]> jfr.im git - yt-dlp.git/blame - youtube_dlc/extractor/generic.py
Updated to release 2020.11.21.1
[yt-dlp.git] / youtube_dlc / 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,
61ca9a80 23 is_html,
a4a554a7 24 js_to_json,
63d990d2 25 KNOWN_EXTENSIONS,
6cc62232 26 merge_dicts,
63d990d2 27 mimetype2ext,
ed2d6a19 28 orderedSet,
5c2266df 29 sanitized_Request,
9d4660ca
PH
30 smuggle_url,
31 unescapeHTML,
42393ce2 32 unified_strdate,
4d54ef20 33 unsmuggle_url,
416c7fcb 34 UnsupportedError,
76c73715 35 xpath_text,
9b122384 36)
b7a8c1bc 37from .commonprotocols import RtmpIE
ed126900 38from .brightcove import (
4fcaa4f4 39 BrightcoveLegacyIE,
5c17f0a6 40 BrightcoveNewIE,
ed126900 41)
3f59b015
S
42from .nexx import (
43 NexxIE,
44 NexxEmbedIE,
45)
a2edf2e7 46from .nbc import NBCSportsVPlayerIE
c0d0b01f 47from .ooyala import OoyalaIE
93d020dd 48from .rutv import RUTVIE
954c1d05 49from .tvc import TVCIE
476cf548 50from .sportbox import SportBoxIE
cb3ac1c6 51from .smotri import SmotriIE
6dd94d3a 52from .myvi import MyviIE
1419fafd 53from .condenast import CondeNastIE
418c5cc3 54from .udn import UDNEmbedIE
2fe1b5bd 55from .senateisvp import SenateISVPIE
bab19a8e 56from .svt import SVTIE
65d161c4 57from .pornhub import PornHubIE
2bb5b6d0 58from .xhamster import XHamsterEmbedIE
2c9ca782 59from .tnaflix import TNAFlixNetworkEmbedIE
37e7a71c 60from .drtuber import DrTuberIE
e28ed498 61from .redtube import RedTubeIE
06993715 62from .tube8 import Tube8IE
4e7b5bba 63from .mofosex import MofosexEmbedIE
8fae1a04 64from .spankwire import SpankwireIE
52c4c515 65from .youporn import YouPornIE
b407e173 66from .vimeo import VimeoIE
3c4fbfec 67from .dailymotion import DailymotionIE
71a1db89 68from .dailymail import DailyMailIE
1ac1c4c2 69from .onionstudios import OnionStudiosIE
67167920 70from .viewlift import ViewLiftEmbedIE
46fde8a1 71from .mtv import MTVServicesEmbeddedIE
45dad7ba 72from .pladform import PladformIE
ff18735c 73from .videomore import VideomoreIE
83f1481b 74from .webcaster import WebcasterFeedIE
5b251628 75from .googledrive import GoogleDriveIE
7cb09524 76from .jwplatform import JWPlatformIE
aecfcd4e 77from .digiteka import DigitekaIE
1979969f 78from .arkena import ArkenaIE
5a51775a 79from .instagram import InstagramIE
b8f67449 80from .liveleak import LiveLeakIE
5d39176f 81from .threeqsdn import ThreeQSDNIE
4d8819d2 82from .theplatform import ThePlatformIE
c287f2bc 83from .kaltura import KalturaIE
06a96da1 84from .eagleplatform import EaglePlatformIE
fd6ca382 85from .facebook import FacebookIE
548c3957 86from .soundcloud import SoundcloudEmbedIE
027e2312 87from .tunein import TuneInBaseIE
2a1321a2 88from .vbox7 import Vbox7IE
b0c8f2e9 89from .dbtv import DBTVIE
b1c35797 90from .piksel import PikselIE
e186a9ec 91from .videa import VideaIE
b687c85e 92from .twentymin import TwentyMinutenIE
d77ac737 93from .ustream import UstreamIE
8bdd16b4 94from .arte import ArteTVEmbedIE
6ef3e65a 95from .videopress import VideoPressIE
eb3079b6 96from .rutube import RutubeIE
e5d39886 97from .limelight import LimelightBaseIE
7986c3ab 98from .anvato import AnvatoIE
55719459 99from .washingtonpost import WashingtonPostIE
58bb4402 100from .wistia import WistiaIE
5d29af3d 101from .mediaset import MediasetIE
73cf76a9 102from .joj import JojIE
24e966e8 103from .megaphone import MegaphoneIE
41918eaa 104from .vzaar import VzaarIE
26bae2d9 105from .channel9 import Channel9IE
0987f2dd 106from .vshare import VShareIE
2ca7ed41 107from .mediasite import MediasiteIE
7d540621 108from .springboardplatform import SpringboardPlatformIE
4c780fbd 109from .yapfiles import YapFilesIE
86c8cfc5 110from .vice import ViceIE
178ee883 111from .xfileshare import XFileShareIE
660a230b 112from .cloudflarestream import CloudflareStreamIE
6bd499e8 113from .peertube import PeerTubeIE
5ee7ae5c 114from .teachable import TeachableIE
aee36ca8 115from .indavideo import IndavideoEmbedIE
cfd7f2a6 116from .apa import APAIE
f51f526b 117from .foxnews import FoxNewsIE
9d1b2138 118from .viqeo import ViqeoIE
57c68ec4 119from .expressen import ExpressenIE
83852e57 120from .zype import ZypeIE
416c3ca7 121from .odnoklassniki import OdnoklassnikiIE
55adb63e 122from .kinja import KinjaEmbedIE
9b122384 123
0838239e 124
9b122384 125class GenericIE(InfoExtractor):
79649588 126 IE_DESC = 'Generic downloader that works on some sites'
9b122384 127 _VALID_URL = r'.*'
79649588 128 IE_NAME = 'generic'
cfe50f04 129 _TESTS = [
c5fa81fe
S
130 # Direct link to a video
131 {
132 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
133 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
134 'info_dict': {
135 'id': 'trailer',
136 'ext': 'mp4',
137 'title': 'trailer',
138 'upload_date': '20100513',
139 }
140 },
c5138a7c 141 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
142 {
143 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
144 'md5': '128c42e68b13950268b648275386fc74',
145 'info_dict': {
146 'id': 'FictionJunction-Parallel_Hearts',
147 'ext': 'flac',
148 'title': 'FictionJunction-Parallel_Hearts',
149 'upload_date': '20140522',
150 },
151 'expected_warnings': [
152 'URL could be a direct video link, returning it as such.'
39efc6e3
YCH
153 ],
154 'skip': 'URL invalid',
c5fa81fe
S
155 },
156 # Direct download with broken HEAD
157 {
158 'url': 'http://ai-radio.org:8000/radio.opus',
159 'info_dict': {
160 'id': 'radio',
161 'ext': 'opus',
162 'title': 'radio',
163 },
164 'params': {
165 'skip_download': True, # infinite live stream
166 },
167 'expected_warnings': [
ef0e4e7b
YCH
168 r'501.*Not Implemented',
169 r'400.*Bad Request',
c5fa81fe
S
170 ],
171 },
172 # Direct link with incorrect MIME type
173 {
174 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
175 'md5': '4ccbebe5f36706d85221f204d7eb5913',
176 'info_dict': {
177 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
178 'id': '5_Lennart_Poettering_-_Systemd',
179 'ext': 'webm',
180 'title': '5_Lennart_Poettering_-_Systemd',
181 'upload_date': '20141120',
182 },
183 'expected_warnings': [
184 'URL could be a direct video link, returning it as such.'
185 ]
186 },
187 # RSS feed
188 {
189 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
190 'info_dict': {
191 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
192 'title': 'Zero Punctuation',
193 'description': 're:.*groundbreaking video review series.*'
194 },
195 'playlist_mincount': 11,
196 },
197 # RSS feed with enclosure
198 {
199 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
200 'info_dict': {
201 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
202 'ext': 'm4v',
203 'upload_date': '20150228',
204 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
205 }
206 },
01aec848
BG
207 # RSS feed with enclosures and unsupported link URLs
208 {
209 'url': 'http://www.hellointernet.fm/podcast?format=rss',
210 'info_dict': {
211 'id': 'http://www.hellointernet.fm/podcast?format=rss',
212 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
213 'title': 'Hello Internet',
214 },
215 'playlist_mincount': 100,
216 },
8765222d
S
217 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
218 {
219 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
220 'info_dict': {
221 'id': 'smil',
222 'ext': 'mp4',
223 'title': 'Automatics, robotics and biocybernetics',
224 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 225 'upload_date': '20130627',
8765222d
S
226 'formats': 'mincount:16',
227 'subtitles': 'mincount:1',
228 },
229 'params': {
230 'force_generic_extractor': True,
231 'skip_download': True,
232 },
233 },
234 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
235 {
236 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
237 'info_dict': {
238 'id': 'hds',
239 'ext': 'flv',
240 'title': 'hds',
241 'formats': 'mincount:1',
242 },
243 'params': {
244 'skip_download': True,
245 },
246 },
247 # SMIL from https://www.restudy.dk/video/play/id/1637
248 {
249 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
250 'info_dict': {
251 'id': 'video_1637',
252 'ext': 'flv',
253 'title': 'video_1637',
254 'formats': 'mincount:3',
255 },
256 'params': {
257 'skip_download': True,
258 },
259 },
260 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
261 {
262 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
263 'info_dict': {
264 'id': 'smil-service',
265 'ext': 'flv',
266 'title': 'smil-service',
267 'formats': 'mincount:1',
268 },
269 'params': {
270 'skip_download': True,
271 },
272 },
273 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
274 {
275 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
276 'info_dict': {
277 'id': '4719370',
278 'ext': 'mp4',
279 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
280 'formats': 'mincount:3',
281 },
282 'params': {
283 'skip_download': True,
284 },
285 },
1de5cd3b
S
286 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
287 {
288 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
289 'info_dict': {
290 'id': 'mZlp2ctYIUEB',
291 'ext': 'mp4',
292 'title': 'Tikibad ontruimd wegens brand',
293 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
ec85ded8 294 'thumbnail': r're:^https?://.*\.jpg$',
1de5cd3b
S
295 'duration': 33,
296 },
297 'params': {
298 'skip_download': True,
299 },
300 },
9d939cec
S
301 # MPD from http://dash-mse-test.appspot.com/media.html
302 {
303 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
304 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
305 'info_dict': {
306 'id': 'car-20120827-manifest',
307 'ext': 'mp4',
308 'title': 'car-20120827-manifest',
309 'formats': 'mincount:9',
0738187f 310 'upload_date': '20130904',
9d939cec
S
311 },
312 'params': {
313 'format': 'bestvideo',
314 },
315 },
20938f76
S
316 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
317 {
318 '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',
319 'info_dict': {
320 'id': 'content',
321 'ext': 'mp4',
322 'title': 'content',
323 'formats': 'mincount:8',
324 },
325 'params': {
326 # m3u8 downloads
327 'skip_download': True,
39efc6e3
YCH
328 },
329 'skip': 'video gone',
20938f76 330 },
edd9b71c
S
331 # m3u8 served with Content-Type: text/plain
332 {
333 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
334 'info_dict': {
335 'id': 'index',
336 'ext': 'mp4',
337 'title': 'index',
338 'upload_date': '20140720',
339 'formats': 'mincount:11',
340 },
341 'params': {
342 # m3u8 downloads
343 'skip_download': True,
39efc6e3
YCH
344 },
345 'skip': 'video gone',
edd9b71c 346 },
c5fa81fe
S
347 # google redirect
348 {
349 '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',
350 'info_dict': {
351 'id': 'cmQHVoWB5FY',
352 'ext': 'mp4',
353 'upload_date': '20130224',
354 'uploader_id': 'TheVerge',
ec85ded8 355 'description': r're:^Chris Ziegler takes a look at the\.*',
c5fa81fe
S
356 'uploader': 'The Verge',
357 'title': 'First Firefox OS phones side-by-side',
358 },
359 'params': {
360 'skip_download': False,
361 }
362 },
6c91a5a7
S
363 {
364 # redirect in Refresh HTTP header
365 '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',
366 'info_dict': {
367 'id': 'pO8h3EaFRdo',
368 'ext': 'mp4',
369 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
370 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
371 'upload_date': '20150917',
372 'uploader_id': 'brtvofficial',
373 'uploader': 'Boiler Room',
374 },
375 'params': {
376 'skip_download': False,
377 },
378 },
cfe50f04 379 {
79649588 380 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 381 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 382 'info_dict': {
d360a146
S
383 'id': '13601338388002',
384 'ext': 'mp4',
79649588
PH
385 'uploader': 'www.hodiho.fr',
386 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
387 }
388 },
c19f7764
JMF
389 # bandcamp page with custom domain
390 {
79649588
PH
391 'add_ie': ['Bandcamp'],
392 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 393 'info_dict': {
fd50bf62
S
394 'id': '3235767654',
395 'ext': 'mp3',
79649588
PH
396 'title': 'The Pony Mash',
397 'uploader': 'M_Pallante',
c19f7764 398 },
79649588 399 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 400 },
eeb165e6 401 {
53a664ed
S
402 # embedded brightcove video
403 # it also tests brightcove videos that need to set the 'Referer'
404 # in the http requests
3b7d9aa4 405 'add_ie': ['BrightcoveLegacy'],
79649588
PH
406 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
407 'info_dict': {
408 'id': '2765128793001',
409 'ext': 'mp4',
410 'title': 'Le cours de bourse : l’analyse technique',
411 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
412 'uploader': 'BFM BUSINESS',
eeb165e6 413 },
79649588
PH
414 'params': {
415 'skip_download': True,
eeb165e6
JMF
416 },
417 },
53a664ed
S
418 {
419 # embedded with itemprop embedURL and video id spelled as `idVideo`
420 'add_id': ['BrightcoveLegacy'],
421 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
422 'info_dict': {
423 'id': '5255628253001',
424 'ext': 'mp4',
425 'title': 'md5:37c519b1128915607601e75a87995fc0',
426 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
427 'uploader': 'BFM BUSINESS',
428 'uploader_id': '876450612001',
429 'timestamp': 1482255315,
430 'upload_date': '20161220',
431 },
432 'params': {
433 'skip_download': True,
434 },
435 },
17ab4d3b 436 {
067aa17e 437 # https://github.com/ytdl-org/youtube-dl/issues/2253
17ab4d3b 438 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
439 'md5': '0ba9446db037002366bab3b3eb30c88c',
440 'info_dict': {
fd50bf62
S
441 'id': '3101154703001',
442 'ext': 'mp4',
17ab4d3b
PH
443 'title': 'Still no power',
444 'uploader': 'thestar.com',
445 '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.',
446 },
3b7d9aa4 447 'add_ie': ['BrightcoveLegacy'],
39efc6e3 448 'skip': 'video gone',
17ab4d3b 449 },
0479c625
S
450 {
451 'url': 'http://www.championat.com/video/football/v/87/87499.html',
452 'md5': 'fb973ecf6e4a78a67453647444222983',
453 'info_dict': {
454 'id': '3414141473001',
455 'ext': 'mp4',
456 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
457 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
458 'uploader': 'Championat',
459 },
460 },
bdf97017 461 {
067aa17e 462 # https://github.com/ytdl-org/youtube-dl/issues/3541
3b7d9aa4 463 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
464 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
465 'info_dict': {
466 'id': '3866516442001',
37aab278 467 'ext': 'mp4',
bdf97017
NJ
468 'title': 'Leer mij vrouwen kennen: Aflevering 1',
469 'description': 'Leer mij vrouwen kennen: Aflevering 1',
470 'uploader': 'SBS Broadcasting',
471 },
37aab278 472 'skip': 'Restricted to Netherlands',
bdf97017 473 'params': {
37aab278 474 'skip_download': True, # m3u8 download
bdf97017
NJ
475 },
476 },
06d0ad9a
YCH
477 {
478 # Brightcove video in <iframe>
479 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
480 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
481 'info_dict': {
482 'id': '5360463607001',
483 'ext': 'mp4',
484 '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',
485 '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。',
486 'uploader': 'United Nations',
487 'uploader_id': '1362235914001',
488 'timestamp': 1489593889,
489 'upload_date': '20170315',
490 },
491 'add_ie': ['BrightcoveLegacy'],
492 },
16e2c8f7
YCH
493 {
494 # Brightcove with alternative playerID key
495 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
496 'info_dict': {
497 'id': 'nmeth.2062_SV1',
498 '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',
499 },
500 'playlist': [{
501 'info_dict': {
502 'id': '2228375078001',
503 'ext': 'mp4',
504 'title': 'nmeth.2062-sv1',
505 'description': 'nmeth.2062-sv1',
506 'timestamp': 1363357591,
507 'upload_date': '20130315',
508 'uploader': 'Nature Publishing Group',
509 'uploader_id': '1964492299001',
510 },
511 }],
512 },
40158f55
JH
513 {
514 # Brightcove with UUID in videoPlayer
515 'url': 'http://www8.hp.com/cn/zh/home.html',
516 'info_dict': {
517 'id': '5255815316001',
518 'ext': 'mp4',
519 'title': 'Sprocket Video - China',
520 'description': 'Sprocket Video - China',
521 'uploader': 'HP-Video Gallery',
522 'timestamp': 1482263210,
523 'upload_date': '20161220',
524 'uploader_id': '1107601872001',
525 },
526 'params': {
527 'skip_download': True, # m3u8 download
528 },
529 'skip': 'video rotates...weekly?',
530 },
531 {
532 # Brightcove:new type [2].
533 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
534 'md5': '2b35148fcf48da41c9fb4591650784f3',
535 'info_dict': {
536 'id': '5348741021001',
537 'ext': 'mp4',
538 'upload_date': '20170306',
539 'uploader_id': '4191638492001',
540 'timestamp': 1488769918,
541 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
542
543 },
544 },
545 {
546 # Alternative brightcove <video> attributes
547 '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/',
548 'info_dict': {
549 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
550 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
551 },
552 'playlist': [{
553 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
554 'info_dict': {
555 'id': '5311302538001',
556 'ext': 'mp4',
557 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
558 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
559 'timestamp': 1486321708,
560 'upload_date': '20170205',
561 'uploader_id': '800000640001',
562 },
563 'only_matching': True,
564 }],
565 },
b68a812e
S
566 {
567 # Brightcove with UUID in videoPlayer
568 'url': 'http://www8.hp.com/cn/zh/home.html',
569 'info_dict': {
570 'id': '5255815316001',
571 'ext': 'mp4',
572 'title': 'Sprocket Video - China',
573 'description': 'Sprocket Video - China',
574 'uploader': 'HP-Video Gallery',
575 'timestamp': 1482263210,
576 'upload_date': '20161220',
577 'uploader_id': '1107601872001',
578 },
579 'params': {
580 'skip_download': True, # m3u8 download
581 },
582 },
c0d0b01f
JMF
583 # ooyala video
584 {
79649588 585 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 586 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
587 'info_dict': {
588 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
589 'ext': 'mp4',
3486df38 590 'title': '2cc213299525360.mov', # that's what we get
53e06b25 591 'duration': 238.231,
c0d0b01f 592 },
87830900 593 'add_ie': ['Ooyala'],
c0d0b01f 594 },
bf94d763
S
595 {
596 # ooyala video embedded with http://player.ooyala.com/iframe.js
597 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
598 'info_dict': {
599 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
600 'ext': 'mp4',
601 'title': '"Steve Jobs: Man in the Machine" trailer',
602 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 603 'duration': 135.427,
bf94d763
S
604 },
605 'params': {
606 'skip_download': True,
607 },
39efc6e3 608 'skip': 'movie expired',
bf94d763 609 },
198d4cb4
GR
610 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
611 {
612 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
613 'info_dict': {
614 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
615 'ext': 'mp4',
616 'title': 'Steampunk Fest Comes to Honesdale',
617 'duration': 43.276,
618 },
619 'params': {
620 'skip_download': True,
621 }
622 },
1b86cc41 623 # embed.ly video
624 {
625 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
626 'info_dict': {
627 'id': '9ODmcdjQcHQ',
628 'ext': 'mp4',
0a5bce56
PH
629 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
630 'upload_date': '20140225',
631 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
632 'uploader': 'Tested',
633 'uploader_id': 'testedcom',
1b86cc41 634 },
635 # No need to test YoutubeIE here
636 'params': {
637 'skip_download': True,
638 },
639 },
60cc4dc4
PH
640 # funnyordie embed
641 {
642 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
643 'info_dict': {
644 'id': '18e820ec3f',
645 'ext': 'mp4',
646 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
647 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 648 },
39efc6e3
YCH
649 # HEAD requests lead to endless 301, while GET is OK
650 'expected_warnings': ['301'],
60cc4dc4 651 },
93d020dd
S
652 # RUTV embed
653 {
654 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
655 'info_dict': {
656 'id': '776940',
657 'ext': 'mp4',
658 'title': 'Охотское море стало целиком российским',
659 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
660 },
661 'params': {
662 # m3u8 download
663 'skip_download': True,
664 },
aab74fa1 665 },
f37bdbe5
S
666 # TVC embed
667 {
668 '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/',
669 'info_dict': {
670 'id': '55304',
671 'ext': 'mp4',
672 'title': 'Дошкольное воспитание',
673 },
674 },
b827a601
S
675 # SportBox embed
676 {
677 'url': 'http://www.vestifinance.ru/articles/25753',
678 'info_dict': {
679 'id': '25753',
05d1e7aa 680 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
b827a601
S
681 },
682 'playlist': [{
683 'info_dict': {
684 'id': '370908',
685 'title': 'Госзаказ. День 3',
686 'ext': 'mp4',
687 }
688 }, {
689 'info_dict': {
690 'id': '370905',
691 'title': 'Госзаказ. День 2',
692 'ext': 'mp4',
693 }
694 }, {
695 'info_dict': {
696 'id': '370902',
697 'title': 'Госзаказ. День 1',
698 'ext': 'mp4',
699 }
700 }],
701 'params': {
702 # m3u8 download
703 'skip_download': True,
704 },
705 },
bf20b9c5
S
706 # Myvi.ru embed
707 {
708 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
709 'info_dict': {
710 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
711 'ext': 'mp4',
712 'title': 'Ужастики, русский трейлер (2015)',
ec85ded8 713 'thumbnail': r're:^https?://.*\.jpg$',
bf20b9c5
S
714 'duration': 153,
715 }
716 },
c76799c5
S
717 # XHamster embed
718 {
719 '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',
720 'info_dict': {
721 'id': 'showthread',
722 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
723 },
724 'playlist_mincount': 7,
39efc6e3
YCH
725 # This forum does not allow <iframe> syntaxes anymore
726 # Now HTML tags are displayed as-is
727 'skip': 'No videos on this page',
c76799c5 728 },
aab74fa1
PH
729 # Embedded TED video
730 {
731 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 732 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 733 'info_dict': {
a8eb5a8e 734 'id': '1969',
aab74fa1 735 'ext': 'mp4',
a8eb5a8e
PH
736 'title': 'Hidden miracles of the natural world',
737 'uploader': 'Louie Schwartzberg',
738 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 739 }
60cc4dc4 740 },
d95e35d6
S
741 # nowvideo embed hidden behind percent encoding
742 {
743 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
744 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
745 'info_dict': {
746 'id': '06e53103ca9aa',
747 'ext': 'flv',
748 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
749 'description': 'No description',
750 },
0f2a2ba1 751 },
893f8832
PH
752 # arte embed
753 {
754 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
755 'md5': '7653032cbb25bf6c80d80f217055fa43',
756 'info_dict': {
757 'id': '048195-004_PLUS7-F',
758 'ext': 'flv',
759 'title': 'X:enius',
760 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
761 'upload_date': '20140320',
762 },
763 'params': {
764 'skip_download': 'Requires rtmpdump'
39efc6e3
YCH
765 },
766 'skip': 'video gone',
893f8832 767 },
cbd55ade
S
768 # francetv embed
769 {
770 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
771 'info_dict': {
772 'id': 'EV_30231',
773 'ext': 'mp4',
774 'title': 'Alcaline, le concert avec Calogero',
775 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
776 'upload_date': '20150226',
777 'timestamp': 1424989860,
778 'duration': 5400,
779 },
780 'params': {
781 # m3u8 downloads
782 'skip_download': True,
783 },
784 'expected_warnings': [
785 'Forbidden'
786 ]
787 },
fa35cdad
PH
788 # Condé Nast embed
789 {
790 'url': 'http://www.wired.com/2014/04/honda-asimo/',
791 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
792 'info_dict': {
793 'id': '53501be369702d3275860000',
794 'ext': 'mp4',
795 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
796 }
ebd3c7b3
PH
797 },
798 # Dailymotion embed
799 {
800 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
801 'md5': '441aeeb82eb72c422c7f14ec533999cd',
802 'info_dict': {
803 'id': 'k2mm4bCdJ6CQ2i7c8o2',
804 'ext': 'mp4',
805 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 806 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 807 'uploader': 'Spi0n',
0738187f
YCH
808 'uploader_id': 'xgditw',
809 'upload_date': '20140425',
810 'timestamp': 1398441542,
ebd3c7b3
PH
811 },
812 'add_ie': ['Dailymotion'],
2b88feed 813 },
71a1db89
S
814 # DailyMail embed
815 {
816 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
817 'info_dict': {
818 'id': '1495629',
819 'ext': 'mp4',
820 'title': 'Care worker punches elderly dementia patient in head 11 times',
821 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
822 },
823 'add_ie': ['DailyMail'],
824 'params': {
825 'skip_download': True,
826 },
827 },
2b88feed
PH
828 # YouTube embed
829 {
830 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
831 'info_dict': {
832 'id': 'FXRb4ykk4S0',
833 'ext': 'mp4',
834 'title': 'The NBL Auction 2014',
835 'uploader': 'BADMINTON England',
836 'uploader_id': 'BADMINTONEvents',
837 'upload_date': '20140603',
838 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
839 },
840 'add_ie': ['Youtube'],
841 'params': {
842 'skip_download': True,
843 }
844 },
a0566bbf 845 # MTVServices embed
c5cd249e 846 {
1fa309da
YCH
847 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
848 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 849 'info_dict': {
1fa309da 850 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 851 'ext': 'mp4',
1fa309da
YCH
852 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
853 'description': 'Two valets share their love for movie star Liam Neesons.',
05d1e7aa
YCH
854 'timestamp': 1349922600,
855 'upload_date': '20121011',
c5cd249e
JMF
856 },
857 },
61013473 858 # YouTube embed via <data-embed-url="">
859 {
860 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 861 'info_dict': {
a8eb5a8e 862 'id': '4vAffPZIT44',
61013473 863 'ext': 'mp4',
a8eb5a8e 864 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
865 'uploader': 'Gameloft',
866 'uploader_id': 'gameloft',
a8eb5a8e
PH
867 'upload_date': '20140828',
868 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
869 },
870 'params': {
871 'skip_download': True,
61013473 872 }
c8e9a235 873 },
61568e50
JH
874 # YouTube <object> embed
875 {
876 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
877 'md5': '516718101ec834f74318df76259fb3cc',
878 'info_dict': {
879 'id': 'msN87y-iEx0',
880 'ext': 'webm',
881 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
882 'upload_date': '20080526',
883 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
884 'uploader': 'Christopher Sykes',
885 'uploader_id': 'ChristopherJSykes',
886 },
887 'add_ie': ['Youtube'],
888 },
c8e9a235
PH
889 # Camtasia studio
890 {
891 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
892 'playlist': [{
893 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
894 'info_dict': {
895 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
896 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
897 'ext': 'flv',
898 'duration': 2235.90,
899 }
900 }, {
901 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
902 'info_dict': {
903 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
904 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
905 'ext': 'flv',
906 'duration': 2235.93,
907 }
908 }],
909 'info_dict': {
910 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
911 }
4d805e06
PH
912 },
913 # Flowplayer
914 {
915 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
916 'md5': '9d65602bf31c6e20014319c7d07fba27',
917 'info_dict': {
918 'id': '5123ea6d5e5a7',
919 'ext': 'mp4',
920 'age_limit': 18,
921 'uploader': 'www.handjobhub.com',
d6d9186f 922 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 923 }
0990305d 924 },
22a6f150 925 # Multiple brightcove videos
067aa17e 926 # https://github.com/ytdl-org/youtube-dl/issues/2283
22a6f150
PH
927 {
928 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
929 'info_dict': {
930 'id': 'always-never',
931 'title': 'Always / Never - The New Yorker',
932 },
933 'playlist_count': 3,
934 'params': {
935 'extract_flat': False,
936 'skip_download': True,
937 }
1a94ff68
S
938 },
939 # MLB embed
940 {
941 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
942 'md5': '96f09a37e44da40dd083e12d9a683327',
943 'info_dict': {
944 'id': '33322633',
945 'ext': 'mp4',
946 'title': 'Ump changes call to ball',
947 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
948 'duration': 48,
949 'timestamp': 1401537900,
950 'upload_date': '20140531',
ec85ded8 951 'thumbnail': r're:^https?://.*\.jpg$',
1a94ff68
S
952 },
953 },
746c67d7
NJ
954 # Wistia embed
955 {
6c114b12
S
956 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
957 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 958 'info_dict': {
6c114b12 959 'id': '6e2wtrbdaf',
746c67d7 960 'ext': 'mov',
6c114b12
S
961 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
962 'description': 'a Paywall Videos video from Remilon',
963 'duration': 644.072,
964 'uploader': 'study.com',
965 'timestamp': 1459678540,
966 'upload_date': '20160403',
967 'filesize': 24687186,
746c67d7
NJ
968 },
969 },
52cffcb1 970 {
971 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
972 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
973 'info_dict': {
974 'id': 'uxjb0lwrcz',
975 'ext': 'mp4',
6c114b12 976 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 977 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 978 'duration': 1715.0,
85d7b765 979 'uploader': 'thoughtworks.wistia.com',
0738187f 980 'timestamp': 1401832161,
6c114b12 981 'upload_date': '20140603',
70b7e3fb 982 },
52cffcb1 983 },
7ded6545
S
984 # Wistia standard embed (async)
985 {
986 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
987 'info_dict': {
988 'id': '807fafadvk',
989 'ext': 'mp4',
990 'title': 'Drip Brennan Dunn Workshop',
991 'description': 'a JV Webinars video from getdrip-1',
992 'duration': 4986.95,
7ded6545 993 'timestamp': 1463607249,
6c114b12 994 'upload_date': '20160518',
7ded6545
S
995 },
996 'params': {
997 'skip_download': True,
998 }
999 },
ac645ac7
PH
1000 # Soundcloud embed
1001 {
1002 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1003 'info_dict': {
1004 'id': '174391317',
1005 'ext': 'mp3',
1006 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1007 'uploader': 'Sophos Security',
1008 'title': 'Chet Chat 171 - Oct 29, 2014',
1009 'upload_date': '20141029',
1010 }
af63fed7 1011 },
db19df6c
S
1012 # Soundcloud multiple embeds
1013 {
1014 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1015 'info_dict': {
1016 'id': '52809',
1017 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1018 },
1019 'playlist_mincount': 7,
1020 },
027e2312
S
1021 # TuneIn station embed
1022 {
1023 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1024 'info_dict': {
1025 'id': '204146',
1026 'ext': 'mp3',
1027 'title': 'CNRV',
1028 'location': 'Paris, France',
1029 'is_live': True,
1030 },
1031 'params': {
1032 # Live stream
1033 'skip_download': True,
1034 },
1035 },
af63fed7
PH
1036 # Livestream embed
1037 {
1038 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1039 'info_dict': {
1040 'id': '67864563',
1041 'ext': 'flv',
1042 'upload_date': '20141112',
1043 'title': 'Rosetta #CometLanding webcast HL 10',
1044 }
1045 },
78d3b3e2
YCH
1046 # Another Livestream embed, without 'new.' in URL
1047 {
1048 'url': 'https://www.freespeech.org/',
1049 'info_dict': {
1050 'id': '123537347',
1051 'ext': 'mp4',
1052 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1053 },
1054 'params': {
1055 # Live stream
1056 'skip_download': True,
1057 },
1058 },
65f3a228
PH
1059 # LazyYT
1060 {
e8e4cc5a 1061 'url': 'https://skiplagged.com/',
65f3a228 1062 'info_dict': {
e8e4cc5a
JH
1063 'id': 'skiplagged',
1064 'title': 'Skiplagged: The smart way to find cheap flights',
65f3a228 1065 },
e8e4cc5a
JH
1066 'playlist_mincount': 1,
1067 'add_ie': ['Youtube'],
4e262a88 1068 },
42bdd9d0
PH
1069 # Cinchcast embed
1070 {
1071 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1072 'info_dict': {
1073 'id': '7141703',
1074 'ext': 'mp3',
1075 'upload_date': '20141126',
1076 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1077 }
1078 },
501f13fb
PH
1079 # Cinerama player
1080 {
1081 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1082 'info_dict': {
1083 'id': '730m_DandD_1901_512k',
1084 'ext': 'mp4',
1085 'uploader': 'www.abc.net.au',
1086 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1087 }
796df3c6
S
1088 },
1089 # embedded viddler video
1090 {
1091 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1092 'info_dict': {
1093 'id': '4d03aad9',
1094 'ext': 'mp4',
1095 'uploader': 'deadspin',
1096 'title': 'WALL-TO-GORTAT',
1097 'timestamp': 1422285291,
1098 'upload_date': '20150126',
1099 },
1100 'add_ie': ['Viddler'],
a0f71985 1101 },
2051acde
S
1102 # Libsyn embed
1103 {
1104 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1105 'info_dict': {
1106 'id': '3377616',
1107 'ext': 'mp3',
1108 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1109 'description': 'md5:601cb790edd05908957dae8aaa866465',
1110 'upload_date': '20150220',
1111 },
326fa4e6 1112 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
2051acde 1113 },
a0f71985
PH
1114 # jwplayer YouTube
1115 {
1116 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1117 'info_dict': {
1118 'id': 'Mrj4DVp2zeA',
1119 'ext': 'mp4',
f37e3f99 1120 'upload_date': '20150212',
a0f71985 1121 'uploader': 'The National Archives UK',
2637fadc 1122 'description': 'md5:8078af856dca76edc42910b61273dbbf',
a0f71985
PH
1123 'uploader_id': 'NationalArchives08',
1124 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1125 },
59b8ab58 1126 },
5620f840
S
1127 # jwplayer rtmp
1128 {
6899b1d9 1129 'url': 'http://www.suffolk.edu/sjc/live.php',
5620f840 1130 'info_dict': {
6899b1d9 1131 'id': 'live',
5620f840
S
1132 'ext': 'flv',
1133 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1134 'uploader': 'www.suffolk.edu',
1135 },
1136 'params': {
1137 'skip_download': True,
2637fadc 1138 },
6899b1d9 1139 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
5620f840 1140 },
a4a554a7
YCH
1141 # Complex jwplayer
1142 {
1143 'url': 'http://www.indiedb.com/games/king-machine/videos',
1144 'info_dict': {
1145 'id': 'videos',
1146 'ext': 'mp4',
1147 'title': 'king machine trailer 1',
2637fadc 1148 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
a4a554a7
YCH
1149 'thumbnail': r're:^https?://.*\.jpg$',
1150 },
1151 },
03486dbb
RU
1152 {
1153 # JWPlayer config passed as variable
1154 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1155 'info_dict': {
1156 'id': '3326530_hq',
1157 'ext': 'mp4',
1158 'title': 'ARIELE | Tube Cup',
1159 'uploader': 'www.txxx.com',
1160 'age_limit': 18,
1161 },
1162 'params': {
1163 'skip_download': True,
1164 }
1165 },
939be9ad
JH
1166 {
1167 # JWPlatform iframe
1168 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1169 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1170 'info_dict': {
1171 'id': 'O0c5JcKT',
1172 'ext': 'mp4',
1173 'upload_date': '20171122',
1174 'timestamp': 1511366290,
1175 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1176 },
805f5bf7 1177 'add_ie': [JWPlatformIE.ie_key()],
939be9ad 1178 },
63d990d2 1179 {
c5b7014a 1180 # Video.js embed, multiple formats
63d990d2
S
1181 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1182 'info_dict': {
1183 'id': 'yygqldloqIk',
1184 'ext': 'mp4',
1185 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1186 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1187 'upload_date': '20130314',
1188 'uploader': 'PROстое3D',
1189 'uploader_id': 'PROstoe3D',
1190 },
1191 'params': {
1192 'skip_download': True,
1193 },
1194 },
c5b7014a
S
1195 {
1196 # Video.js embed, single format
1197 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1198 'info_dict': {
1199 'id': 'watch',
1200 'ext': 'mp4',
1201 'title': 'Step 1 - Good Foundation',
1202 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1203 },
1204 'params': {
1205 'skip_download': True,
1206 },
1207 },
59b8ab58
PH
1208 # rtl.nl embed
1209 {
1210 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1211 'playlist_mincount': 5,
1212 'info_dict': {
1213 'id': 'aanslagen-kopenhagen',
2637fadc 1214 'title': 'Aanslagen Kopenhagen',
59b8ab58 1215 }
255fca5e
S
1216 },
1217 # Zapiks embed
1218 {
1219 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1220 'info_dict': {
1221 'id': '118046',
1222 'ext': 'mp4',
1223 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1224 }
1225 },
66e568de
S
1226 # Kaltura embed (different embed code)
1227 {
1228 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1229 'info_dict': {
1230 'id': '1_a52wc67y',
1231 'ext': 'flv',
1232 'upload_date': '20150127',
1233 'uploader_id': 'PremierMedia',
1234 'timestamp': int,
1235 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1236 },
1237 },
87703231
YCH
1238 # Kaltura embed with single quotes
1239 {
1240 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1241 'info_dict': {
1242 'id': '0_izeg5utt',
1243 'ext': 'mp4',
1244 'title': '35871',
1245 'timestamp': 1355743100,
1246 'upload_date': '20121217',
e30991f9 1247 'uploader_id': 'cplapp@learn360.com',
87703231
YCH
1248 },
1249 'add_ie': ['Kaltura'],
1250 },
427cd050
S
1251 {
1252 # Kaltura embedded via quoted entry_id
1253 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1254 'info_dict': {
1255 'id': '0_utuok90b',
1256 'ext': 'mp4',
1257 'title': '06_matthew_brender_raj_dutt',
1258 'timestamp': 1466638791,
1259 'upload_date': '20160622',
1260 },
1261 'add_ie': ['Kaltura'],
1262 'expected_warnings': [
1263 'Could not send HEAD request'
1264 ],
1265 'params': {
1266 'skip_download': True,
1267 }
1268 },
8ab7e6c4
YCH
1269 {
1270 # Kaltura embedded, some fileExt broken (#11480)
1271 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1272 'info_dict': {
1273 'id': '1_sgtvehim',
1274 'ext': 'mp4',
1275 'title': 'Our "Standard Models" of particle physics and cosmology',
1276 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1277 'timestamp': 1321158993,
1278 'upload_date': '20111113',
1279 'uploader_id': 'kps1',
1280 },
1281 'add_ie': ['Kaltura'],
1282 },
a01825a5
JH
1283 {
1284 # Kaltura iframe embed
1285 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1286 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1287 'info_dict': {
1288 'id': '0_f2cfbpwy',
1289 'ext': 'mp4',
1290 'title': 'I. M. Pei: A Centennial Celebration',
1291 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1292 'upload_date': '20170403',
1293 'uploader_id': 'batchUser',
1294 'timestamp': 1491232186,
1295 },
1296 'add_ie': ['Kaltura'],
1297 },
c21692fa
S
1298 {
1299 # Kaltura iframe embed, more sophisticated
1300 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1301 'info_dict': {
1302 'id': '1_9gzouybz',
1303 'ext': 'mp4',
1304 'title': 'lecture-05sep2017',
1305 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1306 'upload_date': '20170913',
1307 'uploader_id': 'eps2',
1308 'timestamp': 1505340777,
1309 },
1310 'params': {
1311 'skip_download': True,
1312 },
1313 'add_ie': ['Kaltura'],
1314 },
e30991f9
S
1315 {
1316 # meta twitter:player
1317 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1318 'info_dict': {
1319 'id': '0_01b42zps',
1320 'ext': 'mp4',
1321 'title': 'Main Twerk (Video)',
1322 'upload_date': '20171208',
1323 'uploader_id': 'sebastian.salinas@thechive.com',
1324 'timestamp': 1512713057,
1325 },
1326 'params': {
1327 'skip_download': True,
1328 },
1329 'add_ie': ['Kaltura'],
1330 },
250b042c
S
1331 # referrer protected EaglePlatform embed
1332 {
1333 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1334 'info_dict': {
1335 'id': '582306',
1336 'ext': 'mp4',
1337 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1338 'thumbnail': r're:^https?://.*\.jpg$',
1339 'duration': 3382,
1340 'view_count': int,
1341 },
1342 'params': {
1343 'skip_download': True,
1344 },
135c9c42 1345 },
665e9452 1346 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1347 {
1348 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1349 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1350 'info_dict': {
1351 'id': '12820',
1352 'ext': 'mp4',
1353 'title': "'O Sole Mio",
ec85ded8 1354 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1355 'duration': 216,
1356 'view_count': int,
1357 },
250b042c
S
1358 'params': {
1359 'skip_download': True,
1360 },
2637fadc 1361 'skip': 'This video is unavailable.',
d47ae7f6 1362 },
f8388757
S
1363 # Pladform embed
1364 {
1365 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1366 'info_dict': {
1367 'id': '100183293',
1368 'ext': 'mp4',
62259846 1369 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1370 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1371 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1372 'duration': 694,
1373 'age_limit': 0,
1374 },
2637fadc 1375 'skip': 'HTTP Error 404: Not Found',
f8388757 1376 },
c798f15b
S
1377 # Playwire embed
1378 {
1379 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1380 'info_dict': {
1381 'id': '3519514',
1382 'ext': 'mp4',
1383 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1384 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1385 'duration': 45.115,
1386 },
1387 },
ad320e9b
NJ
1388 # 5min embed
1389 {
1390 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1391 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1392 'info_dict': {
1393 'id': '518726732',
1394 'ext': 'mp4',
1395 'title': 'Facebook Creates "On This Day" | Crunch Report',
2637fadc
RA
1396 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1397 'timestamp': 1427237531,
1398 'uploader': 'Crunch Report',
1399 'upload_date': '20150324',
1400 },
1401 'params': {
1402 # m3u8 download
1403 'skip_download': True,
ad320e9b
NJ
1404 },
1405 },
a4257017
S
1406 # Crooks and Liars embed
1407 {
1408 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1409 'info_dict': {
1410 'id': '8RUoRhRi',
1411 'ext': 'mp4',
1412 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1413 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1414 'timestamp': 1428207000,
1415 'upload_date': '20150405',
1416 'uploader': 'Heather',
1417 },
1418 },
1419 # Crooks and Liars external embed
1420 {
1421 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1422 'info_dict': {
1423 'id': 'MTE3MjUtMzQ2MzA',
1424 'ext': 'mp4',
1425 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1426 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1427 'timestamp': 1265032391,
1428 'upload_date': '20100201',
1429 'uploader': 'Heather',
1430 },
1431 },
facecb84 1432 # NBC Sports vplayer embed
a2edf2e7 1433 {
facecb84 1434 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1435 'info_dict': {
facecb84
S
1436 'id': 'ln7x1qSThw4k',
1437 'ext': 'flv',
1438 'title': "PFT Live: New leader in the 'new-look' defense",
1439 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1440 'uploader': 'NBCU-SPORTS',
1441 'upload_date': '20140107',
1442 'timestamp': 1389118457,
a2edf2e7 1443 },
2637fadc 1444 'skip': 'Invalid Page URL',
418c5cc3 1445 },
de3eb07e
YCH
1446 # NBC News embed
1447 {
1448 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1449 'md5': '1aa589c675898ae6d37a17913cf68d66',
1450 'info_dict': {
2637fadc 1451 'id': 'x_dtl_oa_LettermanliftPR_160608',
de3eb07e 1452 'ext': 'mp4',
2637fadc 1453 'title': 'David Letterman: A Preview',
de3eb07e 1454 '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
1455 'upload_date': '20160609',
1456 'timestamp': 1465431544,
1457 'uploader': 'NBCU-NEWS',
de3eb07e
YCH
1458 },
1459 },
418c5cc3
YCH
1460 # UDN embed
1461 {
811586eb 1462 'url': 'https://video.udn.com/news/300346',
01c58f84 1463 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1464 'info_dict': {
01c58f84 1465 'id': '300346',
418c5cc3 1466 'ext': 'mp4',
01c58f84 1467 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1468 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1469 },
1470 'params': {
1471 # m3u8 download
1472 'skip_download': True,
1473 },
2637fadc 1474 'expected_warnings': ['Failed to parse JSON Expecting value'],
edfcf7ab 1475 },
b26733ba
YCH
1476 # Brightcove URL in single quotes
1477 {
1478 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1479 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1480 'info_dict': {
1481 'id': '4255764656001',
1482 'ext': 'mp4',
1483 'title': 'SN Presents: Russell Martin, World Citizen',
1484 '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.',
1485 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1486 'uploader_id': '1704050871',
1487 'upload_date': '20150525',
1488 'timestamp': 1432570283,
b26733ba 1489 },
756f574e 1490 },
55adb63e 1491 # Kinja embed
8084be78
S
1492 {
1493 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1494 'info_dict': {
55adb63e 1495 'id': '106351',
8084be78
S
1496 'ext': 'mp4',
1497 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
55adb63e 1498 'description': 'Migrated from OnionStudios',
ec85ded8 1499 'thumbnail': r're:^https?://.*\.jpe?g$',
55adb63e
RA
1500 'uploader': 'clickhole',
1501 'upload_date': '20150527',
1502 'timestamp': 1432744860,
8084be78
S
1503 }
1504 },
b8c1cc1a
S
1505 # SnagFilms embed
1506 {
1507 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1508 'info_dict': {
1509 'id': '74849a00-85a9-11e1-9660-123139220831',
1510 'ext': 'mp4',
1511 'title': '#whilewewatch',
1512 }
1513 },
a5158f38
YCH
1514 # AdobeTVVideo embed
1515 {
1516 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1517 'md5': '43662b577c018ad707a63766462b1e87',
1518 'info_dict': {
1519 'id': '2456',
1520 'ext': 'mp4',
1521 'title': 'New experience with Acrobat DC',
1522 'description': 'New experience with Acrobat DC',
1523 'duration': 248.667,
1524 },
1f812580 1525 },
ed126900 1526 # BrightcoveInPageEmbed embed
1527 {
1528 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1529 'info_dict': {
1530 'id': '4238694884001',
1531 'ext': 'flv',
1532 'title': 'Tabletop: Dread, Last Thoughts',
1533 'description': 'Tabletop: Dread, Last Thoughts',
1534 'duration': 51690,
1535 },
750b9ff0 1536 },
d10fe835
YCH
1537 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1538 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1539 {
1540 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1541 'info_dict': {
1542 'id': '4785848093001',
1543 'ext': 'mp4',
1544 'title': 'The Cardinal Pell Interview',
1545 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1546 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1547 'uploader_id': '2733773828001',
1548 'upload_date': '20160304',
1549 'timestamp': 1457083087,
d10fe835
YCH
1550 },
1551 'params': {
1552 # m3u8 downloads
1553 'skip_download': True,
1554 },
1555 },
9edf47df
S
1556 {
1557 # Brightcove embed with whitespace around attribute names
1558 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1559 'info_dict': {
1560 'id': '3167554373001',
1561 'ext': 'mp4',
1562 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1563 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1564 'uploader_id': '1079349493',
1565 'upload_date': '20140207',
1566 'timestamp': 1391810548,
1567 },
1568 'params': {
1569 'skip_download': True,
1570 },
1571 },
134c207e
YCH
1572 # Another form of arte.tv embed
1573 {
1574 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1575 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1576 'info_dict': {
1577 'id': '030273-562_PLUS7-F',
1578 'ext': 'mp4',
1579 'title': 'ARTE Reportage - Nulle part, en France',
1580 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1581 'upload_date': '20160409',
1582 },
1583 },
b8f67449
KM
1584 # LiveLeak embed
1585 {
1586 'url': 'http://www.wykop.pl/link/3088787/',
09747ba7 1587 'md5': '7619da8c820e835bef21a1efa2a0fc71',
b8f67449
KM
1588 'info_dict': {
1589 'id': '874_1459135191',
1590 'ext': 'mp4',
1591 'title': 'Man shows poor quality of new apartment building',
1592 'description': 'The wall is like a sand pile.',
1593 'uploader': 'Lake8737',
09747ba7
YCH
1594 },
1595 'add_ie': [LiveLeakIE.ie_key()],
1596 },
1597 # Another LiveLeak embed pattern (#13336)
1598 {
1599 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1600 'info_dict': {
1601 'id': '2eb_1496309988',
1602 'ext': 'mp4',
1603 'title': 'Thief robs place where everyone was armed',
1604 'description': 'md5:694d73ee79e535953cf2488562288eee',
1605 'uploader': 'brazilwtf',
1606 },
1607 'add_ie': [LiveLeakIE.ie_key()],
b8f67449 1608 },
4a120778
YCH
1609 # Duplicated embedded video URLs
1610 {
1611 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1612 'info_dict': {
1613 'id': '149298443_480_16c25b74_2',
1614 'ext': 'mp4',
1615 'title': 'vs. Blue Orange Spring Game',
1616 'uploader': 'www.hudl.com',
1617 },
1618 },
371ddb14
S
1619 # twitter:player:stream embed
1620 {
1621 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1622 'info_dict': {
1623 'id': 'master',
1624 'ext': 'mp4',
1625 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1626 'uploader': 'www.rtl.be',
1627 },
1628 'params': {
1629 # m3u8 downloads
1630 'skip_download': True,
1631 },
1632 },
32917907
RA
1633 # twitter:player embed
1634 {
1635 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1636 'md5': 'a3e0df96369831de324f0778e126653c',
1637 'info_dict': {
1638 'id': '4909620399001',
1639 'ext': 'mp4',
1640 'title': 'What Do Black Holes Sound Like?',
1641 'description': 'what do black holes sound like',
1642 'upload_date': '20160524',
1643 'uploader_id': '29913724001',
1644 'timestamp': 1464107587,
1645 'uploader': 'TheAtlantic',
1646 },
1647 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1648 },
1649 # Facebook <iframe> embed
1650 {
1651 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1652 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1653 'info_dict': {
1654 'id': '599637780109885',
1655 'ext': 'mp4',
1656 'title': 'Facebook video #599637780109885',
1657 },
1658 },
fd1c5fba
S
1659 # Facebook <iframe> embed, plugin video
1660 {
1661 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1662 'info_dict': {
1663 'id': '1754168231264132',
1664 'ext': 'mp4',
1665 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1666 'uploader': 'Tariq Ramadan (official)',
1667 'timestamp': 1496758379,
1668 'upload_date': '20170606',
1669 },
1670 'params': {
1671 'skip_download': True,
1672 },
1673 },
fd6ca382
YCH
1674 # Facebook API embed
1675 {
1676 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1677 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1678 'info_dict': {
1679 'id': '10153467542406923',
1680 'ext': 'mp4',
1681 'title': 'Facebook video #10153467542406923',
1682 },
7deef1ba
YCH
1683 },
1684 # Wordpress "YouTube Video Importer" plugin
1685 {
1686 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1687 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1688 'info_dict': {
1689 'id': 'HNTXWDXV9Is',
1690 'ext': 'mp4',
1691 'title': 'Blue Devils Drumline Stanford lot 2016',
1692 'upload_date': '20160627',
1693 'uploader_id': 'GENOCIDE8GENERAL10',
1694 'uploader': 'cylus cyrus',
1695 },
1696 },
81953d1a
RA
1697 {
1698 # video stored on custom kaltura server
1699 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1700 'md5': '537617d06e64dfed891fa1593c4b30cc',
1701 'info_dict': {
1702 'id': '0_1iotm5bh',
1703 'ext': 'mp4',
1704 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1705 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1706 'uploader_id': 'videos.expansion@el-mundo.net',
1707 'upload_date': '20150429',
1708 'timestamp': 1430303472,
1709 },
1710 'add_ie': ['Kaltura'],
1711 },
562de77f
S
1712 {
1713 # multiple kaltura embeds, nsfw
1714 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
1715 'info_dict': {
1716 'id': 'kamila-avec-video-jaime-sadomie',
1717 'title': "Kamila avec vídeo “J'aime sadomie”",
1718 },
1719 'playlist_count': 8,
1720 },
c03adf90
YCH
1721 {
1722 # Non-standard Vimeo embed
1723 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1724 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1725 'info_dict': {
1726 'id': '148867247',
1727 'ext': 'mp4',
1728 'title': 'Understanding the web - Teaser',
1729 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1730 'upload_date': '20151214',
1731 'uploader': 'OpenClassrooms',
1732 'uploader_id': 'openclassrooms',
1733 },
1734 'add_ie': ['Vimeo'],
1735 },
a5ff05df
S
1736 {
1737 # generic vimeo embed that requires original URL passed as Referer
1738 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1739 'only_matching': True,
1740 },
1979969f
S
1741 {
1742 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1743 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1744 'info_dict': {
1745 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1746 'ext': 'mp4',
1747 'title': 'Big Buck Bunny',
1748 'description': 'Royalty free test video',
1749 'timestamp': 1432816365,
1750 'upload_date': '20150528',
1751 'is_live': False,
1752 },
1753 'params': {
1754 'skip_download': True,
1755 },
1756 'add_ie': [ArkenaIE.ie_key()],
1757 },
2a1321a2
S
1758 {
1759 '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/',
1760 'info_dict': {
1761 'id': '1c7141f46c',
1762 'ext': 'mp4',
1763 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1764 },
1765 'params': {
1766 'skip_download': True,
1767 },
1768 'add_ie': [Vbox7IE.ie_key()],
1769 },
b0c8f2e9
DR
1770 {
1771 # DBTV embeds
1772 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1773 'info_dict': {
1774 'id': '43254897',
1775 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1776 },
b0c8f2e9
DR
1777 'playlist_mincount': 3,
1778 },
e186a9ec
S
1779 {
1780 # Videa embeds
1781 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1782 'info_dict': {
1783 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1784 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1785 },
1786 'playlist_mincount': 2,
1787 },
b687c85e
S
1788 {
1789 # 20 minuten embed
1790 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1791 'info_dict': {
1792 'id': '523629',
1793 'ext': 'mp4',
1794 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1795 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1796 },
1797 'params': {
1798 'skip_download': True,
1799 },
1800 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1801 },
1802 {
1803 # VideoPress embed
1804 'url': 'https://en.support.wordpress.com/videopress/',
1805 'info_dict': {
1806 'id': 'OcobLTqC',
1807 'ext': 'm4v',
1808 'title': 'IMG_5786',
1809 'timestamp': 1435711927,
1810 'upload_date': '20150701',
1811 },
1812 'params': {
1813 'skip_download': True,
1814 },
1815 'add_ie': [VideoPressIE.ie_key()],
fef51645 1816 },
eb3079b6
S
1817 {
1818 # Rutube embed
1819 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1820 'info_dict': {
1821 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1822 'ext': 'flv',
1823 'title': 'Магаззино: Казань 2',
1824 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1825 'uploader': 'Магаззино',
1826 'upload_date': '20170228',
1827 'uploader_id': '996642',
1828 },
1829 'params': {
1830 'skip_download': True,
1831 },
1832 'add_ie': [RutubeIE.ie_key()],
1833 },
fef51645
YCH
1834 {
1835 # ThePlatform embedded with whitespaces in URLs
1836 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1837 'only_matching': True,
1838 },
97952bdb
JH
1839 {
1840 # Senate ISVP iframe https
1841 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1842 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1843 'info_dict': {
1844 'id': 'govtaff020316',
1845 'ext': 'mp4',
1846 'title': 'Integrated Senate Video Player',
1847 },
1848 'add_ie': [SenateISVPIE.ie_key()],
1849 },
ab87c260
S
1850 {
1851 # Limelight embeds (1 channel embed + 4 media embeds)
1852 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1853 'info_dict': {
1854 'id': 'FacilitatorTraining2017',
1855 'title': 'Facilitator Training 2017',
1856 },
1857 'playlist_mincount': 5,
1858 },
eb02940c
S
1859 {
1860 # Limelight embed (LimelightPlayerUtil.embed)
1861 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1862 'info_dict': {
1863 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1864 'ext': 'mp4',
1865 'title': '07448641',
1866 'timestamp': 1499890639,
1867 'upload_date': '20170712',
1868 },
1869 'params': {
1870 'skip_download': True,
1871 },
1872 'add_ie': ['LimelightMedia'],
1873 },
7986c3ab
S
1874 {
1875 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1876 'info_dict': {
1877 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1878 'title': 'Standoff with Walnut Creek murder suspect ends',
1879 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1880 },
1881 'playlist_mincount': 4,
1882 },
55719459
JH
1883 {
1884 # WashingtonPost embed
1885 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1886 'info_dict': {
1887 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1888 'ext': 'mp4',
1889 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1890 '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.',
1891 'timestamp': 1455216756,
1892 'uploader': 'The Washington Post',
1893 'upload_date': '20160211',
1894 },
1895 'add_ie': [WashingtonPostIE.ie_key()],
1896 },
2b8e6a68
S
1897 {
1898 # Mediaset embed
1899 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1900 'info_dict': {
1901 'id': '720642',
1902 'ext': 'mp4',
1903 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1904 },
1905 'params': {
1906 'skip_download': True,
1907 },
1908 'add_ie': [MediasetIE.ie_key()],
1909 },
73cf76a9
S
1910 {
1911 # JOJ.sk embeds
1912 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1913 'info_dict': {
1914 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1915 'title': 'Slovenskom sa prehnala vlna silných búrok',
1916 },
1917 'playlist_mincount': 5,
1918 'add_ie': [JojIE.ie_key()],
1919 },
4328ddf8
S
1920 {
1921 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1922 'url': 'https://tvrain.ru/amp/418921/',
1923 'md5': 'cc00413936695987e8de148b67d14f1d',
1924 'info_dict': {
1925 'id': '418921',
1926 'ext': 'mp4',
1927 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1928 },
1929 },
41918eaa 1930 {
1931 # vzaar embed
1663bd6e
S
1932 'url': 'http://help.vzaar.com/article/165-embedding-video',
1933 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1934 'info_dict': {
1663bd6e 1935 'id': '8707641',
41918eaa 1936 'ext': 'mp4',
1663bd6e 1937 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1938 },
1939 },
9ce1ac40 1940 {
1941 # multiple HTML5 videos on one page
1942 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1943 'info_dict': {
1944 'id': 'keyscenarios',
1945 'title': 'Rescue Kit 14 Free Edition - Getting started',
1946 },
1947 'playlist_count': 4,
0987f2dd
T
1948 },
1949 {
1950 # vshare embed
cefecac1 1951 'url': 'https://youtube-dlc-demo.neocities.org/vshare.html',
0987f2dd
T
1952 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1953 'info_dict': {
1954 'id': '0f64ce6',
1955 'title': 'vl14062007715967',
1956 'ext': 'mp4',
1957 }
2ca7ed41
S
1958 },
1959 {
1960 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1961 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1962 'info_dict': {
1963 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1964 'ext': 'mp4',
1965 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1966 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1967 'timestamp': 1474354800,
1968 'upload_date': '20160920',
1969 }
7d540621
S
1970 },
1971 {
1972 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1973 'info_dict': {
1974 'id': '1731611',
1975 'ext': 'mp4',
1976 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1977 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1978 'timestamp': 1516100691,
1979 'upload_date': '20180116',
1980 },
1981 'params': {
1982 'skip_download': True,
1983 },
1984 'add_ie': [SpringboardPlatformIE.ie_key()],
ea696249
S
1985 },
1986 {
1987 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1988 'info_dict': {
1989 'id': 'uPDB5I9wfp8',
1990 'ext': 'webm',
1991 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1992 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1993 'upload_date': '20160219',
1994 'uploader': 'Pocoyo - Português (BR)',
1995 'uploader_id': 'PocoyoBrazil',
1996 },
1997 'add_ie': [YoutubeIE.ie_key()],
1998 'params': {
1999 'skip_download': True,
2000 },
4c780fbd
S
2001 },
2002 {
2003 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
2004 'info_dict': {
2005 'id': 'vMDE4NzI1Mjgt690b',
2006 'ext': 'mp4',
2007 'title': 'Котята',
2008 },
2009 'add_ie': [YapFilesIE.ie_key()],
2010 'params': {
2011 'skip_download': True,
2012 },
1fc37ca3 2013 },
660a230b
S
2014 {
2015 # CloudflareStream embed
2016 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2017 'info_dict': {
2018 'id': '31c9291ab41fac05471db4e73aa11717',
2019 'ext': 'mp4',
2020 'title': '31c9291ab41fac05471db4e73aa11717',
2021 },
2022 'add_ie': [CloudflareStreamIE.ie_key()],
2023 'params': {
2024 'skip_download': True,
2025 },
2026 },
6bd499e8
S
2027 {
2028 # PeerTube embed
2029 'url': 'https://joinpeertube.org/fr/home/',
2030 'info_dict': {
2031 'id': 'home',
2032 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2033 },
2034 'playlist_count': 2,
2035 },
aee36ca8
S
2036 {
2037 # Indavideo embed
2038 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2039 'info_dict': {
2040 'id': '1693903',
2041 'ext': 'mp4',
2042 'title': 'Így kell otthon hamburgert sütni',
2043 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2044 'timestamp': 1426330212,
2045 'upload_date': '20150314',
2046 'uploader': 'StreetKitchen',
2047 'uploader_id': '546363',
2048 },
2049 'add_ie': [IndavideoEmbedIE.ie_key()],
2050 'params': {
2051 'skip_download': True,
2052 },
2053 },
cfd7f2a6
S
2054 {
2055 # APA embed via JWPlatform embed
2056 'url': 'http://www.vol.at/blue-man-group/5593454',
2057 'info_dict': {
2058 'id': 'jjv85FdZ',
2059 'ext': 'mp4',
2060 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2061 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2062 'thumbnail': r're:^https?://.*\.jpg$',
2063 'duration': 254,
2064 'timestamp': 1519211149,
2065 'upload_date': '20180221',
2066 },
2067 'params': {
2068 'skip_download': True,
2069 },
2070 },
1fc37ca3
SO
2071 {
2072 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2073 'md5': 'b68d276de422ab07ee1d49388103f457',
2074 'info_dict': {
2075 'id': '83645793',
2076 'title': 'Lock up and get excited',
1fc37ca3 2077 'ext': 'mp4'
d3431dcb
S
2078 },
2079 'skip': 'TODO: fix nested playlists processing in tests',
2080 },
9d1b2138
S
2081 {
2082 # Viqeo embeds
2083 'url': 'https://viqeo.tv/',
2084 'info_dict': {
2085 'id': 'viqeo',
2086 'title': 'All-new video platform',
2087 },
2088 'playlist_count': 6,
2089 },
d78657fd
BM
2090 {
2091 # Squarespace video embed, 2019-08-28
2092 'url': 'http://ootboxford.com',
2093 'info_dict': {
2094 'id': 'Tc7b_JGdZfw',
2095 'title': 'Out of the Blue, at Childish Things 10',
7cb51b5d
S
2096 'ext': 'mp4',
2097 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2098 'uploader_id': 'helendouglashouse',
2099 'uploader': 'Helen & Douglas House',
2100 'upload_date': '20140328',
d78657fd
BM
2101 },
2102 'params': {
2103 'skip_download': True,
2104 },
2105 },
83852e57
S
2106 {
2107 # Zype embed
2108 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2109 'info_dict': {
2110 'id': '5b400b834b32992a310622b9',
2111 'ext': 'mp4',
2112 'title': 'Smoky Barbecue Favorites',
2113 'thumbnail': r're:^https?://.*\.jpe?g',
a9866c03
RA
2114 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
2115 'upload_date': '20170909',
2116 'timestamp': 1504915200,
83852e57
S
2117 },
2118 'add_ie': [ZypeIE.ie_key()],
2119 'params': {
2120 'skip_download': True,
2121 },
2122 },
e0b6e988
S
2123 {
2124 # videojs embed
2125 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2126 'info_dict': {
2127 'id': 'shell',
2128 'ext': 'mp4',
2129 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2130 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2131 'thumbnail': r're:^https?://.*\.jpg$',
2132 },
2133 'params': {
2134 'skip_download': True,
2135 },
2136 'expected_warnings': ['Failed to download MPD manifest'],
2137 },
5e3da0d4
RA
2138 {
2139 # DailyMotion embed with DM.player
2140 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2141 'info_dict': {
2142 'id': 'k6aKkGHd9FJs4mtJN39',
2143 'ext': 'mp4',
2144 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2145 'description': 'This video is private.',
2146 'uploader_id': 'x1jf30l',
2147 'uploader': 'beIN SPORTS USA',
2148 'upload_date': '20190528',
2149 'timestamp': 1559062971,
2150 },
2151 'params': {
2152 'skip_download': True,
2153 },
2154 },
6e6b70d6
S
2155 # {
2156 # # TODO: find another test
2157 # # http://schema.org/VideoObject
2158 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2159 # 'md5': '888dcf08b7ea671381f00fab74692755',
2160 # 'info_dict': {
2161 # 'id': 'nyvTSJMKId',
2162 # 'ext': 'mp4',
2163 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2164 # 'description': '#love for cats.',
2165 # 'timestamp': 1461244995,
2166 # 'upload_date': '20160421',
2167 # },
2168 # 'params': {
2169 # 'force_generic_extractor': True,
2170 # },
2171 # }
cfe50f04 2172 ]
9b122384 2173
9b122384
PH
2174 def report_following_redirect(self, new_url):
2175 """Report information extraction."""
79649588 2176 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 2177
4fc946b5
PH
2178 def _extract_rss(self, url, video_id, doc):
2179 playlist_title = doc.find('./channel/title').text
2180 playlist_desc_el = doc.find('./channel/description')
2181 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2182
76c73715
PH
2183 entries = []
2184 for it in doc.findall('./channel/item'):
01aec848
BG
2185 next_url = None
2186 enclosure_nodes = it.findall('./enclosure')
2187 for e in enclosure_nodes:
2188 next_url = e.attrib.get('url')
2189 if next_url:
2190 break
2191
76c73715 2192 if not next_url:
01aec848 2193 next_url = xpath_text(it, 'link', fatal=False)
76c73715
PH
2194
2195 if not next_url:
2196 continue
2197
2198 entries.append({
413c1f8e 2199 '_type': 'url_transparent',
76c73715
PH
2200 'url': next_url,
2201 'title': it.find('title').text,
2202 })
4fc946b5
PH
2203
2204 return {
2205 '_type': 'playlist',
2206 'id': url,
2207 'title': playlist_title,
2208 'description': playlist_desc,
2209 'entries': entries,
2210 }
2211
c8e9a235
PH
2212 def _extract_camtasia(self, url, video_id, webpage):
2213 """ Returns None if no camtasia video can be found. """
2214
2215 camtasia_cfg = self._search_regex(
2216 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2217 webpage, 'camtasia configuration file', default=None)
2218 if camtasia_cfg is None:
2219 return None
2220
2221 title = self._html_search_meta('DC.title', webpage, fatal=True)
2222
2223 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2224 camtasia_cfg = self._download_xml(
2225 camtasia_url, video_id,
2226 note='Downloading camtasia configuration',
2227 errnote='Failed to download camtasia configuration')
2228 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2229
2230 entries = []
2231 for n in fileset_node.getchildren():
2232 url_n = n.find('./uri')
2233 if url_n is None:
2234 continue
2235
2236 entries.append({
2237 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2238 'title': '%s - %s' % (title, n.tag),
2239 'url': compat_urlparse.urljoin(url, url_n.text),
2240 'duration': float_or_none(n.find('./duration').text),
2241 })
2242
2243 return {
2244 '_type': 'playlist',
2245 'entries': entries,
2246 'title': title,
2247 }
2248
9b122384 2249 def _real_extract(self, url):
ebd3c7b3 2250 if url.startswith('//'):
d226c560 2251 return self.url_result(self.http_scheme() + url)
ebd3c7b3 2252
a7130543
JMF
2253 parsed_url = compat_urlparse.urlparse(url)
2254 if not parsed_url.scheme:
04b4d394
PH
2255 default_search = self._downloader.params.get('default_search')
2256 if default_search is None:
1f7ccb90 2257 default_search = 'fixup_error'
04b4d394 2258
1f7ccb90 2259 if default_search in ('auto', 'auto_warning', 'fixup_error'):
9c1da4a9 2260 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
04b4d394
PH
2261 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2262 return self.url_result('http://' + url)
1f7ccb90 2263 elif default_search != 'fixup_error':
9c1fc022 2264 if default_search == 'auto_warning':
0e67ab0d
PH
2265 if re.match(r'^(?:url|URL)$', url):
2266 raise ExtractorError(
cefecac1 2267 'Invalid URL: %r . Call youtube-dlc like this: youtube-dlc -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
0e67ab0d
PH
2268 expected=True)
2269 else:
2270 self._downloader.report_warning(
7571c02c 2271 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2272 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2273
2274 if default_search in ('error', 'fixup_error'):
7571c02c 2275 raise ExtractorError(
b74e86f4 2276 '%r is not a valid URL. '
cefecac1 2277 'Set --default-search "ytsearch" (or run youtube-dlc "ytsearch:%s" ) to search YouTube'
b74e86f4 2278 % (url, url), expected=True)
04b4d394 2279 else:
f2f2c0c2
PH
2280 if ':' not in default_search:
2281 default_search += ':'
04b4d394 2282 return self.url_result(default_search + url)
4d54ef20
PH
2283
2284 url, smuggled_data = unsmuggle_url(url)
2285 force_videoid = None
d6e6a422 2286 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2287 if smuggled_data and 'force_videoid' in smuggled_data:
2288 force_videoid = smuggled_data['force_videoid']
2289 video_id = force_videoid
2290 else:
9dcd6fd3 2291 video_id = self._generic_id(url)
3d83a1ae 2292
79649588 2293 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2294
ebab4520 2295 head_req = HEADRequest(url)
23be51d8 2296 head_response = self._request_webpage(
ebab4520
PH
2297 head_req, video_id,
2298 note=False, errnote='Could not send HEAD request to %s' % url,
2299 fatal=False)
42393ce2 2300
23be51d8 2301 if head_response is not False:
42393ce2 2302 # Check for redirect
7947a1f7 2303 new_url = head_response.geturl()
42393ce2
PH
2304 if url != new_url:
2305 self.report_following_redirect(new_url)
4d54ef20
PH
2306 if force_videoid:
2307 new_url = smuggle_url(
2308 new_url, {'force_videoid': force_videoid})
cecaaf3f 2309 return self.url_result(new_url)
42393ce2 2310
23be51d8
PH
2311 full_response = None
2312 if head_response is False:
5c2266df 2313 request = sanitized_Request(url)
58bde34a
S
2314 request.add_header('Accept-Encoding', '*')
2315 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2316 head_response = full_response
2317
f930e0c7
S
2318 info_dict = {
2319 'id': video_id,
9dcd6fd3 2320 'title': self._generic_title(url),
303dcdb9 2321 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
2322 }
2323
23be51d8 2324 # Check for direct link to a video
955737b2 2325 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2326 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2327 if m:
4e363703 2328 format_id = compat_str(m.group('format_id'))
f930e0c7 2329 if format_id.endswith('mpegurl'):
eadc3ccd 2330 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
2331 elif format_id == 'f4m':
2332 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2333 else:
2334 formats = [{
4e363703 2335 'format_id': format_id,
eadc3ccd 2336 'url': url,
2337 'vcodec': 'none' if m.group('type') == 'audio' else None
2338 }]
de6c51e8 2339 info_dict['direct'] = True
19dbaeec 2340 self._sort_formats(formats)
de6c51e8 2341 info_dict['formats'] = formats
f930e0c7 2342 return info_dict
42393ce2 2343
d6e6a422 2344 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
2345 force = self._downloader.params.get('force_generic_extractor', False)
2346 self._downloader.report_warning(
2347 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2348
4e262a88 2349 if not full_response:
5c2266df 2350 request = sanitized_Request(url)
58bde34a
S
2351 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2352 # making it impossible to download only chunk of the file (yet we need only 512kB to
cefecac1 2353 # test whether it's HTML or not). According to youtube-dlc default Accept-Encoding
58bde34a
S
2354 # that will always result in downloading the whole file that is not desirable.
2355 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2356 # to accept raw bytes and being able to download only a chunk.
2357 # It may probably better to solve this by checking Content-Type for application/octet-stream
2358 # after HEAD request finishes, but not sure if we can rely on this.
2359 request.add_header('Accept-Encoding', '*')
2360 full_response = self._request_webpage(request, video_id)
4e262a88 2361
5940862d
S
2362 first_bytes = full_response.read(512)
2363
2364 # Is it an M3U playlist?
0d769bcb 2365 if first_bytes.startswith(b'#EXTM3U'):
5940862d 2366 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 2367 self._sort_formats(info_dict['formats'])
5940862d
S
2368 return info_dict
2369
4e262a88
PH
2370 # Maybe it's a direct link to a video?
2371 # Be careful not to download the whole thing!
61ca9a80 2372 if not is_html(first_bytes):
4e262a88
PH
2373 self._downloader.report_warning(
2374 'URL could be a direct video link, returning it as such.')
f930e0c7 2375 info_dict.update({
4e262a88
PH
2376 'direct': True,
2377 'url': url,
f930e0c7
S
2378 })
2379 return info_dict
4e262a88
PH
2380
2381 webpage = self._webpage_read_content(
2382 full_response, url, video_id, prefix=first_bytes)
2383
9b122384 2384 self.report_extraction(video_id)
887c6acd 2385
1b840245 2386 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2387 try:
f7854627 2388 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
2389 if doc.tag == 'rss':
2390 return self._extract_rss(url, video_id, doc)
cc99a77a
S
2391 elif doc.tag == 'SmoothStreamingMedia':
2392 info_dict['formats'] = self._parse_ism_formats(doc, url)
2393 self._sort_formats(info_dict['formats'])
2394 return info_dict
e5e8d20a 2395 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
2396 smil = self._parse_smil(doc, url, video_id)
2397 self._sort_formats(smil['formats'])
2398 return smil
729accb4 2399 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
96b8b9ab 2400 return self.playlist_result(
47a5cb77
S
2401 self._parse_xspf(
2402 doc, video_id, xspf_url=url,
7947a1f7 2403 xspf_base_url=full_response.geturl()),
96b8b9ab 2404 video_id)
1b840245 2405 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7 2406 info_dict['formats'] = self._parse_mpd_formats(
d3f8b76b 2407 doc,
7947a1f7 2408 mpd_base_url=full_response.geturl().rpartition('/')[0],
86f4d14f 2409 mpd_url=url)
19dbaeec 2410 self._sort_formats(info_dict['formats'])
f930e0c7
S
2411 return info_dict
2412 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2413 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 2414 self._sort_formats(info_dict['formats'])
f930e0c7 2415 return info_dict
f7300c5c 2416 except compat_xml_parse_error:
4fc946b5
PH
2417 pass
2418
c8e9a235
PH
2419 # Is it a Camtasia project?
2420 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2421 if camtasia_res is not None:
2422 return camtasia_res
2423
14390730 2424 # Sometimes embedded video player is hidden behind percent encoding
067aa17e 2425 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
14390730 2426 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 2427 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2428
7cb51b5d
S
2429 # Unescape squarespace embeds to be detected by generic extractor,
2430 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2431 webpage = re.sub(
2432 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2433 lambda x: unescapeHTML(x.group(0)), webpage)
d78657fd 2434
887c6acd
PH
2435 # it's tempting to parse this further, but you would
2436 # have to take into account all the variations like
2437 # Video Title - Site Name
2438 # Site Name | Video Title
2439 # Video Title - Tagline | Site Name
2440 # and so on and so forth; it's just not practical
6f41b2bc
S
2441 video_title = self._og_search_title(
2442 webpage, default=None) or self._html_search_regex(
79649588
PH
2443 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2444 default='video')
ef4fd848 2445
4d805e06
PH
2446 # Try to detect age limit automatically
2447 age_limit = self._rta_search(webpage)
2448 # And then there are the jokers who advertise that they use RTA,
2449 # but actually don't.
2450 AGE_LIMIT_MARKERS = [
197224b7 2451 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
4d805e06
PH
2452 ]
2453 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2454 age_limit = 18
2455
ef4fd848
PH
2456 # video uploader is domain name
2457 video_uploader = self._search_regex(
79649588 2458 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2459
6f41b2bc
S
2460 video_description = self._og_search_description(webpage, default=None)
2461 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2462
b311b0ea
S
2463 info_dict.update({
2464 'title': video_title,
2465 'description': video_description,
2466 'thumbnail': video_thumbnail,
2467 'age_limit': age_limit,
2468 })
2469
1f4b722b 2470 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2471 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2472 if bc_urls:
99877772
PH
2473 entries = [{
2474 '_type': 'url',
2475 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2476 'ie_key': 'BrightcoveLegacy'
99877772
PH
2477 } for bc_url in bc_urls]
2478
2479 return {
2480 '_type': 'playlist',
2481 'title': video_title,
2482 'id': video_id,
2483 'entries': entries,
2484 }
cfe50f04 2485
f6519f89 2486 # Look for Brightcove New Studio embeds
0254f93b 2487 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2488 if bc_urls:
5399ab3f
S
2489 return self.playlist_from_matches(
2490 bc_urls, video_id, video_title,
2491 getter=lambda x: smuggle_url(x, {'referrer': url}),
2492 ie='BrightcoveNew')
ed126900 2493
4e826cd9
S
2494 # Look for Nexx embeds
2495 nexx_urls = NexxIE._extract_urls(webpage)
2496 if nexx_urls:
2497 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2498
3f59b015
S
2499 # Look for Nexx iFrame embeds
2500 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2501 if nexx_embed_urls:
2502 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2503
4d8819d2
S
2504 # Look for ThePlatform embeds
2505 tp_urls = ThePlatformIE._extract_urls(webpage)
2506 if tp_urls:
46b18f23 2507 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2508
59b8ab58
PH
2509 # Look for embedded rtl.nl player
2510 matches = re.findall(
2637fadc 2511 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
59b8ab58
PH
2512 webpage)
2513 if matches:
46b18f23 2514 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2515
09b9c45e
S
2516 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2517 if vimeo_urls:
46b18f23 2518 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2519
a1b85269
YCH
2520 vid_me_embed_url = self._search_regex(
2521 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2522 webpage, 'vid.me embed', default=None)
2523 if vid_me_embed_url is not None:
2524 return self.url_result(vid_me_embed_url, 'Vidme')
2525
66c9fa36
S
2526 # Look for YouTube embeds
2527 youtube_urls = YoutubeIE._extract_urls(webpage)
2528 if youtube_urls:
46b18f23 2529 return self.playlist_from_matches(
66c9fa36 2530 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2531
ad213a1d 2532 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2533 if matches:
46b18f23 2534 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2535
8489578d
NJ
2536 # Look for embedded Dailymotion playlist player (#3822)
2537 m = re.search(
2538 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2539 if m:
2540 playlists = re.findall(
2541 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2542 if playlists:
46b18f23
JH
2543 return self.playlist_from_matches(
2544 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2545
71a1db89
S
2546 # Look for DailyMail embeds
2547 dailymail_urls = DailyMailIE._extract_urls(webpage)
2548 if dailymail_urls:
2549 return self.playlist_from_matches(
2550 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2551
be7dacf9
S
2552 # Look for Teachable embeds, must be before Wistia
2553 teachable_url = TeachableIE._extract_url(webpage, url)
2554 if teachable_url:
2555 return self.url_result(teachable_url)
2556
ef4fd848 2557 # Look for embedded Wistia player
fda6d237
S
2558 wistia_urls = WistiaIE._extract_urls(webpage)
2559 if wistia_urls:
2560 playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
2561 for entry in playlist['entries']:
2562 entry.update({
2563 '_type': 'url_transparent',
2564 'uploader': video_uploader,
2565 })
2566 return playlist
5f6a1245 2567
bab19a8e
S
2568 # Look for SVT player
2569 svt_url = SVTIE._extract_url(webpage)
2570 if svt_url:
2571 return self.url_result(svt_url, 'SVT')
2572
c19f7764
JMF
2573 # Look for Bandcamp pages with custom domain
2574 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2575 if mobj is not None:
2576 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2577 # Don't set the extractor because it can be a track url or an album
2578 return self.url_result(burl)
c19f7764 2579
f25571ff
PH
2580 # Look for embedded Vevo player
2581 mobj = re.search(
2582 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2583 if mobj is not None:
2584 return self.url_result(mobj.group('url'))
796df3c6
S
2585
2586 # Look for embedded Viddler player
cb454b33
S
2587 mobj = re.search(
2588 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2589 webpage)
796df3c6
S
2590 if mobj is not None:
2591 return self.url_result(mobj.group('url'))
f25571ff 2592
3378d67a
S
2593 # Look for NYTimes player
2594 mobj = re.search(
2595 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2596 webpage)
2597 if mobj is not None:
2598 return self.url_result(mobj.group('url'))
2599
cefdf970
S
2600 # Look for Libsyn player
2601 mobj = re.search(
2602 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2603 if mobj is not None:
2604 return self.url_result(mobj.group('url'))
2605
c0d0b01f 2606 # Look for Ooyala videos
3089bc74
S
2607 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2608 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2609 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2610 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2611 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2612 if mobj is not None:
9837cb75
RA
2613 embed_token = self._search_regex(
2614 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2615 webpage, 'ooyala embed token', default=None)
2616 return OoyalaIE._build_url_result(smuggle_url(
2617 mobj.group('ec'), {
2618 'domain': url,
2619 'embed_token': embed_token,
2620 }))
c0d0b01f 2621
f076b638 2622 # Look for multiple Ooyala embeds on SBN network websites
2623 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2624 if mobj is not None:
2625 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2626 if embeds:
46b18f23
JH
2627 return self.playlist_from_matches(
2628 embeds, video_id, video_title,
2629 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2630
aa94a6d3 2631 # Look for Aparat videos
48099643 2632 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2633 if mobj is not None:
2634 return self.url_result(mobj.group(1), 'Aparat')
2635
c93c2ab1 2636 # Look for MPORA videos
c3f51436 2637 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2638 if mobj is not None:
2639 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2640
9834872b 2641 # Look for embedded Facebook player
0646e34c
S
2642 facebook_urls = FacebookIE._extract_urls(webpage)
2643 if facebook_urls:
2644 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2645
ca97a56e
S
2646 # Look for embedded VK player
2647 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2648 if mobj is not None:
2649 return self.url_result(mobj.group('url'), 'VK')
2650
33d4fdab 2651 # Look for embedded Odnoklassniki player
416c3ca7
RA
2652 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2653 if odnoklassniki_url:
2654 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
33d4fdab 2655
0364fa8b
S
2656 # Look for embedded ivi player
2657 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2658 if mobj is not None:
2659 return self.url_result(mobj.group('url'), 'Ivi')
2660
db1f3888
PH
2661 # Look for embedded Huffington Post player
2662 mobj = re.search(
c3f51436 2663 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2664 if mobj is not None:
2665 return self.url_result(mobj.group('url'), 'HuffPost')
2666
1b86cc41 2667 # Look for embed.ly
2668 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2669 if mobj is not None:
2670 return self.url_result(mobj.group('url'))
2671 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2672 if mobj is not None:
f7e6f7fa 2673 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2674
60cc4dc4
PH
2675 # Look for funnyordie embed
2676 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2677 if matches:
46b18f23
JH
2678 return self.playlist_from_matches(
2679 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2680
db546cf8
S
2681 # Look for BBC iPlayer embed
2682 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2683 if matches:
46b18f23 2684 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2685
93d020dd
S
2686 # Look for embedded RUTV player
2687 rutv_url = RUTVIE._extract_url(webpage)
2688 if rutv_url:
2689 return self.url_result(rutv_url, 'RUTV')
2690
494f20cb 2691 # Look for embedded TVC player
b8599718
S
2692 tvc_url = TVCIE._extract_url(webpage)
2693 if tvc_url:
2694 return self.url_result(tvc_url, 'TVC')
494f20cb 2695
d40a3b5b 2696 # Look for embedded SportBox player
476cf548 2697 sportbox_urls = SportBoxIE._extract_urls(webpage)
d40a3b5b 2698 if sportbox_urls:
476cf548 2699 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
d40a3b5b 2700
2bb5b6d0
S
2701 # Look for embedded XHamster player
2702 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2703 if xhamster_urls:
46b18f23 2704 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2705
2c9ca782
S
2706 # Look for embedded TNAFlixNetwork player
2707 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2708 if tnaflix_urls:
46b18f23 2709 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2710
b52c9ef1
S
2711 # Look for embedded PornHub player
2712 pornhub_urls = PornHubIE._extract_urls(webpage)
2713 if pornhub_urls:
46b18f23 2714 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2715
37e7a71c
S
2716 # Look for embedded DrTuber player
2717 drtuber_urls = DrTuberIE._extract_urls(webpage)
2718 if drtuber_urls:
46b18f23 2719 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2720
e28ed498
S
2721 # Look for embedded RedTube player
2722 redtube_urls = RedTubeIE._extract_urls(webpage)
2723 if redtube_urls:
46b18f23 2724 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 2725
06993715
S
2726 # Look for embedded Tube8 player
2727 tube8_urls = Tube8IE._extract_urls(webpage)
2728 if tube8_urls:
2729 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2730
4e7b5bba
S
2731 # Look for embedded Mofosex player
2732 mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
2733 if mofosex_urls:
2734 return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
2735
8fae1a04
S
2736 # Look for embedded Spankwire player
2737 spankwire_urls = SpankwireIE._extract_urls(webpage)
2738 if spankwire_urls:
2739 return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
2740
52c4c515
S
2741 # Look for embedded YouPorn player
2742 youporn_urls = YouPornIE._extract_urls(webpage)
2743 if youporn_urls:
2744 return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
2745
9872d311
S
2746 # Look for embedded Tvigle player
2747 mobj = re.search(
2748 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2749 if mobj is not None:
2750 return self.url_result(mobj.group('url'), 'Tvigle')
2751
7e2ede98
JMF
2752 # Look for embedded TED player
2753 mobj = re.search(
d7cc31b6 2754 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
2755 if mobj is not None:
2756 return self.url_result(mobj.group('url'), 'TED')
2757
5c386252 2758 # Look for embedded Ustream videos
d77ac737
YCH
2759 ustream_url = UstreamIE._extract_url(webpage)
2760 if ustream_url:
2761 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 2762
893f8832 2763 # Look for embedded arte.tv player
8bdd16b4 2764 arte_urls = ArteTVEmbedIE._extract_urls(webpage)
2765 if arte_urls:
2766 return self.playlist_from_matches(arte_urls, video_id, video_title)
893f8832 2767
cbd55ade
S
2768 # Look for embedded francetv player
2769 mobj = re.search(
2770 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2771 webpage)
2772 if mobj is not None:
2773 return self.url_result(mobj.group('url'))
2774
cb3ac1c6
S
2775 # Look for embedded smotri.com player
2776 smotri_url = SmotriIE._extract_url(webpage)
2777 if smotri_url:
2778 return self.url_result(smotri_url, 'Smotri')
2779
e6c2d9ad 2780 # Look for embedded Myvi.ru player
6dd94d3a 2781 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
2782 if myvi_url:
2783 return self.url_result(myvi_url)
2784
dfb1b146 2785 # Look for embedded soundcloud player
548c3957 2786 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
94aae015 2787 if soundcloud_urls:
548c3957 2788 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
20991253 2789
027e2312
S
2790 # Look for tunein player
2791 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2792 if tunein_urls:
46b18f23 2793 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 2794
c5cd249e 2795 # Look for embedded mtvservices player
46fde8a1
S
2796 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2797 if mtvservices_url:
2798 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 2799
49807b4a
S
2800 # Look for embedded yahoo player
2801 mobj = re.search(
2802 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2803 webpage)
2804 if mobj is not None:
2805 return self.url_result(mobj.group('url'), 'Yahoo')
2806
2ef6fcb5
PH
2807 # Look for embedded sbs.com.au player
2808 mobj = re.search(
e98b8e79
PH
2809 r'''(?x)
2810 (?:
2811 <meta\s+property="og:video"\s+content=|
2812 <iframe[^>]+?src=
2813 )
2814 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
2815 webpage)
2816 if mobj is not None:
2817 return self.url_result(mobj.group('url'), 'SBS')
2818
42bdd9d0
PH
2819 # Look for embedded Cinchcast player
2820 mobj = re.search(
2821 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2822 webpage)
2823 if mobj is not None:
2824 return self.url_result(mobj.group('url'), 'Cinchcast')
2825
1a94ff68 2826 mobj = re.search(
5263cdfc 2827 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 2828 webpage)
8001607e
YCH
2829 if not mobj:
2830 mobj = re.search(
2831 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2832 webpage)
1a94ff68
S
2833 if mobj is not None:
2834 return self.url_result(mobj.group('url'), 'MLB')
2835
1419fafd 2836 mobj = re.search(
dd467d33 2837 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
2838 webpage)
2839 if mobj is not None:
2840 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2841
af63fed7 2842 mobj = re.search(
78d3b3e2 2843 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
2844 webpage)
2845 if mobj is not None:
2846 return self.url_result(mobj.group('url'), 'Livestream')
2847
255fca5e
S
2848 # Look for Zapiks embed
2849 mobj = re.search(
2850 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2851 if mobj is not None:
2852 return self.url_result(mobj.group('url'), 'Zapiks')
2853
e3216b82 2854 # Look for Kaltura embeds
562de77f
S
2855 kaltura_urls = KalturaIE._extract_urls(webpage)
2856 if kaltura_urls:
2857 return self.playlist_from_matches(
2858 kaltura_urls, video_id, video_title,
2859 getter=lambda x: smuggle_url(x, {'source_url': url}),
2860 ie=KalturaIE.ie_key())
e3216b82 2861
665e9452 2862 # Look for EaglePlatform embeds
06a96da1
S
2863 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2864 if eagleplatform_url:
665e9452 2865 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 2866
665e9452 2867 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
2868 mobj = re.search(
2869 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2870 if mobj is not None:
2871 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2872
f8388757 2873 # Look for Pladform embeds
45dad7ba
S
2874 pladform_url = PladformIE._extract_url(webpage)
2875 if pladform_url:
2876 return self.url_result(pladform_url)
f8388757 2877
ff18735c
S
2878 # Look for Videomore embeds
2879 videomore_url = VideomoreIE._extract_url(webpage)
2880 if videomore_url:
2881 return self.url_result(videomore_url)
2882
83f1481b
S
2883 # Look for Webcaster embeds
2884 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2885 if webcaster_url:
2886 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2887
2dcc114f
S
2888 # Look for Playwire embeds
2889 mobj = re.search(
2890 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2891 if mobj is not None:
2892 return self.url_result(mobj.group('url'))
2893
ad320e9b
NJ
2894 # Look for 5min embeds
2895 mobj = re.search(
2896 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2897 if mobj is not None:
2898 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2899
18153f1b
S
2900 # Look for Crooks and Liars embeds
2901 mobj = re.search(
2902 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2903 if mobj is not None:
2904 return self.url_result(mobj.group('url'))
2905
a2edf2e7
YCH
2906 # Look for NBC Sports VPlayer embeds
2907 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2908 if nbc_sports_url:
2909 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2910
de3eb07e
YCH
2911 # Look for NBC News embeds
2912 nbc_news_embed_url = re.search(
2913 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2914 if nbc_news_embed_url:
2915 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2916
653789af 2917 # Look for Google Drive embeds
5b251628 2918 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 2919 if google_drive_url:
2920 return self.url_result(google_drive_url, 'GoogleDrive')
2921
418c5cc3
YCH
2922 # Look for UDN embeds
2923 mobj = re.search(
2637fadc 2924 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
2925 if mobj is not None:
2926 return self.url_result(
0a160363 2927 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 2928
2fe1b5bd
YCH
2929 # Look for Senate ISVP iframe
2930 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2931 if senate_isvp_url:
25c3a734 2932 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 2933
55adb63e
RA
2934 # Look for Kinja embeds
2935 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
2936 if kinja_embed_urls:
2937 return self.playlist_from_matches(
2938 kinja_embed_urls, video_id, video_title)
2939
1ac1c4c2
S
2940 # Look for OnionStudios embeds
2941 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2942 if onionstudios_url:
2943 return self.url_result(onionstudios_url)
2944
67167920 2945 # Look for ViewLift embeds
2946 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2947 if viewlift_url:
2948 return self.url_result(viewlift_url)
eedd20ef 2949
7cb09524 2950 # Look for JWPlatform embeds
b0ead0e0
S
2951 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2952 if jwplatform_urls:
2953 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
7cb09524 2954
aecfcd4e
S
2955 # Look for Digiteka embeds
2956 digiteka_url = DigitekaIE._extract_url(webpage)
2957 if digiteka_url:
2958 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 2959
1979969f
S
2960 # Look for Arkena embeds
2961 arkena_url = ArkenaIE._extract_url(webpage)
2962 if arkena_url:
2963 return self.url_result(arkena_url, ArkenaIE.ie_key())
2964
b1c35797
RA
2965 # Look for Piksel embeds
2966 piksel_url = PikselIE._extract_url(webpage)
2967 if piksel_url:
2968 return self.url_result(piksel_url, PikselIE.ie_key())
2969
1bf996fa 2970 # Look for Limelight embeds
e5d39886
S
2971 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2972 if limelight_urls:
2973 return self.playlist_result(
2974 limelight_urls, video_id, video_title, video_description)
2975
7986c3ab
S
2976 # Look for Anvato embeds
2977 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2978 if anvato_urls:
2979 return self.playlist_result(
2980 anvato_urls, video_id, video_title, video_description)
2981
a5158f38
YCH
2982 # Look for AdobeTVVideo embeds
2983 mobj = re.search(
2984 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2985 webpage)
2986 if mobj is not None:
2987 return self.url_result(
2988 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2989 'AdobeTVVideo')
2990
088e1aac
YCH
2991 # Look for Vine embeds
2992 mobj = re.search(
2993 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2994 webpage)
2995 if mobj is not None:
2996 return self.url_result(
2997 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2998
217d5ae0
RA
2999 # Look for VODPlatform embeds
3000 mobj = re.search(
bd2c211f 3001 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
217d5ae0
RA
3002 webpage)
3003 if mobj is not None:
3004 return self.url_result(
93b84045 3005 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 3006
7d273a38
RA
3007 # Look for Mangomolo embeds
3008 mobj = re.search(
755541a4
RA
3009 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
3010 (?:
3011 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
3012 player\.mangomolo\.com/v1
3013 )/
7d273a38
RA
3014 (?:
3015 video\?.*?\bid=(?P<video_id>\d+)|
755541a4 3016 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
7d273a38
RA
3017 ).+?)\1''', webpage)
3018 if mobj is not None:
3019 info = {
3020 '_type': 'url_transparent',
3021 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
3022 'title': video_title,
3023 'description': video_description,
3024 'thumbnail': video_thumbnail,
3025 'uploader': video_uploader,
3026 }
3027 video_id = mobj.group('video_id')
3028 if video_id:
3029 info.update({
3030 'ie_key': 'MangomoloVideo',
3031 'id': video_id,
3032 })
3033 else:
3034 info.update({
3035 'ie_key': 'MangomoloLive',
3036 'id': mobj.group('channel_id'),
3037 })
3038 return info
3039
5a51775a
YCH
3040 # Look for Instagram embeds
3041 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3042 if instagram_embed_url is not None:
11e60fca
S
3043 return self.url_result(
3044 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 3045
b8f67449 3046 # Look for LiveLeak embeds
09747ba7
YCH
3047 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3048 if liveleak_urls:
3049 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
b8f67449 3050
5d39176f
S
3051 # Look for 3Q SDN embeds
3052 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3053 if threeqsdn_url:
6f41b2bc
S
3054 return {
3055 '_type': 'url_transparent',
3056 'ie_key': ThreeQSDNIE.ie_key(),
3057 'url': self._proto_relative_url(threeqsdn_url),
3058 'title': video_title,
3059 'description': video_description,
3060 'thumbnail': video_thumbnail,
3061 'uploader': video_uploader,
3062 }
5d39176f 3063
2a1321a2
S
3064 # Look for VBOX7 embeds
3065 vbox7_url = Vbox7IE._extract_url(webpage)
3066 if vbox7_url:
3067 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3068
b0c8f2e9
DR
3069 # Look for DBTV embeds
3070 dbtv_urls = DBTVIE._extract_urls(webpage)
3071 if dbtv_urls:
46b18f23 3072 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 3073
e186a9ec
S
3074 # Look for Videa embeds
3075 videa_urls = VideaIE._extract_urls(webpage)
3076 if videa_urls:
46b18f23 3077 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 3078
b687c85e
S
3079 # Look for 20 minuten embeds
3080 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3081 if twentymin_urls:
46b18f23
JH
3082 return self.playlist_from_matches(
3083 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 3084
6ef3e65a
S
3085 # Look for VideoPress embeds
3086 videopress_urls = VideoPressIE._extract_urls(webpage)
3087 if videopress_urls:
46b18f23
JH
3088 return self.playlist_from_matches(
3089 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 3090
eb3079b6
S
3091 # Look for Rutube embeds
3092 rutube_urls = RutubeIE._extract_urls(webpage)
3093 if rutube_urls:
46b18f23 3094 return self.playlist_from_matches(
2583c0b5 3095 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 3096
55719459
JH
3097 # Look for WashingtonPost embeds
3098 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3099 if wapo_urls:
3100 return self.playlist_from_matches(
3101 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3102
5d29af3d 3103 # Look for Mediaset embeds
8fd12a08 3104 mediaset_urls = MediasetIE._extract_urls(self, webpage)
5d29af3d
S
3105 if mediaset_urls:
3106 return self.playlist_from_matches(
3107 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3108
73cf76a9
S
3109 # Look for JOJ.sk embeds
3110 joj_urls = JojIE._extract_urls(webpage)
3111 if joj_urls:
3112 return self.playlist_from_matches(
3113 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3114
24e966e8
PH
3115 # Look for megaphone.fm embeds
3116 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3117 if mpfn_urls:
3118 return self.playlist_from_matches(
3119 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3120
1663bd6e
S
3121 # Look for vzaar embeds
3122 vzaar_urls = VzaarIE._extract_urls(webpage)
3123 if vzaar_urls:
3124 return self.playlist_from_matches(
3125 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3126
26bae2d9
S
3127 channel9_urls = Channel9IE._extract_urls(webpage)
3128 if channel9_urls:
3129 return self.playlist_from_matches(
3130 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3131
0987f2dd
T
3132 vshare_urls = VShareIE._extract_urls(webpage)
3133 if vshare_urls:
3134 return self.playlist_from_matches(
3135 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3136
8056c854 3137 # Look for Mediasite embeds
2ca7ed41
S
3138 mediasite_urls = MediasiteIE._extract_urls(webpage)
3139 if mediasite_urls:
3140 entries = [
3141 self.url_result(smuggle_url(
3142 compat_urlparse.urljoin(url, mediasite_url),
3143 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3144 for mediasite_url in mediasite_urls]
3145 return self.playlist_result(entries, video_id, video_title)
8056c854 3146
7d540621
S
3147 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3148 if springboardplatform_urls:
3149 return self.playlist_from_matches(
3150 springboardplatform_urls, video_id, video_title,
3151 ie=SpringboardPlatformIE.ie_key())
3152
4c780fbd
S
3153 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3154 if yapfiles_urls:
3155 return self.playlist_from_matches(
3156 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3157
86c8cfc5
S
3158 vice_urls = ViceIE._extract_urls(webpage)
3159 if vice_urls:
3160 return self.playlist_from_matches(
3161 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3162
178ee883
S
3163 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3164 if xfileshare_urls:
3165 return self.playlist_from_matches(
3166 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3167
660a230b
S
3168 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3169 if cloudflarestream_urls:
3170 return self.playlist_from_matches(
3171 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3172
8b4b400a 3173 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
6bd499e8
S
3174 if peertube_urls:
3175 return self.playlist_from_matches(
3176 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3177
aee36ca8
S
3178 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3179 if indavideo_urls:
3180 return self.playlist_from_matches(
3181 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3182
cfd7f2a6
S
3183 apa_urls = APAIE._extract_urls(webpage)
3184 if apa_urls:
3185 return self.playlist_from_matches(
3186 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3187
f51f526b
S
3188 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3189 if foxnews_urls:
3190 return self.playlist_from_matches(
3191 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3192
2e4350ee 3193 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
d3431dcb
S
3194 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3195 webpage)]
3196 if sharevideos_urls:
3197 return self.playlist_from_matches(
3198 sharevideos_urls, video_id, video_title)
3199
9d1b2138
S
3200 viqeo_urls = ViqeoIE._extract_urls(webpage)
3201 if viqeo_urls:
3202 return self.playlist_from_matches(
3203 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
57c68ec4
S
3204
3205 expressen_urls = ExpressenIE._extract_urls(webpage)
3206 if expressen_urls:
3207 return self.playlist_from_matches(
3208 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
9d1b2138 3209
83852e57
S
3210 zype_urls = ZypeIE._extract_urls(webpage)
3211 if zype_urls:
3212 return self.playlist_from_matches(
3213 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3214
bd264412
YCH
3215 # Look for HTML5 media
3216 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3217 if entries:
9ce1ac40 3218 if len(entries) == 1:
3219 entries[0].update({
bd264412
YCH
3220 'id': video_id,
3221 'title': video_title,
3222 })
9ce1ac40 3223 else:
3224 for num, entry in enumerate(entries, start=1):
3225 entry.update({
3226 'id': '%s-%s' % (video_id, num),
3227 'title': '%s (%d)' % (video_title, num),
3228 })
3229 for entry in entries:
bd264412 3230 self._sort_formats(entry['formats'])
9ce1ac40 3231 return self.playlist_result(entries, video_id, video_title)
bd264412 3232
c73e330e
RU
3233 jwplayer_data = self._find_jwplayer_data(
3234 webpage, video_id, transform_source=js_to_json)
3235 if jwplayer_data:
3d08f63d
MYM
3236 try:
3237 info = self._parse_jwplayer_data(
3238 jwplayer_data, video_id, require_title=False, base_url=url)
3239 return merge_dicts(info, info_dict)
3240 except ExtractorError:
067aa17e 3241 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3d08f63d 3242 pass
a4a554a7 3243
63d990d2
S
3244 # Video.js embed
3245 mobj = re.search(
c5b7014a 3246 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
3247 webpage)
3248 if mobj is not None:
3249 sources = self._parse_json(
3250 mobj.group(1), video_id, transform_source=js_to_json,
3251 fatal=False) or []
c5b7014a
S
3252 if not isinstance(sources, list):
3253 sources = [sources]
63d990d2
S
3254 formats = []
3255 for source in sources:
e0b6e988
S
3256 src = source.get('src')
3257 if not src or not isinstance(src, compat_str):
63d990d2
S
3258 continue
3259 src = compat_urlparse.urljoin(url, src)
3260 src_type = source.get('type')
3261 if isinstance(src_type, compat_str):
3262 src_type = src_type.lower()
3263 ext = determine_ext(src).lower()
3264 if src_type == 'video/youtube':
3265 return self.url_result(src, YoutubeIE.ie_key())
3266 if src_type == 'application/dash+xml' or ext == 'mpd':
3267 formats.extend(self._extract_mpd_formats(
3268 src, video_id, mpd_id='dash', fatal=False))
3269 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3270 formats.extend(self._extract_m3u8_formats(
3271 src, video_id, 'mp4', entry_protocol='m3u8_native',
3272 m3u8_id='hls', fatal=False))
3273 else:
3274 formats.append({
3275 'url': src,
3089bc74
S
3276 'ext': (mimetype2ext(src_type)
3277 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
63d990d2
S
3278 })
3279 if formats:
3280 self._sort_formats(formats)
3281 info_dict['formats'] = formats
3282 return info_dict
3283
ff17be3a
S
3284 # Looking for http://schema.org/VideoObject
3285 json_ld = self._search_json_ld(
3286 webpage, video_id, default={}, expected_type='VideoObject')
3287 if json_ld.get('url'):
3288 return merge_dicts(json_ld, info_dict)
3289
ced659bb 3290 def check_video(vurl):
a0f71985
PH
3291 if YoutubeIE.suitable(vurl):
3292 return True
b7a8c1bc
S
3293 if RtmpIE.suitable(vurl):
3294 return True
ced659bb
S
3295 vpath = compat_urlparse.urlparse(vurl).path
3296 vext = determine_ext(vpath)
0ee79a37 3297 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
3298
3299 def filter_video(urls):
3300 return list(filter(check_video, urls))
3301
9b122384 3302 # Start with something easy: JW Player in SWFObject
ced659bb 3303 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 3304 if not found:
d981cef6 3305 # Look for gorilla-vid style embedding
ced659bb 3306 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
3307 (?:
3308 jw_plugins|
3309 JWPlayerOptions|
3310 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3311 )
a0f71985
PH
3312 .*?
3313 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 3314 if not found:
9b122384 3315 # Broaden the search a little bit
ced659bb 3316 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
3317 if not found:
3318 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 3319 found = filter_video(re.findall(
54a9328b 3320 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
3321 if not found:
3322 # Flow player
ced659bb 3323 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
3324 flowplayer\("[^"]+",\s*
3325 \{[^}]+?\}\s*,
52585fd6 3326 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 3327 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 3328 ''', webpage))
501f13fb
PH
3329 if not found:
3330 # Cinerama player
3331 found = re.findall(
3332 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 3333 if not found:
9b122384 3334 # Try to find twitter cards info
371ddb14
S
3335 # twitter:player:stream should be checked before twitter:player since
3336 # it is expected to contain a raw stream (see
3337 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3338 found = filter_video(re.findall(
3339 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 3340 if not found:
9b122384
PH
3341 # We look for Open Graph info:
3342 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3343 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3344 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3345 if m_video_type is not None:
ced659bb 3346 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 3347 if not found:
ed9a25dd 3348 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3349 found = re.search(
89ef304b 3350 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3351 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3352 webpage)
84f81016
S
3353 if not found:
3354 # Look also in Refresh HTTP header
3355 refresh_header = head_response.headers.get('Refresh')
3356 if refresh_header:
6c91a5a7
S
3357 # In python 2 response HTTP headers are bytestrings
3358 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3359 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3360 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3361 if found:
b37317d8 3362 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3363 if new_url != url:
3364 self.report_following_redirect(new_url)
3365 return {
3366 '_type': 'url',
3367 'url': new_url,
3368 }
3369 else:
3370 found = None
371ddb14
S
3371
3372 if not found:
3373 # twitter:player is a https URL to iframe player that may or may not
cefecac1 3374 # be supported by youtube-dlc thus this is checked the very last (see
371ddb14
S
3375 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3376 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3377 if embed_url and embed_url != url:
371ddb14
S
3378 return self.url_result(embed_url)
3379
b30b8698 3380 if not found:
416c7fcb 3381 raise UnsupportedError(url)
9b122384 3382
b30b8698 3383 entries = []
4a120778 3384 for video_url in orderedSet(found):
949b6497 3385 video_url = unescapeHTML(video_url)
6cc37c69 3386 video_url = video_url.replace('\\/', '/')
b30b8698 3387 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3388 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3389
b30b8698
PH
3390 # Sometimes, jwplayer extraction will result in a YouTube URL
3391 if YoutubeIE.suitable(video_url):
3392 entries.append(self.url_result(video_url, 'Youtube'))
3393 continue
9b122384 3394
b30b8698
PH
3395 # here's a fun little line of code for you:
3396 video_id = os.path.splitext(video_id)[0]
fc9713a1 3397
28602e74
YCH
3398 entry_info_dict = {
3399 'id': video_id,
3400 'uploader': video_uploader,
3401 'title': video_title,
3402 'age_limit': age_limit,
3403 }
3404
5620f840
S
3405 if RtmpIE.suitable(video_url):
3406 entry_info_dict.update({
3407 '_type': 'url_transparent',
3408 'ie_key': RtmpIE.ie_key(),
3409 'url': video_url,
3410 })
3411 entries.append(entry_info_dict)
3412 continue
3413
729accb4
S
3414 ext = determine_ext(video_url)
3415 if ext == 'smil':
28602e74 3416 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
3417 elif ext == 'xspf':
3418 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
3419 elif ext == 'm3u8':
3420 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
3421 elif ext == 'mpd':
3422 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
3423 elif ext == 'f4m':
3424 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3425 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3426 # Just matching .ism/manifest is not enough to be reliably sure
3427 # whether it's actually an ISM manifest or some other streaming
3428 # manifest since there are various streaming URL formats
3429 # possible (see [1]) as well as some other shenanigans like
3430 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3431 # so on.
3432 # Thus the most reasonable way to solve this is to delegate
3433 # to generic extractor in order to look into the contents of
3434 # the manifest itself.
3435 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3436 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3437 entry_info_dict = self.url_result(
3438 smuggle_url(video_url, {'to_generic': True}),
3439 GenericIE.ie_key())
d6fd958c 3440 else:
28602e74
YCH
3441 entry_info_dict['url'] = video_url
3442
19dbaeec
S
3443 if entry_info_dict.get('formats'):
3444 self._sort_formats(entry_info_dict['formats'])
3445
28602e74 3446 entries.append(entry_info_dict)
b30b8698
PH
3447
3448 if len(entries) == 1:
669f0e7c 3449 return entries[0]
b30b8698
PH
3450 else:
3451 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3452 # 'url' results don't have a title
3453 if e.get('title') is not None:
3454 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3455 return {
3456 '_type': 'playlist',
3457 'entries': entries,
3458 }