]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
[ard] Skip invalid stream URLs (closes #14906)
[yt-dlp.git] / youtube_dl / extractor / generic.py
CommitLineData
dcdb292f 1# coding: utf-8
cfe50f04 2
79649588
PH
3from __future__ import unicode_literals
4
9b122384
PH
5import os
6import re
6c91a5a7 7import sys
9b122384
PH
8
9from .common import InfoExtractor
fc9713a1 10from .youtube import YoutubeIE
8c25f81b 11from ..compat import (
f7854627 12 compat_etree_fromstring,
4e363703 13 compat_str,
1ddb9456 14 compat_urllib_parse_unquote,
a5caba1e 15 compat_urlparse,
f7300c5c 16 compat_xml_parse_error,
8c25f81b
PH
17)
18from ..utils import (
b759a0d4 19 determine_ext,
9b122384 20 ExtractorError,
c8e9a235 21 float_or_none,
aa94a6d3 22 HEADRequest,
61ca9a80 23 is_html,
a4a554a7 24 js_to_json,
63d990d2
S
25 KNOWN_EXTENSIONS,
26 mimetype2ext,
ed2d6a19 27 orderedSet,
5c2266df 28 sanitized_Request,
9d4660ca
PH
29 smuggle_url,
30 unescapeHTML,
42393ce2 31 unified_strdate,
4d54ef20 32 unsmuggle_url,
416c7fcb 33 UnsupportedError,
76c73715 34 xpath_text,
9b122384 35)
b7a8c1bc 36from .commonprotocols import RtmpIE
ed126900 37from .brightcove import (
4fcaa4f4 38 BrightcoveLegacyIE,
5c17f0a6 39 BrightcoveNewIE,
ed126900 40)
3f59b015
S
41from .nexx import (
42 NexxIE,
43 NexxEmbedIE,
44)
a2edf2e7 45from .nbc import NBCSportsVPlayerIE
c0d0b01f 46from .ooyala import OoyalaIE
93d020dd 47from .rutv import RUTVIE
954c1d05 48from .tvc import TVCIE
d40a3b5b 49from .sportbox import SportBoxEmbedIE
cb3ac1c6 50from .smotri import SmotriIE
6dd94d3a 51from .myvi import MyviIE
1419fafd 52from .condenast import CondeNastIE
418c5cc3 53from .udn import UDNEmbedIE
2fe1b5bd 54from .senateisvp import SenateISVPIE
bab19a8e 55from .svt import SVTIE
65d161c4 56from .pornhub import PornHubIE
2bb5b6d0 57from .xhamster import XHamsterEmbedIE
2c9ca782 58from .tnaflix import TNAFlixNetworkEmbedIE
37e7a71c 59from .drtuber import DrTuberIE
e28ed498 60from .redtube import RedTubeIE
b407e173 61from .vimeo import VimeoIE
ad213a1d
YCH
62from .dailymotion import (
63 DailymotionIE,
64 DailymotionCloudIE,
65)
71a1db89 66from .dailymail import DailyMailIE
1ac1c4c2 67from .onionstudios import OnionStudiosIE
67167920 68from .viewlift import ViewLiftEmbedIE
46fde8a1 69from .mtv import MTVServicesEmbeddedIE
45dad7ba 70from .pladform import PladformIE
ff18735c 71from .videomore import VideomoreIE
83f1481b 72from .webcaster import WebcasterFeedIE
5b251628 73from .googledrive import GoogleDriveIE
7cb09524 74from .jwplatform import JWPlatformIE
aecfcd4e 75from .digiteka import DigitekaIE
1979969f 76from .arkena import ArkenaIE
5a51775a 77from .instagram import InstagramIE
b8f67449 78from .liveleak import LiveLeakIE
5d39176f 79from .threeqsdn import ThreeQSDNIE
4d8819d2 80from .theplatform import ThePlatformIE
48a5eabc 81from .vessel import VesselIE
c287f2bc 82from .kaltura import KalturaIE
06a96da1 83from .eagleplatform import EaglePlatformIE
fd6ca382 84from .facebook import FacebookIE
94aae015 85from .soundcloud import SoundcloudIE
027e2312 86from .tunein import TuneInBaseIE
2a1321a2 87from .vbox7 import Vbox7IE
b0c8f2e9 88from .dbtv import DBTVIE
b1c35797 89from .piksel import PikselIE
e186a9ec 90from .videa import VideaIE
b687c85e 91from .twentymin import TwentyMinutenIE
d77ac737 92from .ustream import UstreamIE
17f8deeb 93from .openload import OpenloadIE
6ef3e65a 94from .videopress import VideoPressIE
eb3079b6 95from .rutube import RutubeIE
e5d39886 96from .limelight import LimelightBaseIE
7986c3ab 97from .anvato import AnvatoIE
55719459 98from .washingtonpost import WashingtonPostIE
58bb4402 99from .wistia import WistiaIE
5d29af3d 100from .mediaset import MediasetIE
73cf76a9 101from .joj import JojIE
24e966e8 102from .megaphone import MegaphoneIE
41918eaa 103from .vzaar import VzaarIE
26bae2d9 104from .channel9 import Channel9IE
0987f2dd 105from .vshare import VShareIE
9b122384 106
0838239e 107
9b122384 108class GenericIE(InfoExtractor):
79649588 109 IE_DESC = 'Generic downloader that works on some sites'
9b122384 110 _VALID_URL = r'.*'
79649588 111 IE_NAME = 'generic'
cfe50f04 112 _TESTS = [
c5fa81fe
S
113 # Direct link to a video
114 {
115 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
116 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
117 'info_dict': {
118 'id': 'trailer',
119 'ext': 'mp4',
120 'title': 'trailer',
121 'upload_date': '20100513',
122 }
123 },
c5138a7c 124 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
125 {
126 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
127 'md5': '128c42e68b13950268b648275386fc74',
128 'info_dict': {
129 'id': 'FictionJunction-Parallel_Hearts',
130 'ext': 'flac',
131 'title': 'FictionJunction-Parallel_Hearts',
132 'upload_date': '20140522',
133 },
134 'expected_warnings': [
135 'URL could be a direct video link, returning it as such.'
39efc6e3
YCH
136 ],
137 'skip': 'URL invalid',
c5fa81fe
S
138 },
139 # Direct download with broken HEAD
140 {
141 'url': 'http://ai-radio.org:8000/radio.opus',
142 'info_dict': {
143 'id': 'radio',
144 'ext': 'opus',
145 'title': 'radio',
146 },
147 'params': {
148 'skip_download': True, # infinite live stream
149 },
150 'expected_warnings': [
ef0e4e7b
YCH
151 r'501.*Not Implemented',
152 r'400.*Bad Request',
c5fa81fe
S
153 ],
154 },
155 # Direct link with incorrect MIME type
156 {
157 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
158 'md5': '4ccbebe5f36706d85221f204d7eb5913',
159 'info_dict': {
160 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
161 'id': '5_Lennart_Poettering_-_Systemd',
162 'ext': 'webm',
163 'title': '5_Lennart_Poettering_-_Systemd',
164 'upload_date': '20141120',
165 },
166 'expected_warnings': [
167 'URL could be a direct video link, returning it as such.'
168 ]
169 },
170 # RSS feed
171 {
172 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
173 'info_dict': {
174 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
175 'title': 'Zero Punctuation',
176 'description': 're:.*groundbreaking video review series.*'
177 },
178 'playlist_mincount': 11,
179 },
180 # RSS feed with enclosure
181 {
182 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
183 'info_dict': {
184 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
185 'ext': 'm4v',
186 'upload_date': '20150228',
187 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
188 }
189 },
8765222d
S
190 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
191 {
192 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
193 'info_dict': {
194 'id': 'smil',
195 'ext': 'mp4',
196 'title': 'Automatics, robotics and biocybernetics',
197 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 198 'upload_date': '20130627',
8765222d
S
199 'formats': 'mincount:16',
200 'subtitles': 'mincount:1',
201 },
202 'params': {
203 'force_generic_extractor': True,
204 'skip_download': True,
205 },
206 },
207 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
208 {
209 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
210 'info_dict': {
211 'id': 'hds',
212 'ext': 'flv',
213 'title': 'hds',
214 'formats': 'mincount:1',
215 },
216 'params': {
217 'skip_download': True,
218 },
219 },
220 # SMIL from https://www.restudy.dk/video/play/id/1637
221 {
222 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
223 'info_dict': {
224 'id': 'video_1637',
225 'ext': 'flv',
226 'title': 'video_1637',
227 'formats': 'mincount:3',
228 },
229 'params': {
230 'skip_download': True,
231 },
232 },
233 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
234 {
235 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
236 'info_dict': {
237 'id': 'smil-service',
238 'ext': 'flv',
239 'title': 'smil-service',
240 'formats': 'mincount:1',
241 },
242 'params': {
243 'skip_download': True,
244 },
245 },
246 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
247 {
248 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
249 'info_dict': {
250 'id': '4719370',
251 'ext': 'mp4',
252 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
253 'formats': 'mincount:3',
254 },
255 'params': {
256 'skip_download': True,
257 },
258 },
1de5cd3b
S
259 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
260 {
261 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
262 'info_dict': {
263 'id': 'mZlp2ctYIUEB',
264 'ext': 'mp4',
265 'title': 'Tikibad ontruimd wegens brand',
266 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
ec85ded8 267 'thumbnail': r're:^https?://.*\.jpg$',
1de5cd3b
S
268 'duration': 33,
269 },
270 'params': {
271 'skip_download': True,
272 },
273 },
9d939cec
S
274 # MPD from http://dash-mse-test.appspot.com/media.html
275 {
276 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
277 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
278 'info_dict': {
279 'id': 'car-20120827-manifest',
280 'ext': 'mp4',
281 'title': 'car-20120827-manifest',
282 'formats': 'mincount:9',
0738187f 283 'upload_date': '20130904',
9d939cec
S
284 },
285 'params': {
286 'format': 'bestvideo',
287 },
288 },
20938f76
S
289 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
290 {
291 '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',
292 'info_dict': {
293 'id': 'content',
294 'ext': 'mp4',
295 'title': 'content',
296 'formats': 'mincount:8',
297 },
298 'params': {
299 # m3u8 downloads
300 'skip_download': True,
39efc6e3
YCH
301 },
302 'skip': 'video gone',
20938f76 303 },
edd9b71c
S
304 # m3u8 served with Content-Type: text/plain
305 {
306 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
307 'info_dict': {
308 'id': 'index',
309 'ext': 'mp4',
310 'title': 'index',
311 'upload_date': '20140720',
312 'formats': 'mincount:11',
313 },
314 'params': {
315 # m3u8 downloads
316 'skip_download': True,
39efc6e3
YCH
317 },
318 'skip': 'video gone',
edd9b71c 319 },
c5fa81fe
S
320 # google redirect
321 {
322 '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',
323 'info_dict': {
324 'id': 'cmQHVoWB5FY',
325 'ext': 'mp4',
326 'upload_date': '20130224',
327 'uploader_id': 'TheVerge',
ec85ded8 328 'description': r're:^Chris Ziegler takes a look at the\.*',
c5fa81fe
S
329 'uploader': 'The Verge',
330 'title': 'First Firefox OS phones side-by-side',
331 },
332 'params': {
333 'skip_download': False,
334 }
335 },
6c91a5a7
S
336 {
337 # redirect in Refresh HTTP header
338 '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',
339 'info_dict': {
340 'id': 'pO8h3EaFRdo',
341 'ext': 'mp4',
342 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
343 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
344 'upload_date': '20150917',
345 'uploader_id': 'brtvofficial',
346 'uploader': 'Boiler Room',
347 },
348 'params': {
349 'skip_download': False,
350 },
351 },
cfe50f04 352 {
79649588 353 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 354 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 355 'info_dict': {
d360a146
S
356 'id': '13601338388002',
357 'ext': 'mp4',
79649588
PH
358 'uploader': 'www.hodiho.fr',
359 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
360 }
361 },
c19f7764
JMF
362 # bandcamp page with custom domain
363 {
79649588
PH
364 'add_ie': ['Bandcamp'],
365 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 366 'info_dict': {
fd50bf62
S
367 'id': '3235767654',
368 'ext': 'mp3',
79649588
PH
369 'title': 'The Pony Mash',
370 'uploader': 'M_Pallante',
c19f7764 371 },
79649588 372 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 373 },
eeb165e6 374 {
53a664ed
S
375 # embedded brightcove video
376 # it also tests brightcove videos that need to set the 'Referer'
377 # in the http requests
3b7d9aa4 378 'add_ie': ['BrightcoveLegacy'],
79649588
PH
379 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
380 'info_dict': {
381 'id': '2765128793001',
382 'ext': 'mp4',
383 'title': 'Le cours de bourse : l’analyse technique',
384 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
385 'uploader': 'BFM BUSINESS',
eeb165e6 386 },
79649588
PH
387 'params': {
388 'skip_download': True,
eeb165e6
JMF
389 },
390 },
53a664ed
S
391 {
392 # embedded with itemprop embedURL and video id spelled as `idVideo`
393 'add_id': ['BrightcoveLegacy'],
394 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
395 'info_dict': {
396 'id': '5255628253001',
397 'ext': 'mp4',
398 'title': 'md5:37c519b1128915607601e75a87995fc0',
399 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
400 'uploader': 'BFM BUSINESS',
401 'uploader_id': '876450612001',
402 'timestamp': 1482255315,
403 'upload_date': '20161220',
404 },
405 'params': {
406 'skip_download': True,
407 },
408 },
17ab4d3b
PH
409 {
410 # https://github.com/rg3/youtube-dl/issues/2253
411 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
412 'md5': '0ba9446db037002366bab3b3eb30c88c',
413 'info_dict': {
fd50bf62
S
414 'id': '3101154703001',
415 'ext': 'mp4',
17ab4d3b
PH
416 'title': 'Still no power',
417 'uploader': 'thestar.com',
418 '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.',
419 },
3b7d9aa4 420 'add_ie': ['BrightcoveLegacy'],
39efc6e3 421 'skip': 'video gone',
17ab4d3b 422 },
0479c625
S
423 {
424 'url': 'http://www.championat.com/video/football/v/87/87499.html',
425 'md5': 'fb973ecf6e4a78a67453647444222983',
426 'info_dict': {
427 'id': '3414141473001',
428 'ext': 'mp4',
429 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
430 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
431 'uploader': 'Championat',
432 },
433 },
bdf97017 434 {
37aab278 435 # https://github.com/rg3/youtube-dl/issues/3541
3b7d9aa4 436 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
437 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
438 'info_dict': {
439 'id': '3866516442001',
37aab278 440 'ext': 'mp4',
bdf97017
NJ
441 'title': 'Leer mij vrouwen kennen: Aflevering 1',
442 'description': 'Leer mij vrouwen kennen: Aflevering 1',
443 'uploader': 'SBS Broadcasting',
444 },
37aab278 445 'skip': 'Restricted to Netherlands',
bdf97017 446 'params': {
37aab278 447 'skip_download': True, # m3u8 download
bdf97017
NJ
448 },
449 },
06d0ad9a
YCH
450 {
451 # Brightcove video in <iframe>
452 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
453 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
454 'info_dict': {
455 'id': '5360463607001',
456 'ext': 'mp4',
457 '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',
458 '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。',
459 'uploader': 'United Nations',
460 'uploader_id': '1362235914001',
461 'timestamp': 1489593889,
462 'upload_date': '20170315',
463 },
464 'add_ie': ['BrightcoveLegacy'],
465 },
16e2c8f7
YCH
466 {
467 # Brightcove with alternative playerID key
468 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
469 'info_dict': {
470 'id': 'nmeth.2062_SV1',
471 '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',
472 },
473 'playlist': [{
474 'info_dict': {
475 'id': '2228375078001',
476 'ext': 'mp4',
477 'title': 'nmeth.2062-sv1',
478 'description': 'nmeth.2062-sv1',
479 'timestamp': 1363357591,
480 'upload_date': '20130315',
481 'uploader': 'Nature Publishing Group',
482 'uploader_id': '1964492299001',
483 },
484 }],
485 },
40158f55
JH
486 {
487 # Brightcove with UUID in videoPlayer
488 'url': 'http://www8.hp.com/cn/zh/home.html',
489 'info_dict': {
490 'id': '5255815316001',
491 'ext': 'mp4',
492 'title': 'Sprocket Video - China',
493 'description': 'Sprocket Video - China',
494 'uploader': 'HP-Video Gallery',
495 'timestamp': 1482263210,
496 'upload_date': '20161220',
497 'uploader_id': '1107601872001',
498 },
499 'params': {
500 'skip_download': True, # m3u8 download
501 },
502 'skip': 'video rotates...weekly?',
503 },
504 {
505 # Brightcove:new type [2].
506 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
507 'md5': '2b35148fcf48da41c9fb4591650784f3',
508 'info_dict': {
509 'id': '5348741021001',
510 'ext': 'mp4',
511 'upload_date': '20170306',
512 'uploader_id': '4191638492001',
513 'timestamp': 1488769918,
514 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
515
516 },
517 },
518 {
519 # Alternative brightcove <video> attributes
520 '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/',
521 'info_dict': {
522 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
523 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
524 },
525 'playlist': [{
526 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
527 'info_dict': {
528 'id': '5311302538001',
529 'ext': 'mp4',
530 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
531 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
532 'timestamp': 1486321708,
533 'upload_date': '20170205',
534 'uploader_id': '800000640001',
535 },
536 'only_matching': True,
537 }],
538 },
b68a812e
S
539 {
540 # Brightcove with UUID in videoPlayer
541 'url': 'http://www8.hp.com/cn/zh/home.html',
542 'info_dict': {
543 'id': '5255815316001',
544 'ext': 'mp4',
545 'title': 'Sprocket Video - China',
546 'description': 'Sprocket Video - China',
547 'uploader': 'HP-Video Gallery',
548 'timestamp': 1482263210,
549 'upload_date': '20161220',
550 'uploader_id': '1107601872001',
551 },
552 'params': {
553 'skip_download': True, # m3u8 download
554 },
555 },
c0d0b01f
JMF
556 # ooyala video
557 {
79649588 558 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 559 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
560 'info_dict': {
561 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
562 'ext': 'mp4',
3486df38 563 'title': '2cc213299525360.mov', # that's what we get
53e06b25 564 'duration': 238.231,
c0d0b01f 565 },
87830900 566 'add_ie': ['Ooyala'],
c0d0b01f 567 },
bf94d763
S
568 {
569 # ooyala video embedded with http://player.ooyala.com/iframe.js
570 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
571 'info_dict': {
572 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
573 'ext': 'mp4',
574 'title': '"Steve Jobs: Man in the Machine" trailer',
575 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 576 'duration': 135.427,
bf94d763
S
577 },
578 'params': {
579 'skip_download': True,
580 },
39efc6e3 581 'skip': 'movie expired',
bf94d763 582 },
198d4cb4
GR
583 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
584 {
585 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
586 'info_dict': {
587 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
588 'ext': 'mp4',
589 'title': 'Steampunk Fest Comes to Honesdale',
590 'duration': 43.276,
591 },
592 'params': {
593 'skip_download': True,
594 }
595 },
1b86cc41 596 # embed.ly video
597 {
598 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
599 'info_dict': {
600 'id': '9ODmcdjQcHQ',
601 'ext': 'mp4',
0a5bce56
PH
602 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
603 'upload_date': '20140225',
604 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
605 'uploader': 'Tested',
606 'uploader_id': 'testedcom',
1b86cc41 607 },
608 # No need to test YoutubeIE here
609 'params': {
610 'skip_download': True,
611 },
612 },
60cc4dc4
PH
613 # funnyordie embed
614 {
615 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
616 'info_dict': {
617 'id': '18e820ec3f',
618 'ext': 'mp4',
619 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
620 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 621 },
39efc6e3
YCH
622 # HEAD requests lead to endless 301, while GET is OK
623 'expected_warnings': ['301'],
60cc4dc4 624 },
93d020dd
S
625 # RUTV embed
626 {
627 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
628 'info_dict': {
629 'id': '776940',
630 'ext': 'mp4',
631 'title': 'Охотское море стало целиком российским',
632 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
633 },
634 'params': {
635 # m3u8 download
636 'skip_download': True,
637 },
aab74fa1 638 },
f37bdbe5
S
639 # TVC embed
640 {
641 '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/',
642 'info_dict': {
643 'id': '55304',
644 'ext': 'mp4',
645 'title': 'Дошкольное воспитание',
646 },
647 },
b827a601
S
648 # SportBox embed
649 {
650 'url': 'http://www.vestifinance.ru/articles/25753',
651 'info_dict': {
652 'id': '25753',
05d1e7aa 653 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
b827a601
S
654 },
655 'playlist': [{
656 'info_dict': {
657 'id': '370908',
658 'title': 'Госзаказ. День 3',
659 'ext': 'mp4',
660 }
661 }, {
662 'info_dict': {
663 'id': '370905',
664 'title': 'Госзаказ. День 2',
665 'ext': 'mp4',
666 }
667 }, {
668 'info_dict': {
669 'id': '370902',
670 'title': 'Госзаказ. День 1',
671 'ext': 'mp4',
672 }
673 }],
674 'params': {
675 # m3u8 download
676 'skip_download': True,
677 },
678 },
bf20b9c5
S
679 # Myvi.ru embed
680 {
681 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
682 'info_dict': {
683 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
684 'ext': 'mp4',
685 'title': 'Ужастики, русский трейлер (2015)',
ec85ded8 686 'thumbnail': r're:^https?://.*\.jpg$',
bf20b9c5
S
687 'duration': 153,
688 }
689 },
c76799c5
S
690 # XHamster embed
691 {
692 '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',
693 'info_dict': {
694 'id': 'showthread',
695 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
696 },
697 'playlist_mincount': 7,
39efc6e3
YCH
698 # This forum does not allow <iframe> syntaxes anymore
699 # Now HTML tags are displayed as-is
700 'skip': 'No videos on this page',
c76799c5 701 },
aab74fa1
PH
702 # Embedded TED video
703 {
704 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 705 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 706 'info_dict': {
a8eb5a8e 707 'id': '1969',
aab74fa1 708 'ext': 'mp4',
a8eb5a8e
PH
709 'title': 'Hidden miracles of the natural world',
710 'uploader': 'Louie Schwartzberg',
711 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 712 }
60cc4dc4 713 },
d95e35d6
S
714 # nowvideo embed hidden behind percent encoding
715 {
716 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
717 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
718 'info_dict': {
719 'id': '06e53103ca9aa',
720 'ext': 'flv',
721 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
722 'description': 'No description',
723 },
0f2a2ba1 724 },
893f8832
PH
725 # arte embed
726 {
727 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
728 'md5': '7653032cbb25bf6c80d80f217055fa43',
729 'info_dict': {
730 'id': '048195-004_PLUS7-F',
731 'ext': 'flv',
732 'title': 'X:enius',
733 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
734 'upload_date': '20140320',
735 },
736 'params': {
737 'skip_download': 'Requires rtmpdump'
39efc6e3
YCH
738 },
739 'skip': 'video gone',
893f8832 740 },
cbd55ade
S
741 # francetv embed
742 {
743 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
744 'info_dict': {
745 'id': 'EV_30231',
746 'ext': 'mp4',
747 'title': 'Alcaline, le concert avec Calogero',
748 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
749 'upload_date': '20150226',
750 'timestamp': 1424989860,
751 'duration': 5400,
752 },
753 'params': {
754 # m3u8 downloads
755 'skip_download': True,
756 },
757 'expected_warnings': [
758 'Forbidden'
759 ]
760 },
fa35cdad
PH
761 # Condé Nast embed
762 {
763 'url': 'http://www.wired.com/2014/04/honda-asimo/',
764 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
765 'info_dict': {
766 'id': '53501be369702d3275860000',
767 'ext': 'mp4',
768 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
769 }
ebd3c7b3
PH
770 },
771 # Dailymotion embed
772 {
773 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
774 'md5': '441aeeb82eb72c422c7f14ec533999cd',
775 'info_dict': {
776 'id': 'k2mm4bCdJ6CQ2i7c8o2',
777 'ext': 'mp4',
778 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 779 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 780 'uploader': 'Spi0n',
0738187f
YCH
781 'uploader_id': 'xgditw',
782 'upload_date': '20140425',
783 'timestamp': 1398441542,
ebd3c7b3
PH
784 },
785 'add_ie': ['Dailymotion'],
2b88feed 786 },
71a1db89
S
787 # DailyMail embed
788 {
789 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
790 'info_dict': {
791 'id': '1495629',
792 'ext': 'mp4',
793 'title': 'Care worker punches elderly dementia patient in head 11 times',
794 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
795 },
796 'add_ie': ['DailyMail'],
797 'params': {
798 'skip_download': True,
799 },
800 },
2b88feed
PH
801 # YouTube embed
802 {
803 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
804 'info_dict': {
805 'id': 'FXRb4ykk4S0',
806 'ext': 'mp4',
807 'title': 'The NBL Auction 2014',
808 'uploader': 'BADMINTON England',
809 'uploader_id': 'BADMINTONEvents',
810 'upload_date': '20140603',
811 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
812 },
813 'add_ie': ['Youtube'],
814 'params': {
815 'skip_download': True,
816 }
817 },
c5cd249e
JMF
818 # MTVSercices embed
819 {
1fa309da
YCH
820 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
821 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 822 'info_dict': {
1fa309da 823 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 824 'ext': 'mp4',
1fa309da
YCH
825 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
826 'description': 'Two valets share their love for movie star Liam Neesons.',
05d1e7aa
YCH
827 'timestamp': 1349922600,
828 'upload_date': '20121011',
c5cd249e
JMF
829 },
830 },
61013473 831 # YouTube embed via <data-embed-url="">
832 {
833 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 834 'info_dict': {
a8eb5a8e 835 'id': '4vAffPZIT44',
61013473 836 'ext': 'mp4',
a8eb5a8e 837 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
838 'uploader': 'Gameloft',
839 'uploader_id': 'gameloft',
a8eb5a8e
PH
840 'upload_date': '20140828',
841 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
842 },
843 'params': {
844 'skip_download': True,
61013473 845 }
c8e9a235 846 },
61568e50
JH
847 # YouTube <object> embed
848 {
849 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
850 'md5': '516718101ec834f74318df76259fb3cc',
851 'info_dict': {
852 'id': 'msN87y-iEx0',
853 'ext': 'webm',
854 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
855 'upload_date': '20080526',
856 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
857 'uploader': 'Christopher Sykes',
858 'uploader_id': 'ChristopherJSykes',
859 },
860 'add_ie': ['Youtube'],
861 },
c8e9a235
PH
862 # Camtasia studio
863 {
864 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
865 'playlist': [{
866 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
867 'info_dict': {
868 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
869 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
870 'ext': 'flv',
871 'duration': 2235.90,
872 }
873 }, {
874 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
875 'info_dict': {
876 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
877 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
878 'ext': 'flv',
879 'duration': 2235.93,
880 }
881 }],
882 'info_dict': {
883 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
884 }
4d805e06
PH
885 },
886 # Flowplayer
887 {
888 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
889 'md5': '9d65602bf31c6e20014319c7d07fba27',
890 'info_dict': {
891 'id': '5123ea6d5e5a7',
892 'ext': 'mp4',
893 'age_limit': 18,
894 'uploader': 'www.handjobhub.com',
d6d9186f 895 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 896 }
0990305d 897 },
22a6f150
PH
898 # Multiple brightcove videos
899 # https://github.com/rg3/youtube-dl/issues/2283
900 {
901 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
902 'info_dict': {
903 'id': 'always-never',
904 'title': 'Always / Never - The New Yorker',
905 },
906 'playlist_count': 3,
907 'params': {
908 'extract_flat': False,
909 'skip_download': True,
910 }
1a94ff68
S
911 },
912 # MLB embed
913 {
914 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
915 'md5': '96f09a37e44da40dd083e12d9a683327',
916 'info_dict': {
917 'id': '33322633',
918 'ext': 'mp4',
919 'title': 'Ump changes call to ball',
920 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
921 'duration': 48,
922 'timestamp': 1401537900,
923 'upload_date': '20140531',
ec85ded8 924 'thumbnail': r're:^https?://.*\.jpg$',
1a94ff68
S
925 },
926 },
746c67d7
NJ
927 # Wistia embed
928 {
6c114b12
S
929 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
930 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 931 'info_dict': {
6c114b12 932 'id': '6e2wtrbdaf',
746c67d7 933 'ext': 'mov',
6c114b12
S
934 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
935 'description': 'a Paywall Videos video from Remilon',
936 'duration': 644.072,
937 'uploader': 'study.com',
938 'timestamp': 1459678540,
939 'upload_date': '20160403',
940 'filesize': 24687186,
746c67d7
NJ
941 },
942 },
52cffcb1 943 {
944 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
945 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
946 'info_dict': {
947 'id': 'uxjb0lwrcz',
948 'ext': 'mp4',
6c114b12 949 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 950 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 951 'duration': 1715.0,
85d7b765 952 'uploader': 'thoughtworks.wistia.com',
0738187f 953 'timestamp': 1401832161,
6c114b12 954 'upload_date': '20140603',
70b7e3fb 955 },
52cffcb1 956 },
7ded6545
S
957 # Wistia standard embed (async)
958 {
959 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
960 'info_dict': {
961 'id': '807fafadvk',
962 'ext': 'mp4',
963 'title': 'Drip Brennan Dunn Workshop',
964 'description': 'a JV Webinars video from getdrip-1',
965 'duration': 4986.95,
7ded6545 966 'timestamp': 1463607249,
6c114b12 967 'upload_date': '20160518',
7ded6545
S
968 },
969 'params': {
970 'skip_download': True,
971 }
972 },
ac645ac7
PH
973 # Soundcloud embed
974 {
975 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
976 'info_dict': {
977 'id': '174391317',
978 'ext': 'mp3',
979 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
980 'uploader': 'Sophos Security',
981 'title': 'Chet Chat 171 - Oct 29, 2014',
982 'upload_date': '20141029',
983 }
af63fed7 984 },
db19df6c
S
985 # Soundcloud multiple embeds
986 {
987 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
988 'info_dict': {
989 'id': '52809',
990 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
991 },
992 'playlist_mincount': 7,
993 },
027e2312
S
994 # TuneIn station embed
995 {
996 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
997 'info_dict': {
998 'id': '204146',
999 'ext': 'mp3',
1000 'title': 'CNRV',
1001 'location': 'Paris, France',
1002 'is_live': True,
1003 },
1004 'params': {
1005 # Live stream
1006 'skip_download': True,
1007 },
1008 },
af63fed7
PH
1009 # Livestream embed
1010 {
1011 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1012 'info_dict': {
1013 'id': '67864563',
1014 'ext': 'flv',
1015 'upload_date': '20141112',
1016 'title': 'Rosetta #CometLanding webcast HL 10',
1017 }
1018 },
78d3b3e2
YCH
1019 # Another Livestream embed, without 'new.' in URL
1020 {
1021 'url': 'https://www.freespeech.org/',
1022 'info_dict': {
1023 'id': '123537347',
1024 'ext': 'mp4',
1025 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1026 },
1027 'params': {
1028 # Live stream
1029 'skip_download': True,
1030 },
1031 },
65f3a228
PH
1032 # LazyYT
1033 {
e8e4cc5a 1034 'url': 'https://skiplagged.com/',
65f3a228 1035 'info_dict': {
e8e4cc5a
JH
1036 'id': 'skiplagged',
1037 'title': 'Skiplagged: The smart way to find cheap flights',
65f3a228 1038 },
e8e4cc5a
JH
1039 'playlist_mincount': 1,
1040 'add_ie': ['Youtube'],
4e262a88 1041 },
42bdd9d0
PH
1042 # Cinchcast embed
1043 {
1044 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1045 'info_dict': {
1046 'id': '7141703',
1047 'ext': 'mp3',
1048 'upload_date': '20141126',
1049 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1050 }
1051 },
501f13fb
PH
1052 # Cinerama player
1053 {
1054 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1055 'info_dict': {
1056 'id': '730m_DandD_1901_512k',
1057 'ext': 'mp4',
1058 'uploader': 'www.abc.net.au',
1059 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1060 }
796df3c6
S
1061 },
1062 # embedded viddler video
1063 {
1064 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1065 'info_dict': {
1066 'id': '4d03aad9',
1067 'ext': 'mp4',
1068 'uploader': 'deadspin',
1069 'title': 'WALL-TO-GORTAT',
1070 'timestamp': 1422285291,
1071 'upload_date': '20150126',
1072 },
1073 'add_ie': ['Viddler'],
a0f71985 1074 },
2051acde
S
1075 # Libsyn embed
1076 {
1077 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1078 'info_dict': {
1079 'id': '3377616',
1080 'ext': 'mp3',
1081 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1082 'description': 'md5:601cb790edd05908957dae8aaa866465',
1083 'upload_date': '20150220',
1084 },
326fa4e6 1085 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
2051acde 1086 },
a0f71985
PH
1087 # jwplayer YouTube
1088 {
1089 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1090 'info_dict': {
1091 'id': 'Mrj4DVp2zeA',
1092 'ext': 'mp4',
f37e3f99 1093 'upload_date': '20150212',
a0f71985 1094 'uploader': 'The National Archives UK',
2637fadc 1095 'description': 'md5:8078af856dca76edc42910b61273dbbf',
a0f71985
PH
1096 'uploader_id': 'NationalArchives08',
1097 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1098 },
59b8ab58 1099 },
5620f840
S
1100 # jwplayer rtmp
1101 {
6899b1d9 1102 'url': 'http://www.suffolk.edu/sjc/live.php',
5620f840 1103 'info_dict': {
6899b1d9 1104 'id': 'live',
5620f840
S
1105 'ext': 'flv',
1106 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1107 'uploader': 'www.suffolk.edu',
1108 },
1109 'params': {
1110 'skip_download': True,
2637fadc 1111 },
6899b1d9 1112 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
5620f840 1113 },
a4a554a7
YCH
1114 # Complex jwplayer
1115 {
1116 'url': 'http://www.indiedb.com/games/king-machine/videos',
1117 'info_dict': {
1118 'id': 'videos',
1119 'ext': 'mp4',
1120 'title': 'king machine trailer 1',
2637fadc 1121 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
a4a554a7
YCH
1122 'thumbnail': r're:^https?://.*\.jpg$',
1123 },
1124 },
03486dbb
RU
1125 {
1126 # JWPlayer config passed as variable
1127 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1128 'info_dict': {
1129 'id': '3326530_hq',
1130 'ext': 'mp4',
1131 'title': 'ARIELE | Tube Cup',
1132 'uploader': 'www.txxx.com',
1133 'age_limit': 18,
1134 },
1135 'params': {
1136 'skip_download': True,
1137 }
1138 },
939be9ad
JH
1139 {
1140 # JWPlatform iframe
1141 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1142 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1143 'info_dict': {
1144 'id': 'O0c5JcKT',
1145 'ext': 'mp4',
1146 'upload_date': '20171122',
1147 'timestamp': 1511366290,
1148 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1149 },
805f5bf7 1150 'add_ie': [JWPlatformIE.ie_key()],
939be9ad 1151 },
63d990d2 1152 {
c5b7014a 1153 # Video.js embed, multiple formats
63d990d2
S
1154 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1155 'info_dict': {
1156 'id': 'yygqldloqIk',
1157 'ext': 'mp4',
1158 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1159 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1160 'upload_date': '20130314',
1161 'uploader': 'PROстое3D',
1162 'uploader_id': 'PROstoe3D',
1163 },
1164 'params': {
1165 'skip_download': True,
1166 },
1167 },
c5b7014a
S
1168 {
1169 # Video.js embed, single format
1170 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1171 'info_dict': {
1172 'id': 'watch',
1173 'ext': 'mp4',
1174 'title': 'Step 1 - Good Foundation',
1175 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1176 },
1177 'params': {
1178 'skip_download': True,
1179 },
1180 },
59b8ab58
PH
1181 # rtl.nl embed
1182 {
1183 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1184 'playlist_mincount': 5,
1185 'info_dict': {
1186 'id': 'aanslagen-kopenhagen',
2637fadc 1187 'title': 'Aanslagen Kopenhagen',
59b8ab58 1188 }
255fca5e
S
1189 },
1190 # Zapiks embed
1191 {
1192 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1193 'info_dict': {
1194 'id': '118046',
1195 'ext': 'mp4',
1196 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1197 }
1198 },
66e568de
S
1199 # Kaltura embed (different embed code)
1200 {
1201 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1202 'info_dict': {
1203 'id': '1_a52wc67y',
1204 'ext': 'flv',
1205 'upload_date': '20150127',
1206 'uploader_id': 'PremierMedia',
1207 'timestamp': int,
1208 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1209 },
1210 },
87703231
YCH
1211 # Kaltura embed with single quotes
1212 {
1213 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1214 'info_dict': {
1215 'id': '0_izeg5utt',
1216 'ext': 'mp4',
1217 'title': '35871',
1218 'timestamp': 1355743100,
1219 'upload_date': '20121217',
1220 'uploader_id': 'batchUser',
1221 },
1222 'add_ie': ['Kaltura'],
1223 },
427cd050
S
1224 {
1225 # Kaltura embedded via quoted entry_id
1226 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1227 'info_dict': {
1228 'id': '0_utuok90b',
1229 'ext': 'mp4',
1230 'title': '06_matthew_brender_raj_dutt',
1231 'timestamp': 1466638791,
1232 'upload_date': '20160622',
1233 },
1234 'add_ie': ['Kaltura'],
1235 'expected_warnings': [
1236 'Could not send HEAD request'
1237 ],
1238 'params': {
1239 'skip_download': True,
1240 }
1241 },
8ab7e6c4
YCH
1242 {
1243 # Kaltura embedded, some fileExt broken (#11480)
1244 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1245 'info_dict': {
1246 'id': '1_sgtvehim',
1247 'ext': 'mp4',
1248 'title': 'Our "Standard Models" of particle physics and cosmology',
1249 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1250 'timestamp': 1321158993,
1251 'upload_date': '20111113',
1252 'uploader_id': 'kps1',
1253 },
1254 'add_ie': ['Kaltura'],
1255 },
a01825a5
JH
1256 {
1257 # Kaltura iframe embed
1258 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1259 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1260 'info_dict': {
1261 'id': '0_f2cfbpwy',
1262 'ext': 'mp4',
1263 'title': 'I. M. Pei: A Centennial Celebration',
1264 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1265 'upload_date': '20170403',
1266 'uploader_id': 'batchUser',
1267 'timestamp': 1491232186,
1268 },
1269 'add_ie': ['Kaltura'],
1270 },
665e9452 1271 # EaglePlatform embed (generic URL)
135c9c42
S
1272 {
1273 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
4645432d 1274 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
135c9c42
S
1275 'info_dict': {
1276 'id': '227304',
1277 'ext': 'mp4',
1278 'title': 'Навальный вышел на свободу',
1279 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
ec85ded8 1280 'thumbnail': r're:^https?://.*\.jpg$',
135c9c42
S
1281 'duration': 87,
1282 'view_count': int,
1283 'age_limit': 0,
1284 },
250b042c
S
1285 'params': {
1286 'skip_download': True,
1287 },
1288 },
1289 # referrer protected EaglePlatform embed
1290 {
1291 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1292 'info_dict': {
1293 'id': '582306',
1294 'ext': 'mp4',
1295 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1296 'thumbnail': r're:^https?://.*\.jpg$',
1297 'duration': 3382,
1298 'view_count': int,
1299 },
1300 'params': {
1301 'skip_download': True,
1302 },
135c9c42 1303 },
665e9452 1304 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1305 {
1306 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1307 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1308 'info_dict': {
1309 'id': '12820',
1310 'ext': 'mp4',
1311 'title': "'O Sole Mio",
ec85ded8 1312 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1313 'duration': 216,
1314 'view_count': int,
1315 },
250b042c
S
1316 'params': {
1317 'skip_download': True,
1318 },
2637fadc 1319 'skip': 'This video is unavailable.',
d47ae7f6 1320 },
f8388757
S
1321 # Pladform embed
1322 {
1323 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1324 'info_dict': {
1325 'id': '100183293',
1326 'ext': 'mp4',
62259846 1327 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1328 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1329 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1330 'duration': 694,
1331 'age_limit': 0,
1332 },
2637fadc 1333 'skip': 'HTTP Error 404: Not Found',
f8388757 1334 },
c798f15b
S
1335 # Playwire embed
1336 {
1337 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1338 'info_dict': {
1339 'id': '3519514',
1340 'ext': 'mp4',
1341 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1342 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1343 'duration': 45.115,
1344 },
1345 },
ad320e9b
NJ
1346 # 5min embed
1347 {
1348 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1349 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1350 'info_dict': {
1351 'id': '518726732',
1352 'ext': 'mp4',
1353 'title': 'Facebook Creates "On This Day" | Crunch Report',
2637fadc
RA
1354 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1355 'timestamp': 1427237531,
1356 'uploader': 'Crunch Report',
1357 'upload_date': '20150324',
1358 },
1359 'params': {
1360 # m3u8 download
1361 'skip_download': True,
ad320e9b
NJ
1362 },
1363 },
dc455a5f
S
1364 # SVT embed
1365 {
1366 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1367 'info_dict': {
1368 'id': '2900353',
1369 'ext': 'flv',
1370 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1371 'duration': 27,
1372 'age_limit': 0,
1373 },
1374 },
a4257017
S
1375 # Crooks and Liars embed
1376 {
1377 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1378 'info_dict': {
1379 'id': '8RUoRhRi',
1380 'ext': 'mp4',
1381 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1382 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1383 'timestamp': 1428207000,
1384 'upload_date': '20150405',
1385 'uploader': 'Heather',
1386 },
1387 },
1388 # Crooks and Liars external embed
1389 {
1390 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1391 'info_dict': {
1392 'id': 'MTE3MjUtMzQ2MzA',
1393 'ext': 'mp4',
1394 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1395 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1396 'timestamp': 1265032391,
1397 'upload_date': '20100201',
1398 'uploader': 'Heather',
1399 },
1400 },
facecb84 1401 # NBC Sports vplayer embed
a2edf2e7 1402 {
facecb84 1403 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1404 'info_dict': {
facecb84
S
1405 'id': 'ln7x1qSThw4k',
1406 'ext': 'flv',
1407 'title': "PFT Live: New leader in the 'new-look' defense",
1408 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1409 'uploader': 'NBCU-SPORTS',
1410 'upload_date': '20140107',
1411 'timestamp': 1389118457,
a2edf2e7 1412 },
2637fadc 1413 'skip': 'Invalid Page URL',
418c5cc3 1414 },
de3eb07e
YCH
1415 # NBC News embed
1416 {
1417 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1418 'md5': '1aa589c675898ae6d37a17913cf68d66',
1419 'info_dict': {
2637fadc 1420 'id': 'x_dtl_oa_LettermanliftPR_160608',
de3eb07e 1421 'ext': 'mp4',
2637fadc 1422 'title': 'David Letterman: A Preview',
de3eb07e 1423 '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
1424 'upload_date': '20160609',
1425 'timestamp': 1465431544,
1426 'uploader': 'NBCU-NEWS',
de3eb07e
YCH
1427 },
1428 },
418c5cc3
YCH
1429 # UDN embed
1430 {
811586eb 1431 'url': 'https://video.udn.com/news/300346',
01c58f84 1432 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1433 'info_dict': {
01c58f84 1434 'id': '300346',
418c5cc3 1435 'ext': 'mp4',
01c58f84 1436 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1437 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1438 },
1439 'params': {
1440 # m3u8 download
1441 'skip_download': True,
1442 },
2637fadc 1443 'expected_warnings': ['Failed to parse JSON Expecting value'],
edfcf7ab
YCH
1444 },
1445 # Ooyala embed
1446 {
1447 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1448 'info_dict': {
1449 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1450 'ext': 'mp4',
2637fadc 1451 'description': 'Index/Match versus VLOOKUP.',
edfcf7ab 1452 'title': 'This is what separates the Excel masters from the wannabes',
53e06b25 1453 'duration': 191.933,
edfcf7ab
YCH
1454 },
1455 'params': {
1456 # m3u8 downloads
1457 'skip_download': True,
1458 }
d6fd958c 1459 },
b26733ba
YCH
1460 # Brightcove URL in single quotes
1461 {
1462 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1463 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1464 'info_dict': {
1465 'id': '4255764656001',
1466 'ext': 'mp4',
1467 'title': 'SN Presents: Russell Martin, World Citizen',
1468 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1469 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1470 'uploader_id': '1704050871',
1471 'upload_date': '20150525',
1472 'timestamp': 1432570283,
b26733ba 1473 },
756f574e
YCH
1474 },
1475 # Dailymotion Cloud video
1476 {
1477 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
7d52c052 1478 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
756f574e 1479 'info_dict': {
7d52c052 1480 'id': 'x2uy8t3',
756f574e 1481 'ext': 'mp4',
7d52c052
YCH
1482 'title': 'Sauvons les abeilles ! - Le débat',
1483 'description': 'md5:d9082128b1c5277987825d684939ca26',
ec85ded8 1484 'thumbnail': r're:^https?://.*\.jpe?g$',
7d52c052
YCH
1485 'timestamp': 1434970506,
1486 'upload_date': '20150622',
1487 'uploader': 'Public Sénat',
1488 'uploader_id': 'xa9gza',
2637fadc
RA
1489 },
1490 'skip': 'File not found.',
a5158f38 1491 },
8084be78
S
1492 # OnionStudios embed
1493 {
1494 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1495 'info_dict': {
1496 'id': '2855',
1497 'ext': 'mp4',
1498 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
ec85ded8 1499 'thumbnail': r're:^https?://.*\.jpe?g$',
8084be78
S
1500 'uploader': 'ClickHole',
1501 'uploader_id': 'clickhole',
1502 }
1503 },
b8c1cc1a
S
1504 # SnagFilms embed
1505 {
1506 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1507 'info_dict': {
1508 'id': '74849a00-85a9-11e1-9660-123139220831',
1509 'ext': 'mp4',
1510 'title': '#whilewewatch',
1511 }
1512 },
a5158f38
YCH
1513 # AdobeTVVideo embed
1514 {
1515 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1516 'md5': '43662b577c018ad707a63766462b1e87',
1517 'info_dict': {
1518 'id': '2456',
1519 'ext': 'mp4',
1520 'title': 'New experience with Acrobat DC',
1521 'description': 'New experience with Acrobat DC',
1522 'duration': 248.667,
1523 },
1f812580 1524 },
ed126900 1525 # BrightcoveInPageEmbed embed
1526 {
1527 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1528 'info_dict': {
1529 'id': '4238694884001',
1530 'ext': 'flv',
1531 'title': 'Tabletop: Dread, Last Thoughts',
1532 'description': 'Tabletop: Dread, Last Thoughts',
1533 'duration': 51690,
1534 },
750b9ff0 1535 },
d10fe835
YCH
1536 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1537 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1538 {
1539 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1540 'info_dict': {
1541 'id': '4785848093001',
1542 'ext': 'mp4',
1543 'title': 'The Cardinal Pell Interview',
1544 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1545 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1546 'uploader_id': '2733773828001',
1547 'upload_date': '20160304',
1548 'timestamp': 1457083087,
d10fe835
YCH
1549 },
1550 'params': {
1551 # m3u8 downloads
1552 'skip_download': True,
1553 },
1554 },
9edf47df
S
1555 {
1556 # Brightcove embed with whitespace around attribute names
1557 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1558 'info_dict': {
1559 'id': '3167554373001',
1560 'ext': 'mp4',
1561 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1562 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1563 'uploader_id': '1079349493',
1564 'upload_date': '20140207',
1565 'timestamp': 1391810548,
1566 },
1567 'params': {
1568 'skip_download': True,
1569 },
1570 },
134c207e
YCH
1571 # Another form of arte.tv embed
1572 {
1573 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1574 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1575 'info_dict': {
1576 'id': '030273-562_PLUS7-F',
1577 'ext': 'mp4',
1578 'title': 'ARTE Reportage - Nulle part, en France',
1579 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1580 'upload_date': '20160409',
1581 },
1582 },
b8f67449
KM
1583 # LiveLeak embed
1584 {
1585 'url': 'http://www.wykop.pl/link/3088787/',
09747ba7 1586 'md5': '7619da8c820e835bef21a1efa2a0fc71',
b8f67449
KM
1587 'info_dict': {
1588 'id': '874_1459135191',
1589 'ext': 'mp4',
1590 'title': 'Man shows poor quality of new apartment building',
1591 'description': 'The wall is like a sand pile.',
1592 'uploader': 'Lake8737',
09747ba7
YCH
1593 },
1594 'add_ie': [LiveLeakIE.ie_key()],
1595 },
1596 # Another LiveLeak embed pattern (#13336)
1597 {
1598 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1599 'info_dict': {
1600 'id': '2eb_1496309988',
1601 'ext': 'mp4',
1602 'title': 'Thief robs place where everyone was armed',
1603 'description': 'md5:694d73ee79e535953cf2488562288eee',
1604 'uploader': 'brazilwtf',
1605 },
1606 'add_ie': [LiveLeakIE.ie_key()],
b8f67449 1607 },
4a120778
YCH
1608 # Duplicated embedded video URLs
1609 {
1610 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1611 'info_dict': {
1612 'id': '149298443_480_16c25b74_2',
1613 'ext': 'mp4',
1614 'title': 'vs. Blue Orange Spring Game',
1615 'uploader': 'www.hudl.com',
1616 },
1617 },
371ddb14
S
1618 # twitter:player:stream embed
1619 {
1620 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1621 'info_dict': {
1622 'id': 'master',
1623 'ext': 'mp4',
1624 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1625 'uploader': 'www.rtl.be',
1626 },
1627 'params': {
1628 # m3u8 downloads
1629 'skip_download': True,
1630 },
1631 },
32917907
RA
1632 # twitter:player embed
1633 {
1634 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1635 'md5': 'a3e0df96369831de324f0778e126653c',
1636 'info_dict': {
1637 'id': '4909620399001',
1638 'ext': 'mp4',
1639 'title': 'What Do Black Holes Sound Like?',
1640 'description': 'what do black holes sound like',
1641 'upload_date': '20160524',
1642 'uploader_id': '29913724001',
1643 'timestamp': 1464107587,
1644 'uploader': 'TheAtlantic',
1645 },
1646 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1647 },
1648 # Facebook <iframe> embed
1649 {
1650 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1651 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1652 'info_dict': {
1653 'id': '599637780109885',
1654 'ext': 'mp4',
1655 'title': 'Facebook video #599637780109885',
1656 },
1657 },
fd1c5fba
S
1658 # Facebook <iframe> embed, plugin video
1659 {
1660 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1661 'info_dict': {
1662 'id': '1754168231264132',
1663 'ext': 'mp4',
1664 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1665 'uploader': 'Tariq Ramadan (official)',
1666 'timestamp': 1496758379,
1667 'upload_date': '20170606',
1668 },
1669 'params': {
1670 'skip_download': True,
1671 },
1672 },
fd6ca382
YCH
1673 # Facebook API embed
1674 {
1675 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1676 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1677 'info_dict': {
1678 'id': '10153467542406923',
1679 'ext': 'mp4',
1680 'title': 'Facebook video #10153467542406923',
1681 },
7deef1ba
YCH
1682 },
1683 # Wordpress "YouTube Video Importer" plugin
1684 {
1685 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1686 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1687 'info_dict': {
1688 'id': 'HNTXWDXV9Is',
1689 'ext': 'mp4',
1690 'title': 'Blue Devils Drumline Stanford lot 2016',
1691 'upload_date': '20160627',
1692 'uploader_id': 'GENOCIDE8GENERAL10',
1693 'uploader': 'cylus cyrus',
1694 },
1695 },
81953d1a
RA
1696 {
1697 # video stored on custom kaltura server
1698 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1699 'md5': '537617d06e64dfed891fa1593c4b30cc',
1700 'info_dict': {
1701 'id': '0_1iotm5bh',
1702 'ext': 'mp4',
1703 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1704 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1705 'uploader_id': 'videos.expansion@el-mundo.net',
1706 'upload_date': '20150429',
1707 'timestamp': 1430303472,
1708 },
1709 'add_ie': ['Kaltura'],
1710 },
c03adf90
YCH
1711 {
1712 # Non-standard Vimeo embed
1713 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1714 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1715 'info_dict': {
1716 'id': '148867247',
1717 'ext': 'mp4',
1718 'title': 'Understanding the web - Teaser',
1719 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1720 'upload_date': '20151214',
1721 'uploader': 'OpenClassrooms',
1722 'uploader_id': 'openclassrooms',
1723 },
1724 'add_ie': ['Vimeo'],
1725 },
a5ff05df
S
1726 {
1727 # generic vimeo embed that requires original URL passed as Referer
1728 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1729 'only_matching': True,
1730 },
1979969f
S
1731 {
1732 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1733 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1734 'info_dict': {
1735 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1736 'ext': 'mp4',
1737 'title': 'Big Buck Bunny',
1738 'description': 'Royalty free test video',
1739 'timestamp': 1432816365,
1740 'upload_date': '20150528',
1741 'is_live': False,
1742 },
1743 'params': {
1744 'skip_download': True,
1745 },
1746 'add_ie': [ArkenaIE.ie_key()],
1747 },
2a1321a2
S
1748 {
1749 '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/',
1750 'info_dict': {
1751 'id': '1c7141f46c',
1752 'ext': 'mp4',
1753 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1754 },
1755 'params': {
1756 'skip_download': True,
1757 },
1758 'add_ie': [Vbox7IE.ie_key()],
1759 },
b0c8f2e9
DR
1760 {
1761 # DBTV embeds
1762 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1763 'info_dict': {
1764 'id': '43254897',
1765 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1766 },
b0c8f2e9
DR
1767 'playlist_mincount': 3,
1768 },
e186a9ec
S
1769 {
1770 # Videa embeds
1771 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1772 'info_dict': {
1773 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1774 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1775 },
1776 'playlist_mincount': 2,
1777 },
b687c85e
S
1778 {
1779 # 20 minuten embed
1780 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1781 'info_dict': {
1782 'id': '523629',
1783 'ext': 'mp4',
1784 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1785 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1786 },
1787 'params': {
1788 'skip_download': True,
1789 },
1790 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1791 },
1792 {
1793 # VideoPress embed
1794 'url': 'https://en.support.wordpress.com/videopress/',
1795 'info_dict': {
1796 'id': 'OcobLTqC',
1797 'ext': 'm4v',
1798 'title': 'IMG_5786',
1799 'timestamp': 1435711927,
1800 'upload_date': '20150701',
1801 },
1802 'params': {
1803 'skip_download': True,
1804 },
1805 'add_ie': [VideoPressIE.ie_key()],
fef51645 1806 },
eb3079b6
S
1807 {
1808 # Rutube embed
1809 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1810 'info_dict': {
1811 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1812 'ext': 'flv',
1813 'title': 'Магаззино: Казань 2',
1814 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1815 'uploader': 'Магаззино',
1816 'upload_date': '20170228',
1817 'uploader_id': '996642',
1818 },
1819 'params': {
1820 'skip_download': True,
1821 },
1822 'add_ie': [RutubeIE.ie_key()],
1823 },
fef51645
YCH
1824 {
1825 # ThePlatform embedded with whitespaces in URLs
1826 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1827 'only_matching': True,
1828 },
97952bdb
JH
1829 {
1830 # Senate ISVP iframe https
1831 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1832 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1833 'info_dict': {
1834 'id': 'govtaff020316',
1835 'ext': 'mp4',
1836 'title': 'Integrated Senate Video Player',
1837 },
1838 'add_ie': [SenateISVPIE.ie_key()],
1839 },
ab87c260
S
1840 {
1841 # Limelight embeds (1 channel embed + 4 media embeds)
1842 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1843 'info_dict': {
1844 'id': 'FacilitatorTraining2017',
1845 'title': 'Facilitator Training 2017',
1846 },
1847 'playlist_mincount': 5,
1848 },
eb02940c
S
1849 {
1850 # Limelight embed (LimelightPlayerUtil.embed)
1851 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1852 'info_dict': {
1853 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1854 'ext': 'mp4',
1855 'title': '07448641',
1856 'timestamp': 1499890639,
1857 'upload_date': '20170712',
1858 },
1859 'params': {
1860 'skip_download': True,
1861 },
1862 'add_ie': ['LimelightMedia'],
1863 },
7986c3ab
S
1864 {
1865 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1866 'info_dict': {
1867 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1868 'title': 'Standoff with Walnut Creek murder suspect ends',
1869 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1870 },
1871 'playlist_mincount': 4,
1872 },
55719459
JH
1873 {
1874 # WashingtonPost embed
1875 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1876 'info_dict': {
1877 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1878 'ext': 'mp4',
1879 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1880 '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.',
1881 'timestamp': 1455216756,
1882 'uploader': 'The Washington Post',
1883 'upload_date': '20160211',
1884 },
1885 'add_ie': [WashingtonPostIE.ie_key()],
1886 },
2b8e6a68
S
1887 {
1888 # Mediaset embed
1889 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1890 'info_dict': {
1891 'id': '720642',
1892 'ext': 'mp4',
1893 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1894 },
1895 'params': {
1896 'skip_download': True,
1897 },
1898 'add_ie': [MediasetIE.ie_key()],
1899 },
73cf76a9
S
1900 {
1901 # JOJ.sk embeds
1902 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1903 'info_dict': {
1904 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1905 'title': 'Slovenskom sa prehnala vlna silných búrok',
1906 },
1907 'playlist_mincount': 5,
1908 'add_ie': [JojIE.ie_key()],
1909 },
4328ddf8
S
1910 {
1911 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1912 'url': 'https://tvrain.ru/amp/418921/',
1913 'md5': 'cc00413936695987e8de148b67d14f1d',
1914 'info_dict': {
1915 'id': '418921',
1916 'ext': 'mp4',
1917 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1918 },
1919 },
41918eaa 1920 {
1921 # vzaar embed
1663bd6e
S
1922 'url': 'http://help.vzaar.com/article/165-embedding-video',
1923 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1924 'info_dict': {
1663bd6e 1925 'id': '8707641',
41918eaa 1926 'ext': 'mp4',
1663bd6e 1927 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1928 },
1929 },
9ce1ac40 1930 {
1931 # multiple HTML5 videos on one page
1932 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1933 'info_dict': {
1934 'id': 'keyscenarios',
1935 'title': 'Rescue Kit 14 Free Edition - Getting started',
1936 },
1937 'playlist_count': 4,
0987f2dd
T
1938 },
1939 {
1940 # vshare embed
1941 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1942 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1943 'info_dict': {
1944 'id': '0f64ce6',
1945 'title': 'vl14062007715967',
1946 'ext': 'mp4',
1947 }
9ce1ac40 1948 }
6e6b70d6
S
1949 # {
1950 # # TODO: find another test
1951 # # http://schema.org/VideoObject
1952 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1953 # 'md5': '888dcf08b7ea671381f00fab74692755',
1954 # 'info_dict': {
1955 # 'id': 'nyvTSJMKId',
1956 # 'ext': 'mp4',
1957 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1958 # 'description': '#love for cats.',
1959 # 'timestamp': 1461244995,
1960 # 'upload_date': '20160421',
1961 # },
1962 # 'params': {
1963 # 'force_generic_extractor': True,
1964 # },
1965 # }
cfe50f04 1966 ]
9b122384 1967
9b122384
PH
1968 def report_following_redirect(self, new_url):
1969 """Report information extraction."""
79649588 1970 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 1971
4fc946b5
PH
1972 def _extract_rss(self, url, video_id, doc):
1973 playlist_title = doc.find('./channel/title').text
1974 playlist_desc_el = doc.find('./channel/description')
1975 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1976
76c73715
PH
1977 entries = []
1978 for it in doc.findall('./channel/item'):
1979 next_url = xpath_text(it, 'link', fatal=False)
1980 if not next_url:
1981 enclosure_nodes = it.findall('./enclosure')
1982 for e in enclosure_nodes:
1983 next_url = e.attrib.get('url')
1984 if next_url:
1985 break
1986
1987 if not next_url:
1988 continue
1989
1990 entries.append({
413c1f8e 1991 '_type': 'url_transparent',
76c73715
PH
1992 'url': next_url,
1993 'title': it.find('title').text,
1994 })
4fc946b5
PH
1995
1996 return {
1997 '_type': 'playlist',
1998 'id': url,
1999 'title': playlist_title,
2000 'description': playlist_desc,
2001 'entries': entries,
2002 }
2003
c8e9a235
PH
2004 def _extract_camtasia(self, url, video_id, webpage):
2005 """ Returns None if no camtasia video can be found. """
2006
2007 camtasia_cfg = self._search_regex(
2008 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2009 webpage, 'camtasia configuration file', default=None)
2010 if camtasia_cfg is None:
2011 return None
2012
2013 title = self._html_search_meta('DC.title', webpage, fatal=True)
2014
2015 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2016 camtasia_cfg = self._download_xml(
2017 camtasia_url, video_id,
2018 note='Downloading camtasia configuration',
2019 errnote='Failed to download camtasia configuration')
2020 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2021
2022 entries = []
2023 for n in fileset_node.getchildren():
2024 url_n = n.find('./uri')
2025 if url_n is None:
2026 continue
2027
2028 entries.append({
2029 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2030 'title': '%s - %s' % (title, n.tag),
2031 'url': compat_urlparse.urljoin(url, url_n.text),
2032 'duration': float_or_none(n.find('./duration').text),
2033 })
2034
2035 return {
2036 '_type': 'playlist',
2037 'entries': entries,
2038 'title': title,
2039 }
2040
9b122384 2041 def _real_extract(self, url):
ebd3c7b3
PH
2042 if url.startswith('//'):
2043 return {
2044 '_type': 'url',
20991253 2045 'url': self.http_scheme() + url,
ebd3c7b3
PH
2046 }
2047
a7130543
JMF
2048 parsed_url = compat_urlparse.urlparse(url)
2049 if not parsed_url.scheme:
04b4d394
PH
2050 default_search = self._downloader.params.get('default_search')
2051 if default_search is None:
1f7ccb90 2052 default_search = 'fixup_error'
04b4d394 2053
1f7ccb90 2054 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
2055 if '/' in url:
2056 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2057 return self.url_result('http://' + url)
1f7ccb90 2058 elif default_search != 'fixup_error':
9c1fc022 2059 if default_search == 'auto_warning':
0e67ab0d
PH
2060 if re.match(r'^(?:url|URL)$', url):
2061 raise ExtractorError(
2062 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2063 expected=True)
2064 else:
2065 self._downloader.report_warning(
7571c02c 2066 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2067 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2068
2069 if default_search in ('error', 'fixup_error'):
7571c02c 2070 raise ExtractorError(
b74e86f4
PH
2071 '%r is not a valid URL. '
2072 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2073 % (url, url), expected=True)
04b4d394 2074 else:
f2f2c0c2
PH
2075 if ':' not in default_search:
2076 default_search += ':'
04b4d394 2077 return self.url_result(default_search + url)
4d54ef20
PH
2078
2079 url, smuggled_data = unsmuggle_url(url)
2080 force_videoid = None
d6e6a422 2081 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2082 if smuggled_data and 'force_videoid' in smuggled_data:
2083 force_videoid = smuggled_data['force_videoid']
2084 video_id = force_videoid
2085 else:
9dcd6fd3 2086 video_id = self._generic_id(url)
3d83a1ae 2087
79649588 2088 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2089
ebab4520 2090 head_req = HEADRequest(url)
23be51d8 2091 head_response = self._request_webpage(
ebab4520
PH
2092 head_req, video_id,
2093 note=False, errnote='Could not send HEAD request to %s' % url,
2094 fatal=False)
42393ce2 2095
23be51d8 2096 if head_response is not False:
42393ce2 2097 # Check for redirect
5551d771 2098 new_url = compat_str(head_response.geturl())
42393ce2
PH
2099 if url != new_url:
2100 self.report_following_redirect(new_url)
4d54ef20
PH
2101 if force_videoid:
2102 new_url = smuggle_url(
2103 new_url, {'force_videoid': force_videoid})
cecaaf3f 2104 return self.url_result(new_url)
42393ce2 2105
23be51d8
PH
2106 full_response = None
2107 if head_response is False:
5c2266df 2108 request = sanitized_Request(url)
58bde34a
S
2109 request.add_header('Accept-Encoding', '*')
2110 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2111 head_response = full_response
2112
f930e0c7
S
2113 info_dict = {
2114 'id': video_id,
9dcd6fd3 2115 'title': self._generic_title(url),
303dcdb9 2116 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
2117 }
2118
23be51d8 2119 # Check for direct link to a video
955737b2 2120 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2121 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2122 if m:
4e363703 2123 format_id = compat_str(m.group('format_id'))
f930e0c7 2124 if format_id.endswith('mpegurl'):
eadc3ccd 2125 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
2126 elif format_id == 'f4m':
2127 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2128 else:
2129 formats = [{
4e363703 2130 'format_id': format_id,
eadc3ccd 2131 'url': url,
2132 'vcodec': 'none' if m.group('type') == 'audio' else None
2133 }]
de6c51e8 2134 info_dict['direct'] = True
19dbaeec 2135 self._sort_formats(formats)
de6c51e8 2136 info_dict['formats'] = formats
f930e0c7 2137 return info_dict
42393ce2 2138
d6e6a422 2139 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
2140 force = self._downloader.params.get('force_generic_extractor', False)
2141 self._downloader.report_warning(
2142 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2143
4e262a88 2144 if not full_response:
5c2266df 2145 request = sanitized_Request(url)
58bde34a
S
2146 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2147 # making it impossible to download only chunk of the file (yet we need only 512kB to
2148 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2149 # that will always result in downloading the whole file that is not desirable.
2150 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2151 # to accept raw bytes and being able to download only a chunk.
2152 # It may probably better to solve this by checking Content-Type for application/octet-stream
2153 # after HEAD request finishes, but not sure if we can rely on this.
2154 request.add_header('Accept-Encoding', '*')
2155 full_response = self._request_webpage(request, video_id)
4e262a88 2156
5940862d
S
2157 first_bytes = full_response.read(512)
2158
2159 # Is it an M3U playlist?
0d769bcb 2160 if first_bytes.startswith(b'#EXTM3U'):
5940862d 2161 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 2162 self._sort_formats(info_dict['formats'])
5940862d
S
2163 return info_dict
2164
4e262a88
PH
2165 # Maybe it's a direct link to a video?
2166 # Be careful not to download the whole thing!
61ca9a80 2167 if not is_html(first_bytes):
4e262a88
PH
2168 self._downloader.report_warning(
2169 'URL could be a direct video link, returning it as such.')
f930e0c7 2170 info_dict.update({
4e262a88
PH
2171 'direct': True,
2172 'url': url,
f930e0c7
S
2173 })
2174 return info_dict
4e262a88
PH
2175
2176 webpage = self._webpage_read_content(
2177 full_response, url, video_id, prefix=first_bytes)
2178
9b122384 2179 self.report_extraction(video_id)
887c6acd 2180
1b840245 2181 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2182 try:
f7854627 2183 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
2184 if doc.tag == 'rss':
2185 return self._extract_rss(url, video_id, doc)
cc99a77a
S
2186 elif doc.tag == 'SmoothStreamingMedia':
2187 info_dict['formats'] = self._parse_ism_formats(doc, url)
2188 self._sort_formats(info_dict['formats'])
2189 return info_dict
e5e8d20a 2190 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
2191 smil = self._parse_smil(doc, url, video_id)
2192 self._sort_formats(smil['formats'])
2193 return smil
729accb4
S
2194 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2195 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1b840245 2196 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7 2197 info_dict['formats'] = self._parse_mpd_formats(
86f4d14f 2198 doc, video_id,
5551d771 2199 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
86f4d14f 2200 mpd_url=url)
19dbaeec 2201 self._sort_formats(info_dict['formats'])
f930e0c7
S
2202 return info_dict
2203 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2204 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 2205 self._sort_formats(info_dict['formats'])
f930e0c7 2206 return info_dict
f7300c5c 2207 except compat_xml_parse_error:
4fc946b5
PH
2208 pass
2209
c8e9a235
PH
2210 # Is it a Camtasia project?
2211 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2212 if camtasia_res is not None:
2213 return camtasia_res
2214
14390730
S
2215 # Sometimes embedded video player is hidden behind percent encoding
2216 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2217 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 2218 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2219
887c6acd
PH
2220 # it's tempting to parse this further, but you would
2221 # have to take into account all the variations like
2222 # Video Title - Site Name
2223 # Site Name | Video Title
2224 # Video Title - Tagline | Site Name
2225 # and so on and so forth; it's just not practical
6f41b2bc
S
2226 video_title = self._og_search_title(
2227 webpage, default=None) or self._html_search_regex(
79649588
PH
2228 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2229 default='video')
ef4fd848 2230
4d805e06
PH
2231 # Try to detect age limit automatically
2232 age_limit = self._rta_search(webpage)
2233 # And then there are the jokers who advertise that they use RTA,
2234 # but actually don't.
2235 AGE_LIMIT_MARKERS = [
197224b7 2236 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
4d805e06
PH
2237 ]
2238 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2239 age_limit = 18
2240
ef4fd848
PH
2241 # video uploader is domain name
2242 video_uploader = self._search_regex(
79649588 2243 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2244
6f41b2bc
S
2245 video_description = self._og_search_description(webpage, default=None)
2246 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2247
b311b0ea
S
2248 info_dict.update({
2249 'title': video_title,
2250 'description': video_description,
2251 'thumbnail': video_thumbnail,
2252 'age_limit': age_limit,
2253 })
2254
1f4b722b 2255 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2256 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2257 if bc_urls:
99877772
PH
2258 entries = [{
2259 '_type': 'url',
2260 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2261 'ie_key': 'BrightcoveLegacy'
99877772
PH
2262 } for bc_url in bc_urls]
2263
2264 return {
2265 '_type': 'playlist',
2266 'title': video_title,
2267 'id': video_id,
2268 'entries': entries,
2269 }
cfe50f04 2270
f6519f89 2271 # Look for Brightcove New Studio embeds
0254f93b 2272 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2273 if bc_urls:
46b18f23 2274 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
ed126900 2275
4e826cd9
S
2276 # Look for Nexx embeds
2277 nexx_urls = NexxIE._extract_urls(webpage)
2278 if nexx_urls:
2279 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2280
3f59b015
S
2281 # Look for Nexx iFrame embeds
2282 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2283 if nexx_embed_urls:
2284 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2285
4d8819d2
S
2286 # Look for ThePlatform embeds
2287 tp_urls = ThePlatformIE._extract_urls(webpage)
2288 if tp_urls:
46b18f23 2289 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2290
48a5eabc
S
2291 # Look for Vessel embeds
2292 vessel_urls = VesselIE._extract_urls(webpage)
2293 if vessel_urls:
46b18f23 2294 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
48a5eabc 2295
59b8ab58
PH
2296 # Look for embedded rtl.nl player
2297 matches = re.findall(
2637fadc 2298 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
59b8ab58
PH
2299 webpage)
2300 if matches:
46b18f23 2301 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2302
09b9c45e
S
2303 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2304 if vimeo_urls:
46b18f23 2305 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2306
a1b85269
YCH
2307 vid_me_embed_url = self._search_regex(
2308 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2309 webpage, 'vid.me embed', default=None)
2310 if vid_me_embed_url is not None:
2311 return self.url_result(vid_me_embed_url, 'Vidme')
2312
66c9fa36
S
2313 # Look for YouTube embeds
2314 youtube_urls = YoutubeIE._extract_urls(webpage)
2315 if youtube_urls:
46b18f23 2316 return self.playlist_from_matches(
66c9fa36 2317 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2318
ad213a1d 2319 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2320 if matches:
46b18f23 2321 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2322
8489578d
NJ
2323 # Look for embedded Dailymotion playlist player (#3822)
2324 m = re.search(
2325 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2326 if m:
2327 playlists = re.findall(
2328 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2329 if playlists:
46b18f23
JH
2330 return self.playlist_from_matches(
2331 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2332
71a1db89
S
2333 # Look for DailyMail embeds
2334 dailymail_urls = DailyMailIE._extract_urls(webpage)
2335 if dailymail_urls:
2336 return self.playlist_from_matches(
2337 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2338
ef4fd848 2339 # Look for embedded Wistia player
58bb4402
S
2340 wistia_url = WistiaIE._extract_url(webpage)
2341 if wistia_url:
ef4fd848
PH
2342 return {
2343 '_type': 'url_transparent',
58bb4402
S
2344 'url': self._proto_relative_url(wistia_url),
2345 'ie_key': WistiaIE.ie_key(),
ef4fd848 2346 'uploader': video_uploader,
ef4fd848 2347 }
5f6a1245 2348
bab19a8e
S
2349 # Look for SVT player
2350 svt_url = SVTIE._extract_url(webpage)
2351 if svt_url:
2352 return self.url_result(svt_url, 'SVT')
2353
c19f7764
JMF
2354 # Look for Bandcamp pages with custom domain
2355 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2356 if mobj is not None:
2357 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2358 # Don't set the extractor because it can be a track url or an album
2359 return self.url_result(burl)
c19f7764 2360
f25571ff
PH
2361 # Look for embedded Vevo player
2362 mobj = re.search(
2363 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2364 if mobj is not None:
2365 return self.url_result(mobj.group('url'))
796df3c6
S
2366
2367 # Look for embedded Viddler player
cb454b33
S
2368 mobj = re.search(
2369 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2370 webpage)
796df3c6
S
2371 if mobj is not None:
2372 return self.url_result(mobj.group('url'))
f25571ff 2373
3378d67a
S
2374 # Look for NYTimes player
2375 mobj = re.search(
2376 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2377 webpage)
2378 if mobj is not None:
2379 return self.url_result(mobj.group('url'))
2380
cefdf970
S
2381 # Look for Libsyn player
2382 mobj = re.search(
2383 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2384 if mobj is not None:
2385 return self.url_result(mobj.group('url'))
2386
c0d0b01f 2387 # Look for Ooyala videos
8a37aa15 2388 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 2389 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
198d4cb4 2390 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
2391 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2392 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2393 if mobj is not None:
9837cb75
RA
2394 embed_token = self._search_regex(
2395 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2396 webpage, 'ooyala embed token', default=None)
2397 return OoyalaIE._build_url_result(smuggle_url(
2398 mobj.group('ec'), {
2399 'domain': url,
2400 'embed_token': embed_token,
2401 }))
c0d0b01f 2402
f076b638 2403 # Look for multiple Ooyala embeds on SBN network websites
2404 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2405 if mobj is not None:
2406 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2407 if embeds:
46b18f23
JH
2408 return self.playlist_from_matches(
2409 embeds, video_id, video_title,
2410 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2411
aa94a6d3 2412 # Look for Aparat videos
48099643 2413 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2414 if mobj is not None:
2415 return self.url_result(mobj.group(1), 'Aparat')
2416
c93c2ab1 2417 # Look for MPORA videos
c3f51436 2418 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2419 if mobj is not None:
2420 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2421
15c0e8e7 2422 # Look for embedded NovaMov-based player
8f89e687 2423 mobj = re.search(
8dfa187b 2424 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
2425 (?P<url>http://(?:(?:embed|www)\.)?
2426 (?:novamov\.com|
2427 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2428 videoweed\.(?:es|com)|
2429 movshare\.(?:net|sx|ag)|
2430 divxstage\.(?:eu|net|ch|co|at|ag))
2431 /embed\.php.+?)\1''', webpage)
8f89e687 2432 if mobj is not None:
15c0e8e7 2433 return self.url_result(mobj.group('url'))
50f56607 2434
9834872b 2435 # Look for embedded Facebook player
0646e34c
S
2436 facebook_urls = FacebookIE._extract_urls(webpage)
2437 if facebook_urls:
2438 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2439
ca97a56e
S
2440 # Look for embedded VK player
2441 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2442 if mobj is not None:
2443 return self.url_result(mobj.group('url'), 'VK')
2444
33d4fdab
S
2445 # Look for embedded Odnoklassniki player
2446 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2447 if mobj is not None:
2448 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2449
0364fa8b
S
2450 # Look for embedded ivi player
2451 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2452 if mobj is not None:
2453 return self.url_result(mobj.group('url'), 'Ivi')
2454
db1f3888
PH
2455 # Look for embedded Huffington Post player
2456 mobj = re.search(
c3f51436 2457 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2458 if mobj is not None:
2459 return self.url_result(mobj.group('url'), 'HuffPost')
2460
1b86cc41 2461 # Look for embed.ly
2462 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2463 if mobj is not None:
2464 return self.url_result(mobj.group('url'))
2465 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2466 if mobj is not None:
f7e6f7fa 2467 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2468
60cc4dc4
PH
2469 # Look for funnyordie embed
2470 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2471 if matches:
46b18f23
JH
2472 return self.playlist_from_matches(
2473 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2474
db546cf8
S
2475 # Look for BBC iPlayer embed
2476 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2477 if matches:
46b18f23 2478 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2479
93d020dd
S
2480 # Look for embedded RUTV player
2481 rutv_url = RUTVIE._extract_url(webpage)
2482 if rutv_url:
2483 return self.url_result(rutv_url, 'RUTV')
2484
494f20cb 2485 # Look for embedded TVC player
b8599718
S
2486 tvc_url = TVCIE._extract_url(webpage)
2487 if tvc_url:
2488 return self.url_result(tvc_url, 'TVC')
494f20cb 2489
d40a3b5b
S
2490 # Look for embedded SportBox player
2491 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2492 if sportbox_urls:
46b18f23 2493 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
d40a3b5b 2494
2bb5b6d0
S
2495 # Look for embedded XHamster player
2496 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2497 if xhamster_urls:
46b18f23 2498 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2499
2c9ca782
S
2500 # Look for embedded TNAFlixNetwork player
2501 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2502 if tnaflix_urls:
46b18f23 2503 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2504
b52c9ef1
S
2505 # Look for embedded PornHub player
2506 pornhub_urls = PornHubIE._extract_urls(webpage)
2507 if pornhub_urls:
46b18f23 2508 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2509
37e7a71c
S
2510 # Look for embedded DrTuber player
2511 drtuber_urls = DrTuberIE._extract_urls(webpage)
2512 if drtuber_urls:
46b18f23 2513 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2514
e28ed498
S
2515 # Look for embedded RedTube player
2516 redtube_urls = RedTubeIE._extract_urls(webpage)
2517 if redtube_urls:
46b18f23 2518 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 2519
9872d311
S
2520 # Look for embedded Tvigle player
2521 mobj = re.search(
2522 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2523 if mobj is not None:
2524 return self.url_result(mobj.group('url'), 'Tvigle')
2525
7e2ede98
JMF
2526 # Look for embedded TED player
2527 mobj = re.search(
d7cc31b6 2528 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
2529 if mobj is not None:
2530 return self.url_result(mobj.group('url'), 'TED')
2531
5c386252 2532 # Look for embedded Ustream videos
d77ac737
YCH
2533 ustream_url = UstreamIE._extract_url(webpage)
2534 if ustream_url:
2535 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 2536
893f8832
PH
2537 # Look for embedded arte.tv player
2538 mobj = re.search(
134c207e 2539 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
893f8832
PH
2540 webpage)
2541 if mobj is not None:
2542 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2543
cbd55ade
S
2544 # Look for embedded francetv player
2545 mobj = re.search(
2546 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2547 webpage)
2548 if mobj is not None:
2549 return self.url_result(mobj.group('url'))
2550
cb3ac1c6
S
2551 # Look for embedded smotri.com player
2552 smotri_url = SmotriIE._extract_url(webpage)
2553 if smotri_url:
2554 return self.url_result(smotri_url, 'Smotri')
2555
e6c2d9ad 2556 # Look for embedded Myvi.ru player
6dd94d3a 2557 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
2558 if myvi_url:
2559 return self.url_result(myvi_url)
2560
dfb1b146 2561 # Look for embedded soundcloud player
94aae015
S
2562 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2563 if soundcloud_urls:
46b18f23 2564 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
20991253 2565
027e2312
S
2566 # Look for tunein player
2567 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2568 if tunein_urls:
46b18f23 2569 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 2570
c5cd249e 2571 # Look for embedded mtvservices player
46fde8a1
S
2572 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2573 if mtvservices_url:
2574 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 2575
49807b4a
S
2576 # Look for embedded yahoo player
2577 mobj = re.search(
2578 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2579 webpage)
2580 if mobj is not None:
2581 return self.url_result(mobj.group('url'), 'Yahoo')
2582
2ef6fcb5
PH
2583 # Look for embedded sbs.com.au player
2584 mobj = re.search(
e98b8e79
PH
2585 r'''(?x)
2586 (?:
2587 <meta\s+property="og:video"\s+content=|
2588 <iframe[^>]+?src=
2589 )
2590 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
2591 webpage)
2592 if mobj is not None:
2593 return self.url_result(mobj.group('url'), 'SBS')
2594
42bdd9d0
PH
2595 # Look for embedded Cinchcast player
2596 mobj = re.search(
2597 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2598 webpage)
2599 if mobj is not None:
2600 return self.url_result(mobj.group('url'), 'Cinchcast')
2601
1a94ff68 2602 mobj = re.search(
5263cdfc 2603 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 2604 webpage)
8001607e
YCH
2605 if not mobj:
2606 mobj = re.search(
2607 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2608 webpage)
1a94ff68
S
2609 if mobj is not None:
2610 return self.url_result(mobj.group('url'), 'MLB')
2611
1419fafd 2612 mobj = re.search(
dd467d33 2613 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
2614 webpage)
2615 if mobj is not None:
2616 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2617
af63fed7 2618 mobj = re.search(
78d3b3e2 2619 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
2620 webpage)
2621 if mobj is not None:
2622 return self.url_result(mobj.group('url'), 'Livestream')
2623
255fca5e
S
2624 # Look for Zapiks embed
2625 mobj = re.search(
2626 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2627 if mobj is not None:
2628 return self.url_result(mobj.group('url'), 'Zapiks')
2629
e3216b82 2630 # Look for Kaltura embeds
c287f2bc
S
2631 kaltura_url = KalturaIE._extract_url(webpage)
2632 if kaltura_url:
2633 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
e3216b82 2634
665e9452 2635 # Look for EaglePlatform embeds
06a96da1
S
2636 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2637 if eagleplatform_url:
665e9452 2638 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 2639
665e9452 2640 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
2641 mobj = re.search(
2642 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2643 if mobj is not None:
2644 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2645
f8388757 2646 # Look for Pladform embeds
45dad7ba
S
2647 pladform_url = PladformIE._extract_url(webpage)
2648 if pladform_url:
2649 return self.url_result(pladform_url)
f8388757 2650
ff18735c
S
2651 # Look for Videomore embeds
2652 videomore_url = VideomoreIE._extract_url(webpage)
2653 if videomore_url:
2654 return self.url_result(videomore_url)
2655
83f1481b
S
2656 # Look for Webcaster embeds
2657 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2658 if webcaster_url:
2659 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2660
2dcc114f
S
2661 # Look for Playwire embeds
2662 mobj = re.search(
2663 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2664 if mobj is not None:
2665 return self.url_result(mobj.group('url'))
2666
ad320e9b
NJ
2667 # Look for 5min embeds
2668 mobj = re.search(
2669 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2670 if mobj is not None:
2671 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2672
18153f1b
S
2673 # Look for Crooks and Liars embeds
2674 mobj = re.search(
2675 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2676 if mobj is not None:
2677 return self.url_result(mobj.group('url'))
2678
a2edf2e7
YCH
2679 # Look for NBC Sports VPlayer embeds
2680 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2681 if nbc_sports_url:
2682 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2683
de3eb07e
YCH
2684 # Look for NBC News embeds
2685 nbc_news_embed_url = re.search(
2686 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2687 if nbc_news_embed_url:
2688 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2689
653789af 2690 # Look for Google Drive embeds
5b251628 2691 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 2692 if google_drive_url:
2693 return self.url_result(google_drive_url, 'GoogleDrive')
2694
418c5cc3
YCH
2695 # Look for UDN embeds
2696 mobj = re.search(
2637fadc 2697 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
2698 if mobj is not None:
2699 return self.url_result(
0a160363 2700 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 2701
2fe1b5bd
YCH
2702 # Look for Senate ISVP iframe
2703 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2704 if senate_isvp_url:
25c3a734 2705 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 2706
756f574e
YCH
2707 # Look for Dailymotion Cloud videos
2708 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2709 if dmcloud_url:
2710 return self.url_result(dmcloud_url, 'DailymotionCloud')
2711
1ac1c4c2
S
2712 # Look for OnionStudios embeds
2713 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2714 if onionstudios_url:
2715 return self.url_result(onionstudios_url)
2716
67167920 2717 # Look for ViewLift embeds
2718 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2719 if viewlift_url:
2720 return self.url_result(viewlift_url)
eedd20ef 2721
7cb09524 2722 # Look for JWPlatform embeds
2723 jwplatform_url = JWPlatformIE._extract_url(webpage)
2724 if jwplatform_url:
2725 return self.url_result(jwplatform_url, 'JWPlatform')
2726
aecfcd4e
S
2727 # Look for Digiteka embeds
2728 digiteka_url = DigitekaIE._extract_url(webpage)
2729 if digiteka_url:
2730 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 2731
1979969f
S
2732 # Look for Arkena embeds
2733 arkena_url = ArkenaIE._extract_url(webpage)
2734 if arkena_url:
2735 return self.url_result(arkena_url, ArkenaIE.ie_key())
2736
b1c35797
RA
2737 # Look for Piksel embeds
2738 piksel_url = PikselIE._extract_url(webpage)
2739 if piksel_url:
2740 return self.url_result(piksel_url, PikselIE.ie_key())
2741
1bf996fa 2742 # Look for Limelight embeds
e5d39886
S
2743 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2744 if limelight_urls:
2745 return self.playlist_result(
2746 limelight_urls, video_id, video_title, video_description)
2747
7986c3ab
S
2748 # Look for Anvato embeds
2749 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2750 if anvato_urls:
2751 return self.playlist_result(
2752 anvato_urls, video_id, video_title, video_description)
2753
a5158f38
YCH
2754 # Look for AdobeTVVideo embeds
2755 mobj = re.search(
2756 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2757 webpage)
2758 if mobj is not None:
2759 return self.url_result(
2760 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2761 'AdobeTVVideo')
2762
088e1aac
YCH
2763 # Look for Vine embeds
2764 mobj = re.search(
2765 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2766 webpage)
2767 if mobj is not None:
2768 return self.url_result(
2769 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2770
217d5ae0
RA
2771 # Look for VODPlatform embeds
2772 mobj = re.search(
93b84045 2773 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
217d5ae0
RA
2774 webpage)
2775 if mobj is not None:
2776 return self.url_result(
93b84045 2777 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 2778
7d273a38
RA
2779 # Look for Mangomolo embeds
2780 mobj = re.search(
d05ef09d 2781 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
7d273a38
RA
2782 (?:
2783 video\?.*?\bid=(?P<video_id>\d+)|
2784 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2785 ).+?)\1''', webpage)
2786 if mobj is not None:
2787 info = {
2788 '_type': 'url_transparent',
2789 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2790 'title': video_title,
2791 'description': video_description,
2792 'thumbnail': video_thumbnail,
2793 'uploader': video_uploader,
2794 }
2795 video_id = mobj.group('video_id')
2796 if video_id:
2797 info.update({
2798 'ie_key': 'MangomoloVideo',
2799 'id': video_id,
2800 })
2801 else:
2802 info.update({
2803 'ie_key': 'MangomoloLive',
2804 'id': mobj.group('channel_id'),
2805 })
2806 return info
2807
5a51775a
YCH
2808 # Look for Instagram embeds
2809 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2810 if instagram_embed_url is not None:
11e60fca
S
2811 return self.url_result(
2812 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 2813
b8f67449 2814 # Look for LiveLeak embeds
09747ba7
YCH
2815 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2816 if liveleak_urls:
2817 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
b8f67449 2818
5d39176f
S
2819 # Look for 3Q SDN embeds
2820 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2821 if threeqsdn_url:
6f41b2bc
S
2822 return {
2823 '_type': 'url_transparent',
2824 'ie_key': ThreeQSDNIE.ie_key(),
2825 'url': self._proto_relative_url(threeqsdn_url),
2826 'title': video_title,
2827 'description': video_description,
2828 'thumbnail': video_thumbnail,
2829 'uploader': video_uploader,
2830 }
5d39176f 2831
2a1321a2
S
2832 # Look for VBOX7 embeds
2833 vbox7_url = Vbox7IE._extract_url(webpage)
2834 if vbox7_url:
2835 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2836
b0c8f2e9
DR
2837 # Look for DBTV embeds
2838 dbtv_urls = DBTVIE._extract_urls(webpage)
2839 if dbtv_urls:
46b18f23 2840 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 2841
e186a9ec
S
2842 # Look for Videa embeds
2843 videa_urls = VideaIE._extract_urls(webpage)
2844 if videa_urls:
46b18f23 2845 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 2846
b687c85e
S
2847 # Look for 20 minuten embeds
2848 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2849 if twentymin_urls:
46b18f23
JH
2850 return self.playlist_from_matches(
2851 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 2852
17f8deeb
S
2853 # Look for Openload embeds
2854 openload_urls = OpenloadIE._extract_urls(webpage)
2855 if openload_urls:
46b18f23
JH
2856 return self.playlist_from_matches(
2857 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
17f8deeb 2858
6ef3e65a
S
2859 # Look for VideoPress embeds
2860 videopress_urls = VideoPressIE._extract_urls(webpage)
2861 if videopress_urls:
46b18f23
JH
2862 return self.playlist_from_matches(
2863 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 2864
eb3079b6
S
2865 # Look for Rutube embeds
2866 rutube_urls = RutubeIE._extract_urls(webpage)
2867 if rutube_urls:
46b18f23 2868 return self.playlist_from_matches(
2583c0b5 2869 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 2870
55719459
JH
2871 # Look for WashingtonPost embeds
2872 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2873 if wapo_urls:
2874 return self.playlist_from_matches(
2875 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2876
5d29af3d
S
2877 # Look for Mediaset embeds
2878 mediaset_urls = MediasetIE._extract_urls(webpage)
2879 if mediaset_urls:
2880 return self.playlist_from_matches(
2881 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2882
73cf76a9
S
2883 # Look for JOJ.sk embeds
2884 joj_urls = JojIE._extract_urls(webpage)
2885 if joj_urls:
2886 return self.playlist_from_matches(
2887 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2888
24e966e8
PH
2889 # Look for megaphone.fm embeds
2890 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2891 if mpfn_urls:
2892 return self.playlist_from_matches(
2893 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2894
1663bd6e
S
2895 # Look for vzaar embeds
2896 vzaar_urls = VzaarIE._extract_urls(webpage)
2897 if vzaar_urls:
2898 return self.playlist_from_matches(
2899 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2900
26bae2d9
S
2901 channel9_urls = Channel9IE._extract_urls(webpage)
2902 if channel9_urls:
2903 return self.playlist_from_matches(
2904 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2905
0987f2dd
T
2906 vshare_urls = VShareIE._extract_urls(webpage)
2907 if vshare_urls:
2908 return self.playlist_from_matches(
2909 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2910
b311b0ea
S
2911 def merge_dicts(dict1, dict2):
2912 merged = {}
2913 for k, v in dict1.items():
2914 if v is not None:
2915 merged[k] = v
2916 for k, v in dict2.items():
2917 if v is None:
2918 continue
2919 if (k not in merged or
2920 (isinstance(v, compat_str) and v and
2921 isinstance(merged[k], compat_str) and
2922 not merged[k])):
2923 merged[k] = v
2924 return merged
2925
bd264412
YCH
2926 # Look for HTML5 media
2927 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2928 if entries:
9ce1ac40 2929 if len(entries) == 1:
2930 entries[0].update({
bd264412
YCH
2931 'id': video_id,
2932 'title': video_title,
2933 })
9ce1ac40 2934 else:
2935 for num, entry in enumerate(entries, start=1):
2936 entry.update({
2937 'id': '%s-%s' % (video_id, num),
2938 'title': '%s (%d)' % (video_title, num),
2939 })
2940 for entry in entries:
bd264412 2941 self._sort_formats(entry['formats'])
9ce1ac40 2942 return self.playlist_result(entries, video_id, video_title)
bd264412 2943
c73e330e
RU
2944 jwplayer_data = self._find_jwplayer_data(
2945 webpage, video_id, transform_source=js_to_json)
2946 if jwplayer_data:
4f06c1c9 2947 info = self._parse_jwplayer_data(
3e943cfe 2948 jwplayer_data, video_id, require_title=False, base_url=url)
b311b0ea 2949 return merge_dicts(info, info_dict)
a4a554a7 2950
63d990d2
S
2951 # Video.js embed
2952 mobj = re.search(
c5b7014a 2953 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
2954 webpage)
2955 if mobj is not None:
2956 sources = self._parse_json(
2957 mobj.group(1), video_id, transform_source=js_to_json,
2958 fatal=False) or []
c5b7014a
S
2959 if not isinstance(sources, list):
2960 sources = [sources]
63d990d2
S
2961 formats = []
2962 for source in sources:
2963 src = source.get('src')
2964 if not src or not isinstance(src, compat_str):
2965 continue
2966 src = compat_urlparse.urljoin(url, src)
2967 src_type = source.get('type')
2968 if isinstance(src_type, compat_str):
2969 src_type = src_type.lower()
2970 ext = determine_ext(src).lower()
2971 if src_type == 'video/youtube':
2972 return self.url_result(src, YoutubeIE.ie_key())
2973 if src_type == 'application/dash+xml' or ext == 'mpd':
2974 formats.extend(self._extract_mpd_formats(
2975 src, video_id, mpd_id='dash', fatal=False))
2976 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
2977 formats.extend(self._extract_m3u8_formats(
2978 src, video_id, 'mp4', entry_protocol='m3u8_native',
2979 m3u8_id='hls', fatal=False))
2980 else:
2981 formats.append({
2982 'url': src,
2983 'ext': (mimetype2ext(src_type) or
2984 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
2985 })
2986 if formats:
2987 self._sort_formats(formats)
2988 info_dict['formats'] = formats
2989 return info_dict
2990
ff17be3a
S
2991 # Looking for http://schema.org/VideoObject
2992 json_ld = self._search_json_ld(
2993 webpage, video_id, default={}, expected_type='VideoObject')
2994 if json_ld.get('url'):
2995 return merge_dicts(json_ld, info_dict)
2996
ced659bb 2997 def check_video(vurl):
a0f71985
PH
2998 if YoutubeIE.suitable(vurl):
2999 return True
b7a8c1bc
S
3000 if RtmpIE.suitable(vurl):
3001 return True
ced659bb
S
3002 vpath = compat_urlparse.urlparse(vurl).path
3003 vext = determine_ext(vpath)
0ee79a37 3004 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
3005
3006 def filter_video(urls):
3007 return list(filter(check_video, urls))
3008
9b122384 3009 # Start with something easy: JW Player in SWFObject
ced659bb 3010 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 3011 if not found:
d981cef6 3012 # Look for gorilla-vid style embedding
ced659bb 3013 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
3014 (?:
3015 jw_plugins|
3016 JWPlayerOptions|
3017 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3018 )
a0f71985
PH
3019 .*?
3020 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 3021 if not found:
9b122384 3022 # Broaden the search a little bit
ced659bb 3023 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
3024 if not found:
3025 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 3026 found = filter_video(re.findall(
54a9328b 3027 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
3028 if not found:
3029 # Flow player
ced659bb 3030 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
3031 flowplayer\("[^"]+",\s*
3032 \{[^}]+?\}\s*,
52585fd6 3033 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 3034 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 3035 ''', webpage))
501f13fb
PH
3036 if not found:
3037 # Cinerama player
3038 found = re.findall(
3039 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 3040 if not found:
9b122384 3041 # Try to find twitter cards info
371ddb14
S
3042 # twitter:player:stream should be checked before twitter:player since
3043 # it is expected to contain a raw stream (see
3044 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3045 found = filter_video(re.findall(
3046 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 3047 if not found:
9b122384
PH
3048 # We look for Open Graph info:
3049 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3050 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3051 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3052 if m_video_type is not None:
ced659bb 3053 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 3054 if not found:
ed9a25dd 3055 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3056 found = re.search(
89ef304b 3057 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3058 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3059 webpage)
84f81016
S
3060 if not found:
3061 # Look also in Refresh HTTP header
3062 refresh_header = head_response.headers.get('Refresh')
3063 if refresh_header:
6c91a5a7
S
3064 # In python 2 response HTTP headers are bytestrings
3065 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3066 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3067 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3068 if found:
b37317d8 3069 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3070 if new_url != url:
3071 self.report_following_redirect(new_url)
3072 return {
3073 '_type': 'url',
3074 'url': new_url,
3075 }
3076 else:
3077 found = None
371ddb14
S
3078
3079 if not found:
3080 # twitter:player is a https URL to iframe player that may or may not
3081 # be supported by youtube-dl thus this is checked the very last (see
3082 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3083 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3084 if embed_url and embed_url != url:
371ddb14
S
3085 return self.url_result(embed_url)
3086
b30b8698 3087 if not found:
416c7fcb 3088 raise UnsupportedError(url)
9b122384 3089
b30b8698 3090 entries = []
4a120778 3091 for video_url in orderedSet(found):
949b6497 3092 video_url = unescapeHTML(video_url)
6cc37c69 3093 video_url = video_url.replace('\\/', '/')
b30b8698 3094 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3095 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3096
b30b8698
PH
3097 # Sometimes, jwplayer extraction will result in a YouTube URL
3098 if YoutubeIE.suitable(video_url):
3099 entries.append(self.url_result(video_url, 'Youtube'))
3100 continue
9b122384 3101
b30b8698
PH
3102 # here's a fun little line of code for you:
3103 video_id = os.path.splitext(video_id)[0]
fc9713a1 3104
28602e74
YCH
3105 entry_info_dict = {
3106 'id': video_id,
3107 'uploader': video_uploader,
3108 'title': video_title,
3109 'age_limit': age_limit,
3110 }
3111
5620f840
S
3112 if RtmpIE.suitable(video_url):
3113 entry_info_dict.update({
3114 '_type': 'url_transparent',
3115 'ie_key': RtmpIE.ie_key(),
3116 'url': video_url,
3117 })
3118 entries.append(entry_info_dict)
3119 continue
3120
729accb4
S
3121 ext = determine_ext(video_url)
3122 if ext == 'smil':
28602e74 3123 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
3124 elif ext == 'xspf':
3125 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
3126 elif ext == 'm3u8':
3127 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
3128 elif ext == 'mpd':
3129 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
3130 elif ext == 'f4m':
3131 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3132 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3133 # Just matching .ism/manifest is not enough to be reliably sure
3134 # whether it's actually an ISM manifest or some other streaming
3135 # manifest since there are various streaming URL formats
3136 # possible (see [1]) as well as some other shenanigans like
3137 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3138 # so on.
3139 # Thus the most reasonable way to solve this is to delegate
3140 # to generic extractor in order to look into the contents of
3141 # the manifest itself.
3142 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3143 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3144 entry_info_dict = self.url_result(
3145 smuggle_url(video_url, {'to_generic': True}),
3146 GenericIE.ie_key())
d6fd958c 3147 else:
28602e74
YCH
3148 entry_info_dict['url'] = video_url
3149
19dbaeec
S
3150 if entry_info_dict.get('formats'):
3151 self._sort_formats(entry_info_dict['formats'])
3152
28602e74 3153 entries.append(entry_info_dict)
b30b8698
PH
3154
3155 if len(entries) == 1:
669f0e7c 3156 return entries[0]
b30b8698
PH
3157 else:
3158 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3159 # 'url' results don't have a title
3160 if e.get('title') is not None:
3161 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3162 return {
3163 '_type': 'playlist',
3164 'entries': entries,
3165 }