]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
[odnoklassniki] Improve _VALID_URL readability
[yt-dlp.git] / youtube_dl / 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
S
25 KNOWN_EXTENSIONS,
26 mimetype2ext,
ed2d6a19 27 orderedSet,
5c2266df 28 sanitized_Request,
9d4660ca
PH
29 smuggle_url,
30 unescapeHTML,
42393ce2 31 unified_strdate,
4d54ef20 32 unsmuggle_url,
416c7fcb 33 UnsupportedError,
76c73715 34 xpath_text,
9b122384 35)
b7a8c1bc 36from .commonprotocols import RtmpIE
ed126900 37from .brightcove import (
4fcaa4f4 38 BrightcoveLegacyIE,
5c17f0a6 39 BrightcoveNewIE,
ed126900 40)
3f59b015
S
41from .nexx import (
42 NexxIE,
43 NexxEmbedIE,
44)
a2edf2e7 45from .nbc import NBCSportsVPlayerIE
c0d0b01f 46from .ooyala import OoyalaIE
93d020dd 47from .rutv import RUTVIE
954c1d05 48from .tvc import TVCIE
d40a3b5b 49from .sportbox import SportBoxEmbedIE
cb3ac1c6 50from .smotri import SmotriIE
6dd94d3a 51from .myvi import MyviIE
1419fafd 52from .condenast import CondeNastIE
418c5cc3 53from .udn import UDNEmbedIE
2fe1b5bd 54from .senateisvp import SenateISVPIE
bab19a8e 55from .svt import SVTIE
65d161c4 56from .pornhub import PornHubIE
2bb5b6d0 57from .xhamster import XHamsterEmbedIE
2c9ca782 58from .tnaflix import TNAFlixNetworkEmbedIE
37e7a71c 59from .drtuber import DrTuberIE
e28ed498 60from .redtube import RedTubeIE
b407e173 61from .vimeo import VimeoIE
3c4fbfec 62from .dailymotion import DailymotionIE
71a1db89 63from .dailymail import DailyMailIE
1ac1c4c2 64from .onionstudios import OnionStudiosIE
67167920 65from .viewlift import ViewLiftEmbedIE
46fde8a1 66from .mtv import MTVServicesEmbeddedIE
45dad7ba 67from .pladform import PladformIE
ff18735c 68from .videomore import VideomoreIE
83f1481b 69from .webcaster import WebcasterFeedIE
5b251628 70from .googledrive import GoogleDriveIE
7cb09524 71from .jwplatform import JWPlatformIE
aecfcd4e 72from .digiteka import DigitekaIE
1979969f 73from .arkena import ArkenaIE
5a51775a 74from .instagram import InstagramIE
b8f67449 75from .liveleak import LiveLeakIE
5d39176f 76from .threeqsdn import ThreeQSDNIE
4d8819d2 77from .theplatform import ThePlatformIE
48a5eabc 78from .vessel import VesselIE
c287f2bc 79from .kaltura import KalturaIE
06a96da1 80from .eagleplatform import EaglePlatformIE
fd6ca382 81from .facebook import FacebookIE
94aae015 82from .soundcloud import SoundcloudIE
027e2312 83from .tunein import TuneInBaseIE
2a1321a2 84from .vbox7 import Vbox7IE
b0c8f2e9 85from .dbtv import DBTVIE
b1c35797 86from .piksel import PikselIE
e186a9ec 87from .videa import VideaIE
b687c85e 88from .twentymin import TwentyMinutenIE
d77ac737 89from .ustream import UstreamIE
17f8deeb 90from .openload import OpenloadIE
6ef3e65a 91from .videopress import VideoPressIE
eb3079b6 92from .rutube import RutubeIE
e5d39886 93from .limelight import LimelightBaseIE
7986c3ab 94from .anvato import AnvatoIE
55719459 95from .washingtonpost import WashingtonPostIE
58bb4402 96from .wistia import WistiaIE
5d29af3d 97from .mediaset import MediasetIE
73cf76a9 98from .joj import JojIE
24e966e8 99from .megaphone import MegaphoneIE
41918eaa 100from .vzaar import VzaarIE
26bae2d9 101from .channel9 import Channel9IE
0987f2dd 102from .vshare import VShareIE
2ca7ed41 103from .mediasite import MediasiteIE
7d540621 104from .springboardplatform import SpringboardPlatformIE
4c780fbd 105from .yapfiles import YapFilesIE
86c8cfc5 106from .vice import ViceIE
178ee883 107from .xfileshare import XFileShareIE
9b122384 108
0838239e 109
9b122384 110class GenericIE(InfoExtractor):
79649588 111 IE_DESC = 'Generic downloader that works on some sites'
9b122384 112 _VALID_URL = r'.*'
79649588 113 IE_NAME = 'generic'
cfe50f04 114 _TESTS = [
c5fa81fe
S
115 # Direct link to a video
116 {
117 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
118 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
119 'info_dict': {
120 'id': 'trailer',
121 'ext': 'mp4',
122 'title': 'trailer',
123 'upload_date': '20100513',
124 }
125 },
c5138a7c 126 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
127 {
128 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
129 'md5': '128c42e68b13950268b648275386fc74',
130 'info_dict': {
131 'id': 'FictionJunction-Parallel_Hearts',
132 'ext': 'flac',
133 'title': 'FictionJunction-Parallel_Hearts',
134 'upload_date': '20140522',
135 },
136 'expected_warnings': [
137 'URL could be a direct video link, returning it as such.'
39efc6e3
YCH
138 ],
139 'skip': 'URL invalid',
c5fa81fe
S
140 },
141 # Direct download with broken HEAD
142 {
143 'url': 'http://ai-radio.org:8000/radio.opus',
144 'info_dict': {
145 'id': 'radio',
146 'ext': 'opus',
147 'title': 'radio',
148 },
149 'params': {
150 'skip_download': True, # infinite live stream
151 },
152 'expected_warnings': [
ef0e4e7b
YCH
153 r'501.*Not Implemented',
154 r'400.*Bad Request',
c5fa81fe
S
155 ],
156 },
157 # Direct link with incorrect MIME type
158 {
159 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
160 'md5': '4ccbebe5f36706d85221f204d7eb5913',
161 'info_dict': {
162 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
163 'id': '5_Lennart_Poettering_-_Systemd',
164 'ext': 'webm',
165 'title': '5_Lennart_Poettering_-_Systemd',
166 'upload_date': '20141120',
167 },
168 'expected_warnings': [
169 'URL could be a direct video link, returning it as such.'
170 ]
171 },
172 # RSS feed
173 {
174 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
175 'info_dict': {
176 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
177 'title': 'Zero Punctuation',
178 'description': 're:.*groundbreaking video review series.*'
179 },
180 'playlist_mincount': 11,
181 },
182 # RSS feed with enclosure
183 {
184 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
185 'info_dict': {
186 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
187 'ext': 'm4v',
188 'upload_date': '20150228',
189 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
190 }
191 },
8765222d
S
192 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
193 {
194 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
195 'info_dict': {
196 'id': 'smil',
197 'ext': 'mp4',
198 'title': 'Automatics, robotics and biocybernetics',
199 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 200 'upload_date': '20130627',
8765222d
S
201 'formats': 'mincount:16',
202 'subtitles': 'mincount:1',
203 },
204 'params': {
205 'force_generic_extractor': True,
206 'skip_download': True,
207 },
208 },
209 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
210 {
211 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
212 'info_dict': {
213 'id': 'hds',
214 'ext': 'flv',
215 'title': 'hds',
216 'formats': 'mincount:1',
217 },
218 'params': {
219 'skip_download': True,
220 },
221 },
222 # SMIL from https://www.restudy.dk/video/play/id/1637
223 {
224 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
225 'info_dict': {
226 'id': 'video_1637',
227 'ext': 'flv',
228 'title': 'video_1637',
229 'formats': 'mincount:3',
230 },
231 'params': {
232 'skip_download': True,
233 },
234 },
235 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
236 {
237 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
238 'info_dict': {
239 'id': 'smil-service',
240 'ext': 'flv',
241 'title': 'smil-service',
242 'formats': 'mincount:1',
243 },
244 'params': {
245 'skip_download': True,
246 },
247 },
248 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
249 {
250 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
251 'info_dict': {
252 'id': '4719370',
253 'ext': 'mp4',
254 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
255 'formats': 'mincount:3',
256 },
257 'params': {
258 'skip_download': True,
259 },
260 },
1de5cd3b
S
261 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
262 {
263 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
264 'info_dict': {
265 'id': 'mZlp2ctYIUEB',
266 'ext': 'mp4',
267 'title': 'Tikibad ontruimd wegens brand',
268 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
ec85ded8 269 'thumbnail': r're:^https?://.*\.jpg$',
1de5cd3b
S
270 'duration': 33,
271 },
272 'params': {
273 'skip_download': True,
274 },
275 },
9d939cec
S
276 # MPD from http://dash-mse-test.appspot.com/media.html
277 {
278 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
279 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
280 'info_dict': {
281 'id': 'car-20120827-manifest',
282 'ext': 'mp4',
283 'title': 'car-20120827-manifest',
284 'formats': 'mincount:9',
0738187f 285 'upload_date': '20130904',
9d939cec
S
286 },
287 'params': {
288 'format': 'bestvideo',
289 },
290 },
20938f76
S
291 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
292 {
293 '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',
294 'info_dict': {
295 'id': 'content',
296 'ext': 'mp4',
297 'title': 'content',
298 'formats': 'mincount:8',
299 },
300 'params': {
301 # m3u8 downloads
302 'skip_download': True,
39efc6e3
YCH
303 },
304 'skip': 'video gone',
20938f76 305 },
edd9b71c
S
306 # m3u8 served with Content-Type: text/plain
307 {
308 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
309 'info_dict': {
310 'id': 'index',
311 'ext': 'mp4',
312 'title': 'index',
313 'upload_date': '20140720',
314 'formats': 'mincount:11',
315 },
316 'params': {
317 # m3u8 downloads
318 'skip_download': True,
39efc6e3
YCH
319 },
320 'skip': 'video gone',
edd9b71c 321 },
c5fa81fe
S
322 # google redirect
323 {
324 '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',
325 'info_dict': {
326 'id': 'cmQHVoWB5FY',
327 'ext': 'mp4',
328 'upload_date': '20130224',
329 'uploader_id': 'TheVerge',
ec85ded8 330 'description': r're:^Chris Ziegler takes a look at the\.*',
c5fa81fe
S
331 'uploader': 'The Verge',
332 'title': 'First Firefox OS phones side-by-side',
333 },
334 'params': {
335 'skip_download': False,
336 }
337 },
6c91a5a7
S
338 {
339 # redirect in Refresh HTTP header
340 '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',
341 'info_dict': {
342 'id': 'pO8h3EaFRdo',
343 'ext': 'mp4',
344 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
345 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
346 'upload_date': '20150917',
347 'uploader_id': 'brtvofficial',
348 'uploader': 'Boiler Room',
349 },
350 'params': {
351 'skip_download': False,
352 },
353 },
cfe50f04 354 {
79649588 355 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 356 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 357 'info_dict': {
d360a146
S
358 'id': '13601338388002',
359 'ext': 'mp4',
79649588
PH
360 'uploader': 'www.hodiho.fr',
361 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
362 }
363 },
c19f7764
JMF
364 # bandcamp page with custom domain
365 {
79649588
PH
366 'add_ie': ['Bandcamp'],
367 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 368 'info_dict': {
fd50bf62
S
369 'id': '3235767654',
370 'ext': 'mp3',
79649588
PH
371 'title': 'The Pony Mash',
372 'uploader': 'M_Pallante',
c19f7764 373 },
79649588 374 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 375 },
eeb165e6 376 {
53a664ed
S
377 # embedded brightcove video
378 # it also tests brightcove videos that need to set the 'Referer'
379 # in the http requests
3b7d9aa4 380 'add_ie': ['BrightcoveLegacy'],
79649588
PH
381 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
382 'info_dict': {
383 'id': '2765128793001',
384 'ext': 'mp4',
385 'title': 'Le cours de bourse : l’analyse technique',
386 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
387 'uploader': 'BFM BUSINESS',
eeb165e6 388 },
79649588
PH
389 'params': {
390 'skip_download': True,
eeb165e6
JMF
391 },
392 },
53a664ed
S
393 {
394 # embedded with itemprop embedURL and video id spelled as `idVideo`
395 'add_id': ['BrightcoveLegacy'],
396 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
397 'info_dict': {
398 'id': '5255628253001',
399 'ext': 'mp4',
400 'title': 'md5:37c519b1128915607601e75a87995fc0',
401 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
402 'uploader': 'BFM BUSINESS',
403 'uploader_id': '876450612001',
404 'timestamp': 1482255315,
405 'upload_date': '20161220',
406 },
407 'params': {
408 'skip_download': True,
409 },
410 },
17ab4d3b
PH
411 {
412 # https://github.com/rg3/youtube-dl/issues/2253
413 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
414 'md5': '0ba9446db037002366bab3b3eb30c88c',
415 'info_dict': {
fd50bf62
S
416 'id': '3101154703001',
417 'ext': 'mp4',
17ab4d3b
PH
418 'title': 'Still no power',
419 'uploader': 'thestar.com',
420 '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.',
421 },
3b7d9aa4 422 'add_ie': ['BrightcoveLegacy'],
39efc6e3 423 'skip': 'video gone',
17ab4d3b 424 },
0479c625
S
425 {
426 'url': 'http://www.championat.com/video/football/v/87/87499.html',
427 'md5': 'fb973ecf6e4a78a67453647444222983',
428 'info_dict': {
429 'id': '3414141473001',
430 'ext': 'mp4',
431 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
432 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
433 'uploader': 'Championat',
434 },
435 },
bdf97017 436 {
37aab278 437 # https://github.com/rg3/youtube-dl/issues/3541
3b7d9aa4 438 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
439 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
440 'info_dict': {
441 'id': '3866516442001',
37aab278 442 'ext': 'mp4',
bdf97017
NJ
443 'title': 'Leer mij vrouwen kennen: Aflevering 1',
444 'description': 'Leer mij vrouwen kennen: Aflevering 1',
445 'uploader': 'SBS Broadcasting',
446 },
37aab278 447 'skip': 'Restricted to Netherlands',
bdf97017 448 'params': {
37aab278 449 'skip_download': True, # m3u8 download
bdf97017
NJ
450 },
451 },
06d0ad9a
YCH
452 {
453 # Brightcove video in <iframe>
454 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
455 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
456 'info_dict': {
457 'id': '5360463607001',
458 'ext': 'mp4',
459 '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',
460 '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。',
461 'uploader': 'United Nations',
462 'uploader_id': '1362235914001',
463 'timestamp': 1489593889,
464 'upload_date': '20170315',
465 },
466 'add_ie': ['BrightcoveLegacy'],
467 },
16e2c8f7
YCH
468 {
469 # Brightcove with alternative playerID key
470 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
471 'info_dict': {
472 'id': 'nmeth.2062_SV1',
473 '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',
474 },
475 'playlist': [{
476 'info_dict': {
477 'id': '2228375078001',
478 'ext': 'mp4',
479 'title': 'nmeth.2062-sv1',
480 'description': 'nmeth.2062-sv1',
481 'timestamp': 1363357591,
482 'upload_date': '20130315',
483 'uploader': 'Nature Publishing Group',
484 'uploader_id': '1964492299001',
485 },
486 }],
487 },
40158f55
JH
488 {
489 # Brightcove with UUID in videoPlayer
490 'url': 'http://www8.hp.com/cn/zh/home.html',
491 'info_dict': {
492 'id': '5255815316001',
493 'ext': 'mp4',
494 'title': 'Sprocket Video - China',
495 'description': 'Sprocket Video - China',
496 'uploader': 'HP-Video Gallery',
497 'timestamp': 1482263210,
498 'upload_date': '20161220',
499 'uploader_id': '1107601872001',
500 },
501 'params': {
502 'skip_download': True, # m3u8 download
503 },
504 'skip': 'video rotates...weekly?',
505 },
506 {
507 # Brightcove:new type [2].
508 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
509 'md5': '2b35148fcf48da41c9fb4591650784f3',
510 'info_dict': {
511 'id': '5348741021001',
512 'ext': 'mp4',
513 'upload_date': '20170306',
514 'uploader_id': '4191638492001',
515 'timestamp': 1488769918,
516 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
517
518 },
519 },
520 {
521 # Alternative brightcove <video> attributes
522 '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/',
523 'info_dict': {
524 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
525 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
526 },
527 'playlist': [{
528 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
529 'info_dict': {
530 'id': '5311302538001',
531 'ext': 'mp4',
532 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
533 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
534 'timestamp': 1486321708,
535 'upload_date': '20170205',
536 'uploader_id': '800000640001',
537 },
538 'only_matching': True,
539 }],
540 },
b68a812e
S
541 {
542 # Brightcove with UUID in videoPlayer
543 'url': 'http://www8.hp.com/cn/zh/home.html',
544 'info_dict': {
545 'id': '5255815316001',
546 'ext': 'mp4',
547 'title': 'Sprocket Video - China',
548 'description': 'Sprocket Video - China',
549 'uploader': 'HP-Video Gallery',
550 'timestamp': 1482263210,
551 'upload_date': '20161220',
552 'uploader_id': '1107601872001',
553 },
554 'params': {
555 'skip_download': True, # m3u8 download
556 },
557 },
c0d0b01f
JMF
558 # ooyala video
559 {
79649588 560 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 561 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
562 'info_dict': {
563 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
564 'ext': 'mp4',
3486df38 565 'title': '2cc213299525360.mov', # that's what we get
53e06b25 566 'duration': 238.231,
c0d0b01f 567 },
87830900 568 'add_ie': ['Ooyala'],
c0d0b01f 569 },
bf94d763
S
570 {
571 # ooyala video embedded with http://player.ooyala.com/iframe.js
572 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
573 'info_dict': {
574 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
575 'ext': 'mp4',
576 'title': '"Steve Jobs: Man in the Machine" trailer',
577 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 578 'duration': 135.427,
bf94d763
S
579 },
580 'params': {
581 'skip_download': True,
582 },
39efc6e3 583 'skip': 'movie expired',
bf94d763 584 },
198d4cb4
GR
585 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
586 {
587 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
588 'info_dict': {
589 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
590 'ext': 'mp4',
591 'title': 'Steampunk Fest Comes to Honesdale',
592 'duration': 43.276,
593 },
594 'params': {
595 'skip_download': True,
596 }
597 },
1b86cc41 598 # embed.ly video
599 {
600 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
601 'info_dict': {
602 'id': '9ODmcdjQcHQ',
603 'ext': 'mp4',
0a5bce56
PH
604 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
605 'upload_date': '20140225',
606 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
607 'uploader': 'Tested',
608 'uploader_id': 'testedcom',
1b86cc41 609 },
610 # No need to test YoutubeIE here
611 'params': {
612 'skip_download': True,
613 },
614 },
60cc4dc4
PH
615 # funnyordie embed
616 {
617 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
618 'info_dict': {
619 'id': '18e820ec3f',
620 'ext': 'mp4',
621 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
622 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 623 },
39efc6e3
YCH
624 # HEAD requests lead to endless 301, while GET is OK
625 'expected_warnings': ['301'],
60cc4dc4 626 },
93d020dd
S
627 # RUTV embed
628 {
629 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
630 'info_dict': {
631 'id': '776940',
632 'ext': 'mp4',
633 'title': 'Охотское море стало целиком российским',
634 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
635 },
636 'params': {
637 # m3u8 download
638 'skip_download': True,
639 },
aab74fa1 640 },
f37bdbe5
S
641 # TVC embed
642 {
643 '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/',
644 'info_dict': {
645 'id': '55304',
646 'ext': 'mp4',
647 'title': 'Дошкольное воспитание',
648 },
649 },
b827a601
S
650 # SportBox embed
651 {
652 'url': 'http://www.vestifinance.ru/articles/25753',
653 'info_dict': {
654 'id': '25753',
05d1e7aa 655 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
b827a601
S
656 },
657 'playlist': [{
658 'info_dict': {
659 'id': '370908',
660 'title': 'Госзаказ. День 3',
661 'ext': 'mp4',
662 }
663 }, {
664 'info_dict': {
665 'id': '370905',
666 'title': 'Госзаказ. День 2',
667 'ext': 'mp4',
668 }
669 }, {
670 'info_dict': {
671 'id': '370902',
672 'title': 'Госзаказ. День 1',
673 'ext': 'mp4',
674 }
675 }],
676 'params': {
677 # m3u8 download
678 'skip_download': True,
679 },
680 },
bf20b9c5
S
681 # Myvi.ru embed
682 {
683 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
684 'info_dict': {
685 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
686 'ext': 'mp4',
687 'title': 'Ужастики, русский трейлер (2015)',
ec85ded8 688 'thumbnail': r're:^https?://.*\.jpg$',
bf20b9c5
S
689 'duration': 153,
690 }
691 },
c76799c5
S
692 # XHamster embed
693 {
694 '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',
695 'info_dict': {
696 'id': 'showthread',
697 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
698 },
699 'playlist_mincount': 7,
39efc6e3
YCH
700 # This forum does not allow <iframe> syntaxes anymore
701 # Now HTML tags are displayed as-is
702 'skip': 'No videos on this page',
c76799c5 703 },
aab74fa1
PH
704 # Embedded TED video
705 {
706 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 707 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 708 'info_dict': {
a8eb5a8e 709 'id': '1969',
aab74fa1 710 'ext': 'mp4',
a8eb5a8e
PH
711 'title': 'Hidden miracles of the natural world',
712 'uploader': 'Louie Schwartzberg',
713 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 714 }
60cc4dc4 715 },
d95e35d6
S
716 # nowvideo embed hidden behind percent encoding
717 {
718 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
719 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
720 'info_dict': {
721 'id': '06e53103ca9aa',
722 'ext': 'flv',
723 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
724 'description': 'No description',
725 },
0f2a2ba1 726 },
893f8832
PH
727 # arte embed
728 {
729 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
730 'md5': '7653032cbb25bf6c80d80f217055fa43',
731 'info_dict': {
732 'id': '048195-004_PLUS7-F',
733 'ext': 'flv',
734 'title': 'X:enius',
735 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
736 'upload_date': '20140320',
737 },
738 'params': {
739 'skip_download': 'Requires rtmpdump'
39efc6e3
YCH
740 },
741 'skip': 'video gone',
893f8832 742 },
cbd55ade
S
743 # francetv embed
744 {
745 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
746 'info_dict': {
747 'id': 'EV_30231',
748 'ext': 'mp4',
749 'title': 'Alcaline, le concert avec Calogero',
750 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
751 'upload_date': '20150226',
752 'timestamp': 1424989860,
753 'duration': 5400,
754 },
755 'params': {
756 # m3u8 downloads
757 'skip_download': True,
758 },
759 'expected_warnings': [
760 'Forbidden'
761 ]
762 },
fa35cdad
PH
763 # Condé Nast embed
764 {
765 'url': 'http://www.wired.com/2014/04/honda-asimo/',
766 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
767 'info_dict': {
768 'id': '53501be369702d3275860000',
769 'ext': 'mp4',
770 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
771 }
ebd3c7b3
PH
772 },
773 # Dailymotion embed
774 {
775 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
776 'md5': '441aeeb82eb72c422c7f14ec533999cd',
777 'info_dict': {
778 'id': 'k2mm4bCdJ6CQ2i7c8o2',
779 'ext': 'mp4',
780 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 781 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 782 'uploader': 'Spi0n',
0738187f
YCH
783 'uploader_id': 'xgditw',
784 'upload_date': '20140425',
785 'timestamp': 1398441542,
ebd3c7b3
PH
786 },
787 'add_ie': ['Dailymotion'],
2b88feed 788 },
71a1db89
S
789 # DailyMail embed
790 {
791 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
792 'info_dict': {
793 'id': '1495629',
794 'ext': 'mp4',
795 'title': 'Care worker punches elderly dementia patient in head 11 times',
796 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
797 },
798 'add_ie': ['DailyMail'],
799 'params': {
800 'skip_download': True,
801 },
802 },
2b88feed
PH
803 # YouTube embed
804 {
805 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
806 'info_dict': {
807 'id': 'FXRb4ykk4S0',
808 'ext': 'mp4',
809 'title': 'The NBL Auction 2014',
810 'uploader': 'BADMINTON England',
811 'uploader_id': 'BADMINTONEvents',
812 'upload_date': '20140603',
813 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
814 },
815 'add_ie': ['Youtube'],
816 'params': {
817 'skip_download': True,
818 }
819 },
c5cd249e
JMF
820 # MTVSercices embed
821 {
1fa309da
YCH
822 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
823 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 824 'info_dict': {
1fa309da 825 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 826 'ext': 'mp4',
1fa309da
YCH
827 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
828 'description': 'Two valets share their love for movie star Liam Neesons.',
05d1e7aa
YCH
829 'timestamp': 1349922600,
830 'upload_date': '20121011',
c5cd249e
JMF
831 },
832 },
61013473 833 # YouTube embed via <data-embed-url="">
834 {
835 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 836 'info_dict': {
a8eb5a8e 837 'id': '4vAffPZIT44',
61013473 838 'ext': 'mp4',
a8eb5a8e 839 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
840 'uploader': 'Gameloft',
841 'uploader_id': 'gameloft',
a8eb5a8e
PH
842 'upload_date': '20140828',
843 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
844 },
845 'params': {
846 'skip_download': True,
61013473 847 }
c8e9a235 848 },
61568e50
JH
849 # YouTube <object> embed
850 {
851 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
852 'md5': '516718101ec834f74318df76259fb3cc',
853 'info_dict': {
854 'id': 'msN87y-iEx0',
855 'ext': 'webm',
856 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
857 'upload_date': '20080526',
858 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
859 'uploader': 'Christopher Sykes',
860 'uploader_id': 'ChristopherJSykes',
861 },
862 'add_ie': ['Youtube'],
863 },
c8e9a235
PH
864 # Camtasia studio
865 {
866 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
867 'playlist': [{
868 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
869 'info_dict': {
870 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
871 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
872 'ext': 'flv',
873 'duration': 2235.90,
874 }
875 }, {
876 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
877 'info_dict': {
878 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
879 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
880 'ext': 'flv',
881 'duration': 2235.93,
882 }
883 }],
884 'info_dict': {
885 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
886 }
4d805e06
PH
887 },
888 # Flowplayer
889 {
890 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
891 'md5': '9d65602bf31c6e20014319c7d07fba27',
892 'info_dict': {
893 'id': '5123ea6d5e5a7',
894 'ext': 'mp4',
895 'age_limit': 18,
896 'uploader': 'www.handjobhub.com',
d6d9186f 897 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 898 }
0990305d 899 },
22a6f150
PH
900 # Multiple brightcove videos
901 # https://github.com/rg3/youtube-dl/issues/2283
902 {
903 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
904 'info_dict': {
905 'id': 'always-never',
906 'title': 'Always / Never - The New Yorker',
907 },
908 'playlist_count': 3,
909 'params': {
910 'extract_flat': False,
911 'skip_download': True,
912 }
1a94ff68
S
913 },
914 # MLB embed
915 {
916 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
917 'md5': '96f09a37e44da40dd083e12d9a683327',
918 'info_dict': {
919 'id': '33322633',
920 'ext': 'mp4',
921 'title': 'Ump changes call to ball',
922 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
923 'duration': 48,
924 'timestamp': 1401537900,
925 'upload_date': '20140531',
ec85ded8 926 'thumbnail': r're:^https?://.*\.jpg$',
1a94ff68
S
927 },
928 },
746c67d7
NJ
929 # Wistia embed
930 {
6c114b12
S
931 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
932 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 933 'info_dict': {
6c114b12 934 'id': '6e2wtrbdaf',
746c67d7 935 'ext': 'mov',
6c114b12
S
936 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
937 'description': 'a Paywall Videos video from Remilon',
938 'duration': 644.072,
939 'uploader': 'study.com',
940 'timestamp': 1459678540,
941 'upload_date': '20160403',
942 'filesize': 24687186,
746c67d7
NJ
943 },
944 },
52cffcb1 945 {
946 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
947 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
948 'info_dict': {
949 'id': 'uxjb0lwrcz',
950 'ext': 'mp4',
6c114b12 951 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 952 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 953 'duration': 1715.0,
85d7b765 954 'uploader': 'thoughtworks.wistia.com',
0738187f 955 'timestamp': 1401832161,
6c114b12 956 'upload_date': '20140603',
70b7e3fb 957 },
52cffcb1 958 },
7ded6545
S
959 # Wistia standard embed (async)
960 {
961 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
962 'info_dict': {
963 'id': '807fafadvk',
964 'ext': 'mp4',
965 'title': 'Drip Brennan Dunn Workshop',
966 'description': 'a JV Webinars video from getdrip-1',
967 'duration': 4986.95,
7ded6545 968 'timestamp': 1463607249,
6c114b12 969 'upload_date': '20160518',
7ded6545
S
970 },
971 'params': {
972 'skip_download': True,
973 }
974 },
ac645ac7
PH
975 # Soundcloud embed
976 {
977 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
978 'info_dict': {
979 'id': '174391317',
980 'ext': 'mp3',
981 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
982 'uploader': 'Sophos Security',
983 'title': 'Chet Chat 171 - Oct 29, 2014',
984 'upload_date': '20141029',
985 }
af63fed7 986 },
db19df6c
S
987 # Soundcloud multiple embeds
988 {
989 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
990 'info_dict': {
991 'id': '52809',
992 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
993 },
994 'playlist_mincount': 7,
995 },
027e2312
S
996 # TuneIn station embed
997 {
998 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
999 'info_dict': {
1000 'id': '204146',
1001 'ext': 'mp3',
1002 'title': 'CNRV',
1003 'location': 'Paris, France',
1004 'is_live': True,
1005 },
1006 'params': {
1007 # Live stream
1008 'skip_download': True,
1009 },
1010 },
af63fed7
PH
1011 # Livestream embed
1012 {
1013 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1014 'info_dict': {
1015 'id': '67864563',
1016 'ext': 'flv',
1017 'upload_date': '20141112',
1018 'title': 'Rosetta #CometLanding webcast HL 10',
1019 }
1020 },
78d3b3e2
YCH
1021 # Another Livestream embed, without 'new.' in URL
1022 {
1023 'url': 'https://www.freespeech.org/',
1024 'info_dict': {
1025 'id': '123537347',
1026 'ext': 'mp4',
1027 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1028 },
1029 'params': {
1030 # Live stream
1031 'skip_download': True,
1032 },
1033 },
65f3a228
PH
1034 # LazyYT
1035 {
e8e4cc5a 1036 'url': 'https://skiplagged.com/',
65f3a228 1037 'info_dict': {
e8e4cc5a
JH
1038 'id': 'skiplagged',
1039 'title': 'Skiplagged: The smart way to find cheap flights',
65f3a228 1040 },
e8e4cc5a
JH
1041 'playlist_mincount': 1,
1042 'add_ie': ['Youtube'],
4e262a88 1043 },
42bdd9d0
PH
1044 # Cinchcast embed
1045 {
1046 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1047 'info_dict': {
1048 'id': '7141703',
1049 'ext': 'mp3',
1050 'upload_date': '20141126',
1051 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1052 }
1053 },
501f13fb
PH
1054 # Cinerama player
1055 {
1056 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1057 'info_dict': {
1058 'id': '730m_DandD_1901_512k',
1059 'ext': 'mp4',
1060 'uploader': 'www.abc.net.au',
1061 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1062 }
796df3c6
S
1063 },
1064 # embedded viddler video
1065 {
1066 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1067 'info_dict': {
1068 'id': '4d03aad9',
1069 'ext': 'mp4',
1070 'uploader': 'deadspin',
1071 'title': 'WALL-TO-GORTAT',
1072 'timestamp': 1422285291,
1073 'upload_date': '20150126',
1074 },
1075 'add_ie': ['Viddler'],
a0f71985 1076 },
2051acde
S
1077 # Libsyn embed
1078 {
1079 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1080 'info_dict': {
1081 'id': '3377616',
1082 'ext': 'mp3',
1083 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1084 'description': 'md5:601cb790edd05908957dae8aaa866465',
1085 'upload_date': '20150220',
1086 },
326fa4e6 1087 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
2051acde 1088 },
a0f71985
PH
1089 # jwplayer YouTube
1090 {
1091 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1092 'info_dict': {
1093 'id': 'Mrj4DVp2zeA',
1094 'ext': 'mp4',
f37e3f99 1095 'upload_date': '20150212',
a0f71985 1096 'uploader': 'The National Archives UK',
2637fadc 1097 'description': 'md5:8078af856dca76edc42910b61273dbbf',
a0f71985
PH
1098 'uploader_id': 'NationalArchives08',
1099 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1100 },
59b8ab58 1101 },
5620f840
S
1102 # jwplayer rtmp
1103 {
6899b1d9 1104 'url': 'http://www.suffolk.edu/sjc/live.php',
5620f840 1105 'info_dict': {
6899b1d9 1106 'id': 'live',
5620f840
S
1107 'ext': 'flv',
1108 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1109 'uploader': 'www.suffolk.edu',
1110 },
1111 'params': {
1112 'skip_download': True,
2637fadc 1113 },
6899b1d9 1114 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
5620f840 1115 },
a4a554a7
YCH
1116 # Complex jwplayer
1117 {
1118 'url': 'http://www.indiedb.com/games/king-machine/videos',
1119 'info_dict': {
1120 'id': 'videos',
1121 'ext': 'mp4',
1122 'title': 'king machine trailer 1',
2637fadc 1123 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
a4a554a7
YCH
1124 'thumbnail': r're:^https?://.*\.jpg$',
1125 },
1126 },
03486dbb
RU
1127 {
1128 # JWPlayer config passed as variable
1129 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1130 'info_dict': {
1131 'id': '3326530_hq',
1132 'ext': 'mp4',
1133 'title': 'ARIELE | Tube Cup',
1134 'uploader': 'www.txxx.com',
1135 'age_limit': 18,
1136 },
1137 'params': {
1138 'skip_download': True,
1139 }
1140 },
939be9ad
JH
1141 {
1142 # JWPlatform iframe
1143 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1144 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1145 'info_dict': {
1146 'id': 'O0c5JcKT',
1147 'ext': 'mp4',
1148 'upload_date': '20171122',
1149 'timestamp': 1511366290,
1150 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1151 },
805f5bf7 1152 'add_ie': [JWPlatformIE.ie_key()],
939be9ad 1153 },
63d990d2 1154 {
c5b7014a 1155 # Video.js embed, multiple formats
63d990d2
S
1156 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1157 'info_dict': {
1158 'id': 'yygqldloqIk',
1159 'ext': 'mp4',
1160 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1161 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1162 'upload_date': '20130314',
1163 'uploader': 'PROстое3D',
1164 'uploader_id': 'PROstoe3D',
1165 },
1166 'params': {
1167 'skip_download': True,
1168 },
1169 },
c5b7014a
S
1170 {
1171 # Video.js embed, single format
1172 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1173 'info_dict': {
1174 'id': 'watch',
1175 'ext': 'mp4',
1176 'title': 'Step 1 - Good Foundation',
1177 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1178 },
1179 'params': {
1180 'skip_download': True,
1181 },
1182 },
59b8ab58
PH
1183 # rtl.nl embed
1184 {
1185 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1186 'playlist_mincount': 5,
1187 'info_dict': {
1188 'id': 'aanslagen-kopenhagen',
2637fadc 1189 'title': 'Aanslagen Kopenhagen',
59b8ab58 1190 }
255fca5e
S
1191 },
1192 # Zapiks embed
1193 {
1194 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1195 'info_dict': {
1196 'id': '118046',
1197 'ext': 'mp4',
1198 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1199 }
1200 },
66e568de
S
1201 # Kaltura embed (different embed code)
1202 {
1203 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1204 'info_dict': {
1205 'id': '1_a52wc67y',
1206 'ext': 'flv',
1207 'upload_date': '20150127',
1208 'uploader_id': 'PremierMedia',
1209 'timestamp': int,
1210 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1211 },
1212 },
87703231
YCH
1213 # Kaltura embed with single quotes
1214 {
1215 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1216 'info_dict': {
1217 'id': '0_izeg5utt',
1218 'ext': 'mp4',
1219 'title': '35871',
1220 'timestamp': 1355743100,
1221 'upload_date': '20121217',
1222 'uploader_id': 'batchUser',
1223 },
1224 'add_ie': ['Kaltura'],
1225 },
427cd050
S
1226 {
1227 # Kaltura embedded via quoted entry_id
1228 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1229 'info_dict': {
1230 'id': '0_utuok90b',
1231 'ext': 'mp4',
1232 'title': '06_matthew_brender_raj_dutt',
1233 'timestamp': 1466638791,
1234 'upload_date': '20160622',
1235 },
1236 'add_ie': ['Kaltura'],
1237 'expected_warnings': [
1238 'Could not send HEAD request'
1239 ],
1240 'params': {
1241 'skip_download': True,
1242 }
1243 },
8ab7e6c4
YCH
1244 {
1245 # Kaltura embedded, some fileExt broken (#11480)
1246 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1247 'info_dict': {
1248 'id': '1_sgtvehim',
1249 'ext': 'mp4',
1250 'title': 'Our "Standard Models" of particle physics and cosmology',
1251 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1252 'timestamp': 1321158993,
1253 'upload_date': '20111113',
1254 'uploader_id': 'kps1',
1255 },
1256 'add_ie': ['Kaltura'],
1257 },
a01825a5
JH
1258 {
1259 # Kaltura iframe embed
1260 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1261 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1262 'info_dict': {
1263 'id': '0_f2cfbpwy',
1264 'ext': 'mp4',
1265 'title': 'I. M. Pei: A Centennial Celebration',
1266 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1267 'upload_date': '20170403',
1268 'uploader_id': 'batchUser',
1269 'timestamp': 1491232186,
1270 },
1271 'add_ie': ['Kaltura'],
1272 },
250b042c
S
1273 # referrer protected EaglePlatform embed
1274 {
1275 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1276 'info_dict': {
1277 'id': '582306',
1278 'ext': 'mp4',
1279 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1280 'thumbnail': r're:^https?://.*\.jpg$',
1281 'duration': 3382,
1282 'view_count': int,
1283 },
1284 'params': {
1285 'skip_download': True,
1286 },
135c9c42 1287 },
665e9452 1288 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1289 {
1290 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1291 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1292 'info_dict': {
1293 'id': '12820',
1294 'ext': 'mp4',
1295 'title': "'O Sole Mio",
ec85ded8 1296 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1297 'duration': 216,
1298 'view_count': int,
1299 },
250b042c
S
1300 'params': {
1301 'skip_download': True,
1302 },
2637fadc 1303 'skip': 'This video is unavailable.',
d47ae7f6 1304 },
f8388757
S
1305 # Pladform embed
1306 {
1307 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1308 'info_dict': {
1309 'id': '100183293',
1310 'ext': 'mp4',
62259846 1311 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1312 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1313 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1314 'duration': 694,
1315 'age_limit': 0,
1316 },
2637fadc 1317 'skip': 'HTTP Error 404: Not Found',
f8388757 1318 },
c798f15b
S
1319 # Playwire embed
1320 {
1321 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1322 'info_dict': {
1323 'id': '3519514',
1324 'ext': 'mp4',
1325 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1326 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1327 'duration': 45.115,
1328 },
1329 },
ad320e9b
NJ
1330 # 5min embed
1331 {
1332 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1333 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1334 'info_dict': {
1335 'id': '518726732',
1336 'ext': 'mp4',
1337 'title': 'Facebook Creates "On This Day" | Crunch Report',
2637fadc
RA
1338 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1339 'timestamp': 1427237531,
1340 'uploader': 'Crunch Report',
1341 'upload_date': '20150324',
1342 },
1343 'params': {
1344 # m3u8 download
1345 'skip_download': True,
ad320e9b
NJ
1346 },
1347 },
dc455a5f
S
1348 # SVT embed
1349 {
1350 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1351 'info_dict': {
1352 'id': '2900353',
1353 'ext': 'flv',
1354 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1355 'duration': 27,
1356 'age_limit': 0,
1357 },
1358 },
a4257017
S
1359 # Crooks and Liars embed
1360 {
1361 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1362 'info_dict': {
1363 'id': '8RUoRhRi',
1364 'ext': 'mp4',
1365 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1366 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1367 'timestamp': 1428207000,
1368 'upload_date': '20150405',
1369 'uploader': 'Heather',
1370 },
1371 },
1372 # Crooks and Liars external embed
1373 {
1374 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1375 'info_dict': {
1376 'id': 'MTE3MjUtMzQ2MzA',
1377 'ext': 'mp4',
1378 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1379 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1380 'timestamp': 1265032391,
1381 'upload_date': '20100201',
1382 'uploader': 'Heather',
1383 },
1384 },
facecb84 1385 # NBC Sports vplayer embed
a2edf2e7 1386 {
facecb84 1387 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1388 'info_dict': {
facecb84
S
1389 'id': 'ln7x1qSThw4k',
1390 'ext': 'flv',
1391 'title': "PFT Live: New leader in the 'new-look' defense",
1392 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1393 'uploader': 'NBCU-SPORTS',
1394 'upload_date': '20140107',
1395 'timestamp': 1389118457,
a2edf2e7 1396 },
2637fadc 1397 'skip': 'Invalid Page URL',
418c5cc3 1398 },
de3eb07e
YCH
1399 # NBC News embed
1400 {
1401 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1402 'md5': '1aa589c675898ae6d37a17913cf68d66',
1403 'info_dict': {
2637fadc 1404 'id': 'x_dtl_oa_LettermanliftPR_160608',
de3eb07e 1405 'ext': 'mp4',
2637fadc 1406 'title': 'David Letterman: A Preview',
de3eb07e 1407 '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
1408 'upload_date': '20160609',
1409 'timestamp': 1465431544,
1410 'uploader': 'NBCU-NEWS',
de3eb07e
YCH
1411 },
1412 },
418c5cc3
YCH
1413 # UDN embed
1414 {
811586eb 1415 'url': 'https://video.udn.com/news/300346',
01c58f84 1416 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1417 'info_dict': {
01c58f84 1418 'id': '300346',
418c5cc3 1419 'ext': 'mp4',
01c58f84 1420 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1421 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1422 },
1423 'params': {
1424 # m3u8 download
1425 'skip_download': True,
1426 },
2637fadc 1427 'expected_warnings': ['Failed to parse JSON Expecting value'],
edfcf7ab
YCH
1428 },
1429 # Ooyala embed
1430 {
1431 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1432 'info_dict': {
1433 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1434 'ext': 'mp4',
2637fadc 1435 'description': 'Index/Match versus VLOOKUP.',
edfcf7ab 1436 'title': 'This is what separates the Excel masters from the wannabes',
53e06b25 1437 'duration': 191.933,
edfcf7ab
YCH
1438 },
1439 'params': {
1440 # m3u8 downloads
1441 'skip_download': True,
1442 }
d6fd958c 1443 },
b26733ba
YCH
1444 # Brightcove URL in single quotes
1445 {
1446 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1447 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1448 'info_dict': {
1449 'id': '4255764656001',
1450 'ext': 'mp4',
1451 'title': 'SN Presents: Russell Martin, World Citizen',
1452 '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.',
1453 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1454 'uploader_id': '1704050871',
1455 'upload_date': '20150525',
1456 'timestamp': 1432570283,
b26733ba 1457 },
756f574e 1458 },
8084be78
S
1459 # OnionStudios embed
1460 {
1461 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1462 'info_dict': {
1463 'id': '2855',
1464 'ext': 'mp4',
1465 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
ec85ded8 1466 'thumbnail': r're:^https?://.*\.jpe?g$',
8084be78
S
1467 'uploader': 'ClickHole',
1468 'uploader_id': 'clickhole',
1469 }
1470 },
b8c1cc1a
S
1471 # SnagFilms embed
1472 {
1473 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1474 'info_dict': {
1475 'id': '74849a00-85a9-11e1-9660-123139220831',
1476 'ext': 'mp4',
1477 'title': '#whilewewatch',
1478 }
1479 },
a5158f38
YCH
1480 # AdobeTVVideo embed
1481 {
1482 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1483 'md5': '43662b577c018ad707a63766462b1e87',
1484 'info_dict': {
1485 'id': '2456',
1486 'ext': 'mp4',
1487 'title': 'New experience with Acrobat DC',
1488 'description': 'New experience with Acrobat DC',
1489 'duration': 248.667,
1490 },
1f812580 1491 },
ed126900 1492 # BrightcoveInPageEmbed embed
1493 {
1494 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1495 'info_dict': {
1496 'id': '4238694884001',
1497 'ext': 'flv',
1498 'title': 'Tabletop: Dread, Last Thoughts',
1499 'description': 'Tabletop: Dread, Last Thoughts',
1500 'duration': 51690,
1501 },
750b9ff0 1502 },
d10fe835
YCH
1503 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1504 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1505 {
1506 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1507 'info_dict': {
1508 'id': '4785848093001',
1509 'ext': 'mp4',
1510 'title': 'The Cardinal Pell Interview',
1511 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1512 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1513 'uploader_id': '2733773828001',
1514 'upload_date': '20160304',
1515 'timestamp': 1457083087,
d10fe835
YCH
1516 },
1517 'params': {
1518 # m3u8 downloads
1519 'skip_download': True,
1520 },
1521 },
9edf47df
S
1522 {
1523 # Brightcove embed with whitespace around attribute names
1524 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1525 'info_dict': {
1526 'id': '3167554373001',
1527 'ext': 'mp4',
1528 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1529 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1530 'uploader_id': '1079349493',
1531 'upload_date': '20140207',
1532 'timestamp': 1391810548,
1533 },
1534 'params': {
1535 'skip_download': True,
1536 },
1537 },
134c207e
YCH
1538 # Another form of arte.tv embed
1539 {
1540 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1541 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1542 'info_dict': {
1543 'id': '030273-562_PLUS7-F',
1544 'ext': 'mp4',
1545 'title': 'ARTE Reportage - Nulle part, en France',
1546 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1547 'upload_date': '20160409',
1548 },
1549 },
b8f67449
KM
1550 # LiveLeak embed
1551 {
1552 'url': 'http://www.wykop.pl/link/3088787/',
09747ba7 1553 'md5': '7619da8c820e835bef21a1efa2a0fc71',
b8f67449
KM
1554 'info_dict': {
1555 'id': '874_1459135191',
1556 'ext': 'mp4',
1557 'title': 'Man shows poor quality of new apartment building',
1558 'description': 'The wall is like a sand pile.',
1559 'uploader': 'Lake8737',
09747ba7
YCH
1560 },
1561 'add_ie': [LiveLeakIE.ie_key()],
1562 },
1563 # Another LiveLeak embed pattern (#13336)
1564 {
1565 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1566 'info_dict': {
1567 'id': '2eb_1496309988',
1568 'ext': 'mp4',
1569 'title': 'Thief robs place where everyone was armed',
1570 'description': 'md5:694d73ee79e535953cf2488562288eee',
1571 'uploader': 'brazilwtf',
1572 },
1573 'add_ie': [LiveLeakIE.ie_key()],
b8f67449 1574 },
4a120778
YCH
1575 # Duplicated embedded video URLs
1576 {
1577 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1578 'info_dict': {
1579 'id': '149298443_480_16c25b74_2',
1580 'ext': 'mp4',
1581 'title': 'vs. Blue Orange Spring Game',
1582 'uploader': 'www.hudl.com',
1583 },
1584 },
371ddb14
S
1585 # twitter:player:stream embed
1586 {
1587 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1588 'info_dict': {
1589 'id': 'master',
1590 'ext': 'mp4',
1591 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1592 'uploader': 'www.rtl.be',
1593 },
1594 'params': {
1595 # m3u8 downloads
1596 'skip_download': True,
1597 },
1598 },
32917907
RA
1599 # twitter:player embed
1600 {
1601 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1602 'md5': 'a3e0df96369831de324f0778e126653c',
1603 'info_dict': {
1604 'id': '4909620399001',
1605 'ext': 'mp4',
1606 'title': 'What Do Black Holes Sound Like?',
1607 'description': 'what do black holes sound like',
1608 'upload_date': '20160524',
1609 'uploader_id': '29913724001',
1610 'timestamp': 1464107587,
1611 'uploader': 'TheAtlantic',
1612 },
1613 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1614 },
1615 # Facebook <iframe> embed
1616 {
1617 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1618 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1619 'info_dict': {
1620 'id': '599637780109885',
1621 'ext': 'mp4',
1622 'title': 'Facebook video #599637780109885',
1623 },
1624 },
fd1c5fba
S
1625 # Facebook <iframe> embed, plugin video
1626 {
1627 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1628 'info_dict': {
1629 'id': '1754168231264132',
1630 'ext': 'mp4',
1631 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1632 'uploader': 'Tariq Ramadan (official)',
1633 'timestamp': 1496758379,
1634 'upload_date': '20170606',
1635 },
1636 'params': {
1637 'skip_download': True,
1638 },
1639 },
fd6ca382
YCH
1640 # Facebook API embed
1641 {
1642 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1643 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1644 'info_dict': {
1645 'id': '10153467542406923',
1646 'ext': 'mp4',
1647 'title': 'Facebook video #10153467542406923',
1648 },
7deef1ba
YCH
1649 },
1650 # Wordpress "YouTube Video Importer" plugin
1651 {
1652 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1653 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1654 'info_dict': {
1655 'id': 'HNTXWDXV9Is',
1656 'ext': 'mp4',
1657 'title': 'Blue Devils Drumline Stanford lot 2016',
1658 'upload_date': '20160627',
1659 'uploader_id': 'GENOCIDE8GENERAL10',
1660 'uploader': 'cylus cyrus',
1661 },
1662 },
81953d1a
RA
1663 {
1664 # video stored on custom kaltura server
1665 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1666 'md5': '537617d06e64dfed891fa1593c4b30cc',
1667 'info_dict': {
1668 'id': '0_1iotm5bh',
1669 'ext': 'mp4',
1670 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1671 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1672 'uploader_id': 'videos.expansion@el-mundo.net',
1673 'upload_date': '20150429',
1674 'timestamp': 1430303472,
1675 },
1676 'add_ie': ['Kaltura'],
1677 },
c03adf90
YCH
1678 {
1679 # Non-standard Vimeo embed
1680 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1681 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1682 'info_dict': {
1683 'id': '148867247',
1684 'ext': 'mp4',
1685 'title': 'Understanding the web - Teaser',
1686 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1687 'upload_date': '20151214',
1688 'uploader': 'OpenClassrooms',
1689 'uploader_id': 'openclassrooms',
1690 },
1691 'add_ie': ['Vimeo'],
1692 },
a5ff05df
S
1693 {
1694 # generic vimeo embed that requires original URL passed as Referer
1695 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1696 'only_matching': True,
1697 },
1979969f
S
1698 {
1699 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1700 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1701 'info_dict': {
1702 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1703 'ext': 'mp4',
1704 'title': 'Big Buck Bunny',
1705 'description': 'Royalty free test video',
1706 'timestamp': 1432816365,
1707 'upload_date': '20150528',
1708 'is_live': False,
1709 },
1710 'params': {
1711 'skip_download': True,
1712 },
1713 'add_ie': [ArkenaIE.ie_key()],
1714 },
2a1321a2
S
1715 {
1716 '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/',
1717 'info_dict': {
1718 'id': '1c7141f46c',
1719 'ext': 'mp4',
1720 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1721 },
1722 'params': {
1723 'skip_download': True,
1724 },
1725 'add_ie': [Vbox7IE.ie_key()],
1726 },
b0c8f2e9
DR
1727 {
1728 # DBTV embeds
1729 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1730 'info_dict': {
1731 'id': '43254897',
1732 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1733 },
b0c8f2e9
DR
1734 'playlist_mincount': 3,
1735 },
e186a9ec
S
1736 {
1737 # Videa embeds
1738 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1739 'info_dict': {
1740 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1741 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1742 },
1743 'playlist_mincount': 2,
1744 },
b687c85e
S
1745 {
1746 # 20 minuten embed
1747 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1748 'info_dict': {
1749 'id': '523629',
1750 'ext': 'mp4',
1751 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1752 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1753 },
1754 'params': {
1755 'skip_download': True,
1756 },
1757 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1758 },
1759 {
1760 # VideoPress embed
1761 'url': 'https://en.support.wordpress.com/videopress/',
1762 'info_dict': {
1763 'id': 'OcobLTqC',
1764 'ext': 'm4v',
1765 'title': 'IMG_5786',
1766 'timestamp': 1435711927,
1767 'upload_date': '20150701',
1768 },
1769 'params': {
1770 'skip_download': True,
1771 },
1772 'add_ie': [VideoPressIE.ie_key()],
fef51645 1773 },
eb3079b6
S
1774 {
1775 # Rutube embed
1776 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1777 'info_dict': {
1778 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1779 'ext': 'flv',
1780 'title': 'Магаззино: Казань 2',
1781 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1782 'uploader': 'Магаззино',
1783 'upload_date': '20170228',
1784 'uploader_id': '996642',
1785 },
1786 'params': {
1787 'skip_download': True,
1788 },
1789 'add_ie': [RutubeIE.ie_key()],
1790 },
fef51645
YCH
1791 {
1792 # ThePlatform embedded with whitespaces in URLs
1793 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1794 'only_matching': True,
1795 },
97952bdb
JH
1796 {
1797 # Senate ISVP iframe https
1798 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1799 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1800 'info_dict': {
1801 'id': 'govtaff020316',
1802 'ext': 'mp4',
1803 'title': 'Integrated Senate Video Player',
1804 },
1805 'add_ie': [SenateISVPIE.ie_key()],
1806 },
ab87c260
S
1807 {
1808 # Limelight embeds (1 channel embed + 4 media embeds)
1809 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1810 'info_dict': {
1811 'id': 'FacilitatorTraining2017',
1812 'title': 'Facilitator Training 2017',
1813 },
1814 'playlist_mincount': 5,
1815 },
eb02940c
S
1816 {
1817 # Limelight embed (LimelightPlayerUtil.embed)
1818 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1819 'info_dict': {
1820 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1821 'ext': 'mp4',
1822 'title': '07448641',
1823 'timestamp': 1499890639,
1824 'upload_date': '20170712',
1825 },
1826 'params': {
1827 'skip_download': True,
1828 },
1829 'add_ie': ['LimelightMedia'],
1830 },
7986c3ab
S
1831 {
1832 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1833 'info_dict': {
1834 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1835 'title': 'Standoff with Walnut Creek murder suspect ends',
1836 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1837 },
1838 'playlist_mincount': 4,
1839 },
55719459
JH
1840 {
1841 # WashingtonPost embed
1842 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1843 'info_dict': {
1844 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1845 'ext': 'mp4',
1846 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1847 '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.',
1848 'timestamp': 1455216756,
1849 'uploader': 'The Washington Post',
1850 'upload_date': '20160211',
1851 },
1852 'add_ie': [WashingtonPostIE.ie_key()],
1853 },
2b8e6a68
S
1854 {
1855 # Mediaset embed
1856 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1857 'info_dict': {
1858 'id': '720642',
1859 'ext': 'mp4',
1860 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1861 },
1862 'params': {
1863 'skip_download': True,
1864 },
1865 'add_ie': [MediasetIE.ie_key()],
1866 },
73cf76a9
S
1867 {
1868 # JOJ.sk embeds
1869 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1870 'info_dict': {
1871 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1872 'title': 'Slovenskom sa prehnala vlna silných búrok',
1873 },
1874 'playlist_mincount': 5,
1875 'add_ie': [JojIE.ie_key()],
1876 },
4328ddf8
S
1877 {
1878 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1879 'url': 'https://tvrain.ru/amp/418921/',
1880 'md5': 'cc00413936695987e8de148b67d14f1d',
1881 'info_dict': {
1882 'id': '418921',
1883 'ext': 'mp4',
1884 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1885 },
1886 },
41918eaa 1887 {
1888 # vzaar embed
1663bd6e
S
1889 'url': 'http://help.vzaar.com/article/165-embedding-video',
1890 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1891 'info_dict': {
1663bd6e 1892 'id': '8707641',
41918eaa 1893 'ext': 'mp4',
1663bd6e 1894 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1895 },
1896 },
9ce1ac40 1897 {
1898 # multiple HTML5 videos on one page
1899 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1900 'info_dict': {
1901 'id': 'keyscenarios',
1902 'title': 'Rescue Kit 14 Free Edition - Getting started',
1903 },
1904 'playlist_count': 4,
0987f2dd
T
1905 },
1906 {
1907 # vshare embed
1908 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1909 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1910 'info_dict': {
1911 'id': '0f64ce6',
1912 'title': 'vl14062007715967',
1913 'ext': 'mp4',
1914 }
2ca7ed41
S
1915 },
1916 {
1917 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1918 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1919 'info_dict': {
1920 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1921 'ext': 'mp4',
1922 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1923 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1924 'timestamp': 1474354800,
1925 'upload_date': '20160920',
1926 }
7d540621
S
1927 },
1928 {
1929 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1930 'info_dict': {
1931 'id': '1731611',
1932 'ext': 'mp4',
1933 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1934 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1935 'timestamp': 1516100691,
1936 'upload_date': '20180116',
1937 },
1938 'params': {
1939 'skip_download': True,
1940 },
1941 'add_ie': [SpringboardPlatformIE.ie_key()],
ea696249
S
1942 },
1943 {
1944 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1945 'info_dict': {
1946 'id': 'uPDB5I9wfp8',
1947 'ext': 'webm',
1948 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1949 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1950 'upload_date': '20160219',
1951 'uploader': 'Pocoyo - Português (BR)',
1952 'uploader_id': 'PocoyoBrazil',
1953 },
1954 'add_ie': [YoutubeIE.ie_key()],
1955 'params': {
1956 'skip_download': True,
1957 },
4c780fbd
S
1958 },
1959 {
1960 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1961 'info_dict': {
1962 'id': 'vMDE4NzI1Mjgt690b',
1963 'ext': 'mp4',
1964 'title': 'Котята',
1965 },
1966 'add_ie': [YapFilesIE.ie_key()],
1967 'params': {
1968 'skip_download': True,
1969 },
9ce1ac40 1970 }
6e6b70d6
S
1971 # {
1972 # # TODO: find another test
1973 # # http://schema.org/VideoObject
1974 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1975 # 'md5': '888dcf08b7ea671381f00fab74692755',
1976 # 'info_dict': {
1977 # 'id': 'nyvTSJMKId',
1978 # 'ext': 'mp4',
1979 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1980 # 'description': '#love for cats.',
1981 # 'timestamp': 1461244995,
1982 # 'upload_date': '20160421',
1983 # },
1984 # 'params': {
1985 # 'force_generic_extractor': True,
1986 # },
1987 # }
cfe50f04 1988 ]
9b122384 1989
9b122384
PH
1990 def report_following_redirect(self, new_url):
1991 """Report information extraction."""
79649588 1992 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 1993
4fc946b5
PH
1994 def _extract_rss(self, url, video_id, doc):
1995 playlist_title = doc.find('./channel/title').text
1996 playlist_desc_el = doc.find('./channel/description')
1997 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1998
76c73715
PH
1999 entries = []
2000 for it in doc.findall('./channel/item'):
2001 next_url = xpath_text(it, 'link', fatal=False)
2002 if not next_url:
2003 enclosure_nodes = it.findall('./enclosure')
2004 for e in enclosure_nodes:
2005 next_url = e.attrib.get('url')
2006 if next_url:
2007 break
2008
2009 if not next_url:
2010 continue
2011
2012 entries.append({
413c1f8e 2013 '_type': 'url_transparent',
76c73715
PH
2014 'url': next_url,
2015 'title': it.find('title').text,
2016 })
4fc946b5
PH
2017
2018 return {
2019 '_type': 'playlist',
2020 'id': url,
2021 'title': playlist_title,
2022 'description': playlist_desc,
2023 'entries': entries,
2024 }
2025
c8e9a235
PH
2026 def _extract_camtasia(self, url, video_id, webpage):
2027 """ Returns None if no camtasia video can be found. """
2028
2029 camtasia_cfg = self._search_regex(
2030 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2031 webpage, 'camtasia configuration file', default=None)
2032 if camtasia_cfg is None:
2033 return None
2034
2035 title = self._html_search_meta('DC.title', webpage, fatal=True)
2036
2037 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2038 camtasia_cfg = self._download_xml(
2039 camtasia_url, video_id,
2040 note='Downloading camtasia configuration',
2041 errnote='Failed to download camtasia configuration')
2042 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2043
2044 entries = []
2045 for n in fileset_node.getchildren():
2046 url_n = n.find('./uri')
2047 if url_n is None:
2048 continue
2049
2050 entries.append({
2051 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2052 'title': '%s - %s' % (title, n.tag),
2053 'url': compat_urlparse.urljoin(url, url_n.text),
2054 'duration': float_or_none(n.find('./duration').text),
2055 })
2056
2057 return {
2058 '_type': 'playlist',
2059 'entries': entries,
2060 'title': title,
2061 }
2062
9b122384 2063 def _real_extract(self, url):
ebd3c7b3
PH
2064 if url.startswith('//'):
2065 return {
2066 '_type': 'url',
20991253 2067 'url': self.http_scheme() + url,
ebd3c7b3
PH
2068 }
2069
a7130543
JMF
2070 parsed_url = compat_urlparse.urlparse(url)
2071 if not parsed_url.scheme:
04b4d394
PH
2072 default_search = self._downloader.params.get('default_search')
2073 if default_search is None:
1f7ccb90 2074 default_search = 'fixup_error'
04b4d394 2075
1f7ccb90 2076 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
2077 if '/' in url:
2078 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2079 return self.url_result('http://' + url)
1f7ccb90 2080 elif default_search != 'fixup_error':
9c1fc022 2081 if default_search == 'auto_warning':
0e67ab0d
PH
2082 if re.match(r'^(?:url|URL)$', url):
2083 raise ExtractorError(
2084 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2085 expected=True)
2086 else:
2087 self._downloader.report_warning(
7571c02c 2088 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2089 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2090
2091 if default_search in ('error', 'fixup_error'):
7571c02c 2092 raise ExtractorError(
b74e86f4
PH
2093 '%r is not a valid URL. '
2094 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2095 % (url, url), expected=True)
04b4d394 2096 else:
f2f2c0c2
PH
2097 if ':' not in default_search:
2098 default_search += ':'
04b4d394 2099 return self.url_result(default_search + url)
4d54ef20
PH
2100
2101 url, smuggled_data = unsmuggle_url(url)
2102 force_videoid = None
d6e6a422 2103 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2104 if smuggled_data and 'force_videoid' in smuggled_data:
2105 force_videoid = smuggled_data['force_videoid']
2106 video_id = force_videoid
2107 else:
9dcd6fd3 2108 video_id = self._generic_id(url)
3d83a1ae 2109
79649588 2110 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2111
ebab4520 2112 head_req = HEADRequest(url)
23be51d8 2113 head_response = self._request_webpage(
ebab4520
PH
2114 head_req, video_id,
2115 note=False, errnote='Could not send HEAD request to %s' % url,
2116 fatal=False)
42393ce2 2117
23be51d8 2118 if head_response is not False:
42393ce2 2119 # Check for redirect
5551d771 2120 new_url = compat_str(head_response.geturl())
42393ce2
PH
2121 if url != new_url:
2122 self.report_following_redirect(new_url)
4d54ef20
PH
2123 if force_videoid:
2124 new_url = smuggle_url(
2125 new_url, {'force_videoid': force_videoid})
cecaaf3f 2126 return self.url_result(new_url)
42393ce2 2127
23be51d8
PH
2128 full_response = None
2129 if head_response is False:
5c2266df 2130 request = sanitized_Request(url)
58bde34a
S
2131 request.add_header('Accept-Encoding', '*')
2132 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2133 head_response = full_response
2134
f930e0c7
S
2135 info_dict = {
2136 'id': video_id,
9dcd6fd3 2137 'title': self._generic_title(url),
303dcdb9 2138 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
2139 }
2140
23be51d8 2141 # Check for direct link to a video
955737b2 2142 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2143 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2144 if m:
4e363703 2145 format_id = compat_str(m.group('format_id'))
f930e0c7 2146 if format_id.endswith('mpegurl'):
eadc3ccd 2147 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
2148 elif format_id == 'f4m':
2149 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2150 else:
2151 formats = [{
4e363703 2152 'format_id': format_id,
eadc3ccd 2153 'url': url,
2154 'vcodec': 'none' if m.group('type') == 'audio' else None
2155 }]
de6c51e8 2156 info_dict['direct'] = True
19dbaeec 2157 self._sort_formats(formats)
de6c51e8 2158 info_dict['formats'] = formats
f930e0c7 2159 return info_dict
42393ce2 2160
d6e6a422 2161 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
2162 force = self._downloader.params.get('force_generic_extractor', False)
2163 self._downloader.report_warning(
2164 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2165
4e262a88 2166 if not full_response:
5c2266df 2167 request = sanitized_Request(url)
58bde34a
S
2168 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2169 # making it impossible to download only chunk of the file (yet we need only 512kB to
2170 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2171 # that will always result in downloading the whole file that is not desirable.
2172 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2173 # to accept raw bytes and being able to download only a chunk.
2174 # It may probably better to solve this by checking Content-Type for application/octet-stream
2175 # after HEAD request finishes, but not sure if we can rely on this.
2176 request.add_header('Accept-Encoding', '*')
2177 full_response = self._request_webpage(request, video_id)
4e262a88 2178
5940862d
S
2179 first_bytes = full_response.read(512)
2180
2181 # Is it an M3U playlist?
0d769bcb 2182 if first_bytes.startswith(b'#EXTM3U'):
5940862d 2183 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 2184 self._sort_formats(info_dict['formats'])
5940862d
S
2185 return info_dict
2186
4e262a88
PH
2187 # Maybe it's a direct link to a video?
2188 # Be careful not to download the whole thing!
61ca9a80 2189 if not is_html(first_bytes):
4e262a88
PH
2190 self._downloader.report_warning(
2191 'URL could be a direct video link, returning it as such.')
f930e0c7 2192 info_dict.update({
4e262a88
PH
2193 'direct': True,
2194 'url': url,
f930e0c7
S
2195 })
2196 return info_dict
4e262a88
PH
2197
2198 webpage = self._webpage_read_content(
2199 full_response, url, video_id, prefix=first_bytes)
2200
9b122384 2201 self.report_extraction(video_id)
887c6acd 2202
1b840245 2203 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2204 try:
f7854627 2205 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
2206 if doc.tag == 'rss':
2207 return self._extract_rss(url, video_id, doc)
cc99a77a
S
2208 elif doc.tag == 'SmoothStreamingMedia':
2209 info_dict['formats'] = self._parse_ism_formats(doc, url)
2210 self._sort_formats(info_dict['formats'])
2211 return info_dict
e5e8d20a 2212 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
2213 smil = self._parse_smil(doc, url, video_id)
2214 self._sort_formats(smil['formats'])
2215 return smil
729accb4 2216 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
96b8b9ab 2217 return self.playlist_result(
47a5cb77
S
2218 self._parse_xspf(
2219 doc, video_id, xspf_url=url,
2220 xspf_base_url=compat_str(full_response.geturl())),
96b8b9ab 2221 video_id)
1b840245 2222 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7 2223 info_dict['formats'] = self._parse_mpd_formats(
d3f8b76b 2224 doc,
5551d771 2225 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
86f4d14f 2226 mpd_url=url)
19dbaeec 2227 self._sort_formats(info_dict['formats'])
f930e0c7
S
2228 return info_dict
2229 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2230 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 2231 self._sort_formats(info_dict['formats'])
f930e0c7 2232 return info_dict
f7300c5c 2233 except compat_xml_parse_error:
4fc946b5
PH
2234 pass
2235
c8e9a235
PH
2236 # Is it a Camtasia project?
2237 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2238 if camtasia_res is not None:
2239 return camtasia_res
2240
14390730
S
2241 # Sometimes embedded video player is hidden behind percent encoding
2242 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2243 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 2244 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2245
887c6acd
PH
2246 # it's tempting to parse this further, but you would
2247 # have to take into account all the variations like
2248 # Video Title - Site Name
2249 # Site Name | Video Title
2250 # Video Title - Tagline | Site Name
2251 # and so on and so forth; it's just not practical
6f41b2bc
S
2252 video_title = self._og_search_title(
2253 webpage, default=None) or self._html_search_regex(
79649588
PH
2254 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2255 default='video')
ef4fd848 2256
4d805e06
PH
2257 # Try to detect age limit automatically
2258 age_limit = self._rta_search(webpage)
2259 # And then there are the jokers who advertise that they use RTA,
2260 # but actually don't.
2261 AGE_LIMIT_MARKERS = [
197224b7 2262 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
4d805e06
PH
2263 ]
2264 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2265 age_limit = 18
2266
ef4fd848
PH
2267 # video uploader is domain name
2268 video_uploader = self._search_regex(
79649588 2269 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2270
6f41b2bc
S
2271 video_description = self._og_search_description(webpage, default=None)
2272 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2273
b311b0ea
S
2274 info_dict.update({
2275 'title': video_title,
2276 'description': video_description,
2277 'thumbnail': video_thumbnail,
2278 'age_limit': age_limit,
2279 })
2280
1f4b722b 2281 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2282 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2283 if bc_urls:
99877772
PH
2284 entries = [{
2285 '_type': 'url',
2286 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2287 'ie_key': 'BrightcoveLegacy'
99877772
PH
2288 } for bc_url in bc_urls]
2289
2290 return {
2291 '_type': 'playlist',
2292 'title': video_title,
2293 'id': video_id,
2294 'entries': entries,
2295 }
cfe50f04 2296
f6519f89 2297 # Look for Brightcove New Studio embeds
0254f93b 2298 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2299 if bc_urls:
5399ab3f
S
2300 return self.playlist_from_matches(
2301 bc_urls, video_id, video_title,
2302 getter=lambda x: smuggle_url(x, {'referrer': url}),
2303 ie='BrightcoveNew')
ed126900 2304
4e826cd9
S
2305 # Look for Nexx embeds
2306 nexx_urls = NexxIE._extract_urls(webpage)
2307 if nexx_urls:
2308 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2309
3f59b015
S
2310 # Look for Nexx iFrame embeds
2311 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2312 if nexx_embed_urls:
2313 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2314
4d8819d2
S
2315 # Look for ThePlatform embeds
2316 tp_urls = ThePlatformIE._extract_urls(webpage)
2317 if tp_urls:
46b18f23 2318 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2319
48a5eabc
S
2320 # Look for Vessel embeds
2321 vessel_urls = VesselIE._extract_urls(webpage)
2322 if vessel_urls:
46b18f23 2323 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
48a5eabc 2324
59b8ab58
PH
2325 # Look for embedded rtl.nl player
2326 matches = re.findall(
2637fadc 2327 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
59b8ab58
PH
2328 webpage)
2329 if matches:
46b18f23 2330 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2331
09b9c45e
S
2332 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2333 if vimeo_urls:
46b18f23 2334 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2335
a1b85269
YCH
2336 vid_me_embed_url = self._search_regex(
2337 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2338 webpage, 'vid.me embed', default=None)
2339 if vid_me_embed_url is not None:
2340 return self.url_result(vid_me_embed_url, 'Vidme')
2341
66c9fa36
S
2342 # Look for YouTube embeds
2343 youtube_urls = YoutubeIE._extract_urls(webpage)
2344 if youtube_urls:
46b18f23 2345 return self.playlist_from_matches(
66c9fa36 2346 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2347
ad213a1d 2348 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2349 if matches:
46b18f23 2350 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2351
8489578d
NJ
2352 # Look for embedded Dailymotion playlist player (#3822)
2353 m = re.search(
2354 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2355 if m:
2356 playlists = re.findall(
2357 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2358 if playlists:
46b18f23
JH
2359 return self.playlist_from_matches(
2360 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2361
71a1db89
S
2362 # Look for DailyMail embeds
2363 dailymail_urls = DailyMailIE._extract_urls(webpage)
2364 if dailymail_urls:
2365 return self.playlist_from_matches(
2366 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2367
ef4fd848 2368 # Look for embedded Wistia player
58bb4402
S
2369 wistia_url = WistiaIE._extract_url(webpage)
2370 if wistia_url:
ef4fd848
PH
2371 return {
2372 '_type': 'url_transparent',
58bb4402
S
2373 'url': self._proto_relative_url(wistia_url),
2374 'ie_key': WistiaIE.ie_key(),
ef4fd848 2375 'uploader': video_uploader,
ef4fd848 2376 }
5f6a1245 2377
bab19a8e
S
2378 # Look for SVT player
2379 svt_url = SVTIE._extract_url(webpage)
2380 if svt_url:
2381 return self.url_result(svt_url, 'SVT')
2382
c19f7764
JMF
2383 # Look for Bandcamp pages with custom domain
2384 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2385 if mobj is not None:
2386 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2387 # Don't set the extractor because it can be a track url or an album
2388 return self.url_result(burl)
c19f7764 2389
f25571ff
PH
2390 # Look for embedded Vevo player
2391 mobj = re.search(
2392 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2393 if mobj is not None:
2394 return self.url_result(mobj.group('url'))
796df3c6
S
2395
2396 # Look for embedded Viddler player
cb454b33
S
2397 mobj = re.search(
2398 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2399 webpage)
796df3c6
S
2400 if mobj is not None:
2401 return self.url_result(mobj.group('url'))
f25571ff 2402
3378d67a
S
2403 # Look for NYTimes player
2404 mobj = re.search(
2405 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2406 webpage)
2407 if mobj is not None:
2408 return self.url_result(mobj.group('url'))
2409
cefdf970
S
2410 # Look for Libsyn player
2411 mobj = re.search(
2412 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2413 if mobj is not None:
2414 return self.url_result(mobj.group('url'))
2415
c0d0b01f 2416 # Look for Ooyala videos
8a37aa15 2417 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 2418 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
198d4cb4 2419 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
2420 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2421 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2422 if mobj is not None:
9837cb75
RA
2423 embed_token = self._search_regex(
2424 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2425 webpage, 'ooyala embed token', default=None)
2426 return OoyalaIE._build_url_result(smuggle_url(
2427 mobj.group('ec'), {
2428 'domain': url,
2429 'embed_token': embed_token,
2430 }))
c0d0b01f 2431
f076b638 2432 # Look for multiple Ooyala embeds on SBN network websites
2433 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2434 if mobj is not None:
2435 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2436 if embeds:
46b18f23
JH
2437 return self.playlist_from_matches(
2438 embeds, video_id, video_title,
2439 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2440
aa94a6d3 2441 # Look for Aparat videos
48099643 2442 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2443 if mobj is not None:
2444 return self.url_result(mobj.group(1), 'Aparat')
2445
c93c2ab1 2446 # Look for MPORA videos
c3f51436 2447 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2448 if mobj is not None:
2449 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2450
15c0e8e7 2451 # Look for embedded NovaMov-based player
8f89e687 2452 mobj = re.search(
8dfa187b 2453 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
2454 (?P<url>http://(?:(?:embed|www)\.)?
2455 (?:novamov\.com|
2456 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2457 videoweed\.(?:es|com)|
2458 movshare\.(?:net|sx|ag)|
2459 divxstage\.(?:eu|net|ch|co|at|ag))
2460 /embed\.php.+?)\1''', webpage)
8f89e687 2461 if mobj is not None:
15c0e8e7 2462 return self.url_result(mobj.group('url'))
50f56607 2463
9834872b 2464 # Look for embedded Facebook player
0646e34c
S
2465 facebook_urls = FacebookIE._extract_urls(webpage)
2466 if facebook_urls:
2467 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2468
ca97a56e
S
2469 # Look for embedded VK player
2470 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2471 if mobj is not None:
2472 return self.url_result(mobj.group('url'), 'VK')
2473
33d4fdab
S
2474 # Look for embedded Odnoklassniki player
2475 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2476 if mobj is not None:
2477 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2478
0364fa8b
S
2479 # Look for embedded ivi player
2480 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2481 if mobj is not None:
2482 return self.url_result(mobj.group('url'), 'Ivi')
2483
db1f3888
PH
2484 # Look for embedded Huffington Post player
2485 mobj = re.search(
c3f51436 2486 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2487 if mobj is not None:
2488 return self.url_result(mobj.group('url'), 'HuffPost')
2489
1b86cc41 2490 # Look for embed.ly
2491 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2492 if mobj is not None:
2493 return self.url_result(mobj.group('url'))
2494 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2495 if mobj is not None:
f7e6f7fa 2496 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2497
60cc4dc4
PH
2498 # Look for funnyordie embed
2499 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2500 if matches:
46b18f23
JH
2501 return self.playlist_from_matches(
2502 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2503
db546cf8
S
2504 # Look for BBC iPlayer embed
2505 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2506 if matches:
46b18f23 2507 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2508
93d020dd
S
2509 # Look for embedded RUTV player
2510 rutv_url = RUTVIE._extract_url(webpage)
2511 if rutv_url:
2512 return self.url_result(rutv_url, 'RUTV')
2513
494f20cb 2514 # Look for embedded TVC player
b8599718
S
2515 tvc_url = TVCIE._extract_url(webpage)
2516 if tvc_url:
2517 return self.url_result(tvc_url, 'TVC')
494f20cb 2518
d40a3b5b
S
2519 # Look for embedded SportBox player
2520 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2521 if sportbox_urls:
46b18f23 2522 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
d40a3b5b 2523
2bb5b6d0
S
2524 # Look for embedded XHamster player
2525 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2526 if xhamster_urls:
46b18f23 2527 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2528
2c9ca782
S
2529 # Look for embedded TNAFlixNetwork player
2530 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2531 if tnaflix_urls:
46b18f23 2532 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2533
b52c9ef1
S
2534 # Look for embedded PornHub player
2535 pornhub_urls = PornHubIE._extract_urls(webpage)
2536 if pornhub_urls:
46b18f23 2537 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2538
37e7a71c
S
2539 # Look for embedded DrTuber player
2540 drtuber_urls = DrTuberIE._extract_urls(webpage)
2541 if drtuber_urls:
46b18f23 2542 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2543
e28ed498
S
2544 # Look for embedded RedTube player
2545 redtube_urls = RedTubeIE._extract_urls(webpage)
2546 if redtube_urls:
46b18f23 2547 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 2548
9872d311
S
2549 # Look for embedded Tvigle player
2550 mobj = re.search(
2551 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2552 if mobj is not None:
2553 return self.url_result(mobj.group('url'), 'Tvigle')
2554
7e2ede98
JMF
2555 # Look for embedded TED player
2556 mobj = re.search(
d7cc31b6 2557 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
2558 if mobj is not None:
2559 return self.url_result(mobj.group('url'), 'TED')
2560
5c386252 2561 # Look for embedded Ustream videos
d77ac737
YCH
2562 ustream_url = UstreamIE._extract_url(webpage)
2563 if ustream_url:
2564 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 2565
893f8832
PH
2566 # Look for embedded arte.tv player
2567 mobj = re.search(
134c207e 2568 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
893f8832
PH
2569 webpage)
2570 if mobj is not None:
2571 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2572
cbd55ade
S
2573 # Look for embedded francetv player
2574 mobj = re.search(
2575 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2576 webpage)
2577 if mobj is not None:
2578 return self.url_result(mobj.group('url'))
2579
cb3ac1c6
S
2580 # Look for embedded smotri.com player
2581 smotri_url = SmotriIE._extract_url(webpage)
2582 if smotri_url:
2583 return self.url_result(smotri_url, 'Smotri')
2584
e6c2d9ad 2585 # Look for embedded Myvi.ru player
6dd94d3a 2586 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
2587 if myvi_url:
2588 return self.url_result(myvi_url)
2589
dfb1b146 2590 # Look for embedded soundcloud player
94aae015
S
2591 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2592 if soundcloud_urls:
46b18f23 2593 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
20991253 2594
027e2312
S
2595 # Look for tunein player
2596 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2597 if tunein_urls:
46b18f23 2598 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 2599
c5cd249e 2600 # Look for embedded mtvservices player
46fde8a1
S
2601 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2602 if mtvservices_url:
2603 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 2604
49807b4a
S
2605 # Look for embedded yahoo player
2606 mobj = re.search(
2607 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2608 webpage)
2609 if mobj is not None:
2610 return self.url_result(mobj.group('url'), 'Yahoo')
2611
2ef6fcb5
PH
2612 # Look for embedded sbs.com.au player
2613 mobj = re.search(
e98b8e79
PH
2614 r'''(?x)
2615 (?:
2616 <meta\s+property="og:video"\s+content=|
2617 <iframe[^>]+?src=
2618 )
2619 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
2620 webpage)
2621 if mobj is not None:
2622 return self.url_result(mobj.group('url'), 'SBS')
2623
42bdd9d0
PH
2624 # Look for embedded Cinchcast player
2625 mobj = re.search(
2626 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2627 webpage)
2628 if mobj is not None:
2629 return self.url_result(mobj.group('url'), 'Cinchcast')
2630
1a94ff68 2631 mobj = re.search(
5263cdfc 2632 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 2633 webpage)
8001607e
YCH
2634 if not mobj:
2635 mobj = re.search(
2636 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2637 webpage)
1a94ff68
S
2638 if mobj is not None:
2639 return self.url_result(mobj.group('url'), 'MLB')
2640
1419fafd 2641 mobj = re.search(
dd467d33 2642 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
2643 webpage)
2644 if mobj is not None:
2645 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2646
af63fed7 2647 mobj = re.search(
78d3b3e2 2648 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
2649 webpage)
2650 if mobj is not None:
2651 return self.url_result(mobj.group('url'), 'Livestream')
2652
255fca5e
S
2653 # Look for Zapiks embed
2654 mobj = re.search(
2655 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2656 if mobj is not None:
2657 return self.url_result(mobj.group('url'), 'Zapiks')
2658
e3216b82 2659 # Look for Kaltura embeds
c287f2bc
S
2660 kaltura_url = KalturaIE._extract_url(webpage)
2661 if kaltura_url:
2662 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
e3216b82 2663
665e9452 2664 # Look for EaglePlatform embeds
06a96da1
S
2665 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2666 if eagleplatform_url:
665e9452 2667 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 2668
665e9452 2669 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
2670 mobj = re.search(
2671 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2672 if mobj is not None:
2673 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2674
f8388757 2675 # Look for Pladform embeds
45dad7ba
S
2676 pladform_url = PladformIE._extract_url(webpage)
2677 if pladform_url:
2678 return self.url_result(pladform_url)
f8388757 2679
ff18735c
S
2680 # Look for Videomore embeds
2681 videomore_url = VideomoreIE._extract_url(webpage)
2682 if videomore_url:
2683 return self.url_result(videomore_url)
2684
83f1481b
S
2685 # Look for Webcaster embeds
2686 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2687 if webcaster_url:
2688 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2689
2dcc114f
S
2690 # Look for Playwire embeds
2691 mobj = re.search(
2692 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2693 if mobj is not None:
2694 return self.url_result(mobj.group('url'))
2695
ad320e9b
NJ
2696 # Look for 5min embeds
2697 mobj = re.search(
2698 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2699 if mobj is not None:
2700 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2701
18153f1b
S
2702 # Look for Crooks and Liars embeds
2703 mobj = re.search(
2704 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2705 if mobj is not None:
2706 return self.url_result(mobj.group('url'))
2707
a2edf2e7
YCH
2708 # Look for NBC Sports VPlayer embeds
2709 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2710 if nbc_sports_url:
2711 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2712
de3eb07e
YCH
2713 # Look for NBC News embeds
2714 nbc_news_embed_url = re.search(
2715 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2716 if nbc_news_embed_url:
2717 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2718
653789af 2719 # Look for Google Drive embeds
5b251628 2720 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 2721 if google_drive_url:
2722 return self.url_result(google_drive_url, 'GoogleDrive')
2723
418c5cc3
YCH
2724 # Look for UDN embeds
2725 mobj = re.search(
2637fadc 2726 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
2727 if mobj is not None:
2728 return self.url_result(
0a160363 2729 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 2730
2fe1b5bd
YCH
2731 # Look for Senate ISVP iframe
2732 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2733 if senate_isvp_url:
25c3a734 2734 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 2735
1ac1c4c2
S
2736 # Look for OnionStudios embeds
2737 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2738 if onionstudios_url:
2739 return self.url_result(onionstudios_url)
2740
67167920 2741 # Look for ViewLift embeds
2742 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2743 if viewlift_url:
2744 return self.url_result(viewlift_url)
eedd20ef 2745
7cb09524 2746 # Look for JWPlatform embeds
b0ead0e0
S
2747 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2748 if jwplatform_urls:
2749 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
7cb09524 2750
aecfcd4e
S
2751 # Look for Digiteka embeds
2752 digiteka_url = DigitekaIE._extract_url(webpage)
2753 if digiteka_url:
2754 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 2755
1979969f
S
2756 # Look for Arkena embeds
2757 arkena_url = ArkenaIE._extract_url(webpage)
2758 if arkena_url:
2759 return self.url_result(arkena_url, ArkenaIE.ie_key())
2760
b1c35797
RA
2761 # Look for Piksel embeds
2762 piksel_url = PikselIE._extract_url(webpage)
2763 if piksel_url:
2764 return self.url_result(piksel_url, PikselIE.ie_key())
2765
1bf996fa 2766 # Look for Limelight embeds
e5d39886
S
2767 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2768 if limelight_urls:
2769 return self.playlist_result(
2770 limelight_urls, video_id, video_title, video_description)
2771
7986c3ab
S
2772 # Look for Anvato embeds
2773 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2774 if anvato_urls:
2775 return self.playlist_result(
2776 anvato_urls, video_id, video_title, video_description)
2777
a5158f38
YCH
2778 # Look for AdobeTVVideo embeds
2779 mobj = re.search(
2780 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2781 webpage)
2782 if mobj is not None:
2783 return self.url_result(
2784 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2785 'AdobeTVVideo')
2786
088e1aac
YCH
2787 # Look for Vine embeds
2788 mobj = re.search(
2789 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2790 webpage)
2791 if mobj is not None:
2792 return self.url_result(
2793 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2794
217d5ae0
RA
2795 # Look for VODPlatform embeds
2796 mobj = re.search(
93b84045 2797 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
217d5ae0
RA
2798 webpage)
2799 if mobj is not None:
2800 return self.url_result(
93b84045 2801 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 2802
7d273a38
RA
2803 # Look for Mangomolo embeds
2804 mobj = re.search(
d05ef09d 2805 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
7d273a38
RA
2806 (?:
2807 video\?.*?\bid=(?P<video_id>\d+)|
2808 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2809 ).+?)\1''', webpage)
2810 if mobj is not None:
2811 info = {
2812 '_type': 'url_transparent',
2813 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2814 'title': video_title,
2815 'description': video_description,
2816 'thumbnail': video_thumbnail,
2817 'uploader': video_uploader,
2818 }
2819 video_id = mobj.group('video_id')
2820 if video_id:
2821 info.update({
2822 'ie_key': 'MangomoloVideo',
2823 'id': video_id,
2824 })
2825 else:
2826 info.update({
2827 'ie_key': 'MangomoloLive',
2828 'id': mobj.group('channel_id'),
2829 })
2830 return info
2831
5a51775a
YCH
2832 # Look for Instagram embeds
2833 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2834 if instagram_embed_url is not None:
11e60fca
S
2835 return self.url_result(
2836 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 2837
b8f67449 2838 # Look for LiveLeak embeds
09747ba7
YCH
2839 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2840 if liveleak_urls:
2841 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
b8f67449 2842
5d39176f
S
2843 # Look for 3Q SDN embeds
2844 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2845 if threeqsdn_url:
6f41b2bc
S
2846 return {
2847 '_type': 'url_transparent',
2848 'ie_key': ThreeQSDNIE.ie_key(),
2849 'url': self._proto_relative_url(threeqsdn_url),
2850 'title': video_title,
2851 'description': video_description,
2852 'thumbnail': video_thumbnail,
2853 'uploader': video_uploader,
2854 }
5d39176f 2855
2a1321a2
S
2856 # Look for VBOX7 embeds
2857 vbox7_url = Vbox7IE._extract_url(webpage)
2858 if vbox7_url:
2859 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2860
b0c8f2e9
DR
2861 # Look for DBTV embeds
2862 dbtv_urls = DBTVIE._extract_urls(webpage)
2863 if dbtv_urls:
46b18f23 2864 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 2865
e186a9ec
S
2866 # Look for Videa embeds
2867 videa_urls = VideaIE._extract_urls(webpage)
2868 if videa_urls:
46b18f23 2869 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 2870
b687c85e
S
2871 # Look for 20 minuten embeds
2872 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2873 if twentymin_urls:
46b18f23
JH
2874 return self.playlist_from_matches(
2875 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 2876
17f8deeb
S
2877 # Look for Openload embeds
2878 openload_urls = OpenloadIE._extract_urls(webpage)
2879 if openload_urls:
46b18f23
JH
2880 return self.playlist_from_matches(
2881 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
17f8deeb 2882
6ef3e65a
S
2883 # Look for VideoPress embeds
2884 videopress_urls = VideoPressIE._extract_urls(webpage)
2885 if videopress_urls:
46b18f23
JH
2886 return self.playlist_from_matches(
2887 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 2888
eb3079b6
S
2889 # Look for Rutube embeds
2890 rutube_urls = RutubeIE._extract_urls(webpage)
2891 if rutube_urls:
46b18f23 2892 return self.playlist_from_matches(
2583c0b5 2893 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 2894
55719459
JH
2895 # Look for WashingtonPost embeds
2896 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2897 if wapo_urls:
2898 return self.playlist_from_matches(
2899 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2900
5d29af3d
S
2901 # Look for Mediaset embeds
2902 mediaset_urls = MediasetIE._extract_urls(webpage)
2903 if mediaset_urls:
2904 return self.playlist_from_matches(
2905 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2906
73cf76a9
S
2907 # Look for JOJ.sk embeds
2908 joj_urls = JojIE._extract_urls(webpage)
2909 if joj_urls:
2910 return self.playlist_from_matches(
2911 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2912
24e966e8
PH
2913 # Look for megaphone.fm embeds
2914 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2915 if mpfn_urls:
2916 return self.playlist_from_matches(
2917 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2918
1663bd6e
S
2919 # Look for vzaar embeds
2920 vzaar_urls = VzaarIE._extract_urls(webpage)
2921 if vzaar_urls:
2922 return self.playlist_from_matches(
2923 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2924
26bae2d9
S
2925 channel9_urls = Channel9IE._extract_urls(webpage)
2926 if channel9_urls:
2927 return self.playlist_from_matches(
2928 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2929
0987f2dd
T
2930 vshare_urls = VShareIE._extract_urls(webpage)
2931 if vshare_urls:
2932 return self.playlist_from_matches(
2933 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2934
8056c854 2935 # Look for Mediasite embeds
2ca7ed41
S
2936 mediasite_urls = MediasiteIE._extract_urls(webpage)
2937 if mediasite_urls:
2938 entries = [
2939 self.url_result(smuggle_url(
2940 compat_urlparse.urljoin(url, mediasite_url),
2941 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
2942 for mediasite_url in mediasite_urls]
2943 return self.playlist_result(entries, video_id, video_title)
8056c854 2944
7d540621
S
2945 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
2946 if springboardplatform_urls:
2947 return self.playlist_from_matches(
2948 springboardplatform_urls, video_id, video_title,
2949 ie=SpringboardPlatformIE.ie_key())
2950
4c780fbd
S
2951 yapfiles_urls = YapFilesIE._extract_urls(webpage)
2952 if yapfiles_urls:
2953 return self.playlist_from_matches(
2954 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
2955
86c8cfc5
S
2956 vice_urls = ViceIE._extract_urls(webpage)
2957 if vice_urls:
2958 return self.playlist_from_matches(
2959 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
2960
178ee883
S
2961 xfileshare_urls = XFileShareIE._extract_urls(webpage)
2962 if xfileshare_urls:
2963 return self.playlist_from_matches(
2964 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
2965
b311b0ea
S
2966 def merge_dicts(dict1, dict2):
2967 merged = {}
2968 for k, v in dict1.items():
2969 if v is not None:
2970 merged[k] = v
2971 for k, v in dict2.items():
2972 if v is None:
2973 continue
2974 if (k not in merged or
2975 (isinstance(v, compat_str) and v and
2976 isinstance(merged[k], compat_str) and
2977 not merged[k])):
2978 merged[k] = v
2979 return merged
2980
bd264412
YCH
2981 # Look for HTML5 media
2982 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2983 if entries:
9ce1ac40 2984 if len(entries) == 1:
2985 entries[0].update({
bd264412
YCH
2986 'id': video_id,
2987 'title': video_title,
2988 })
9ce1ac40 2989 else:
2990 for num, entry in enumerate(entries, start=1):
2991 entry.update({
2992 'id': '%s-%s' % (video_id, num),
2993 'title': '%s (%d)' % (video_title, num),
2994 })
2995 for entry in entries:
bd264412 2996 self._sort_formats(entry['formats'])
9ce1ac40 2997 return self.playlist_result(entries, video_id, video_title)
bd264412 2998
c73e330e
RU
2999 jwplayer_data = self._find_jwplayer_data(
3000 webpage, video_id, transform_source=js_to_json)
3001 if jwplayer_data:
4f06c1c9 3002 info = self._parse_jwplayer_data(
3e943cfe 3003 jwplayer_data, video_id, require_title=False, base_url=url)
b311b0ea 3004 return merge_dicts(info, info_dict)
a4a554a7 3005
63d990d2
S
3006 # Video.js embed
3007 mobj = re.search(
c5b7014a 3008 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
3009 webpage)
3010 if mobj is not None:
3011 sources = self._parse_json(
3012 mobj.group(1), video_id, transform_source=js_to_json,
3013 fatal=False) or []
c5b7014a
S
3014 if not isinstance(sources, list):
3015 sources = [sources]
63d990d2
S
3016 formats = []
3017 for source in sources:
3018 src = source.get('src')
3019 if not src or not isinstance(src, compat_str):
3020 continue
3021 src = compat_urlparse.urljoin(url, src)
3022 src_type = source.get('type')
3023 if isinstance(src_type, compat_str):
3024 src_type = src_type.lower()
3025 ext = determine_ext(src).lower()
3026 if src_type == 'video/youtube':
3027 return self.url_result(src, YoutubeIE.ie_key())
3028 if src_type == 'application/dash+xml' or ext == 'mpd':
3029 formats.extend(self._extract_mpd_formats(
3030 src, video_id, mpd_id='dash', fatal=False))
3031 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3032 formats.extend(self._extract_m3u8_formats(
3033 src, video_id, 'mp4', entry_protocol='m3u8_native',
3034 m3u8_id='hls', fatal=False))
3035 else:
3036 formats.append({
3037 'url': src,
3038 'ext': (mimetype2ext(src_type) or
3039 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3040 })
3041 if formats:
3042 self._sort_formats(formats)
3043 info_dict['formats'] = formats
3044 return info_dict
3045
ff17be3a
S
3046 # Looking for http://schema.org/VideoObject
3047 json_ld = self._search_json_ld(
3048 webpage, video_id, default={}, expected_type='VideoObject')
3049 if json_ld.get('url'):
3050 return merge_dicts(json_ld, info_dict)
3051
ced659bb 3052 def check_video(vurl):
a0f71985
PH
3053 if YoutubeIE.suitable(vurl):
3054 return True
b7a8c1bc
S
3055 if RtmpIE.suitable(vurl):
3056 return True
ced659bb
S
3057 vpath = compat_urlparse.urlparse(vurl).path
3058 vext = determine_ext(vpath)
0ee79a37 3059 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
3060
3061 def filter_video(urls):
3062 return list(filter(check_video, urls))
3063
9b122384 3064 # Start with something easy: JW Player in SWFObject
ced659bb 3065 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 3066 if not found:
d981cef6 3067 # Look for gorilla-vid style embedding
ced659bb 3068 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
3069 (?:
3070 jw_plugins|
3071 JWPlayerOptions|
3072 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3073 )
a0f71985
PH
3074 .*?
3075 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 3076 if not found:
9b122384 3077 # Broaden the search a little bit
ced659bb 3078 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
3079 if not found:
3080 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 3081 found = filter_video(re.findall(
54a9328b 3082 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
3083 if not found:
3084 # Flow player
ced659bb 3085 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
3086 flowplayer\("[^"]+",\s*
3087 \{[^}]+?\}\s*,
52585fd6 3088 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 3089 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 3090 ''', webpage))
501f13fb
PH
3091 if not found:
3092 # Cinerama player
3093 found = re.findall(
3094 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 3095 if not found:
9b122384 3096 # Try to find twitter cards info
371ddb14
S
3097 # twitter:player:stream should be checked before twitter:player since
3098 # it is expected to contain a raw stream (see
3099 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3100 found = filter_video(re.findall(
3101 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 3102 if not found:
9b122384
PH
3103 # We look for Open Graph info:
3104 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3105 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3106 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3107 if m_video_type is not None:
ced659bb 3108 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 3109 if not found:
ed9a25dd 3110 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3111 found = re.search(
89ef304b 3112 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3113 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3114 webpage)
84f81016
S
3115 if not found:
3116 # Look also in Refresh HTTP header
3117 refresh_header = head_response.headers.get('Refresh')
3118 if refresh_header:
6c91a5a7
S
3119 # In python 2 response HTTP headers are bytestrings
3120 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3121 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3122 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3123 if found:
b37317d8 3124 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3125 if new_url != url:
3126 self.report_following_redirect(new_url)
3127 return {
3128 '_type': 'url',
3129 'url': new_url,
3130 }
3131 else:
3132 found = None
371ddb14
S
3133
3134 if not found:
3135 # twitter:player is a https URL to iframe player that may or may not
3136 # be supported by youtube-dl thus this is checked the very last (see
3137 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3138 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3139 if embed_url and embed_url != url:
371ddb14
S
3140 return self.url_result(embed_url)
3141
b30b8698 3142 if not found:
416c7fcb 3143 raise UnsupportedError(url)
9b122384 3144
b30b8698 3145 entries = []
4a120778 3146 for video_url in orderedSet(found):
949b6497 3147 video_url = unescapeHTML(video_url)
6cc37c69 3148 video_url = video_url.replace('\\/', '/')
b30b8698 3149 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3150 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3151
b30b8698
PH
3152 # Sometimes, jwplayer extraction will result in a YouTube URL
3153 if YoutubeIE.suitable(video_url):
3154 entries.append(self.url_result(video_url, 'Youtube'))
3155 continue
9b122384 3156
b30b8698
PH
3157 # here's a fun little line of code for you:
3158 video_id = os.path.splitext(video_id)[0]
fc9713a1 3159
28602e74
YCH
3160 entry_info_dict = {
3161 'id': video_id,
3162 'uploader': video_uploader,
3163 'title': video_title,
3164 'age_limit': age_limit,
3165 }
3166
5620f840
S
3167 if RtmpIE.suitable(video_url):
3168 entry_info_dict.update({
3169 '_type': 'url_transparent',
3170 'ie_key': RtmpIE.ie_key(),
3171 'url': video_url,
3172 })
3173 entries.append(entry_info_dict)
3174 continue
3175
729accb4
S
3176 ext = determine_ext(video_url)
3177 if ext == 'smil':
28602e74 3178 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
3179 elif ext == 'xspf':
3180 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
3181 elif ext == 'm3u8':
3182 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
3183 elif ext == 'mpd':
3184 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
3185 elif ext == 'f4m':
3186 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3187 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3188 # Just matching .ism/manifest is not enough to be reliably sure
3189 # whether it's actually an ISM manifest or some other streaming
3190 # manifest since there are various streaming URL formats
3191 # possible (see [1]) as well as some other shenanigans like
3192 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3193 # so on.
3194 # Thus the most reasonable way to solve this is to delegate
3195 # to generic extractor in order to look into the contents of
3196 # the manifest itself.
3197 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3198 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3199 entry_info_dict = self.url_result(
3200 smuggle_url(video_url, {'to_generic': True}),
3201 GenericIE.ie_key())
d6fd958c 3202 else:
28602e74
YCH
3203 entry_info_dict['url'] = video_url
3204
19dbaeec
S
3205 if entry_info_dict.get('formats'):
3206 self._sort_formats(entry_info_dict['formats'])
3207
28602e74 3208 entries.append(entry_info_dict)
b30b8698
PH
3209
3210 if len(entries) == 1:
669f0e7c 3211 return entries[0]
b30b8698
PH
3212 else:
3213 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3214 # 'url' results don't have a title
3215 if e.get('title') is not None:
3216 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3217 return {
3218 '_type': 'playlist',
3219 'entries': entries,
3220 }