': 'kelis-4th-of-july',
2271 'ext': 'mp4',
2272 'title': 'Kelis - 4th Of July / Embed Player',
2273 'thumbnail': 'https://kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
2274 },
2275 'params': {
2276 'skip_download': True,
2277 },
2278 }, {
2279 # KVS Player
2280 'url': 'https://thisvid.com/videos/french-boy-pantsed/',
2281 'md5': '3397979512c682f6b85b3b04989df224',
2282 'info_dict': {
2283 'id': '2400174',
2284 'display_id': 'french-boy-pantsed',
2285 'ext': 'mp4',
2286 'title': 'French Boy Pantsed - ThisVid.com',
2287 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2288 }
2289 }, {
2290 # KVS Player
2291 'url': 'https://thisvid.com/embed/2400174/',
2292 'md5': '3397979512c682f6b85b3b04989df224',
2293 'info_dict': {
2294 'id': '2400174',
2295 'display_id': 'french-boy-pantsed',
2296 'ext': 'mp4',
2297 'title': 'French Boy Pantsed - ThisVid.com',
2298 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/2400000/2400174/preview.mp4.jpg',
2299 }
2300 }, {
2301 # KVS Player
2302 'url': 'https://youix.com/video/leningrad-zoj/',
2303 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2304 'info_dict': {
2305 'id': '18485',
2306 'display_id': 'leningrad-zoj',
2307 'ext': 'mp4',
2308 'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
2309 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2310 }
2311 }, {
2312 # KVS Player
2313 'url': 'https://youix.com/embed/18485',
2314 'md5': '94f96ba95706dc3880812b27b7d8a2b8',
2315 'info_dict': {
2316 'id': '18485',
2317 'display_id': 'leningrad-zoj',
2318 'ext': 'mp4',
2319 'title': 'Ленинград - ЗОЖ',
2320 'thumbnail': 'https://youix.com/contents/videos_screenshots/18000/18485/preview_480x320_youix_com.mp4.jpg',
2321 }
2322 }, {
2323 # KVS Player
2324 'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
2325 'md5': '94166bdb26b4cb1fb9214319a629fc51',
2326 'info_dict': {
2327 'id': '21217',
2328 'display_id': '40-nochey-40-nights-2016',
2329 'ext': 'mp4',
2330 'title': '40 ночей (2016) - BogMedia.org',
2331 'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
2332 }
e4edeb62 2333 },
cfe50f04 2334 ]
9b122384 2335
9b122384
PH
2336 def report_following_redirect(self, new_url):
2337 """Report information extraction."""
79649588 2338 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 2339
aa9369a2 2340 def report_detected(self, name):
2341 self._downloader.write_debug(f'Identified a {name}')
2342
4fc946b5
PH
2343 def _extract_rss(self, url, video_id, doc):
2344 playlist_title = doc.find('./channel/title').text
2345 playlist_desc_el = doc.find('./channel/description')
2346 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2347
29f7c58a 2348 NS_MAP = {
2349 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
2350 }
2351
76c73715
PH
2352 entries = []
2353 for it in doc.findall('./channel/item'):
01aec848
BG
2354 next_url = None
2355 enclosure_nodes = it.findall('./enclosure')
2356 for e in enclosure_nodes:
2357 next_url = e.attrib.get('url')
2358 if next_url:
2359 break
2360
76c73715 2361 if not next_url:
01aec848 2362 next_url = xpath_text(it, 'link', fatal=False)
76c73715
PH
2363
2364 if not next_url:
2365 continue
2366
29f7c58a 2367 def itunes(key):
2368 return xpath_text(
2369 it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
2370 default=None)
2371
2372 duration = itunes('duration')
2373 explicit = (itunes('explicit') or '').lower()
2374 if explicit in ('true', 'yes'):
2375 age_limit = 18
2376 elif explicit in ('false', 'no'):
2377 age_limit = 0
2378 else:
2379 age_limit = None
2380
76c73715 2381 entries.append({
413c1f8e 2382 '_type': 'url_transparent',
76c73715
PH
2383 'url': next_url,
2384 'title': it.find('title').text,
29f7c58a 2385 'description': xpath_text(it, 'description', default=None),
2386 'timestamp': unified_timestamp(
2387 xpath_text(it, 'pubDate', default=None)),
2388 'duration': int_or_none(duration) or parse_duration(duration),
2389 'thumbnail': url_or_none(xpath_attr(it, xpath_with_ns('./itunes:image', NS_MAP), 'href')),
2390 'episode': itunes('title'),
2391 'episode_number': int_or_none(itunes('episode')),
2392 'season_number': int_or_none(itunes('season')),
2393 'age_limit': age_limit,
76c73715 2394 })
4fc946b5
PH
2395
2396 return {
2397 '_type': 'playlist',
2398 'id': url,
2399 'title': playlist_title,
2400 'description': playlist_desc,
2401 'entries': entries,
2402 }
2403
c8e9a235
PH
2404 def _extract_camtasia(self, url, video_id, webpage):
2405 """ Returns None if no camtasia video can be found. """
2406
2407 camtasia_cfg = self._search_regex(
2408 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2409 webpage, 'camtasia configuration file', default=None)
2410 if camtasia_cfg is None:
2411 return None
2412
2413 title = self._html_search_meta('DC.title', webpage, fatal=True)
2414
2415 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2416 camtasia_cfg = self._download_xml(
2417 camtasia_url, video_id,
2418 note='Downloading camtasia configuration',
2419 errnote='Failed to download camtasia configuration')
2420 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2421
2422 entries = []
2423 for n in fileset_node.getchildren():
2424 url_n = n.find('./uri')
2425 if url_n is None:
2426 continue
2427
2428 entries.append({
2429 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2430 'title': '%s - %s' % (title, n.tag),
2431 'url': compat_urlparse.urljoin(url, url_n.text),
2432 'duration': float_or_none(n.find('./duration').text),
2433 })
2434
2435 return {
2436 '_type': 'playlist',
2437 'entries': entries,
2438 'title': title,
2439 }
2440
a318f59d 2441 def _kvs_getrealurl(self, video_url, license_code):
2442 if not video_url.startswith('function/0/'):
2443 return video_url # not obfuscated
2444
2445 url_path, _, url_query = video_url.partition('?')
2446 urlparts = url_path.split('/')[2:]
2447 license = self._kvs_getlicensetoken(license_code)
2448 newmagic = urlparts[5][:32]
2449
2450 for o in range(len(newmagic) - 1, -1, -1):
2451 new = ''
2452 l = (o + sum([int(n) for n in license[o:]])) % 32
2453
2454 for i in range(0, len(newmagic)):
2455 if i == o:
2456 new += newmagic[l]
2457 elif i == l:
2458 new += newmagic[o]
2459 else:
2460 new += newmagic[i]
2461 newmagic = new
2462
2463 urlparts[5] = newmagic + urlparts[5][32:]
2464 return '/'.join(urlparts) + '?' + url_query
2465
2466 def _kvs_getlicensetoken(self, license):
2467 modlicense = license.replace('$', '').replace('0', '1')
2468 center = int(len(modlicense) / 2)
2469 fronthalf = int(modlicense[:center + 1])
2470 backhalf = int(modlicense[center:])
2471
2472 modlicense = str(4 * abs(fronthalf - backhalf))
2473 retval = ''
2474 for o in range(0, center + 1):
2475 for i in range(1, 5):
2476 retval += str((int(license[o + i]) + int(modlicense[o])) % 10)
2477 return retval
2478
9b122384 2479 def _real_extract(self, url):
ebd3c7b3 2480 if url.startswith('//'):
d226c560 2481 return self.url_result(self.http_scheme() + url)
ebd3c7b3 2482
a7130543
JMF
2483 parsed_url = compat_urlparse.urlparse(url)
2484 if not parsed_url.scheme:
a06916d9 2485 default_search = self.get_param('default_search')
04b4d394 2486 if default_search is None:
1f7ccb90 2487 default_search = 'fixup_error'
04b4d394 2488
1f7ccb90 2489 if default_search in ('auto', 'auto_warning', 'fixup_error'):
9c1da4a9 2490 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
6a39ee13 2491 self.report_warning('The url doesn\'t specify the protocol, trying with http')
04b4d394 2492 return self.url_result('http://' + url)
1f7ccb90 2493 elif default_search != 'fixup_error':
9c1fc022 2494 if default_search == 'auto_warning':
0e67ab0d
PH
2495 if re.match(r'^(?:url|URL)$', url):
2496 raise ExtractorError(
7a5c1cfe 2497 'Invalid URL: %r . Call yt-dlp like this: yt-dlp -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
0e67ab0d
PH
2498 expected=True)
2499 else:
6a39ee13 2500 self.report_warning(
7571c02c 2501 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2502 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2503
2504 if default_search in ('error', 'fixup_error'):
7571c02c 2505 raise ExtractorError(
b74e86f4 2506 '%r is not a valid URL. '
7a5c1cfe 2507 'Set --default-search "ytsearch" (or run yt-dlp "ytsearch:%s" ) to search YouTube'
b74e86f4 2508 % (url, url), expected=True)
04b4d394 2509 else:
f2f2c0c2
PH
2510 if ':' not in default_search:
2511 default_search += ':'
04b4d394 2512 return self.url_result(default_search + url)
4d54ef20
PH
2513
2514 url, smuggled_data = unsmuggle_url(url)
2515 force_videoid = None
d6e6a422 2516 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2517 if smuggled_data and 'force_videoid' in smuggled_data:
2518 force_videoid = smuggled_data['force_videoid']
2519 video_id = force_videoid
2520 else:
9dcd6fd3 2521 video_id = self._generic_id(url)
3d83a1ae 2522
79649588 2523 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2524
ebab4520 2525 head_req = HEADRequest(url)
23be51d8 2526 head_response = self._request_webpage(
ebab4520
PH
2527 head_req, video_id,
2528 note=False, errnote='Could not send HEAD request to %s' % url,
2529 fatal=False)
42393ce2 2530
23be51d8 2531 if head_response is not False:
42393ce2 2532 # Check for redirect
7947a1f7 2533 new_url = head_response.geturl()
42393ce2
PH
2534 if url != new_url:
2535 self.report_following_redirect(new_url)
4d54ef20
PH
2536 if force_videoid:
2537 new_url = smuggle_url(
2538 new_url, {'force_videoid': force_videoid})
cecaaf3f 2539 return self.url_result(new_url)
42393ce2 2540
23be51d8
PH
2541 full_response = None
2542 if head_response is False:
5c2266df 2543 request = sanitized_Request(url)
58bde34a
S
2544 request.add_header('Accept-Encoding', '*')
2545 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2546 head_response = full_response
2547
f930e0c7
S
2548 info_dict = {
2549 'id': video_id,
9dcd6fd3 2550 'title': self._generic_title(url),
29f7c58a 2551 'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
f930e0c7
S
2552 }
2553
23be51d8 2554 # Check for direct link to a video
955737b2 2555 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2556 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2557 if m:
aa9369a2 2558 self.report_detected('direct video link')
4e363703 2559 format_id = compat_str(m.group('format_id'))
c26326c1 2560 subtitles = {}
f930e0c7 2561 if format_id.endswith('mpegurl'):
c26326c1 2562 formats, subtitles = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
f930e0c7
S
2563 elif format_id == 'f4m':
2564 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2565 else:
2566 formats = [{
4e363703 2567 'format_id': format_id,
eadc3ccd 2568 'url': url,
2569 'vcodec': 'none' if m.group('type') == 'audio' else None
2570 }]
de6c51e8 2571 info_dict['direct'] = True
19dbaeec 2572 self._sort_formats(formats)
de6c51e8 2573 info_dict['formats'] = formats
c26326c1 2574 info_dict['subtitles'] = subtitles
f930e0c7 2575 return info_dict
42393ce2 2576
a06916d9 2577 if not self.get_param('test', False) and not is_intentional:
2578 force = self.get_param('force_generic_extractor', False)
6a39ee13 2579 self.report_warning(
2fece970 2580 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2581
4e262a88 2582 if not full_response:
5c2266df 2583 request = sanitized_Request(url)
58bde34a
S
2584 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2585 # making it impossible to download only chunk of the file (yet we need only 512kB to
7a5c1cfe 2586 # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
58bde34a
S
2587 # that will always result in downloading the whole file that is not desirable.
2588 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2589 # to accept raw bytes and being able to download only a chunk.
2590 # It may probably better to solve this by checking Content-Type for application/octet-stream
2591 # after HEAD request finishes, but not sure if we can rely on this.
2592 request.add_header('Accept-Encoding', '*')
2593 full_response = self._request_webpage(request, video_id)
4e262a88 2594
5940862d
S
2595 first_bytes = full_response.read(512)
2596
2597 # Is it an M3U playlist?
0d769bcb 2598 if first_bytes.startswith(b'#EXTM3U'):
aa9369a2 2599 self.report_detected('M3U playlist')
da1c94ee 2600 info_dict['formats'], info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
19dbaeec 2601 self._sort_formats(info_dict['formats'])
5940862d
S
2602 return info_dict
2603
4e262a88
PH
2604 # Maybe it's a direct link to a video?
2605 # Be careful not to download the whole thing!
61ca9a80 2606 if not is_html(first_bytes):
6a39ee13 2607 self.report_warning(
4e262a88 2608 'URL could be a direct video link, returning it as such.')
f930e0c7 2609 info_dict.update({
4e262a88
PH
2610 'direct': True,
2611 'url': url,
f930e0c7
S
2612 })
2613 return info_dict
4e262a88
PH
2614
2615 webpage = self._webpage_read_content(
2616 full_response, url, video_id, prefix=first_bytes)
2617
2181983a 2618 if '<title>DPG Media Privacy Gate</title>' in webpage:
2619 webpage = self._download_webpage(url, video_id)
2620
9b122384 2621 self.report_extraction(video_id)
887c6acd 2622
1b840245 2623 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2624 try:
61241abb 2625 try:
2626 doc = compat_etree_fromstring(webpage)
2627 except compat_xml_parse_error:
2628 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5 2629 if doc.tag == 'rss':
aa9369a2 2630 self.report_detected('RSS feed')
4fc946b5 2631 return self._extract_rss(url, video_id, doc)
cc99a77a 2632 elif doc.tag == 'SmoothStreamingMedia':
7a450a3b 2633 info_dict['formats'], info_dict['subtitles'] = self._parse_ism_formats_and_subtitles(doc, url)
aa9369a2 2634 self.report_detected('ISM manifest')
cc99a77a
S
2635 self._sort_formats(info_dict['formats'])
2636 return info_dict
e5e8d20a 2637 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec 2638 smil = self._parse_smil(doc, url, video_id)
aa9369a2 2639 self.report_detected('SMIL file')
19dbaeec
S
2640 self._sort_formats(smil['formats'])
2641 return smil
729accb4 2642 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
aa9369a2 2643 self.report_detected('XSPF playlist')
96b8b9ab 2644 return self.playlist_result(
47a5cb77
S
2645 self._parse_xspf(
2646 doc, video_id, xspf_url=url,
7947a1f7 2647 xspf_base_url=full_response.geturl()),
96b8b9ab 2648 video_id)
1b840245 2649 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
7de27caf 2650 info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles(
d3f8b76b 2651 doc,
7947a1f7 2652 mpd_base_url=full_response.geturl().rpartition('/')[0],
86f4d14f 2653 mpd_url=url)
aa9369a2 2654 self.report_detected('DASH manifest')
19dbaeec 2655 self._sort_formats(info_dict['formats'])
f930e0c7
S
2656 return info_dict
2657 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2658 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
aa9369a2 2659 self.report_detected('F4M manifest')
19dbaeec 2660 self._sort_formats(info_dict['formats'])
f930e0c7 2661 return info_dict
f7300c5c 2662 except compat_xml_parse_error:
4fc946b5
PH
2663 pass
2664
c8e9a235
PH
2665 # Is it a Camtasia project?
2666 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2667 if camtasia_res is not None:
aa9369a2 2668 self.report_detected('Camtasia video')
c8e9a235
PH
2669 return camtasia_res
2670
14390730 2671 # Sometimes embedded video player is hidden behind percent encoding
067aa17e 2672 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
14390730 2673 # Unescaping the whole page allows to handle those cases in a generic way
29f7c58a 2674 # FIXME: unescaping the whole page may break URLs, commenting out for now.
2675 # There probably should be a second run of generic extractor on unescaped webpage.
2676 # webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2677
7cb51b5d
S
2678 # Unescape squarespace embeds to be detected by generic extractor,
2679 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2680 webpage = re.sub(
2681 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2682 lambda x: unescapeHTML(x.group(0)), webpage)
d78657fd 2683
887c6acd
PH
2684 # it's tempting to parse this further, but you would
2685 # have to take into account all the variations like
2686 # Video Title - Site Name
2687 # Site Name | Video Title
2688 # Video Title - Tagline | Site Name
2689 # and so on and so forth; it's just not practical
6f41b2bc
S
2690 video_title = self._og_search_title(
2691 webpage, default=None) or self._html_search_regex(
79649588
PH
2692 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2693 default='video')
ef4fd848 2694
4d805e06
PH
2695 # Try to detect age limit automatically
2696 age_limit = self._rta_search(webpage)
2697 # And then there are the jokers who advertise that they use RTA,
2698 # but actually don't.
2699 AGE_LIMIT_MARKERS = [
197224b7 2700 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
4d805e06
PH
2701 ]
2702 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2703 age_limit = 18
2704
ef4fd848
PH
2705 # video uploader is domain name
2706 video_uploader = self._search_regex(
79649588 2707 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2708
6f41b2bc
S
2709 video_description = self._og_search_description(webpage, default=None)
2710 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2711
b311b0ea
S
2712 info_dict.update({
2713 'title': video_title,
2714 'description': video_description,
2715 'thumbnail': video_thumbnail,
2716 'age_limit': age_limit,
2717 })
2718
aa9369a2 2719 self._downloader.write_debug('Looking for video embeds')
2720
1f4b722b 2721 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2722 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2723 if bc_urls:
99877772
PH
2724 entries = [{
2725 '_type': 'url',
2726 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2727 'ie_key': 'BrightcoveLegacy'
99877772
PH
2728 } for bc_url in bc_urls]
2729
2730 return {
2731 '_type': 'playlist',
2732 'title': video_title,
2733 'id': video_id,
2734 'entries': entries,
2735 }
cfe50f04 2736
f6519f89 2737 # Look for Brightcove New Studio embeds
0254f93b 2738 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2739 if bc_urls:
5399ab3f
S
2740 return self.playlist_from_matches(
2741 bc_urls, video_id, video_title,
2742 getter=lambda x: smuggle_url(x, {'referrer': url}),
2743 ie='BrightcoveNew')
ed126900 2744
4e826cd9
S
2745 # Look for Nexx embeds
2746 nexx_urls = NexxIE._extract_urls(webpage)
2747 if nexx_urls:
2748 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2749
3f59b015
S
2750 # Look for Nexx iFrame embeds
2751 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2752 if nexx_embed_urls:
2753 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2754
4d8819d2
S
2755 # Look for ThePlatform embeds
2756 tp_urls = ThePlatformIE._extract_urls(webpage)
2757 if tp_urls:
46b18f23 2758 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2759
29f7c58a 2760 arc_urls = ArcPublishingIE._extract_urls(webpage)
2761 if arc_urls:
2762 return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
2763
2181983a 2764 mychannels_urls = MedialaanIE._extract_urls(webpage)
2765 if mychannels_urls:
2766 return self.playlist_from_matches(
2767 mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
2768
59b8ab58
PH
2769 # Look for embedded rtl.nl player
2770 matches = re.findall(
2637fadc 2771 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
59b8ab58
PH
2772 webpage)
2773 if matches:
46b18f23 2774 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2775
09b9c45e
S
2776 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2777 if vimeo_urls:
46b18f23 2778 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2779
29f7c58a 2780 vhx_url = VHXEmbedIE._extract_url(webpage)
2781 if vhx_url:
2782 return self.url_result(vhx_url, VHXEmbedIE.ie_key())
2783
df0c8151 2784 # Invidious Instances
2785 # https://github.com/yt-dlp/yt-dlp/issues/195
2786 # https://github.com/iv-org/invidious/pull/1730
2787 youtube_url = self._search_regex(
2788 r'<link rel="alternate" href="(https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2789 webpage, 'youtube link', default=None)
2790 if youtube_url:
2791 return self.url_result(youtube_url, YoutubeIE.ie_key())
2792
66c9fa36
S
2793 # Look for YouTube embeds
2794 youtube_urls = YoutubeIE._extract_urls(webpage)
2795 if youtube_urls:
46b18f23 2796 return self.playlist_from_matches(
66c9fa36 2797 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2798
ad213a1d 2799 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2800 if matches:
46b18f23 2801 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2802
8489578d
NJ
2803 # Look for embedded Dailymotion playlist player (#3822)
2804 m = re.search(
2805 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2806 if m:
2807 playlists = re.findall(
2808 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2809 if playlists:
46b18f23
JH
2810 return self.playlist_from_matches(
2811 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2812
71a1db89
S
2813 # Look for DailyMail embeds
2814 dailymail_urls = DailyMailIE._extract_urls(webpage)
2815 if dailymail_urls:
2816 return self.playlist_from_matches(
2817 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2818
be7dacf9
S
2819 # Look for Teachable embeds, must be before Wistia
2820 teachable_url = TeachableIE._extract_url(webpage, url)
2821 if teachable_url:
2822 return self.url_result(teachable_url)
2823
ef4fd848 2824 # Look for embedded Wistia player
fda6d237
S
2825 wistia_urls = WistiaIE._extract_urls(webpage)
2826 if wistia_urls:
2827 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2828 for entry in playlist['entries']:
2829 entry.update({
2830 '_type': 'url_transparent',
2831 'uploader': video_uploader,
2832 })
2833 return playlist
5f6a1245 2834
bab19a8e
S
2835 # Look for SVT player
2836 svt_url = SVTIE._extract_url(webpage)
2837 if svt_url:
2838 return self.url_result(svt_url, 'SVT')
2839
c19f7764
JMF
2840 # Look for Bandcamp pages with custom domain
2841 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2842 if mobj is not None:
2843 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2844 # Don't set the extractor because it can be a track url or an album
2845 return self.url_result(burl)
c19f7764 2846
f25571ff
PH
2847 # Look for embedded Vevo player
2848 mobj = re.search(
2849 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2850 if mobj is not None:
2851 return self.url_result(mobj.group('url'))
796df3c6
S
2852
2853 # Look for embedded Viddler player
cb454b33
S
2854 mobj = re.search(
2855 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2856 webpage)
796df3c6
S
2857 if mobj is not None:
2858 return self.url_result(mobj.group('url'))
f25571ff 2859
3378d67a
S
2860 # Look for NYTimes player
2861 mobj = re.search(
2862 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2863 webpage)
2864 if mobj is not None:
2865 return self.url_result(mobj.group('url'))
2866
cefdf970
S
2867 # Look for Libsyn player
2868 mobj = re.search(
2869 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2870 if mobj is not None:
2871 return self.url_result(mobj.group('url'))
2872
c0d0b01f 2873 # Look for Ooyala videos
3089bc74
S
2874 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2875 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2876 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2877 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2878 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2879 if mobj is not None:
9837cb75
RA
2880 embed_token = self._search_regex(
2881 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2882 webpage, 'ooyala embed token', default=None)
2883 return OoyalaIE._build_url_result(smuggle_url(
2884 mobj.group('ec'), {
2885 'domain': url,
2886 'embed_token': embed_token,
2887 }))
c0d0b01f 2888
f076b638 2889 # Look for multiple Ooyala embeds on SBN network websites
2890 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2891 if mobj is not None:
2892 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2893 if embeds:
46b18f23
JH
2894 return self.playlist_from_matches(
2895 embeds, video_id, video_title,
2896 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2897
aa94a6d3 2898 # Look for Aparat videos
48099643 2899 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2900 if mobj is not None:
2901 return self.url_result(mobj.group(1), 'Aparat')
2902
c93c2ab1 2903 # Look for MPORA videos
c3f51436 2904 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2905 if mobj is not None:
2906 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2907
9834872b 2908 # Look for embedded Facebook player
0646e34c
S
2909 facebook_urls = FacebookIE._extract_urls(webpage)
2910 if facebook_urls:
2911 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2912
ca97a56e
S
2913 # Look for embedded VK player
2914 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2915 if mobj is not None:
2916 return self.url_result(mobj.group('url'), 'VK')
2917
33d4fdab 2918 # Look for embedded Odnoklassniki player
416c3ca7
RA
2919 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2920 if odnoklassniki_url:
2921 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
33d4fdab 2922
b73612a2 2923 # Look for sibnet embedded player
2924 sibnet_urls = VKIE._extract_sibnet_urls(webpage)
2925 if sibnet_urls:
2926 return self.playlist_from_matches(sibnet_urls, video_id, video_title)
2927
0364fa8b
S
2928 # Look for embedded ivi player
2929 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2930 if mobj is not None:
2931 return self.url_result(mobj.group('url'), 'Ivi')
2932
db1f3888
PH
2933 # Look for embedded Huffington Post player
2934 mobj = re.search(
c3f51436 2935 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2936 if mobj is not None:
2937 return self.url_result(mobj.group('url'), 'HuffPost')
2938
1b86cc41 2939 # Look for embed.ly
2940 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2941 if mobj is not None:
2942 return self.url_result(mobj.group('url'))
2943 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2944 if mobj is not None:
f7e6f7fa 2945 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2946
60cc4dc4
PH
2947 # Look for funnyordie embed
2948 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2949 if matches:
46b18f23
JH
2950 return self.playlist_from_matches(
2951 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2952
bc2ca1bb 2953 # Look for Simplecast embeds
2954 simplecast_urls = SimplecastIE._extract_urls(webpage)
2955 if simplecast_urls:
2956 return self.playlist_from_matches(
2957 simplecast_urls, video_id, video_title)
2958
db546cf8
S
2959 # Look for BBC iPlayer embed
2960 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2961 if matches:
46b18f23 2962 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2963
93d020dd
S
2964 # Look for embedded RUTV player
2965 rutv_url = RUTVIE._extract_url(webpage)
2966 if rutv_url:
2967 return self.url_result(rutv_url, 'RUTV')
2968
494f20cb 2969 # Look for embedded TVC player
b8599718
S
2970 tvc_url = TVCIE._extract_url(webpage)
2971 if tvc_url:
2972 return self.url_result(tvc_url, 'TVC')
494f20cb 2973
d40a3b5b 2974 # Look for embedded SportBox player
476cf548 2975 sportbox_urls = SportBoxIE._extract_urls(webpage)
d40a3b5b 2976 if sportbox_urls:
476cf548 2977 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
d40a3b5b 2978
2bb5b6d0
S
2979 # Look for embedded XHamster player
2980 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2981 if xhamster_urls:
46b18f23 2982 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2983
2c9ca782
S
2984 # Look for embedded TNAFlixNetwork player
2985 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2986 if tnaflix_urls:
46b18f23 2987 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2988
b52c9ef1
S
2989 # Look for embedded PornHub player
2990 pornhub_urls = PornHubIE._extract_urls(webpage)
2991 if pornhub_urls:
46b18f23 2992 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2993
37e7a71c
S
2994 # Look for embedded DrTuber player
2995 drtuber_urls = DrTuberIE._extract_urls(webpage)
2996 if drtuber_urls:
46b18f23 2997 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2998
e28ed498
S
2999 # Look for embedded RedTube player
3000 redtube_urls = RedTubeIE._extract_urls(webpage)
3001 if redtube_urls:
46b18f23 3002 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 3003
06993715
S
3004 # Look for embedded Tube8 player
3005 tube8_urls = Tube8IE._extract_urls(webpage)
3006 if tube8_urls:
3007 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
3008
4e7b5bba
S
3009 # Look for embedded Mofosex player
3010 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
3011 if mofosex_urls:
3012 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
3013
8fae1a04
S
3014 # Look for embedded Spankwire player
3015 spankwire_urls = SpankwireIE._extract_urls(webpage)
3016 if spankwire_urls:
3017 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
3018
52c4c515
S
3019 # Look for embedded YouPorn player
3020 youporn_urls = YouPornIE._extract_urls(webpage)
3021 if youporn_urls:
3022 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
3023
9872d311
S
3024 # Look for embedded Tvigle player
3025 mobj = re.search(
3026 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
3027 if mobj is not None:
3028 return self.url_result(mobj.group('url'), 'Tvigle')
3029
7e2ede98
JMF
3030 # Look for embedded TED player
3031 mobj = re.search(
d7cc31b6 3032 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
3033 if mobj is not None:
3034 return self.url_result(mobj.group('url'), 'TED')
3035
5c386252 3036 # Look for embedded Ustream videos
d77ac737
YCH
3037 ustream_url = UstreamIE._extract_url(webpage)
3038 if ustream_url:
3039 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 3040
893f8832 3041 # Look for embedded arte.tv player
8bdd16b4 3042 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
3043 if arte_urls:
3044 return self.playlist_from_matches(arte_urls, video_id, video_title)
893f8832 3045
cbd55ade
S
3046 # Look for embedded francetv player
3047 mobj = re.search(
3048 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
3049 webpage)
3050 if mobj is not None:
3051 return self.url_result(mobj.group('url'))
3052
e6c2d9ad 3053 # Look for embedded Myvi.ru player
6dd94d3a 3054 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
3055 if myvi_url:
3056 return self.url_result(myvi_url)
3057
dfb1b146 3058 # Look for embedded soundcloud player
548c3957 3059 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
94aae015 3060 if soundcloud_urls:
548c3957 3061 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
20991253 3062
027e2312
S
3063 # Look for tunein player
3064 tunein_urls = TuneInBaseIE._extract_urls(webpage)
3065 if tunein_urls:
46b18f23 3066 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 3067
c5cd249e 3068 # Look for embedded mtvservices player
46fde8a1
S
3069 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
3070 if mtvservices_url:
3071 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 3072
49807b4a
S
3073 # Look for embedded yahoo player
3074 mobj = re.search(
3075 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
3076 webpage)
3077 if mobj is not None:
3078 return self.url_result(mobj.group('url'), 'Yahoo')
3079
2ef6fcb5
PH
3080 # Look for embedded sbs.com.au player
3081 mobj = re.search(
e98b8e79
PH
3082 r'''(?x)
3083 (?:
3084 <meta\s+property="og:video"\s+content=|
3085 <iframe[^>]+?src=
3086 )
3087 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
3088 webpage)
3089 if mobj is not None:
3090 return self.url_result(mobj.group('url'), 'SBS')
3091
42bdd9d0
PH
3092 # Look for embedded Cinchcast player
3093 mobj = re.search(
3094 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
3095 webpage)
3096 if mobj is not None:
3097 return self.url_result(mobj.group('url'), 'Cinchcast')
3098
1a94ff68 3099 mobj = re.search(
5263cdfc 3100 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 3101 webpage)
8001607e
YCH
3102 if not mobj:
3103 mobj = re.search(
1418a043 3104 r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
8001607e 3105 webpage)
1a94ff68
S
3106 if mobj is not None:
3107 return self.url_result(mobj.group('url'), 'MLB')
3108
1419fafd 3109 mobj = re.search(
dd467d33 3110 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
3111 webpage)
3112 if mobj is not None:
3113 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
3114
af63fed7 3115 mobj = re.search(
78d3b3e2 3116 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
3117 webpage)
3118 if mobj is not None:
3119 return self.url_result(mobj.group('url'), 'Livestream')
3120
255fca5e
S
3121 # Look for Zapiks embed
3122 mobj = re.search(
3123 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
3124 if mobj is not None:
3125 return self.url_result(mobj.group('url'), 'Zapiks')
3126
e3216b82 3127 # Look for Kaltura embeds
562de77f
S
3128 kaltura_urls = KalturaIE._extract_urls(webpage)
3129 if kaltura_urls:
3130 return self.playlist_from_matches(
3131 kaltura_urls, video_id, video_title,
3132 getter=lambda x: smuggle_url(x, {'source_url': url}),
3133 ie=KalturaIE.ie_key())
e3216b82 3134
665e9452 3135 # Look for EaglePlatform embeds
06a96da1
S
3136 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
3137 if eagleplatform_url:
665e9452 3138 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 3139
665e9452 3140 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
3141 mobj = re.search(
3142 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
3143 if mobj is not None:
3144 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
3145
f8388757 3146 # Look for Pladform embeds
45dad7ba
S
3147 pladform_url = PladformIE._extract_url(webpage)
3148 if pladform_url:
3149 return self.url_result(pladform_url)
f8388757 3150
ff18735c
S
3151 # Look for Videomore embeds
3152 videomore_url = VideomoreIE._extract_url(webpage)
3153 if videomore_url:
3154 return self.url_result(videomore_url)
3155
83f1481b
S
3156 # Look for Webcaster embeds
3157 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
3158 if webcaster_url:
3159 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
3160
2dcc114f
S
3161 # Look for Playwire embeds
3162 mobj = re.search(
3163 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
3164 if mobj is not None:
3165 return self.url_result(mobj.group('url'))
3166
ad320e9b
NJ
3167 # Look for 5min embeds
3168 mobj = re.search(
3169 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
3170 if mobj is not None:
3171 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
3172
18153f1b
S
3173 # Look for Crooks and Liars embeds
3174 mobj = re.search(
3175 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
3176 if mobj is not None:
3177 return self.url_result(mobj.group('url'))
3178
a2edf2e7
YCH
3179 # Look for NBC Sports VPlayer embeds
3180 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
3181 if nbc_sports_url:
3182 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
3183
de3eb07e
YCH
3184 # Look for NBC News embeds
3185 nbc_news_embed_url = re.search(
3186 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
3187 if nbc_news_embed_url:
3188 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
3189
653789af 3190 # Look for Google Drive embeds
5b251628 3191 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 3192 if google_drive_url:
3193 return self.url_result(google_drive_url, 'GoogleDrive')
3194
418c5cc3
YCH
3195 # Look for UDN embeds
3196 mobj = re.search(
2637fadc 3197 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
3198 if mobj is not None:
3199 return self.url_result(
0a160363 3200 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 3201
2fe1b5bd
YCH
3202 # Look for Senate ISVP iframe
3203 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
3204 if senate_isvp_url:
25c3a734 3205 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 3206
55adb63e
RA
3207 # Look for Kinja embeds
3208 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
3209 if kinja_embed_urls:
3210 return self.playlist_from_matches(
3211 kinja_embed_urls, video_id, video_title)
3212
1ac1c4c2
S
3213 # Look for OnionStudios embeds
3214 onionstudios_url = OnionStudiosIE._extract_url(webpage)
3215 if onionstudios_url:
3216 return self.url_result(onionstudios_url)
3217
67167920 3218 # Look for ViewLift embeds
3219 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
3220 if viewlift_url:
3221 return self.url_result(viewlift_url)
eedd20ef 3222
7cb09524 3223 # Look for JWPlatform embeds
b0ead0e0
S
3224 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
3225 if jwplatform_urls:
3226 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
7cb09524 3227
aecfcd4e
S
3228 # Look for Digiteka embeds
3229 digiteka_url = DigitekaIE._extract_url(webpage)
3230 if digiteka_url:
3231 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 3232
1979969f
S
3233 # Look for Arkena embeds
3234 arkena_url = ArkenaIE._extract_url(webpage)
3235 if arkena_url:
3236 return self.url_result(arkena_url, ArkenaIE.ie_key())
3237
b1c35797
RA
3238 # Look for Piksel embeds
3239 piksel_url = PikselIE._extract_url(webpage)
3240 if piksel_url:
3241 return self.url_result(piksel_url, PikselIE.ie_key())
3242
1bf996fa 3243 # Look for Limelight embeds
e5d39886
S
3244 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
3245 if limelight_urls:
3246 return self.playlist_result(
3247 limelight_urls, video_id, video_title, video_description)
3248
7986c3ab
S
3249 # Look for Anvato embeds
3250 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
3251 if anvato_urls:
3252 return self.playlist_result(
3253 anvato_urls, video_id, video_title, video_description)
3254
a5158f38
YCH
3255 # Look for AdobeTVVideo embeds
3256 mobj = re.search(
3257 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
3258 webpage)
3259 if mobj is not None:
3260 return self.url_result(
3261 self._proto_relative_url(unescapeHTML(mobj.group(1))),
3262 'AdobeTVVideo')
3263
088e1aac
YCH
3264 # Look for Vine embeds
3265 mobj = re.search(
3266 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
3267 webpage)
3268 if mobj is not None:
3269 return self.url_result(
3270 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
3271
217d5ae0
RA
3272 # Look for VODPlatform embeds
3273 mobj = re.search(
bd2c211f 3274 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
217d5ae0
RA
3275 webpage)
3276 if mobj is not None:
3277 return self.url_result(
93b84045 3278 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 3279
7d273a38
RA
3280 # Look for Mangomolo embeds
3281 mobj = re.search(
755541a4
RA
3282 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3283 (?:
3284 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3285 player\.mangomolo\.com/v1
3286 )/
7d273a38
RA
3287 (?:
3288 video\?.*?\bid=(?P<video_id>\d+)|
755541a4 3289 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
7d273a38
RA
3290 ).+?)\1''', webpage)
3291 if mobj is not None:
3292 info = {
3293 '_type': 'url_transparent',
3294 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3295 'title': video_title,
3296 'description': video_description,
3297 'thumbnail': video_thumbnail,
3298 'uploader': video_uploader,
3299 }
3300 video_id = mobj.group('video_id')
3301 if video_id:
3302 info.update({
3303 'ie_key': 'MangomoloVideo',
3304 'id': video_id,
3305 })
3306 else:
3307 info.update({
3308 'ie_key': 'MangomoloLive',
3309 'id': mobj.group('channel_id'),
3310 })
3311 return info
3312
5a51775a
YCH
3313 # Look for Instagram embeds
3314 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3315 if instagram_embed_url is not None:
11e60fca
S
3316 return self.url_result(
3317 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 3318
5d39176f
S
3319 # Look for 3Q SDN embeds
3320 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3321 if threeqsdn_url:
6f41b2bc
S
3322 return {
3323 '_type': 'url_transparent',
3324 'ie_key': ThreeQSDNIE.ie_key(),
3325 'url': self._proto_relative_url(threeqsdn_url),
3326 'title': video_title,
3327 'description': video_description,
3328 'thumbnail': video_thumbnail,
3329 'uploader': video_uploader,
3330 }
5d39176f 3331
2a1321a2
S
3332 # Look for VBOX7 embeds
3333 vbox7_url = Vbox7IE._extract_url(webpage)
3334 if vbox7_url:
3335 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3336
b0c8f2e9
DR
3337 # Look for DBTV embeds
3338 dbtv_urls = DBTVIE._extract_urls(webpage)
3339 if dbtv_urls:
46b18f23 3340 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 3341
e186a9ec
S
3342 # Look for Videa embeds
3343 videa_urls = VideaIE._extract_urls(webpage)
3344 if videa_urls:
46b18f23 3345 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 3346
b687c85e
S
3347 # Look for 20 minuten embeds
3348 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3349 if twentymin_urls:
46b18f23
JH
3350 return self.playlist_from_matches(
3351 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 3352
6ef3e65a
S
3353 # Look for VideoPress embeds
3354 videopress_urls = VideoPressIE._extract_urls(webpage)
3355 if videopress_urls:
46b18f23
JH
3356 return self.playlist_from_matches(
3357 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 3358
eb3079b6
S
3359 # Look for Rutube embeds
3360 rutube_urls = RutubeIE._extract_urls(webpage)
3361 if rutube_urls:
46b18f23 3362 return self.playlist_from_matches(
2583c0b5 3363 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 3364
55719459
JH
3365 # Look for WashingtonPost embeds
3366 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3367 if wapo_urls:
3368 return self.playlist_from_matches(
3369 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3370
5d29af3d 3371 # Look for Mediaset embeds
8fd12a08 3372 mediaset_urls = MediasetIE._extract_urls(self, webpage)
5d29af3d
S
3373 if mediaset_urls:
3374 return self.playlist_from_matches(
3375 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3376
73cf76a9
S
3377 # Look for JOJ.sk embeds
3378 joj_urls = JojIE._extract_urls(webpage)
3379 if joj_urls:
3380 return self.playlist_from_matches(
3381 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3382
24e966e8
PH
3383 # Look for megaphone.fm embeds
3384 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3385 if mpfn_urls:
3386 return self.playlist_from_matches(
3387 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3388
1663bd6e
S
3389 # Look for vzaar embeds
3390 vzaar_urls = VzaarIE._extract_urls(webpage)
3391 if vzaar_urls:
3392 return self.playlist_from_matches(
3393 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3394
26bae2d9
S
3395 channel9_urls = Channel9IE._extract_urls(webpage)
3396 if channel9_urls:
3397 return self.playlist_from_matches(
3398 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3399
0987f2dd
T
3400 vshare_urls = VShareIE._extract_urls(webpage)
3401 if vshare_urls:
3402 return self.playlist_from_matches(
3403 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3404
8056c854 3405 # Look for Mediasite embeds
2ca7ed41
S
3406 mediasite_urls = MediasiteIE._extract_urls(webpage)
3407 if mediasite_urls:
3408 entries = [
3409 self.url_result(smuggle_url(
3410 compat_urlparse.urljoin(url, mediasite_url),
3411 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3412 for mediasite_url in mediasite_urls]
3413 return self.playlist_result(entries, video_id, video_title)
8056c854 3414
7d540621
S
3415 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3416 if springboardplatform_urls:
3417 return self.playlist_from_matches(
3418 springboardplatform_urls, video_id, video_title,
3419 ie=SpringboardPlatformIE.ie_key())
3420
4c780fbd
S
3421 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3422 if yapfiles_urls:
3423 return self.playlist_from_matches(
3424 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3425
86c8cfc5
S
3426 vice_urls = ViceIE._extract_urls(webpage)
3427 if vice_urls:
3428 return self.playlist_from_matches(
3429 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3430
178ee883
S
3431 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3432 if xfileshare_urls:
3433 return self.playlist_from_matches(
3434 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3435
660a230b
S
3436 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3437 if cloudflarestream_urls:
3438 return self.playlist_from_matches(
3439 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3440
8b4b400a 3441 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
6bd499e8
S
3442 if peertube_urls:
3443 return self.playlist_from_matches(
3444 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3445
aee36ca8
S
3446 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3447 if indavideo_urls:
3448 return self.playlist_from_matches(
3449 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3450
cfd7f2a6
S
3451 apa_urls = APAIE._extract_urls(webpage)
3452 if apa_urls:
3453 return self.playlist_from_matches(
3454 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3455
f51f526b
S
3456 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3457 if foxnews_urls:
3458 return self.playlist_from_matches(
3459 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3460
2e4350ee 3461 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
d3431dcb
S
3462 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3463 webpage)]
3464 if sharevideos_urls:
3465 return self.playlist_from_matches(
3466 sharevideos_urls, video_id, video_title)
3467
9d1b2138
S
3468 viqeo_urls = ViqeoIE._extract_urls(webpage)
3469 if viqeo_urls:
3470 return self.playlist_from_matches(
3471 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
57c68ec4
S
3472
3473 expressen_urls = ExpressenIE._extract_urls(webpage)
3474 if expressen_urls:
3475 return self.playlist_from_matches(
3476 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
9d1b2138 3477
83852e57
S
3478 zype_urls = ZypeIE._extract_urls(webpage)
3479 if zype_urls:
3480 return self.playlist_from_matches(
3481 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3482
feee67ae 3483 gedi_urls = GediDigitalIE._extract_urls(webpage)
902784a2 3484 if gedi_urls:
3485 return self.playlist_from_matches(
feee67ae 3486 gedi_urls, video_id, video_title, ie=GediDigitalIE.ie_key())
902784a2 3487
feee67ae 3488 # Look for RCS media group embeds
a85e131b 3489 rcs_urls = RCSEmbedsIE._extract_urls(webpage)
3490 if rcs_urls:
3491 return self.playlist_from_matches(
3492 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
3493
e4edeb62 3494 wimtv_urls = WimTVIE._extract_urls(webpage)
3495 if wimtv_urls:
3496 return self.playlist_from_matches(
3497 wimtv_urls, video_id, video_title, ie=WimTVIE.ie_key())
3498
097f1663 3499 bitchute_urls = BitChuteIE._extract_urls(webpage)
3500 if bitchute_urls:
3501 return self.playlist_from_matches(
3502 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
3503
62852977 3504 rumble_urls = RumbleEmbedIE._extract_urls(webpage)
3505 if len(rumble_urls) == 1:
3506 return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
3507 if rumble_urls:
3508 return self.playlist_from_matches(
3509 rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
3510
bd264412
YCH
3511 # Look for HTML5 media
3512 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3513 if entries:
aa9369a2 3514 self.report_detected('HTML5 media')
9ce1ac40 3515 if len(entries) == 1:
3516 entries[0].update({
bd264412
YCH
3517 'id': video_id,
3518 'title': video_title,
3519 })
9ce1ac40 3520 else:
3521 for num, entry in enumerate(entries, start=1):
3522 entry.update({
3523 'id': '%s-%s' % (video_id, num),
3524 'title': '%s (%d)' % (video_title, num),
3525 })
3526 for entry in entries:
bd264412 3527 self._sort_formats(entry['formats'])
9ce1ac40 3528 return self.playlist_result(entries, video_id, video_title)
bd264412 3529
c73e330e
RU
3530 jwplayer_data = self._find_jwplayer_data(
3531 webpage, video_id, transform_source=js_to_json)
3532 if jwplayer_data:
5e7bbac3 3533 if isinstance(jwplayer_data.get('playlist'), str):
aa9369a2 3534 self.report_detected('JW Player playlist')
5e7bbac3 3535 return {
3536 **info_dict,
3537 '_type': 'url',
3538 'ie_key': JWPlatformIE.ie_key(),
3539 'url': jwplayer_data['playlist'],
3540 }
3d08f63d
MYM
3541 try:
3542 info = self._parse_jwplayer_data(
3543 jwplayer_data, video_id, require_title=False, base_url=url)
aa9369a2 3544 self.report_detected('JW Player data')
3d08f63d
MYM
3545 return merge_dicts(info, info_dict)
3546 except ExtractorError:
067aa17e 3547 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3d08f63d 3548 pass
a4a554a7 3549
63d990d2
S
3550 # Video.js embed
3551 mobj = re.search(
c5b7014a 3552 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
3553 webpage)
3554 if mobj is not None:
3555 sources = self._parse_json(
3556 mobj.group(1), video_id, transform_source=js_to_json,
3557 fatal=False) or []
c5b7014a
S
3558 if not isinstance(sources, list):
3559 sources = [sources]
63d990d2 3560 formats = []
da1c94ee 3561 subtitles = {}
63d990d2 3562 for source in sources:
e0b6e988
S
3563 src = source.get('src')
3564 if not src or not isinstance(src, compat_str):
63d990d2
S
3565 continue
3566 src = compat_urlparse.urljoin(url, src)
3567 src_type = source.get('type')
3568 if isinstance(src_type, compat_str):
3569 src_type = src_type.lower()
3570 ext = determine_ext(src).lower()
3571 if src_type == 'video/youtube':
3572 return self.url_result(src, YoutubeIE.ie_key())
3573 if src_type == 'application/dash+xml' or ext == 'mpd':
da1c94ee
F
3574 fmts, subs = self._extract_mpd_formats_and_subtitles(
3575 src, video_id, mpd_id='dash', fatal=False)
3576 formats.extend(fmts)
3577 self._merge_subtitles(subs, target=subtitles)
63d990d2 3578 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
da1c94ee 3579 fmts, subs = self._extract_m3u8_formats_and_subtitles(
63d990d2 3580 src, video_id, 'mp4', entry_protocol='m3u8_native',
da1c94ee
F
3581 m3u8_id='hls', fatal=False)
3582 formats.extend(fmts)
3583 self._merge_subtitles(subs, target=subtitles)
63d990d2
S
3584 else:
3585 formats.append({
3586 'url': src,
3089bc74
S
3587 'ext': (mimetype2ext(src_type)
3588 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
b73612a2 3589 'http_headers': {
3590 'Referer': full_response.geturl(),
3591 },
63d990d2 3592 })
da1c94ee 3593 if formats or subtitles:
aa9369a2 3594 self.report_detected('video.js embed')
63d990d2
S
3595 self._sort_formats(formats)
3596 info_dict['formats'] = formats
da1c94ee 3597 info_dict['subtitles'] = subtitles
63d990d2
S
3598 return info_dict
3599
ff17be3a 3600 # Looking for http://schema.org/VideoObject
fa0b816e 3601 json_ld = self._search_json_ld(webpage, video_id, default={})
ff17be3a 3602 if json_ld.get('url'):
aa9369a2 3603 self.report_detected('JSON LD')
ff17be3a
S
3604 return merge_dicts(json_ld, info_dict)
3605
ced659bb 3606 def check_video(vurl):
a0f71985
PH
3607 if YoutubeIE.suitable(vurl):
3608 return True
b7a8c1bc
S
3609 if RtmpIE.suitable(vurl):
3610 return True
ced659bb
S
3611 vpath = compat_urlparse.urlparse(vurl).path
3612 vext = determine_ext(vpath)
0ee79a37 3613 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
3614
3615 def filter_video(urls):
3616 return list(filter(check_video, urls))
3617
9b122384 3618 # Start with something easy: JW Player in SWFObject
ced659bb 3619 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
aa9369a2 3620 if found:
3621 self.report_detected('JW Player in SFWObject')
3622 else:
d981cef6 3623 # Look for gorilla-vid style embedding
ced659bb 3624 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
3625 (?:
3626 jw_plugins|
3627 JWPlayerOptions|
3628 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3629 )
a0f71985
PH
3630 .*?
3631 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
aa9369a2 3632 if found:
3633 self.report_detected('JW Player embed')
a318f59d 3634 if not found:
3635 # Look for generic KVS player
3636 found = re.search(r'<script [^>]*?src="https://.+?/kt_player\.js\?v=(?P<ver>(?P<maj_ver>\d+)(\.\d+)+)".*?>', webpage)
3637 if found:
aa9369a2 3638 self.report_detected('KWS Player')
a318f59d 3639 if found.group('maj_ver') not in ['4', '5']:
3640 self.report_warning('Untested major version (%s) in player engine--Download may fail.' % found.group('ver'))
3641 flashvars = re.search(r'(?ms)<script.*?>.*?var\s+flashvars\s*=\s*(\{.*?\});.*?</script>', webpage)
3642 flashvars = self._parse_json(flashvars.group(1), video_id, transform_source=js_to_json)
3643
3644 # extract the part after the last / as the display_id from the
3645 # canonical URL.
3646 display_id = self._search_regex(
3647 r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
3648 r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
3649 webpage, 'display_id', fatal=False
3650 )
3651 title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
3652
3653 thumbnail = flashvars['preview_url']
3654 if thumbnail.startswith('//'):
3655 protocol, _, _ = url.partition('/')
3656 thumbnail = protocol + thumbnail
3657
3658 formats = []
3659 for key in ('video_url', 'video_alt_url', 'video_alt_url2'):
3660 if key in flashvars and '/get_file/' in flashvars[key]:
3661 next_format = {
3662 'url': self._kvs_getrealurl(flashvars[key], flashvars['license_code']),
3663 'format_id': flashvars.get(key + '_text', key),
3664 'ext': 'mp4',
3665 }
3666 height = re.search(r'%s_(\d+)p\.mp4(?:/[?].*)?$' % flashvars['video_id'], flashvars[key])
3667 if height:
3668 next_format['height'] = int(height.group(1))
3669 else:
3670 next_format['quality'] = 1
3671 formats.append(next_format)
3672 self._sort_formats(formats)
3673
3674 return {
3675 'id': flashvars['video_id'],
3676 'display_id': display_id,
3677 'title': title,
3678 'thumbnail': thumbnail,
3679 'formats': formats,
3680 }
b30b8698 3681 if not found:
9b122384 3682 # Broaden the search a little bit
ced659bb 3683 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
aa9369a2 3684 if found:
3685 self.report_detected('video file')
b30b8698
PH
3686 if not found:
3687 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 3688 found = filter_video(re.findall(
54a9328b 3689 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
aa9369a2 3690 if found:
3691 self.report_detected('JW Player JS loader')
4d805e06
PH
3692 if not found:
3693 # Flow player
ced659bb 3694 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
3695 flowplayer\("[^"]+",\s*
3696 \{[^}]+?\}\s*,
52585fd6 3697 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 3698 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 3699 ''', webpage))
aa9369a2 3700 if found:
3701 self.report_detected('Flow Player')
501f13fb
PH
3702 if not found:
3703 # Cinerama player
3704 found = re.findall(
3705 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
aa9369a2 3706 if found:
3707 self.report_detected('Cinerama player')
b30b8698 3708 if not found:
9b122384 3709 # Try to find twitter cards info
371ddb14
S
3710 # twitter:player:stream should be checked before twitter:player since
3711 # it is expected to contain a raw stream (see
3712 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3713 found = filter_video(re.findall(
3714 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
aa9369a2 3715 if found:
3716 self.report_detected('Twitter card')
b30b8698 3717 if not found:
9b122384
PH
3718 # We look for Open Graph info:
3719 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3720 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3721 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3722 if m_video_type is not None:
b73612a2 3723 found = filter_video(re.findall(r'<meta.*?property="og:(?:video|audio)".*?content="(.*?)"', webpage))
aa9369a2 3724 if found:
3725 self.report_detected('Open Graph video info')
b30b8698 3726 if not found:
ed9a25dd 3727 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3728 found = re.search(
89ef304b 3729 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3730 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3731 webpage)
84f81016
S
3732 if not found:
3733 # Look also in Refresh HTTP header
3734 refresh_header = head_response.headers.get('Refresh')
3735 if refresh_header:
6c91a5a7
S
3736 # In python 2 response HTTP headers are bytestrings
3737 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3738 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3739 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3740 if found:
b37317d8 3741 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3742 if new_url != url:
3743 self.report_following_redirect(new_url)
3744 return {
3745 '_type': 'url',
3746 'url': new_url,
3747 }
3748 else:
3749 found = None
371ddb14
S
3750
3751 if not found:
3752 # twitter:player is a https URL to iframe player that may or may not
7a5c1cfe 3753 # be supported by yt-dlp thus this is checked the very last (see
371ddb14
S
3754 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3755 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3756 if embed_url and embed_url != url:
aa9369a2 3757 self.report_detected('twitter:player iframe')
371ddb14
S
3758 return self.url_result(embed_url)
3759
b30b8698 3760 if not found:
416c7fcb 3761 raise UnsupportedError(url)
9b122384 3762
b30b8698 3763 entries = []
4a120778 3764 for video_url in orderedSet(found):
949b6497 3765 video_url = unescapeHTML(video_url)
6cc37c69 3766 video_url = video_url.replace('\\/', '/')
b30b8698 3767 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3768 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3769
b30b8698
PH
3770 # Sometimes, jwplayer extraction will result in a YouTube URL
3771 if YoutubeIE.suitable(video_url):
3772 entries.append(self.url_result(video_url, 'Youtube'))
3773 continue
9b122384 3774
b30b8698
PH
3775 # here's a fun little line of code for you:
3776 video_id = os.path.splitext(video_id)[0]
fc9713a1 3777
28602e74
YCH
3778 entry_info_dict = {
3779 'id': video_id,
3780 'uploader': video_uploader,
3781 'title': video_title,
3782 'age_limit': age_limit,
3783 }
3784
5620f840
S
3785 if RtmpIE.suitable(video_url):
3786 entry_info_dict.update({
3787 '_type': 'url_transparent',
3788 'ie_key': RtmpIE.ie_key(),
3789 'url': video_url,
3790 })
3791 entries.append(entry_info_dict)
3792 continue
3793
729accb4
S
3794 ext = determine_ext(video_url)
3795 if ext == 'smil':
da1c94ee 3796 entry_info_dict = {**self._extract_smil_info(video_url, video_id), **entry_info_dict}
729accb4
S
3797 elif ext == 'xspf':
3798 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0 3799 elif ext == 'm3u8':
da1c94ee 3800 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(video_url, video_id, ext='mp4')
79a35085 3801 elif ext == 'mpd':
da1c94ee 3802 entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_mpd_formats_and_subtitles(video_url, video_id)
3f2f4a94
S
3803 elif ext == 'f4m':
3804 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3805 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3806 # Just matching .ism/manifest is not enough to be reliably sure
3807 # whether it's actually an ISM manifest or some other streaming
3808 # manifest since there are various streaming URL formats
3809 # possible (see [1]) as well as some other shenanigans like
3810 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3811 # so on.
3812 # Thus the most reasonable way to solve this is to delegate
3813 # to generic extractor in order to look into the contents of
3814 # the manifest itself.
3815 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3816 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3817 entry_info_dict = self.url_result(
3818 smuggle_url(video_url, {'to_generic': True}),
3819 GenericIE.ie_key())
d6fd958c 3820 else:
28602e74
YCH
3821 entry_info_dict['url'] = video_url
3822
19dbaeec
S
3823 if entry_info_dict.get('formats'):
3824 self._sort_formats(entry_info_dict['formats'])
3825
28602e74 3826 entries.append(entry_info_dict)
b30b8698
PH
3827
3828 if len(entries) == 1:
669f0e7c 3829 return entries[0]
b30b8698
PH
3830 else:
3831 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3832 # 'url' results don't have a title
3833 if e.get('title') is not None:
3834 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3835 return {
3836 '_type': 'playlist',
3837 'entries': entries,
3838 }