]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
Fix some tests
[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
06993715 61from .tube8 import Tube8IE
b407e173 62from .vimeo import VimeoIE
3c4fbfec 63from .dailymotion import DailymotionIE
71a1db89 64from .dailymail import DailyMailIE
1ac1c4c2 65from .onionstudios import OnionStudiosIE
67167920 66from .viewlift import ViewLiftEmbedIE
46fde8a1 67from .mtv import MTVServicesEmbeddedIE
45dad7ba 68from .pladform import PladformIE
ff18735c 69from .videomore import VideomoreIE
83f1481b 70from .webcaster import WebcasterFeedIE
5b251628 71from .googledrive import GoogleDriveIE
7cb09524 72from .jwplatform import JWPlatformIE
aecfcd4e 73from .digiteka import DigitekaIE
1979969f 74from .arkena import ArkenaIE
5a51775a 75from .instagram import InstagramIE
b8f67449 76from .liveleak import LiveLeakIE
5d39176f 77from .threeqsdn import ThreeQSDNIE
4d8819d2 78from .theplatform import ThePlatformIE
48a5eabc 79from .vessel import VesselIE
c287f2bc 80from .kaltura import KalturaIE
06a96da1 81from .eagleplatform import EaglePlatformIE
fd6ca382 82from .facebook import FacebookIE
94aae015 83from .soundcloud import SoundcloudIE
027e2312 84from .tunein import TuneInBaseIE
2a1321a2 85from .vbox7 import Vbox7IE
b0c8f2e9 86from .dbtv import DBTVIE
b1c35797 87from .piksel import PikselIE
e186a9ec 88from .videa import VideaIE
b687c85e 89from .twentymin import TwentyMinutenIE
d77ac737 90from .ustream import UstreamIE
17f8deeb 91from .openload import OpenloadIE
6ef3e65a 92from .videopress import VideoPressIE
eb3079b6 93from .rutube import RutubeIE
e5d39886 94from .limelight import LimelightBaseIE
7986c3ab 95from .anvato import AnvatoIE
55719459 96from .washingtonpost import WashingtonPostIE
58bb4402 97from .wistia import WistiaIE
5d29af3d 98from .mediaset import MediasetIE
73cf76a9 99from .joj import JojIE
24e966e8 100from .megaphone import MegaphoneIE
41918eaa 101from .vzaar import VzaarIE
26bae2d9 102from .channel9 import Channel9IE
0987f2dd 103from .vshare import VShareIE
2ca7ed41 104from .mediasite import MediasiteIE
7d540621 105from .springboardplatform import SpringboardPlatformIE
4c780fbd 106from .yapfiles import YapFilesIE
86c8cfc5 107from .vice import ViceIE
178ee883 108from .xfileshare import XFileShareIE
9b122384 109
0838239e 110
9b122384 111class GenericIE(InfoExtractor):
79649588 112 IE_DESC = 'Generic downloader that works on some sites'
9b122384 113 _VALID_URL = r'.*'
79649588 114 IE_NAME = 'generic'
cfe50f04 115 _TESTS = [
c5fa81fe
S
116 # Direct link to a video
117 {
118 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
119 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
120 'info_dict': {
121 'id': 'trailer',
122 'ext': 'mp4',
123 'title': 'trailer',
124 'upload_date': '20100513',
125 }
126 },
c5138a7c 127 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
128 {
129 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
130 'md5': '128c42e68b13950268b648275386fc74',
131 'info_dict': {
132 'id': 'FictionJunction-Parallel_Hearts',
133 'ext': 'flac',
134 'title': 'FictionJunction-Parallel_Hearts',
135 'upload_date': '20140522',
136 },
137 'expected_warnings': [
138 'URL could be a direct video link, returning it as such.'
39efc6e3
YCH
139 ],
140 'skip': 'URL invalid',
c5fa81fe
S
141 },
142 # Direct download with broken HEAD
143 {
144 'url': 'http://ai-radio.org:8000/radio.opus',
145 'info_dict': {
146 'id': 'radio',
147 'ext': 'opus',
148 'title': 'radio',
149 },
150 'params': {
151 'skip_download': True, # infinite live stream
152 },
153 'expected_warnings': [
ef0e4e7b
YCH
154 r'501.*Not Implemented',
155 r'400.*Bad Request',
c5fa81fe
S
156 ],
157 },
158 # Direct link with incorrect MIME type
159 {
160 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
161 'md5': '4ccbebe5f36706d85221f204d7eb5913',
162 'info_dict': {
163 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
164 'id': '5_Lennart_Poettering_-_Systemd',
165 'ext': 'webm',
166 'title': '5_Lennart_Poettering_-_Systemd',
167 'upload_date': '20141120',
168 },
169 'expected_warnings': [
170 'URL could be a direct video link, returning it as such.'
171 ]
172 },
173 # RSS feed
174 {
175 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
176 'info_dict': {
177 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
178 'title': 'Zero Punctuation',
179 'description': 're:.*groundbreaking video review series.*'
180 },
181 'playlist_mincount': 11,
182 },
183 # RSS feed with enclosure
184 {
185 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
186 'info_dict': {
187 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
188 'ext': 'm4v',
189 'upload_date': '20150228',
190 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
191 }
192 },
8765222d
S
193 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
194 {
195 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
196 'info_dict': {
197 'id': 'smil',
198 'ext': 'mp4',
199 'title': 'Automatics, robotics and biocybernetics',
200 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 201 'upload_date': '20130627',
8765222d
S
202 'formats': 'mincount:16',
203 'subtitles': 'mincount:1',
204 },
205 'params': {
206 'force_generic_extractor': True,
207 'skip_download': True,
208 },
209 },
210 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
211 {
212 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
213 'info_dict': {
214 'id': 'hds',
215 'ext': 'flv',
216 'title': 'hds',
217 'formats': 'mincount:1',
218 },
219 'params': {
220 'skip_download': True,
221 },
222 },
223 # SMIL from https://www.restudy.dk/video/play/id/1637
224 {
225 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
226 'info_dict': {
227 'id': 'video_1637',
228 'ext': 'flv',
229 'title': 'video_1637',
230 'formats': 'mincount:3',
231 },
232 'params': {
233 'skip_download': True,
234 },
235 },
236 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
237 {
238 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
239 'info_dict': {
240 'id': 'smil-service',
241 'ext': 'flv',
242 'title': 'smil-service',
243 'formats': 'mincount:1',
244 },
245 'params': {
246 'skip_download': True,
247 },
248 },
249 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
250 {
251 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
252 'info_dict': {
253 'id': '4719370',
254 'ext': 'mp4',
255 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
256 'formats': 'mincount:3',
257 },
258 'params': {
259 'skip_download': True,
260 },
261 },
1de5cd3b
S
262 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
263 {
264 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
265 'info_dict': {
266 'id': 'mZlp2ctYIUEB',
267 'ext': 'mp4',
268 'title': 'Tikibad ontruimd wegens brand',
269 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
ec85ded8 270 'thumbnail': r're:^https?://.*\.jpg$',
1de5cd3b
S
271 'duration': 33,
272 },
273 'params': {
274 'skip_download': True,
275 },
276 },
9d939cec
S
277 # MPD from http://dash-mse-test.appspot.com/media.html
278 {
279 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
280 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
281 'info_dict': {
282 'id': 'car-20120827-manifest',
283 'ext': 'mp4',
284 'title': 'car-20120827-manifest',
285 'formats': 'mincount:9',
0738187f 286 'upload_date': '20130904',
9d939cec
S
287 },
288 'params': {
289 'format': 'bestvideo',
290 },
291 },
20938f76
S
292 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
293 {
294 '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',
295 'info_dict': {
296 'id': 'content',
297 'ext': 'mp4',
298 'title': 'content',
299 'formats': 'mincount:8',
300 },
301 'params': {
302 # m3u8 downloads
303 'skip_download': True,
39efc6e3
YCH
304 },
305 'skip': 'video gone',
20938f76 306 },
edd9b71c
S
307 # m3u8 served with Content-Type: text/plain
308 {
309 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
310 'info_dict': {
311 'id': 'index',
312 'ext': 'mp4',
313 'title': 'index',
314 'upload_date': '20140720',
315 'formats': 'mincount:11',
316 },
317 'params': {
318 # m3u8 downloads
319 'skip_download': True,
39efc6e3
YCH
320 },
321 'skip': 'video gone',
edd9b71c 322 },
c5fa81fe
S
323 # google redirect
324 {
325 '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',
326 'info_dict': {
327 'id': 'cmQHVoWB5FY',
328 'ext': 'mp4',
329 'upload_date': '20130224',
330 'uploader_id': 'TheVerge',
ec85ded8 331 'description': r're:^Chris Ziegler takes a look at the\.*',
c5fa81fe
S
332 'uploader': 'The Verge',
333 'title': 'First Firefox OS phones side-by-side',
334 },
335 'params': {
336 'skip_download': False,
337 }
338 },
6c91a5a7
S
339 {
340 # redirect in Refresh HTTP header
341 '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',
342 'info_dict': {
343 'id': 'pO8h3EaFRdo',
344 'ext': 'mp4',
345 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
346 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
347 'upload_date': '20150917',
348 'uploader_id': 'brtvofficial',
349 'uploader': 'Boiler Room',
350 },
351 'params': {
352 'skip_download': False,
353 },
354 },
cfe50f04 355 {
79649588 356 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 357 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 358 'info_dict': {
d360a146
S
359 'id': '13601338388002',
360 'ext': 'mp4',
79649588
PH
361 'uploader': 'www.hodiho.fr',
362 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
363 }
364 },
c19f7764
JMF
365 # bandcamp page with custom domain
366 {
79649588
PH
367 'add_ie': ['Bandcamp'],
368 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 369 'info_dict': {
fd50bf62
S
370 'id': '3235767654',
371 'ext': 'mp3',
79649588
PH
372 'title': 'The Pony Mash',
373 'uploader': 'M_Pallante',
c19f7764 374 },
79649588 375 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 376 },
eeb165e6 377 {
53a664ed
S
378 # embedded brightcove video
379 # it also tests brightcove videos that need to set the 'Referer'
380 # in the http requests
3b7d9aa4 381 'add_ie': ['BrightcoveLegacy'],
79649588
PH
382 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
383 'info_dict': {
384 'id': '2765128793001',
385 'ext': 'mp4',
386 'title': 'Le cours de bourse : l’analyse technique',
387 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
388 'uploader': 'BFM BUSINESS',
eeb165e6 389 },
79649588
PH
390 'params': {
391 'skip_download': True,
eeb165e6
JMF
392 },
393 },
53a664ed
S
394 {
395 # embedded with itemprop embedURL and video id spelled as `idVideo`
396 'add_id': ['BrightcoveLegacy'],
397 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
398 'info_dict': {
399 'id': '5255628253001',
400 'ext': 'mp4',
401 'title': 'md5:37c519b1128915607601e75a87995fc0',
402 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
403 'uploader': 'BFM BUSINESS',
404 'uploader_id': '876450612001',
405 'timestamp': 1482255315,
406 'upload_date': '20161220',
407 },
408 'params': {
409 'skip_download': True,
410 },
411 },
17ab4d3b
PH
412 {
413 # https://github.com/rg3/youtube-dl/issues/2253
414 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
415 'md5': '0ba9446db037002366bab3b3eb30c88c',
416 'info_dict': {
fd50bf62
S
417 'id': '3101154703001',
418 'ext': 'mp4',
17ab4d3b
PH
419 'title': 'Still no power',
420 'uploader': 'thestar.com',
421 '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.',
422 },
3b7d9aa4 423 'add_ie': ['BrightcoveLegacy'],
39efc6e3 424 'skip': 'video gone',
17ab4d3b 425 },
0479c625
S
426 {
427 'url': 'http://www.championat.com/video/football/v/87/87499.html',
428 'md5': 'fb973ecf6e4a78a67453647444222983',
429 'info_dict': {
430 'id': '3414141473001',
431 'ext': 'mp4',
432 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
433 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
434 'uploader': 'Championat',
435 },
436 },
bdf97017 437 {
37aab278 438 # https://github.com/rg3/youtube-dl/issues/3541
3b7d9aa4 439 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
440 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
441 'info_dict': {
442 'id': '3866516442001',
37aab278 443 'ext': 'mp4',
bdf97017
NJ
444 'title': 'Leer mij vrouwen kennen: Aflevering 1',
445 'description': 'Leer mij vrouwen kennen: Aflevering 1',
446 'uploader': 'SBS Broadcasting',
447 },
37aab278 448 'skip': 'Restricted to Netherlands',
bdf97017 449 'params': {
37aab278 450 'skip_download': True, # m3u8 download
bdf97017
NJ
451 },
452 },
06d0ad9a
YCH
453 {
454 # Brightcove video in <iframe>
455 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
456 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
457 'info_dict': {
458 'id': '5360463607001',
459 'ext': 'mp4',
460 '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',
461 '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。',
462 'uploader': 'United Nations',
463 'uploader_id': '1362235914001',
464 'timestamp': 1489593889,
465 'upload_date': '20170315',
466 },
467 'add_ie': ['BrightcoveLegacy'],
468 },
16e2c8f7
YCH
469 {
470 # Brightcove with alternative playerID key
471 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
472 'info_dict': {
473 'id': 'nmeth.2062_SV1',
474 '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',
475 },
476 'playlist': [{
477 'info_dict': {
478 'id': '2228375078001',
479 'ext': 'mp4',
480 'title': 'nmeth.2062-sv1',
481 'description': 'nmeth.2062-sv1',
482 'timestamp': 1363357591,
483 'upload_date': '20130315',
484 'uploader': 'Nature Publishing Group',
485 'uploader_id': '1964492299001',
486 },
487 }],
488 },
40158f55
JH
489 {
490 # Brightcove with UUID in videoPlayer
491 'url': 'http://www8.hp.com/cn/zh/home.html',
492 'info_dict': {
493 'id': '5255815316001',
494 'ext': 'mp4',
495 'title': 'Sprocket Video - China',
496 'description': 'Sprocket Video - China',
497 'uploader': 'HP-Video Gallery',
498 'timestamp': 1482263210,
499 'upload_date': '20161220',
500 'uploader_id': '1107601872001',
501 },
502 'params': {
503 'skip_download': True, # m3u8 download
504 },
505 'skip': 'video rotates...weekly?',
506 },
507 {
508 # Brightcove:new type [2].
509 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
510 'md5': '2b35148fcf48da41c9fb4591650784f3',
511 'info_dict': {
512 'id': '5348741021001',
513 'ext': 'mp4',
514 'upload_date': '20170306',
515 'uploader_id': '4191638492001',
516 'timestamp': 1488769918,
517 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
518
519 },
520 },
521 {
522 # Alternative brightcove <video> attributes
523 '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/',
524 'info_dict': {
525 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
526 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
527 },
528 'playlist': [{
529 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
530 'info_dict': {
531 'id': '5311302538001',
532 'ext': 'mp4',
533 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
534 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
535 'timestamp': 1486321708,
536 'upload_date': '20170205',
537 'uploader_id': '800000640001',
538 },
539 'only_matching': True,
540 }],
541 },
b68a812e
S
542 {
543 # Brightcove with UUID in videoPlayer
544 'url': 'http://www8.hp.com/cn/zh/home.html',
545 'info_dict': {
546 'id': '5255815316001',
547 'ext': 'mp4',
548 'title': 'Sprocket Video - China',
549 'description': 'Sprocket Video - China',
550 'uploader': 'HP-Video Gallery',
551 'timestamp': 1482263210,
552 'upload_date': '20161220',
553 'uploader_id': '1107601872001',
554 },
555 'params': {
556 'skip_download': True, # m3u8 download
557 },
558 },
c0d0b01f
JMF
559 # ooyala video
560 {
79649588 561 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 562 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
563 'info_dict': {
564 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
565 'ext': 'mp4',
3486df38 566 'title': '2cc213299525360.mov', # that's what we get
53e06b25 567 'duration': 238.231,
c0d0b01f 568 },
87830900 569 'add_ie': ['Ooyala'],
c0d0b01f 570 },
bf94d763
S
571 {
572 # ooyala video embedded with http://player.ooyala.com/iframe.js
573 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
574 'info_dict': {
575 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
576 'ext': 'mp4',
577 'title': '"Steve Jobs: Man in the Machine" trailer',
578 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 579 'duration': 135.427,
bf94d763
S
580 },
581 'params': {
582 'skip_download': True,
583 },
39efc6e3 584 'skip': 'movie expired',
bf94d763 585 },
198d4cb4
GR
586 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
587 {
588 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
589 'info_dict': {
590 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
591 'ext': 'mp4',
592 'title': 'Steampunk Fest Comes to Honesdale',
593 'duration': 43.276,
594 },
595 'params': {
596 'skip_download': True,
597 }
598 },
1b86cc41 599 # embed.ly video
600 {
601 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
602 'info_dict': {
603 'id': '9ODmcdjQcHQ',
604 'ext': 'mp4',
0a5bce56
PH
605 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
606 'upload_date': '20140225',
607 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
608 'uploader': 'Tested',
609 'uploader_id': 'testedcom',
1b86cc41 610 },
611 # No need to test YoutubeIE here
612 'params': {
613 'skip_download': True,
614 },
615 },
60cc4dc4
PH
616 # funnyordie embed
617 {
618 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
619 'info_dict': {
620 'id': '18e820ec3f',
621 'ext': 'mp4',
622 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
623 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 624 },
39efc6e3
YCH
625 # HEAD requests lead to endless 301, while GET is OK
626 'expected_warnings': ['301'],
60cc4dc4 627 },
93d020dd
S
628 # RUTV embed
629 {
630 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
631 'info_dict': {
632 'id': '776940',
633 'ext': 'mp4',
634 'title': 'Охотское море стало целиком российским',
635 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
636 },
637 'params': {
638 # m3u8 download
639 'skip_download': True,
640 },
aab74fa1 641 },
f37bdbe5
S
642 # TVC embed
643 {
644 '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/',
645 'info_dict': {
646 'id': '55304',
647 'ext': 'mp4',
648 'title': 'Дошкольное воспитание',
649 },
650 },
b827a601
S
651 # SportBox embed
652 {
653 'url': 'http://www.vestifinance.ru/articles/25753',
654 'info_dict': {
655 'id': '25753',
05d1e7aa 656 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
b827a601
S
657 },
658 'playlist': [{
659 'info_dict': {
660 'id': '370908',
661 'title': 'Госзаказ. День 3',
662 'ext': 'mp4',
663 }
664 }, {
665 'info_dict': {
666 'id': '370905',
667 'title': 'Госзаказ. День 2',
668 'ext': 'mp4',
669 }
670 }, {
671 'info_dict': {
672 'id': '370902',
673 'title': 'Госзаказ. День 1',
674 'ext': 'mp4',
675 }
676 }],
677 'params': {
678 # m3u8 download
679 'skip_download': True,
680 },
681 },
bf20b9c5
S
682 # Myvi.ru embed
683 {
684 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
685 'info_dict': {
686 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
687 'ext': 'mp4',
688 'title': 'Ужастики, русский трейлер (2015)',
ec85ded8 689 'thumbnail': r're:^https?://.*\.jpg$',
bf20b9c5
S
690 'duration': 153,
691 }
692 },
c76799c5
S
693 # XHamster embed
694 {
695 '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',
696 'info_dict': {
697 'id': 'showthread',
698 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
699 },
700 'playlist_mincount': 7,
39efc6e3
YCH
701 # This forum does not allow <iframe> syntaxes anymore
702 # Now HTML tags are displayed as-is
703 'skip': 'No videos on this page',
c76799c5 704 },
aab74fa1
PH
705 # Embedded TED video
706 {
707 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 708 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 709 'info_dict': {
a8eb5a8e 710 'id': '1969',
aab74fa1 711 'ext': 'mp4',
a8eb5a8e
PH
712 'title': 'Hidden miracles of the natural world',
713 'uploader': 'Louie Schwartzberg',
714 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 715 }
60cc4dc4 716 },
d95e35d6
S
717 # nowvideo embed hidden behind percent encoding
718 {
719 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
720 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
721 'info_dict': {
722 'id': '06e53103ca9aa',
723 'ext': 'flv',
724 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
725 'description': 'No description',
726 },
0f2a2ba1 727 },
893f8832
PH
728 # arte embed
729 {
730 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
731 'md5': '7653032cbb25bf6c80d80f217055fa43',
732 'info_dict': {
733 'id': '048195-004_PLUS7-F',
734 'ext': 'flv',
735 'title': 'X:enius',
736 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
737 'upload_date': '20140320',
738 },
739 'params': {
740 'skip_download': 'Requires rtmpdump'
39efc6e3
YCH
741 },
742 'skip': 'video gone',
893f8832 743 },
cbd55ade
S
744 # francetv embed
745 {
746 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
747 'info_dict': {
748 'id': 'EV_30231',
749 'ext': 'mp4',
750 'title': 'Alcaline, le concert avec Calogero',
751 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
752 'upload_date': '20150226',
753 'timestamp': 1424989860,
754 'duration': 5400,
755 },
756 'params': {
757 # m3u8 downloads
758 'skip_download': True,
759 },
760 'expected_warnings': [
761 'Forbidden'
762 ]
763 },
fa35cdad
PH
764 # Condé Nast embed
765 {
766 'url': 'http://www.wired.com/2014/04/honda-asimo/',
767 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
768 'info_dict': {
769 'id': '53501be369702d3275860000',
770 'ext': 'mp4',
771 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
772 }
ebd3c7b3
PH
773 },
774 # Dailymotion embed
775 {
776 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
777 'md5': '441aeeb82eb72c422c7f14ec533999cd',
778 'info_dict': {
779 'id': 'k2mm4bCdJ6CQ2i7c8o2',
780 'ext': 'mp4',
781 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 782 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 783 'uploader': 'Spi0n',
0738187f
YCH
784 'uploader_id': 'xgditw',
785 'upload_date': '20140425',
786 'timestamp': 1398441542,
ebd3c7b3
PH
787 },
788 'add_ie': ['Dailymotion'],
2b88feed 789 },
71a1db89
S
790 # DailyMail embed
791 {
792 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
793 'info_dict': {
794 'id': '1495629',
795 'ext': 'mp4',
796 'title': 'Care worker punches elderly dementia patient in head 11 times',
797 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
798 },
799 'add_ie': ['DailyMail'],
800 'params': {
801 'skip_download': True,
802 },
803 },
2b88feed
PH
804 # YouTube embed
805 {
806 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
807 'info_dict': {
808 'id': 'FXRb4ykk4S0',
809 'ext': 'mp4',
810 'title': 'The NBL Auction 2014',
811 'uploader': 'BADMINTON England',
812 'uploader_id': 'BADMINTONEvents',
813 'upload_date': '20140603',
814 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
815 },
816 'add_ie': ['Youtube'],
817 'params': {
818 'skip_download': True,
819 }
820 },
c5cd249e
JMF
821 # MTVSercices embed
822 {
1fa309da
YCH
823 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
824 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 825 'info_dict': {
1fa309da 826 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 827 'ext': 'mp4',
1fa309da
YCH
828 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
829 'description': 'Two valets share their love for movie star Liam Neesons.',
05d1e7aa
YCH
830 'timestamp': 1349922600,
831 'upload_date': '20121011',
c5cd249e
JMF
832 },
833 },
61013473 834 # YouTube embed via <data-embed-url="">
835 {
836 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 837 'info_dict': {
a8eb5a8e 838 'id': '4vAffPZIT44',
61013473 839 'ext': 'mp4',
a8eb5a8e 840 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
841 'uploader': 'Gameloft',
842 'uploader_id': 'gameloft',
a8eb5a8e
PH
843 'upload_date': '20140828',
844 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
845 },
846 'params': {
847 'skip_download': True,
61013473 848 }
c8e9a235 849 },
61568e50
JH
850 # YouTube <object> embed
851 {
852 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
853 'md5': '516718101ec834f74318df76259fb3cc',
854 'info_dict': {
855 'id': 'msN87y-iEx0',
856 'ext': 'webm',
857 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
858 'upload_date': '20080526',
859 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
860 'uploader': 'Christopher Sykes',
861 'uploader_id': 'ChristopherJSykes',
862 },
863 'add_ie': ['Youtube'],
864 },
c8e9a235
PH
865 # Camtasia studio
866 {
867 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
868 'playlist': [{
869 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
870 'info_dict': {
871 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
872 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
873 'ext': 'flv',
874 'duration': 2235.90,
875 }
876 }, {
877 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
878 'info_dict': {
879 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
880 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
881 'ext': 'flv',
882 'duration': 2235.93,
883 }
884 }],
885 'info_dict': {
886 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
887 }
4d805e06
PH
888 },
889 # Flowplayer
890 {
891 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
892 'md5': '9d65602bf31c6e20014319c7d07fba27',
893 'info_dict': {
894 'id': '5123ea6d5e5a7',
895 'ext': 'mp4',
896 'age_limit': 18,
897 'uploader': 'www.handjobhub.com',
d6d9186f 898 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 899 }
0990305d 900 },
22a6f150
PH
901 # Multiple brightcove videos
902 # https://github.com/rg3/youtube-dl/issues/2283
903 {
904 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
905 'info_dict': {
906 'id': 'always-never',
907 'title': 'Always / Never - The New Yorker',
908 },
909 'playlist_count': 3,
910 'params': {
911 'extract_flat': False,
912 'skip_download': True,
913 }
1a94ff68
S
914 },
915 # MLB embed
916 {
917 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
918 'md5': '96f09a37e44da40dd083e12d9a683327',
919 'info_dict': {
920 'id': '33322633',
921 'ext': 'mp4',
922 'title': 'Ump changes call to ball',
923 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
924 'duration': 48,
925 'timestamp': 1401537900,
926 'upload_date': '20140531',
ec85ded8 927 'thumbnail': r're:^https?://.*\.jpg$',
1a94ff68
S
928 },
929 },
746c67d7
NJ
930 # Wistia embed
931 {
6c114b12
S
932 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
933 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 934 'info_dict': {
6c114b12 935 'id': '6e2wtrbdaf',
746c67d7 936 'ext': 'mov',
6c114b12
S
937 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
938 'description': 'a Paywall Videos video from Remilon',
939 'duration': 644.072,
940 'uploader': 'study.com',
941 'timestamp': 1459678540,
942 'upload_date': '20160403',
943 'filesize': 24687186,
746c67d7
NJ
944 },
945 },
52cffcb1 946 {
947 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
948 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
949 'info_dict': {
950 'id': 'uxjb0lwrcz',
951 'ext': 'mp4',
6c114b12 952 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 953 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 954 'duration': 1715.0,
85d7b765 955 'uploader': 'thoughtworks.wistia.com',
0738187f 956 'timestamp': 1401832161,
6c114b12 957 'upload_date': '20140603',
70b7e3fb 958 },
52cffcb1 959 },
7ded6545
S
960 # Wistia standard embed (async)
961 {
962 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
963 'info_dict': {
964 'id': '807fafadvk',
965 'ext': 'mp4',
966 'title': 'Drip Brennan Dunn Workshop',
967 'description': 'a JV Webinars video from getdrip-1',
968 'duration': 4986.95,
7ded6545 969 'timestamp': 1463607249,
6c114b12 970 'upload_date': '20160518',
7ded6545
S
971 },
972 'params': {
973 'skip_download': True,
974 }
975 },
ac645ac7
PH
976 # Soundcloud embed
977 {
978 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
979 'info_dict': {
980 'id': '174391317',
981 'ext': 'mp3',
982 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
983 'uploader': 'Sophos Security',
984 'title': 'Chet Chat 171 - Oct 29, 2014',
985 'upload_date': '20141029',
986 }
af63fed7 987 },
db19df6c
S
988 # Soundcloud multiple embeds
989 {
990 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
991 'info_dict': {
992 'id': '52809',
993 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
994 },
995 'playlist_mincount': 7,
996 },
027e2312
S
997 # TuneIn station embed
998 {
999 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1000 'info_dict': {
1001 'id': '204146',
1002 'ext': 'mp3',
1003 'title': 'CNRV',
1004 'location': 'Paris, France',
1005 'is_live': True,
1006 },
1007 'params': {
1008 # Live stream
1009 'skip_download': True,
1010 },
1011 },
af63fed7
PH
1012 # Livestream embed
1013 {
1014 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1015 'info_dict': {
1016 'id': '67864563',
1017 'ext': 'flv',
1018 'upload_date': '20141112',
1019 'title': 'Rosetta #CometLanding webcast HL 10',
1020 }
1021 },
78d3b3e2
YCH
1022 # Another Livestream embed, without 'new.' in URL
1023 {
1024 'url': 'https://www.freespeech.org/',
1025 'info_dict': {
1026 'id': '123537347',
1027 'ext': 'mp4',
1028 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1029 },
1030 'params': {
1031 # Live stream
1032 'skip_download': True,
1033 },
1034 },
65f3a228
PH
1035 # LazyYT
1036 {
e8e4cc5a 1037 'url': 'https://skiplagged.com/',
65f3a228 1038 'info_dict': {
e8e4cc5a
JH
1039 'id': 'skiplagged',
1040 'title': 'Skiplagged: The smart way to find cheap flights',
65f3a228 1041 },
e8e4cc5a
JH
1042 'playlist_mincount': 1,
1043 'add_ie': ['Youtube'],
4e262a88 1044 },
42bdd9d0
PH
1045 # Cinchcast embed
1046 {
1047 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1048 'info_dict': {
1049 'id': '7141703',
1050 'ext': 'mp3',
1051 'upload_date': '20141126',
1052 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1053 }
1054 },
501f13fb
PH
1055 # Cinerama player
1056 {
1057 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1058 'info_dict': {
1059 'id': '730m_DandD_1901_512k',
1060 'ext': 'mp4',
1061 'uploader': 'www.abc.net.au',
1062 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1063 }
796df3c6
S
1064 },
1065 # embedded viddler video
1066 {
1067 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1068 'info_dict': {
1069 'id': '4d03aad9',
1070 'ext': 'mp4',
1071 'uploader': 'deadspin',
1072 'title': 'WALL-TO-GORTAT',
1073 'timestamp': 1422285291,
1074 'upload_date': '20150126',
1075 },
1076 'add_ie': ['Viddler'],
a0f71985 1077 },
2051acde
S
1078 # Libsyn embed
1079 {
1080 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1081 'info_dict': {
1082 'id': '3377616',
1083 'ext': 'mp3',
1084 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1085 'description': 'md5:601cb790edd05908957dae8aaa866465',
1086 'upload_date': '20150220',
1087 },
326fa4e6 1088 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
2051acde 1089 },
a0f71985
PH
1090 # jwplayer YouTube
1091 {
1092 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1093 'info_dict': {
1094 'id': 'Mrj4DVp2zeA',
1095 'ext': 'mp4',
f37e3f99 1096 'upload_date': '20150212',
a0f71985 1097 'uploader': 'The National Archives UK',
2637fadc 1098 'description': 'md5:8078af856dca76edc42910b61273dbbf',
a0f71985
PH
1099 'uploader_id': 'NationalArchives08',
1100 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1101 },
59b8ab58 1102 },
5620f840
S
1103 # jwplayer rtmp
1104 {
6899b1d9 1105 'url': 'http://www.suffolk.edu/sjc/live.php',
5620f840 1106 'info_dict': {
6899b1d9 1107 'id': 'live',
5620f840
S
1108 'ext': 'flv',
1109 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1110 'uploader': 'www.suffolk.edu',
1111 },
1112 'params': {
1113 'skip_download': True,
2637fadc 1114 },
6899b1d9 1115 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
5620f840 1116 },
a4a554a7
YCH
1117 # Complex jwplayer
1118 {
1119 'url': 'http://www.indiedb.com/games/king-machine/videos',
1120 'info_dict': {
1121 'id': 'videos',
1122 'ext': 'mp4',
1123 'title': 'king machine trailer 1',
2637fadc 1124 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
a4a554a7
YCH
1125 'thumbnail': r're:^https?://.*\.jpg$',
1126 },
1127 },
03486dbb
RU
1128 {
1129 # JWPlayer config passed as variable
1130 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1131 'info_dict': {
1132 'id': '3326530_hq',
1133 'ext': 'mp4',
1134 'title': 'ARIELE | Tube Cup',
1135 'uploader': 'www.txxx.com',
1136 'age_limit': 18,
1137 },
1138 'params': {
1139 'skip_download': True,
1140 }
1141 },
939be9ad
JH
1142 {
1143 # JWPlatform iframe
1144 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1145 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1146 'info_dict': {
1147 'id': 'O0c5JcKT',
1148 'ext': 'mp4',
1149 'upload_date': '20171122',
1150 'timestamp': 1511366290,
1151 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1152 },
805f5bf7 1153 'add_ie': [JWPlatformIE.ie_key()],
939be9ad 1154 },
63d990d2 1155 {
c5b7014a 1156 # Video.js embed, multiple formats
63d990d2
S
1157 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1158 'info_dict': {
1159 'id': 'yygqldloqIk',
1160 'ext': 'mp4',
1161 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1162 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1163 'upload_date': '20130314',
1164 'uploader': 'PROстое3D',
1165 'uploader_id': 'PROstoe3D',
1166 },
1167 'params': {
1168 'skip_download': True,
1169 },
1170 },
c5b7014a
S
1171 {
1172 # Video.js embed, single format
1173 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1174 'info_dict': {
1175 'id': 'watch',
1176 'ext': 'mp4',
1177 'title': 'Step 1 - Good Foundation',
1178 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1179 },
1180 'params': {
1181 'skip_download': True,
1182 },
1183 },
59b8ab58
PH
1184 # rtl.nl embed
1185 {
1186 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1187 'playlist_mincount': 5,
1188 'info_dict': {
1189 'id': 'aanslagen-kopenhagen',
2637fadc 1190 'title': 'Aanslagen Kopenhagen',
59b8ab58 1191 }
255fca5e
S
1192 },
1193 # Zapiks embed
1194 {
1195 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1196 'info_dict': {
1197 'id': '118046',
1198 'ext': 'mp4',
1199 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1200 }
1201 },
66e568de
S
1202 # Kaltura embed (different embed code)
1203 {
1204 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1205 'info_dict': {
1206 'id': '1_a52wc67y',
1207 'ext': 'flv',
1208 'upload_date': '20150127',
1209 'uploader_id': 'PremierMedia',
1210 'timestamp': int,
1211 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1212 },
1213 },
87703231
YCH
1214 # Kaltura embed with single quotes
1215 {
1216 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1217 'info_dict': {
1218 'id': '0_izeg5utt',
1219 'ext': 'mp4',
1220 'title': '35871',
1221 'timestamp': 1355743100,
1222 'upload_date': '20121217',
1223 'uploader_id': 'batchUser',
1224 },
1225 'add_ie': ['Kaltura'],
1226 },
427cd050
S
1227 {
1228 # Kaltura embedded via quoted entry_id
1229 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1230 'info_dict': {
1231 'id': '0_utuok90b',
1232 'ext': 'mp4',
1233 'title': '06_matthew_brender_raj_dutt',
1234 'timestamp': 1466638791,
1235 'upload_date': '20160622',
1236 },
1237 'add_ie': ['Kaltura'],
1238 'expected_warnings': [
1239 'Could not send HEAD request'
1240 ],
1241 'params': {
1242 'skip_download': True,
1243 }
1244 },
8ab7e6c4
YCH
1245 {
1246 # Kaltura embedded, some fileExt broken (#11480)
1247 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1248 'info_dict': {
1249 'id': '1_sgtvehim',
1250 'ext': 'mp4',
1251 'title': 'Our "Standard Models" of particle physics and cosmology',
1252 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1253 'timestamp': 1321158993,
1254 'upload_date': '20111113',
1255 'uploader_id': 'kps1',
1256 },
1257 'add_ie': ['Kaltura'],
1258 },
a01825a5
JH
1259 {
1260 # Kaltura iframe embed
1261 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1262 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1263 'info_dict': {
1264 'id': '0_f2cfbpwy',
1265 'ext': 'mp4',
1266 'title': 'I. M. Pei: A Centennial Celebration',
1267 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1268 'upload_date': '20170403',
1269 'uploader_id': 'batchUser',
1270 'timestamp': 1491232186,
1271 },
1272 'add_ie': ['Kaltura'],
1273 },
250b042c
S
1274 # referrer protected EaglePlatform embed
1275 {
1276 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1277 'info_dict': {
1278 'id': '582306',
1279 'ext': 'mp4',
1280 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1281 'thumbnail': r're:^https?://.*\.jpg$',
1282 'duration': 3382,
1283 'view_count': int,
1284 },
1285 'params': {
1286 'skip_download': True,
1287 },
135c9c42 1288 },
665e9452 1289 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1290 {
1291 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1292 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1293 'info_dict': {
1294 'id': '12820',
1295 'ext': 'mp4',
1296 'title': "'O Sole Mio",
ec85ded8 1297 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1298 'duration': 216,
1299 'view_count': int,
1300 },
250b042c
S
1301 'params': {
1302 'skip_download': True,
1303 },
2637fadc 1304 'skip': 'This video is unavailable.',
d47ae7f6 1305 },
f8388757
S
1306 # Pladform embed
1307 {
1308 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1309 'info_dict': {
1310 'id': '100183293',
1311 'ext': 'mp4',
62259846 1312 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1313 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1314 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1315 'duration': 694,
1316 'age_limit': 0,
1317 },
2637fadc 1318 'skip': 'HTTP Error 404: Not Found',
f8388757 1319 },
c798f15b
S
1320 # Playwire embed
1321 {
1322 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1323 'info_dict': {
1324 'id': '3519514',
1325 'ext': 'mp4',
1326 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1327 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1328 'duration': 45.115,
1329 },
1330 },
ad320e9b
NJ
1331 # 5min embed
1332 {
1333 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1334 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1335 'info_dict': {
1336 'id': '518726732',
1337 'ext': 'mp4',
1338 'title': 'Facebook Creates "On This Day" | Crunch Report',
2637fadc
RA
1339 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1340 'timestamp': 1427237531,
1341 'uploader': 'Crunch Report',
1342 'upload_date': '20150324',
1343 },
1344 'params': {
1345 # m3u8 download
1346 'skip_download': True,
ad320e9b
NJ
1347 },
1348 },
dc455a5f
S
1349 # SVT embed
1350 {
1351 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1352 'info_dict': {
1353 'id': '2900353',
1354 'ext': 'flv',
1355 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1356 'duration': 27,
1357 'age_limit': 0,
1358 },
1359 },
a4257017
S
1360 # Crooks and Liars embed
1361 {
1362 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1363 'info_dict': {
1364 'id': '8RUoRhRi',
1365 'ext': 'mp4',
1366 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1367 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1368 'timestamp': 1428207000,
1369 'upload_date': '20150405',
1370 'uploader': 'Heather',
1371 },
1372 },
1373 # Crooks and Liars external embed
1374 {
1375 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1376 'info_dict': {
1377 'id': 'MTE3MjUtMzQ2MzA',
1378 'ext': 'mp4',
1379 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1380 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1381 'timestamp': 1265032391,
1382 'upload_date': '20100201',
1383 'uploader': 'Heather',
1384 },
1385 },
facecb84 1386 # NBC Sports vplayer embed
a2edf2e7 1387 {
facecb84 1388 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1389 'info_dict': {
facecb84
S
1390 'id': 'ln7x1qSThw4k',
1391 'ext': 'flv',
1392 'title': "PFT Live: New leader in the 'new-look' defense",
1393 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1394 'uploader': 'NBCU-SPORTS',
1395 'upload_date': '20140107',
1396 'timestamp': 1389118457,
a2edf2e7 1397 },
2637fadc 1398 'skip': 'Invalid Page URL',
418c5cc3 1399 },
de3eb07e
YCH
1400 # NBC News embed
1401 {
1402 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1403 'md5': '1aa589c675898ae6d37a17913cf68d66',
1404 'info_dict': {
2637fadc 1405 'id': 'x_dtl_oa_LettermanliftPR_160608',
de3eb07e 1406 'ext': 'mp4',
2637fadc 1407 'title': 'David Letterman: A Preview',
de3eb07e 1408 '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
1409 'upload_date': '20160609',
1410 'timestamp': 1465431544,
1411 'uploader': 'NBCU-NEWS',
de3eb07e
YCH
1412 },
1413 },
418c5cc3
YCH
1414 # UDN embed
1415 {
811586eb 1416 'url': 'https://video.udn.com/news/300346',
01c58f84 1417 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1418 'info_dict': {
01c58f84 1419 'id': '300346',
418c5cc3 1420 'ext': 'mp4',
01c58f84 1421 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1422 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1423 },
1424 'params': {
1425 # m3u8 download
1426 'skip_download': True,
1427 },
2637fadc 1428 'expected_warnings': ['Failed to parse JSON Expecting value'],
edfcf7ab
YCH
1429 },
1430 # Ooyala embed
1431 {
1432 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1433 'info_dict': {
1434 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1435 'ext': 'mp4',
2637fadc 1436 'description': 'Index/Match versus VLOOKUP.',
edfcf7ab 1437 'title': 'This is what separates the Excel masters from the wannabes',
53e06b25 1438 'duration': 191.933,
edfcf7ab
YCH
1439 },
1440 'params': {
1441 # m3u8 downloads
1442 'skip_download': True,
1443 }
d6fd958c 1444 },
b26733ba
YCH
1445 # Brightcove URL in single quotes
1446 {
1447 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1448 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1449 'info_dict': {
1450 'id': '4255764656001',
1451 'ext': 'mp4',
1452 'title': 'SN Presents: Russell Martin, World Citizen',
1453 '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.',
1454 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1455 'uploader_id': '1704050871',
1456 'upload_date': '20150525',
1457 'timestamp': 1432570283,
b26733ba 1458 },
756f574e 1459 },
8084be78
S
1460 # OnionStudios embed
1461 {
1462 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1463 'info_dict': {
1464 'id': '2855',
1465 'ext': 'mp4',
1466 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
ec85ded8 1467 'thumbnail': r're:^https?://.*\.jpe?g$',
8084be78
S
1468 'uploader': 'ClickHole',
1469 'uploader_id': 'clickhole',
1470 }
1471 },
b8c1cc1a
S
1472 # SnagFilms embed
1473 {
1474 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1475 'info_dict': {
1476 'id': '74849a00-85a9-11e1-9660-123139220831',
1477 'ext': 'mp4',
1478 'title': '#whilewewatch',
1479 }
1480 },
a5158f38
YCH
1481 # AdobeTVVideo embed
1482 {
1483 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1484 'md5': '43662b577c018ad707a63766462b1e87',
1485 'info_dict': {
1486 'id': '2456',
1487 'ext': 'mp4',
1488 'title': 'New experience with Acrobat DC',
1489 'description': 'New experience with Acrobat DC',
1490 'duration': 248.667,
1491 },
1f812580 1492 },
ed126900 1493 # BrightcoveInPageEmbed embed
1494 {
1495 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1496 'info_dict': {
1497 'id': '4238694884001',
1498 'ext': 'flv',
1499 'title': 'Tabletop: Dread, Last Thoughts',
1500 'description': 'Tabletop: Dread, Last Thoughts',
1501 'duration': 51690,
1502 },
750b9ff0 1503 },
d10fe835
YCH
1504 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1505 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1506 {
1507 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1508 'info_dict': {
1509 'id': '4785848093001',
1510 'ext': 'mp4',
1511 'title': 'The Cardinal Pell Interview',
1512 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1513 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1514 'uploader_id': '2733773828001',
1515 'upload_date': '20160304',
1516 'timestamp': 1457083087,
d10fe835
YCH
1517 },
1518 'params': {
1519 # m3u8 downloads
1520 'skip_download': True,
1521 },
1522 },
9edf47df
S
1523 {
1524 # Brightcove embed with whitespace around attribute names
1525 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1526 'info_dict': {
1527 'id': '3167554373001',
1528 'ext': 'mp4',
1529 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1530 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1531 'uploader_id': '1079349493',
1532 'upload_date': '20140207',
1533 'timestamp': 1391810548,
1534 },
1535 'params': {
1536 'skip_download': True,
1537 },
1538 },
134c207e
YCH
1539 # Another form of arte.tv embed
1540 {
1541 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1542 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1543 'info_dict': {
1544 'id': '030273-562_PLUS7-F',
1545 'ext': 'mp4',
1546 'title': 'ARTE Reportage - Nulle part, en France',
1547 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1548 'upload_date': '20160409',
1549 },
1550 },
b8f67449
KM
1551 # LiveLeak embed
1552 {
1553 'url': 'http://www.wykop.pl/link/3088787/',
09747ba7 1554 'md5': '7619da8c820e835bef21a1efa2a0fc71',
b8f67449
KM
1555 'info_dict': {
1556 'id': '874_1459135191',
1557 'ext': 'mp4',
1558 'title': 'Man shows poor quality of new apartment building',
1559 'description': 'The wall is like a sand pile.',
1560 'uploader': 'Lake8737',
09747ba7
YCH
1561 },
1562 'add_ie': [LiveLeakIE.ie_key()],
1563 },
1564 # Another LiveLeak embed pattern (#13336)
1565 {
1566 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1567 'info_dict': {
1568 'id': '2eb_1496309988',
1569 'ext': 'mp4',
1570 'title': 'Thief robs place where everyone was armed',
1571 'description': 'md5:694d73ee79e535953cf2488562288eee',
1572 'uploader': 'brazilwtf',
1573 },
1574 'add_ie': [LiveLeakIE.ie_key()],
b8f67449 1575 },
4a120778
YCH
1576 # Duplicated embedded video URLs
1577 {
1578 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1579 'info_dict': {
1580 'id': '149298443_480_16c25b74_2',
1581 'ext': 'mp4',
1582 'title': 'vs. Blue Orange Spring Game',
1583 'uploader': 'www.hudl.com',
1584 },
1585 },
371ddb14
S
1586 # twitter:player:stream embed
1587 {
1588 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1589 'info_dict': {
1590 'id': 'master',
1591 'ext': 'mp4',
1592 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1593 'uploader': 'www.rtl.be',
1594 },
1595 'params': {
1596 # m3u8 downloads
1597 'skip_download': True,
1598 },
1599 },
32917907
RA
1600 # twitter:player embed
1601 {
1602 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1603 'md5': 'a3e0df96369831de324f0778e126653c',
1604 'info_dict': {
1605 'id': '4909620399001',
1606 'ext': 'mp4',
1607 'title': 'What Do Black Holes Sound Like?',
1608 'description': 'what do black holes sound like',
1609 'upload_date': '20160524',
1610 'uploader_id': '29913724001',
1611 'timestamp': 1464107587,
1612 'uploader': 'TheAtlantic',
1613 },
1614 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1615 },
1616 # Facebook <iframe> embed
1617 {
1618 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1619 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1620 'info_dict': {
1621 'id': '599637780109885',
1622 'ext': 'mp4',
1623 'title': 'Facebook video #599637780109885',
1624 },
1625 },
fd1c5fba
S
1626 # Facebook <iframe> embed, plugin video
1627 {
1628 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1629 'info_dict': {
1630 'id': '1754168231264132',
1631 'ext': 'mp4',
1632 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1633 'uploader': 'Tariq Ramadan (official)',
1634 'timestamp': 1496758379,
1635 'upload_date': '20170606',
1636 },
1637 'params': {
1638 'skip_download': True,
1639 },
1640 },
fd6ca382
YCH
1641 # Facebook API embed
1642 {
1643 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1644 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1645 'info_dict': {
1646 'id': '10153467542406923',
1647 'ext': 'mp4',
1648 'title': 'Facebook video #10153467542406923',
1649 },
7deef1ba
YCH
1650 },
1651 # Wordpress "YouTube Video Importer" plugin
1652 {
1653 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1654 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1655 'info_dict': {
1656 'id': 'HNTXWDXV9Is',
1657 'ext': 'mp4',
1658 'title': 'Blue Devils Drumline Stanford lot 2016',
1659 'upload_date': '20160627',
1660 'uploader_id': 'GENOCIDE8GENERAL10',
1661 'uploader': 'cylus cyrus',
1662 },
1663 },
81953d1a
RA
1664 {
1665 # video stored on custom kaltura server
1666 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1667 'md5': '537617d06e64dfed891fa1593c4b30cc',
1668 'info_dict': {
1669 'id': '0_1iotm5bh',
1670 'ext': 'mp4',
1671 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1672 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1673 'uploader_id': 'videos.expansion@el-mundo.net',
1674 'upload_date': '20150429',
1675 'timestamp': 1430303472,
1676 },
1677 'add_ie': ['Kaltura'],
1678 },
c03adf90
YCH
1679 {
1680 # Non-standard Vimeo embed
1681 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1682 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1683 'info_dict': {
1684 'id': '148867247',
1685 'ext': 'mp4',
1686 'title': 'Understanding the web - Teaser',
1687 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1688 'upload_date': '20151214',
1689 'uploader': 'OpenClassrooms',
1690 'uploader_id': 'openclassrooms',
1691 },
1692 'add_ie': ['Vimeo'],
1693 },
a5ff05df
S
1694 {
1695 # generic vimeo embed that requires original URL passed as Referer
1696 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1697 'only_matching': True,
1698 },
1979969f
S
1699 {
1700 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1701 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1702 'info_dict': {
1703 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1704 'ext': 'mp4',
1705 'title': 'Big Buck Bunny',
1706 'description': 'Royalty free test video',
1707 'timestamp': 1432816365,
1708 'upload_date': '20150528',
1709 'is_live': False,
1710 },
1711 'params': {
1712 'skip_download': True,
1713 },
1714 'add_ie': [ArkenaIE.ie_key()],
1715 },
2a1321a2
S
1716 {
1717 '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/',
1718 'info_dict': {
1719 'id': '1c7141f46c',
1720 'ext': 'mp4',
1721 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1722 },
1723 'params': {
1724 'skip_download': True,
1725 },
1726 'add_ie': [Vbox7IE.ie_key()],
1727 },
b0c8f2e9
DR
1728 {
1729 # DBTV embeds
1730 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1731 'info_dict': {
1732 'id': '43254897',
1733 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1734 },
b0c8f2e9
DR
1735 'playlist_mincount': 3,
1736 },
e186a9ec
S
1737 {
1738 # Videa embeds
1739 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1740 'info_dict': {
1741 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1742 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1743 },
1744 'playlist_mincount': 2,
1745 },
b687c85e
S
1746 {
1747 # 20 minuten embed
1748 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1749 'info_dict': {
1750 'id': '523629',
1751 'ext': 'mp4',
1752 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1753 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1754 },
1755 'params': {
1756 'skip_download': True,
1757 },
1758 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1759 },
1760 {
1761 # VideoPress embed
1762 'url': 'https://en.support.wordpress.com/videopress/',
1763 'info_dict': {
1764 'id': 'OcobLTqC',
1765 'ext': 'm4v',
1766 'title': 'IMG_5786',
1767 'timestamp': 1435711927,
1768 'upload_date': '20150701',
1769 },
1770 'params': {
1771 'skip_download': True,
1772 },
1773 'add_ie': [VideoPressIE.ie_key()],
fef51645 1774 },
eb3079b6
S
1775 {
1776 # Rutube embed
1777 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1778 'info_dict': {
1779 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1780 'ext': 'flv',
1781 'title': 'Магаззино: Казань 2',
1782 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1783 'uploader': 'Магаззино',
1784 'upload_date': '20170228',
1785 'uploader_id': '996642',
1786 },
1787 'params': {
1788 'skip_download': True,
1789 },
1790 'add_ie': [RutubeIE.ie_key()],
1791 },
fef51645
YCH
1792 {
1793 # ThePlatform embedded with whitespaces in URLs
1794 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1795 'only_matching': True,
1796 },
97952bdb
JH
1797 {
1798 # Senate ISVP iframe https
1799 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1800 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1801 'info_dict': {
1802 'id': 'govtaff020316',
1803 'ext': 'mp4',
1804 'title': 'Integrated Senate Video Player',
1805 },
1806 'add_ie': [SenateISVPIE.ie_key()],
1807 },
ab87c260
S
1808 {
1809 # Limelight embeds (1 channel embed + 4 media embeds)
1810 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1811 'info_dict': {
1812 'id': 'FacilitatorTraining2017',
1813 'title': 'Facilitator Training 2017',
1814 },
1815 'playlist_mincount': 5,
1816 },
eb02940c
S
1817 {
1818 # Limelight embed (LimelightPlayerUtil.embed)
1819 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1820 'info_dict': {
1821 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1822 'ext': 'mp4',
1823 'title': '07448641',
1824 'timestamp': 1499890639,
1825 'upload_date': '20170712',
1826 },
1827 'params': {
1828 'skip_download': True,
1829 },
1830 'add_ie': ['LimelightMedia'],
1831 },
7986c3ab
S
1832 {
1833 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1834 'info_dict': {
1835 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1836 'title': 'Standoff with Walnut Creek murder suspect ends',
1837 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1838 },
1839 'playlist_mincount': 4,
1840 },
55719459
JH
1841 {
1842 # WashingtonPost embed
1843 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1844 'info_dict': {
1845 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1846 'ext': 'mp4',
1847 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1848 '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.',
1849 'timestamp': 1455216756,
1850 'uploader': 'The Washington Post',
1851 'upload_date': '20160211',
1852 },
1853 'add_ie': [WashingtonPostIE.ie_key()],
1854 },
2b8e6a68
S
1855 {
1856 # Mediaset embed
1857 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1858 'info_dict': {
1859 'id': '720642',
1860 'ext': 'mp4',
1861 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1862 },
1863 'params': {
1864 'skip_download': True,
1865 },
1866 'add_ie': [MediasetIE.ie_key()],
1867 },
73cf76a9
S
1868 {
1869 # JOJ.sk embeds
1870 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1871 'info_dict': {
1872 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1873 'title': 'Slovenskom sa prehnala vlna silných búrok',
1874 },
1875 'playlist_mincount': 5,
1876 'add_ie': [JojIE.ie_key()],
1877 },
4328ddf8
S
1878 {
1879 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1880 'url': 'https://tvrain.ru/amp/418921/',
1881 'md5': 'cc00413936695987e8de148b67d14f1d',
1882 'info_dict': {
1883 'id': '418921',
1884 'ext': 'mp4',
1885 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1886 },
1887 },
41918eaa 1888 {
1889 # vzaar embed
1663bd6e
S
1890 'url': 'http://help.vzaar.com/article/165-embedding-video',
1891 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1892 'info_dict': {
1663bd6e 1893 'id': '8707641',
41918eaa 1894 'ext': 'mp4',
1663bd6e 1895 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1896 },
1897 },
9ce1ac40 1898 {
1899 # multiple HTML5 videos on one page
1900 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1901 'info_dict': {
1902 'id': 'keyscenarios',
1903 'title': 'Rescue Kit 14 Free Edition - Getting started',
1904 },
1905 'playlist_count': 4,
0987f2dd
T
1906 },
1907 {
1908 # vshare embed
1909 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1910 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1911 'info_dict': {
1912 'id': '0f64ce6',
1913 'title': 'vl14062007715967',
1914 'ext': 'mp4',
1915 }
2ca7ed41
S
1916 },
1917 {
1918 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1919 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1920 'info_dict': {
1921 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1922 'ext': 'mp4',
1923 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1924 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1925 'timestamp': 1474354800,
1926 'upload_date': '20160920',
1927 }
7d540621
S
1928 },
1929 {
1930 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1931 'info_dict': {
1932 'id': '1731611',
1933 'ext': 'mp4',
1934 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1935 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1936 'timestamp': 1516100691,
1937 'upload_date': '20180116',
1938 },
1939 'params': {
1940 'skip_download': True,
1941 },
1942 'add_ie': [SpringboardPlatformIE.ie_key()],
ea696249
S
1943 },
1944 {
1945 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1946 'info_dict': {
1947 'id': 'uPDB5I9wfp8',
1948 'ext': 'webm',
1949 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1950 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1951 'upload_date': '20160219',
1952 'uploader': 'Pocoyo - Português (BR)',
1953 'uploader_id': 'PocoyoBrazil',
1954 },
1955 'add_ie': [YoutubeIE.ie_key()],
1956 'params': {
1957 'skip_download': True,
1958 },
4c780fbd
S
1959 },
1960 {
1961 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1962 'info_dict': {
1963 'id': 'vMDE4NzI1Mjgt690b',
1964 'ext': 'mp4',
1965 'title': 'Котята',
1966 },
1967 'add_ie': [YapFilesIE.ie_key()],
1968 'params': {
1969 'skip_download': True,
1970 },
1fc37ca3
SO
1971 },
1972 {
1973 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
1974 'md5': 'b68d276de422ab07ee1d49388103f457',
1975 'info_dict': {
1976 'id': '83645793',
1977 'title': 'Lock up and get excited',
1fc37ca3 1978 'ext': 'mp4'
d3431dcb
S
1979 },
1980 'skip': 'TODO: fix nested playlists processing in tests',
1981 },
6e6b70d6
S
1982 # {
1983 # # TODO: find another test
1984 # # http://schema.org/VideoObject
1985 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1986 # 'md5': '888dcf08b7ea671381f00fab74692755',
1987 # 'info_dict': {
1988 # 'id': 'nyvTSJMKId',
1989 # 'ext': 'mp4',
1990 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1991 # 'description': '#love for cats.',
1992 # 'timestamp': 1461244995,
1993 # 'upload_date': '20160421',
1994 # },
1995 # 'params': {
1996 # 'force_generic_extractor': True,
1997 # },
1998 # }
cfe50f04 1999 ]
9b122384 2000
9b122384
PH
2001 def report_following_redirect(self, new_url):
2002 """Report information extraction."""
79649588 2003 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 2004
4fc946b5
PH
2005 def _extract_rss(self, url, video_id, doc):
2006 playlist_title = doc.find('./channel/title').text
2007 playlist_desc_el = doc.find('./channel/description')
2008 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2009
76c73715
PH
2010 entries = []
2011 for it in doc.findall('./channel/item'):
2012 next_url = xpath_text(it, 'link', fatal=False)
2013 if not next_url:
2014 enclosure_nodes = it.findall('./enclosure')
2015 for e in enclosure_nodes:
2016 next_url = e.attrib.get('url')
2017 if next_url:
2018 break
2019
2020 if not next_url:
2021 continue
2022
2023 entries.append({
413c1f8e 2024 '_type': 'url_transparent',
76c73715
PH
2025 'url': next_url,
2026 'title': it.find('title').text,
2027 })
4fc946b5
PH
2028
2029 return {
2030 '_type': 'playlist',
2031 'id': url,
2032 'title': playlist_title,
2033 'description': playlist_desc,
2034 'entries': entries,
2035 }
2036
c8e9a235
PH
2037 def _extract_camtasia(self, url, video_id, webpage):
2038 """ Returns None if no camtasia video can be found. """
2039
2040 camtasia_cfg = self._search_regex(
2041 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2042 webpage, 'camtasia configuration file', default=None)
2043 if camtasia_cfg is None:
2044 return None
2045
2046 title = self._html_search_meta('DC.title', webpage, fatal=True)
2047
2048 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2049 camtasia_cfg = self._download_xml(
2050 camtasia_url, video_id,
2051 note='Downloading camtasia configuration',
2052 errnote='Failed to download camtasia configuration')
2053 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2054
2055 entries = []
2056 for n in fileset_node.getchildren():
2057 url_n = n.find('./uri')
2058 if url_n is None:
2059 continue
2060
2061 entries.append({
2062 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2063 'title': '%s - %s' % (title, n.tag),
2064 'url': compat_urlparse.urljoin(url, url_n.text),
2065 'duration': float_or_none(n.find('./duration').text),
2066 })
2067
2068 return {
2069 '_type': 'playlist',
2070 'entries': entries,
2071 'title': title,
2072 }
2073
9b122384 2074 def _real_extract(self, url):
ebd3c7b3
PH
2075 if url.startswith('//'):
2076 return {
2077 '_type': 'url',
20991253 2078 'url': self.http_scheme() + url,
ebd3c7b3
PH
2079 }
2080
a7130543
JMF
2081 parsed_url = compat_urlparse.urlparse(url)
2082 if not parsed_url.scheme:
04b4d394
PH
2083 default_search = self._downloader.params.get('default_search')
2084 if default_search is None:
1f7ccb90 2085 default_search = 'fixup_error'
04b4d394 2086
1f7ccb90 2087 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
2088 if '/' in url:
2089 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2090 return self.url_result('http://' + url)
1f7ccb90 2091 elif default_search != 'fixup_error':
9c1fc022 2092 if default_search == 'auto_warning':
0e67ab0d
PH
2093 if re.match(r'^(?:url|URL)$', url):
2094 raise ExtractorError(
2095 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2096 expected=True)
2097 else:
2098 self._downloader.report_warning(
7571c02c 2099 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2100 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2101
2102 if default_search in ('error', 'fixup_error'):
7571c02c 2103 raise ExtractorError(
b74e86f4
PH
2104 '%r is not a valid URL. '
2105 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2106 % (url, url), expected=True)
04b4d394 2107 else:
f2f2c0c2
PH
2108 if ':' not in default_search:
2109 default_search += ':'
04b4d394 2110 return self.url_result(default_search + url)
4d54ef20
PH
2111
2112 url, smuggled_data = unsmuggle_url(url)
2113 force_videoid = None
d6e6a422 2114 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2115 if smuggled_data and 'force_videoid' in smuggled_data:
2116 force_videoid = smuggled_data['force_videoid']
2117 video_id = force_videoid
2118 else:
9dcd6fd3 2119 video_id = self._generic_id(url)
3d83a1ae 2120
79649588 2121 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2122
ebab4520 2123 head_req = HEADRequest(url)
23be51d8 2124 head_response = self._request_webpage(
ebab4520
PH
2125 head_req, video_id,
2126 note=False, errnote='Could not send HEAD request to %s' % url,
2127 fatal=False)
42393ce2 2128
23be51d8 2129 if head_response is not False:
42393ce2 2130 # Check for redirect
5551d771 2131 new_url = compat_str(head_response.geturl())
42393ce2
PH
2132 if url != new_url:
2133 self.report_following_redirect(new_url)
4d54ef20
PH
2134 if force_videoid:
2135 new_url = smuggle_url(
2136 new_url, {'force_videoid': force_videoid})
cecaaf3f 2137 return self.url_result(new_url)
42393ce2 2138
23be51d8
PH
2139 full_response = None
2140 if head_response is False:
5c2266df 2141 request = sanitized_Request(url)
58bde34a
S
2142 request.add_header('Accept-Encoding', '*')
2143 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2144 head_response = full_response
2145
f930e0c7
S
2146 info_dict = {
2147 'id': video_id,
9dcd6fd3 2148 'title': self._generic_title(url),
303dcdb9 2149 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
2150 }
2151
23be51d8 2152 # Check for direct link to a video
955737b2 2153 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2154 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2155 if m:
4e363703 2156 format_id = compat_str(m.group('format_id'))
f930e0c7 2157 if format_id.endswith('mpegurl'):
eadc3ccd 2158 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
2159 elif format_id == 'f4m':
2160 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2161 else:
2162 formats = [{
4e363703 2163 'format_id': format_id,
eadc3ccd 2164 'url': url,
2165 'vcodec': 'none' if m.group('type') == 'audio' else None
2166 }]
de6c51e8 2167 info_dict['direct'] = True
19dbaeec 2168 self._sort_formats(formats)
de6c51e8 2169 info_dict['formats'] = formats
f930e0c7 2170 return info_dict
42393ce2 2171
d6e6a422 2172 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
2173 force = self._downloader.params.get('force_generic_extractor', False)
2174 self._downloader.report_warning(
2175 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2176
4e262a88 2177 if not full_response:
5c2266df 2178 request = sanitized_Request(url)
58bde34a
S
2179 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2180 # making it impossible to download only chunk of the file (yet we need only 512kB to
2181 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2182 # that will always result in downloading the whole file that is not desirable.
2183 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2184 # to accept raw bytes and being able to download only a chunk.
2185 # It may probably better to solve this by checking Content-Type for application/octet-stream
2186 # after HEAD request finishes, but not sure if we can rely on this.
2187 request.add_header('Accept-Encoding', '*')
2188 full_response = self._request_webpage(request, video_id)
4e262a88 2189
5940862d
S
2190 first_bytes = full_response.read(512)
2191
2192 # Is it an M3U playlist?
0d769bcb 2193 if first_bytes.startswith(b'#EXTM3U'):
5940862d 2194 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 2195 self._sort_formats(info_dict['formats'])
5940862d
S
2196 return info_dict
2197
4e262a88
PH
2198 # Maybe it's a direct link to a video?
2199 # Be careful not to download the whole thing!
61ca9a80 2200 if not is_html(first_bytes):
4e262a88
PH
2201 self._downloader.report_warning(
2202 'URL could be a direct video link, returning it as such.')
f930e0c7 2203 info_dict.update({
4e262a88
PH
2204 'direct': True,
2205 'url': url,
f930e0c7
S
2206 })
2207 return info_dict
4e262a88
PH
2208
2209 webpage = self._webpage_read_content(
2210 full_response, url, video_id, prefix=first_bytes)
2211
9b122384 2212 self.report_extraction(video_id)
887c6acd 2213
1b840245 2214 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2215 try:
f7854627 2216 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
2217 if doc.tag == 'rss':
2218 return self._extract_rss(url, video_id, doc)
cc99a77a
S
2219 elif doc.tag == 'SmoothStreamingMedia':
2220 info_dict['formats'] = self._parse_ism_formats(doc, url)
2221 self._sort_formats(info_dict['formats'])
2222 return info_dict
e5e8d20a 2223 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
2224 smil = self._parse_smil(doc, url, video_id)
2225 self._sort_formats(smil['formats'])
2226 return smil
729accb4 2227 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
96b8b9ab 2228 return self.playlist_result(
47a5cb77
S
2229 self._parse_xspf(
2230 doc, video_id, xspf_url=url,
2231 xspf_base_url=compat_str(full_response.geturl())),
96b8b9ab 2232 video_id)
1b840245 2233 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7 2234 info_dict['formats'] = self._parse_mpd_formats(
d3f8b76b 2235 doc,
5551d771 2236 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
86f4d14f 2237 mpd_url=url)
19dbaeec 2238 self._sort_formats(info_dict['formats'])
f930e0c7
S
2239 return info_dict
2240 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2241 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 2242 self._sort_formats(info_dict['formats'])
f930e0c7 2243 return info_dict
f7300c5c 2244 except compat_xml_parse_error:
4fc946b5
PH
2245 pass
2246
c8e9a235
PH
2247 # Is it a Camtasia project?
2248 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2249 if camtasia_res is not None:
2250 return camtasia_res
2251
14390730
S
2252 # Sometimes embedded video player is hidden behind percent encoding
2253 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2254 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 2255 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2256
887c6acd
PH
2257 # it's tempting to parse this further, but you would
2258 # have to take into account all the variations like
2259 # Video Title - Site Name
2260 # Site Name | Video Title
2261 # Video Title - Tagline | Site Name
2262 # and so on and so forth; it's just not practical
6f41b2bc
S
2263 video_title = self._og_search_title(
2264 webpage, default=None) or self._html_search_regex(
79649588
PH
2265 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2266 default='video')
ef4fd848 2267
4d805e06
PH
2268 # Try to detect age limit automatically
2269 age_limit = self._rta_search(webpage)
2270 # And then there are the jokers who advertise that they use RTA,
2271 # but actually don't.
2272 AGE_LIMIT_MARKERS = [
197224b7 2273 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
4d805e06
PH
2274 ]
2275 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2276 age_limit = 18
2277
ef4fd848
PH
2278 # video uploader is domain name
2279 video_uploader = self._search_regex(
79649588 2280 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2281
6f41b2bc
S
2282 video_description = self._og_search_description(webpage, default=None)
2283 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2284
b311b0ea
S
2285 info_dict.update({
2286 'title': video_title,
2287 'description': video_description,
2288 'thumbnail': video_thumbnail,
2289 'age_limit': age_limit,
2290 })
2291
1f4b722b 2292 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2293 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2294 if bc_urls:
99877772
PH
2295 entries = [{
2296 '_type': 'url',
2297 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2298 'ie_key': 'BrightcoveLegacy'
99877772
PH
2299 } for bc_url in bc_urls]
2300
2301 return {
2302 '_type': 'playlist',
2303 'title': video_title,
2304 'id': video_id,
2305 'entries': entries,
2306 }
cfe50f04 2307
f6519f89 2308 # Look for Brightcove New Studio embeds
0254f93b 2309 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2310 if bc_urls:
5399ab3f
S
2311 return self.playlist_from_matches(
2312 bc_urls, video_id, video_title,
2313 getter=lambda x: smuggle_url(x, {'referrer': url}),
2314 ie='BrightcoveNew')
ed126900 2315
4e826cd9
S
2316 # Look for Nexx embeds
2317 nexx_urls = NexxIE._extract_urls(webpage)
2318 if nexx_urls:
2319 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2320
3f59b015
S
2321 # Look for Nexx iFrame embeds
2322 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2323 if nexx_embed_urls:
2324 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2325
4d8819d2
S
2326 # Look for ThePlatform embeds
2327 tp_urls = ThePlatformIE._extract_urls(webpage)
2328 if tp_urls:
46b18f23 2329 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2330
48a5eabc
S
2331 # Look for Vessel embeds
2332 vessel_urls = VesselIE._extract_urls(webpage)
2333 if vessel_urls:
46b18f23 2334 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
48a5eabc 2335
59b8ab58
PH
2336 # Look for embedded rtl.nl player
2337 matches = re.findall(
2637fadc 2338 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
59b8ab58
PH
2339 webpage)
2340 if matches:
46b18f23 2341 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2342
09b9c45e
S
2343 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2344 if vimeo_urls:
46b18f23 2345 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2346
a1b85269
YCH
2347 vid_me_embed_url = self._search_regex(
2348 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2349 webpage, 'vid.me embed', default=None)
2350 if vid_me_embed_url is not None:
2351 return self.url_result(vid_me_embed_url, 'Vidme')
2352
66c9fa36
S
2353 # Look for YouTube embeds
2354 youtube_urls = YoutubeIE._extract_urls(webpage)
2355 if youtube_urls:
46b18f23 2356 return self.playlist_from_matches(
66c9fa36 2357 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2358
ad213a1d 2359 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2360 if matches:
46b18f23 2361 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2362
8489578d
NJ
2363 # Look for embedded Dailymotion playlist player (#3822)
2364 m = re.search(
2365 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2366 if m:
2367 playlists = re.findall(
2368 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2369 if playlists:
46b18f23
JH
2370 return self.playlist_from_matches(
2371 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2372
71a1db89
S
2373 # Look for DailyMail embeds
2374 dailymail_urls = DailyMailIE._extract_urls(webpage)
2375 if dailymail_urls:
2376 return self.playlist_from_matches(
2377 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2378
ef4fd848 2379 # Look for embedded Wistia player
58bb4402
S
2380 wistia_url = WistiaIE._extract_url(webpage)
2381 if wistia_url:
ef4fd848
PH
2382 return {
2383 '_type': 'url_transparent',
58bb4402
S
2384 'url': self._proto_relative_url(wistia_url),
2385 'ie_key': WistiaIE.ie_key(),
ef4fd848 2386 'uploader': video_uploader,
ef4fd848 2387 }
5f6a1245 2388
bab19a8e
S
2389 # Look for SVT player
2390 svt_url = SVTIE._extract_url(webpage)
2391 if svt_url:
2392 return self.url_result(svt_url, 'SVT')
2393
c19f7764
JMF
2394 # Look for Bandcamp pages with custom domain
2395 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2396 if mobj is not None:
2397 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2398 # Don't set the extractor because it can be a track url or an album
2399 return self.url_result(burl)
c19f7764 2400
f25571ff
PH
2401 # Look for embedded Vevo player
2402 mobj = re.search(
2403 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2404 if mobj is not None:
2405 return self.url_result(mobj.group('url'))
796df3c6
S
2406
2407 # Look for embedded Viddler player
cb454b33
S
2408 mobj = re.search(
2409 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2410 webpage)
796df3c6
S
2411 if mobj is not None:
2412 return self.url_result(mobj.group('url'))
f25571ff 2413
3378d67a
S
2414 # Look for NYTimes player
2415 mobj = re.search(
2416 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2417 webpage)
2418 if mobj is not None:
2419 return self.url_result(mobj.group('url'))
2420
cefdf970
S
2421 # Look for Libsyn player
2422 mobj = re.search(
2423 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2424 if mobj is not None:
2425 return self.url_result(mobj.group('url'))
2426
c0d0b01f 2427 # Look for Ooyala videos
8a37aa15 2428 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 2429 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
198d4cb4 2430 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
2431 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2432 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2433 if mobj is not None:
9837cb75
RA
2434 embed_token = self._search_regex(
2435 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2436 webpage, 'ooyala embed token', default=None)
2437 return OoyalaIE._build_url_result(smuggle_url(
2438 mobj.group('ec'), {
2439 'domain': url,
2440 'embed_token': embed_token,
2441 }))
c0d0b01f 2442
f076b638 2443 # Look for multiple Ooyala embeds on SBN network websites
2444 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2445 if mobj is not None:
2446 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2447 if embeds:
46b18f23
JH
2448 return self.playlist_from_matches(
2449 embeds, video_id, video_title,
2450 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2451
aa94a6d3 2452 # Look for Aparat videos
48099643 2453 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2454 if mobj is not None:
2455 return self.url_result(mobj.group(1), 'Aparat')
2456
c93c2ab1 2457 # Look for MPORA videos
c3f51436 2458 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2459 if mobj is not None:
2460 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2461
15c0e8e7 2462 # Look for embedded NovaMov-based player
8f89e687 2463 mobj = re.search(
8dfa187b 2464 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
2465 (?P<url>http://(?:(?:embed|www)\.)?
2466 (?:novamov\.com|
2467 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2468 videoweed\.(?:es|com)|
2469 movshare\.(?:net|sx|ag)|
2470 divxstage\.(?:eu|net|ch|co|at|ag))
2471 /embed\.php.+?)\1''', webpage)
8f89e687 2472 if mobj is not None:
15c0e8e7 2473 return self.url_result(mobj.group('url'))
50f56607 2474
9834872b 2475 # Look for embedded Facebook player
0646e34c
S
2476 facebook_urls = FacebookIE._extract_urls(webpage)
2477 if facebook_urls:
2478 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2479
ca97a56e
S
2480 # Look for embedded VK player
2481 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2482 if mobj is not None:
2483 return self.url_result(mobj.group('url'), 'VK')
2484
33d4fdab
S
2485 # Look for embedded Odnoklassniki player
2486 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2487 if mobj is not None:
2488 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2489
0364fa8b
S
2490 # Look for embedded ivi player
2491 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2492 if mobj is not None:
2493 return self.url_result(mobj.group('url'), 'Ivi')
2494
db1f3888
PH
2495 # Look for embedded Huffington Post player
2496 mobj = re.search(
c3f51436 2497 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2498 if mobj is not None:
2499 return self.url_result(mobj.group('url'), 'HuffPost')
2500
1b86cc41 2501 # Look for embed.ly
2502 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2503 if mobj is not None:
2504 return self.url_result(mobj.group('url'))
2505 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2506 if mobj is not None:
f7e6f7fa 2507 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2508
60cc4dc4
PH
2509 # Look for funnyordie embed
2510 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2511 if matches:
46b18f23
JH
2512 return self.playlist_from_matches(
2513 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2514
db546cf8
S
2515 # Look for BBC iPlayer embed
2516 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2517 if matches:
46b18f23 2518 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2519
93d020dd
S
2520 # Look for embedded RUTV player
2521 rutv_url = RUTVIE._extract_url(webpage)
2522 if rutv_url:
2523 return self.url_result(rutv_url, 'RUTV')
2524
494f20cb 2525 # Look for embedded TVC player
b8599718
S
2526 tvc_url = TVCIE._extract_url(webpage)
2527 if tvc_url:
2528 return self.url_result(tvc_url, 'TVC')
494f20cb 2529
d40a3b5b
S
2530 # Look for embedded SportBox player
2531 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2532 if sportbox_urls:
46b18f23 2533 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
d40a3b5b 2534
2bb5b6d0
S
2535 # Look for embedded XHamster player
2536 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2537 if xhamster_urls:
46b18f23 2538 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2539
2c9ca782
S
2540 # Look for embedded TNAFlixNetwork player
2541 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2542 if tnaflix_urls:
46b18f23 2543 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2544
b52c9ef1
S
2545 # Look for embedded PornHub player
2546 pornhub_urls = PornHubIE._extract_urls(webpage)
2547 if pornhub_urls:
46b18f23 2548 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2549
37e7a71c
S
2550 # Look for embedded DrTuber player
2551 drtuber_urls = DrTuberIE._extract_urls(webpage)
2552 if drtuber_urls:
46b18f23 2553 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2554
e28ed498
S
2555 # Look for embedded RedTube player
2556 redtube_urls = RedTubeIE._extract_urls(webpage)
2557 if redtube_urls:
46b18f23 2558 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 2559
06993715
S
2560 # Look for embedded Tube8 player
2561 tube8_urls = Tube8IE._extract_urls(webpage)
2562 if tube8_urls:
2563 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2564
9872d311
S
2565 # Look for embedded Tvigle player
2566 mobj = re.search(
2567 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2568 if mobj is not None:
2569 return self.url_result(mobj.group('url'), 'Tvigle')
2570
7e2ede98
JMF
2571 # Look for embedded TED player
2572 mobj = re.search(
d7cc31b6 2573 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
2574 if mobj is not None:
2575 return self.url_result(mobj.group('url'), 'TED')
2576
5c386252 2577 # Look for embedded Ustream videos
d77ac737
YCH
2578 ustream_url = UstreamIE._extract_url(webpage)
2579 if ustream_url:
2580 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 2581
893f8832
PH
2582 # Look for embedded arte.tv player
2583 mobj = re.search(
134c207e 2584 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
893f8832
PH
2585 webpage)
2586 if mobj is not None:
2587 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2588
cbd55ade
S
2589 # Look for embedded francetv player
2590 mobj = re.search(
2591 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2592 webpage)
2593 if mobj is not None:
2594 return self.url_result(mobj.group('url'))
2595
cb3ac1c6
S
2596 # Look for embedded smotri.com player
2597 smotri_url = SmotriIE._extract_url(webpage)
2598 if smotri_url:
2599 return self.url_result(smotri_url, 'Smotri')
2600
e6c2d9ad 2601 # Look for embedded Myvi.ru player
6dd94d3a 2602 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
2603 if myvi_url:
2604 return self.url_result(myvi_url)
2605
dfb1b146 2606 # Look for embedded soundcloud player
94aae015
S
2607 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2608 if soundcloud_urls:
46b18f23 2609 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
20991253 2610
027e2312
S
2611 # Look for tunein player
2612 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2613 if tunein_urls:
46b18f23 2614 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 2615
c5cd249e 2616 # Look for embedded mtvservices player
46fde8a1
S
2617 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2618 if mtvservices_url:
2619 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 2620
49807b4a
S
2621 # Look for embedded yahoo player
2622 mobj = re.search(
2623 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2624 webpage)
2625 if mobj is not None:
2626 return self.url_result(mobj.group('url'), 'Yahoo')
2627
2ef6fcb5
PH
2628 # Look for embedded sbs.com.au player
2629 mobj = re.search(
e98b8e79
PH
2630 r'''(?x)
2631 (?:
2632 <meta\s+property="og:video"\s+content=|
2633 <iframe[^>]+?src=
2634 )
2635 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
2636 webpage)
2637 if mobj is not None:
2638 return self.url_result(mobj.group('url'), 'SBS')
2639
42bdd9d0
PH
2640 # Look for embedded Cinchcast player
2641 mobj = re.search(
2642 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2643 webpage)
2644 if mobj is not None:
2645 return self.url_result(mobj.group('url'), 'Cinchcast')
2646
1a94ff68 2647 mobj = re.search(
5263cdfc 2648 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 2649 webpage)
8001607e
YCH
2650 if not mobj:
2651 mobj = re.search(
2652 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2653 webpage)
1a94ff68
S
2654 if mobj is not None:
2655 return self.url_result(mobj.group('url'), 'MLB')
2656
1419fafd 2657 mobj = re.search(
dd467d33 2658 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
2659 webpage)
2660 if mobj is not None:
2661 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2662
af63fed7 2663 mobj = re.search(
78d3b3e2 2664 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
2665 webpage)
2666 if mobj is not None:
2667 return self.url_result(mobj.group('url'), 'Livestream')
2668
255fca5e
S
2669 # Look for Zapiks embed
2670 mobj = re.search(
2671 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2672 if mobj is not None:
2673 return self.url_result(mobj.group('url'), 'Zapiks')
2674
e3216b82 2675 # Look for Kaltura embeds
c287f2bc
S
2676 kaltura_url = KalturaIE._extract_url(webpage)
2677 if kaltura_url:
2678 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
e3216b82 2679
665e9452 2680 # Look for EaglePlatform embeds
06a96da1
S
2681 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2682 if eagleplatform_url:
665e9452 2683 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 2684
665e9452 2685 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
2686 mobj = re.search(
2687 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2688 if mobj is not None:
2689 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2690
f8388757 2691 # Look for Pladform embeds
45dad7ba
S
2692 pladform_url = PladformIE._extract_url(webpage)
2693 if pladform_url:
2694 return self.url_result(pladform_url)
f8388757 2695
ff18735c
S
2696 # Look for Videomore embeds
2697 videomore_url = VideomoreIE._extract_url(webpage)
2698 if videomore_url:
2699 return self.url_result(videomore_url)
2700
83f1481b
S
2701 # Look for Webcaster embeds
2702 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2703 if webcaster_url:
2704 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2705
2dcc114f
S
2706 # Look for Playwire embeds
2707 mobj = re.search(
2708 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2709 if mobj is not None:
2710 return self.url_result(mobj.group('url'))
2711
ad320e9b
NJ
2712 # Look for 5min embeds
2713 mobj = re.search(
2714 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2715 if mobj is not None:
2716 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2717
18153f1b
S
2718 # Look for Crooks and Liars embeds
2719 mobj = re.search(
2720 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2721 if mobj is not None:
2722 return self.url_result(mobj.group('url'))
2723
a2edf2e7
YCH
2724 # Look for NBC Sports VPlayer embeds
2725 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2726 if nbc_sports_url:
2727 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2728
de3eb07e
YCH
2729 # Look for NBC News embeds
2730 nbc_news_embed_url = re.search(
2731 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2732 if nbc_news_embed_url:
2733 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2734
653789af 2735 # Look for Google Drive embeds
5b251628 2736 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 2737 if google_drive_url:
2738 return self.url_result(google_drive_url, 'GoogleDrive')
2739
418c5cc3
YCH
2740 # Look for UDN embeds
2741 mobj = re.search(
2637fadc 2742 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
2743 if mobj is not None:
2744 return self.url_result(
0a160363 2745 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 2746
2fe1b5bd
YCH
2747 # Look for Senate ISVP iframe
2748 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2749 if senate_isvp_url:
25c3a734 2750 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 2751
1ac1c4c2
S
2752 # Look for OnionStudios embeds
2753 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2754 if onionstudios_url:
2755 return self.url_result(onionstudios_url)
2756
67167920 2757 # Look for ViewLift embeds
2758 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2759 if viewlift_url:
2760 return self.url_result(viewlift_url)
eedd20ef 2761
7cb09524 2762 # Look for JWPlatform embeds
b0ead0e0
S
2763 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2764 if jwplatform_urls:
2765 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
7cb09524 2766
aecfcd4e
S
2767 # Look for Digiteka embeds
2768 digiteka_url = DigitekaIE._extract_url(webpage)
2769 if digiteka_url:
2770 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 2771
1979969f
S
2772 # Look for Arkena embeds
2773 arkena_url = ArkenaIE._extract_url(webpage)
2774 if arkena_url:
2775 return self.url_result(arkena_url, ArkenaIE.ie_key())
2776
b1c35797
RA
2777 # Look for Piksel embeds
2778 piksel_url = PikselIE._extract_url(webpage)
2779 if piksel_url:
2780 return self.url_result(piksel_url, PikselIE.ie_key())
2781
1bf996fa 2782 # Look for Limelight embeds
e5d39886
S
2783 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2784 if limelight_urls:
2785 return self.playlist_result(
2786 limelight_urls, video_id, video_title, video_description)
2787
7986c3ab
S
2788 # Look for Anvato embeds
2789 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2790 if anvato_urls:
2791 return self.playlist_result(
2792 anvato_urls, video_id, video_title, video_description)
2793
a5158f38
YCH
2794 # Look for AdobeTVVideo embeds
2795 mobj = re.search(
2796 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2797 webpage)
2798 if mobj is not None:
2799 return self.url_result(
2800 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2801 'AdobeTVVideo')
2802
088e1aac
YCH
2803 # Look for Vine embeds
2804 mobj = re.search(
2805 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2806 webpage)
2807 if mobj is not None:
2808 return self.url_result(
2809 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2810
217d5ae0
RA
2811 # Look for VODPlatform embeds
2812 mobj = re.search(
93b84045 2813 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
217d5ae0
RA
2814 webpage)
2815 if mobj is not None:
2816 return self.url_result(
93b84045 2817 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 2818
7d273a38
RA
2819 # Look for Mangomolo embeds
2820 mobj = re.search(
d05ef09d 2821 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
7d273a38
RA
2822 (?:
2823 video\?.*?\bid=(?P<video_id>\d+)|
2824 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2825 ).+?)\1''', webpage)
2826 if mobj is not None:
2827 info = {
2828 '_type': 'url_transparent',
2829 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2830 'title': video_title,
2831 'description': video_description,
2832 'thumbnail': video_thumbnail,
2833 'uploader': video_uploader,
2834 }
2835 video_id = mobj.group('video_id')
2836 if video_id:
2837 info.update({
2838 'ie_key': 'MangomoloVideo',
2839 'id': video_id,
2840 })
2841 else:
2842 info.update({
2843 'ie_key': 'MangomoloLive',
2844 'id': mobj.group('channel_id'),
2845 })
2846 return info
2847
5a51775a
YCH
2848 # Look for Instagram embeds
2849 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2850 if instagram_embed_url is not None:
11e60fca
S
2851 return self.url_result(
2852 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 2853
b8f67449 2854 # Look for LiveLeak embeds
09747ba7
YCH
2855 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2856 if liveleak_urls:
2857 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
b8f67449 2858
5d39176f
S
2859 # Look for 3Q SDN embeds
2860 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2861 if threeqsdn_url:
6f41b2bc
S
2862 return {
2863 '_type': 'url_transparent',
2864 'ie_key': ThreeQSDNIE.ie_key(),
2865 'url': self._proto_relative_url(threeqsdn_url),
2866 'title': video_title,
2867 'description': video_description,
2868 'thumbnail': video_thumbnail,
2869 'uploader': video_uploader,
2870 }
5d39176f 2871
2a1321a2
S
2872 # Look for VBOX7 embeds
2873 vbox7_url = Vbox7IE._extract_url(webpage)
2874 if vbox7_url:
2875 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2876
b0c8f2e9
DR
2877 # Look for DBTV embeds
2878 dbtv_urls = DBTVIE._extract_urls(webpage)
2879 if dbtv_urls:
46b18f23 2880 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 2881
e186a9ec
S
2882 # Look for Videa embeds
2883 videa_urls = VideaIE._extract_urls(webpage)
2884 if videa_urls:
46b18f23 2885 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 2886
b687c85e
S
2887 # Look for 20 minuten embeds
2888 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2889 if twentymin_urls:
46b18f23
JH
2890 return self.playlist_from_matches(
2891 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 2892
17f8deeb
S
2893 # Look for Openload embeds
2894 openload_urls = OpenloadIE._extract_urls(webpage)
2895 if openload_urls:
46b18f23
JH
2896 return self.playlist_from_matches(
2897 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
17f8deeb 2898
6ef3e65a
S
2899 # Look for VideoPress embeds
2900 videopress_urls = VideoPressIE._extract_urls(webpage)
2901 if videopress_urls:
46b18f23
JH
2902 return self.playlist_from_matches(
2903 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 2904
eb3079b6
S
2905 # Look for Rutube embeds
2906 rutube_urls = RutubeIE._extract_urls(webpage)
2907 if rutube_urls:
46b18f23 2908 return self.playlist_from_matches(
2583c0b5 2909 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 2910
55719459
JH
2911 # Look for WashingtonPost embeds
2912 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2913 if wapo_urls:
2914 return self.playlist_from_matches(
2915 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2916
5d29af3d
S
2917 # Look for Mediaset embeds
2918 mediaset_urls = MediasetIE._extract_urls(webpage)
2919 if mediaset_urls:
2920 return self.playlist_from_matches(
2921 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2922
73cf76a9
S
2923 # Look for JOJ.sk embeds
2924 joj_urls = JojIE._extract_urls(webpage)
2925 if joj_urls:
2926 return self.playlist_from_matches(
2927 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2928
24e966e8
PH
2929 # Look for megaphone.fm embeds
2930 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2931 if mpfn_urls:
2932 return self.playlist_from_matches(
2933 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2934
1663bd6e
S
2935 # Look for vzaar embeds
2936 vzaar_urls = VzaarIE._extract_urls(webpage)
2937 if vzaar_urls:
2938 return self.playlist_from_matches(
2939 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2940
26bae2d9
S
2941 channel9_urls = Channel9IE._extract_urls(webpage)
2942 if channel9_urls:
2943 return self.playlist_from_matches(
2944 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2945
0987f2dd
T
2946 vshare_urls = VShareIE._extract_urls(webpage)
2947 if vshare_urls:
2948 return self.playlist_from_matches(
2949 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2950
8056c854 2951 # Look for Mediasite embeds
2ca7ed41
S
2952 mediasite_urls = MediasiteIE._extract_urls(webpage)
2953 if mediasite_urls:
2954 entries = [
2955 self.url_result(smuggle_url(
2956 compat_urlparse.urljoin(url, mediasite_url),
2957 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
2958 for mediasite_url in mediasite_urls]
2959 return self.playlist_result(entries, video_id, video_title)
8056c854 2960
7d540621
S
2961 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
2962 if springboardplatform_urls:
2963 return self.playlist_from_matches(
2964 springboardplatform_urls, video_id, video_title,
2965 ie=SpringboardPlatformIE.ie_key())
2966
4c780fbd
S
2967 yapfiles_urls = YapFilesIE._extract_urls(webpage)
2968 if yapfiles_urls:
2969 return self.playlist_from_matches(
2970 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
2971
86c8cfc5
S
2972 vice_urls = ViceIE._extract_urls(webpage)
2973 if vice_urls:
2974 return self.playlist_from_matches(
2975 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
2976
178ee883
S
2977 xfileshare_urls = XFileShareIE._extract_urls(webpage)
2978 if xfileshare_urls:
2979 return self.playlist_from_matches(
2980 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
2981
d3431dcb
S
2982 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
2983 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
2984 webpage)]
2985 if sharevideos_urls:
2986 return self.playlist_from_matches(
2987 sharevideos_urls, video_id, video_title)
2988
b311b0ea
S
2989 def merge_dicts(dict1, dict2):
2990 merged = {}
2991 for k, v in dict1.items():
2992 if v is not None:
2993 merged[k] = v
2994 for k, v in dict2.items():
2995 if v is None:
2996 continue
2997 if (k not in merged or
2998 (isinstance(v, compat_str) and v and
2999 isinstance(merged[k], compat_str) and
3000 not merged[k])):
3001 merged[k] = v
3002 return merged
3003
bd264412
YCH
3004 # Look for HTML5 media
3005 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3006 if entries:
9ce1ac40 3007 if len(entries) == 1:
3008 entries[0].update({
bd264412
YCH
3009 'id': video_id,
3010 'title': video_title,
3011 })
9ce1ac40 3012 else:
3013 for num, entry in enumerate(entries, start=1):
3014 entry.update({
3015 'id': '%s-%s' % (video_id, num),
3016 'title': '%s (%d)' % (video_title, num),
3017 })
3018 for entry in entries:
bd264412 3019 self._sort_formats(entry['formats'])
9ce1ac40 3020 return self.playlist_result(entries, video_id, video_title)
bd264412 3021
c73e330e
RU
3022 jwplayer_data = self._find_jwplayer_data(
3023 webpage, video_id, transform_source=js_to_json)
3024 if jwplayer_data:
4f06c1c9 3025 info = self._parse_jwplayer_data(
3e943cfe 3026 jwplayer_data, video_id, require_title=False, base_url=url)
b311b0ea 3027 return merge_dicts(info, info_dict)
a4a554a7 3028
63d990d2
S
3029 # Video.js embed
3030 mobj = re.search(
c5b7014a 3031 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
3032 webpage)
3033 if mobj is not None:
3034 sources = self._parse_json(
3035 mobj.group(1), video_id, transform_source=js_to_json,
3036 fatal=False) or []
c5b7014a
S
3037 if not isinstance(sources, list):
3038 sources = [sources]
63d990d2
S
3039 formats = []
3040 for source in sources:
3041 src = source.get('src')
3042 if not src or not isinstance(src, compat_str):
3043 continue
3044 src = compat_urlparse.urljoin(url, src)
3045 src_type = source.get('type')
3046 if isinstance(src_type, compat_str):
3047 src_type = src_type.lower()
3048 ext = determine_ext(src).lower()
3049 if src_type == 'video/youtube':
3050 return self.url_result(src, YoutubeIE.ie_key())
3051 if src_type == 'application/dash+xml' or ext == 'mpd':
3052 formats.extend(self._extract_mpd_formats(
3053 src, video_id, mpd_id='dash', fatal=False))
3054 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3055 formats.extend(self._extract_m3u8_formats(
3056 src, video_id, 'mp4', entry_protocol='m3u8_native',
3057 m3u8_id='hls', fatal=False))
3058 else:
3059 formats.append({
3060 'url': src,
3061 'ext': (mimetype2ext(src_type) or
3062 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3063 })
3064 if formats:
3065 self._sort_formats(formats)
3066 info_dict['formats'] = formats
3067 return info_dict
3068
ff17be3a
S
3069 # Looking for http://schema.org/VideoObject
3070 json_ld = self._search_json_ld(
3071 webpage, video_id, default={}, expected_type='VideoObject')
3072 if json_ld.get('url'):
3073 return merge_dicts(json_ld, info_dict)
3074
ced659bb 3075 def check_video(vurl):
a0f71985
PH
3076 if YoutubeIE.suitable(vurl):
3077 return True
b7a8c1bc
S
3078 if RtmpIE.suitable(vurl):
3079 return True
ced659bb
S
3080 vpath = compat_urlparse.urlparse(vurl).path
3081 vext = determine_ext(vpath)
0ee79a37 3082 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
3083
3084 def filter_video(urls):
3085 return list(filter(check_video, urls))
3086
9b122384 3087 # Start with something easy: JW Player in SWFObject
ced659bb 3088 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 3089 if not found:
d981cef6 3090 # Look for gorilla-vid style embedding
ced659bb 3091 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
3092 (?:
3093 jw_plugins|
3094 JWPlayerOptions|
3095 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3096 )
a0f71985
PH
3097 .*?
3098 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 3099 if not found:
9b122384 3100 # Broaden the search a little bit
ced659bb 3101 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
3102 if not found:
3103 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 3104 found = filter_video(re.findall(
54a9328b 3105 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
3106 if not found:
3107 # Flow player
ced659bb 3108 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
3109 flowplayer\("[^"]+",\s*
3110 \{[^}]+?\}\s*,
52585fd6 3111 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 3112 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 3113 ''', webpage))
501f13fb
PH
3114 if not found:
3115 # Cinerama player
3116 found = re.findall(
3117 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 3118 if not found:
9b122384 3119 # Try to find twitter cards info
371ddb14
S
3120 # twitter:player:stream should be checked before twitter:player since
3121 # it is expected to contain a raw stream (see
3122 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3123 found = filter_video(re.findall(
3124 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 3125 if not found:
9b122384
PH
3126 # We look for Open Graph info:
3127 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3128 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3129 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3130 if m_video_type is not None:
ced659bb 3131 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 3132 if not found:
ed9a25dd 3133 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3134 found = re.search(
89ef304b 3135 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3136 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3137 webpage)
84f81016
S
3138 if not found:
3139 # Look also in Refresh HTTP header
3140 refresh_header = head_response.headers.get('Refresh')
3141 if refresh_header:
6c91a5a7
S
3142 # In python 2 response HTTP headers are bytestrings
3143 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3144 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3145 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3146 if found:
b37317d8 3147 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3148 if new_url != url:
3149 self.report_following_redirect(new_url)
3150 return {
3151 '_type': 'url',
3152 'url': new_url,
3153 }
3154 else:
3155 found = None
371ddb14
S
3156
3157 if not found:
3158 # twitter:player is a https URL to iframe player that may or may not
3159 # be supported by youtube-dl thus this is checked the very last (see
3160 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3161 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3162 if embed_url and embed_url != url:
371ddb14
S
3163 return self.url_result(embed_url)
3164
b30b8698 3165 if not found:
416c7fcb 3166 raise UnsupportedError(url)
9b122384 3167
b30b8698 3168 entries = []
4a120778 3169 for video_url in orderedSet(found):
949b6497 3170 video_url = unescapeHTML(video_url)
6cc37c69 3171 video_url = video_url.replace('\\/', '/')
b30b8698 3172 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3173 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3174
b30b8698
PH
3175 # Sometimes, jwplayer extraction will result in a YouTube URL
3176 if YoutubeIE.suitable(video_url):
3177 entries.append(self.url_result(video_url, 'Youtube'))
3178 continue
9b122384 3179
b30b8698
PH
3180 # here's a fun little line of code for you:
3181 video_id = os.path.splitext(video_id)[0]
fc9713a1 3182
28602e74
YCH
3183 entry_info_dict = {
3184 'id': video_id,
3185 'uploader': video_uploader,
3186 'title': video_title,
3187 'age_limit': age_limit,
3188 }
3189
5620f840
S
3190 if RtmpIE.suitable(video_url):
3191 entry_info_dict.update({
3192 '_type': 'url_transparent',
3193 'ie_key': RtmpIE.ie_key(),
3194 'url': video_url,
3195 })
3196 entries.append(entry_info_dict)
3197 continue
3198
729accb4
S
3199 ext = determine_ext(video_url)
3200 if ext == 'smil':
28602e74 3201 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
3202 elif ext == 'xspf':
3203 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
3204 elif ext == 'm3u8':
3205 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
3206 elif ext == 'mpd':
3207 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
3208 elif ext == 'f4m':
3209 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3210 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3211 # Just matching .ism/manifest is not enough to be reliably sure
3212 # whether it's actually an ISM manifest or some other streaming
3213 # manifest since there are various streaming URL formats
3214 # possible (see [1]) as well as some other shenanigans like
3215 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3216 # so on.
3217 # Thus the most reasonable way to solve this is to delegate
3218 # to generic extractor in order to look into the contents of
3219 # the manifest itself.
3220 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3221 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3222 entry_info_dict = self.url_result(
3223 smuggle_url(video_url, {'to_generic': True}),
3224 GenericIE.ie_key())
d6fd958c 3225 else:
28602e74
YCH
3226 entry_info_dict['url'] = video_url
3227
19dbaeec
S
3228 if entry_info_dict.get('formats'):
3229 self._sort_formats(entry_info_dict['formats'])
3230
28602e74 3231 entries.append(entry_info_dict)
b30b8698
PH
3232
3233 if len(entries) == 1:
669f0e7c 3234 return entries[0]
b30b8698
PH
3235 else:
3236 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3237 # 'url' results don't have a title
3238 if e.get('title') is not None:
3239 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3240 return {
3241 '_type': 'playlist',
3242 'entries': entries,
3243 }