]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
[JWPlatform] Support iframes
[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 {
1102 'url': 'http://www.suffolk.edu/sjc/',
1103 'info_dict': {
1104 'id': 'sjclive',
1105 'ext': 'flv',
1106 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1107 'uploader': 'www.suffolk.edu',
1108 },
1109 'params': {
1110 'skip_download': True,
2637fadc
RA
1111 },
1112 'skip': 'does not contain a video anymore',
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 },
1150 },
63d990d2 1151 {
c5b7014a 1152 # Video.js embed, multiple formats
63d990d2
S
1153 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1154 'info_dict': {
1155 'id': 'yygqldloqIk',
1156 'ext': 'mp4',
1157 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1158 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1159 'upload_date': '20130314',
1160 'uploader': 'PROстое3D',
1161 'uploader_id': 'PROstoe3D',
1162 },
1163 'params': {
1164 'skip_download': True,
1165 },
1166 },
c5b7014a
S
1167 {
1168 # Video.js embed, single format
1169 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1170 'info_dict': {
1171 'id': 'watch',
1172 'ext': 'mp4',
1173 'title': 'Step 1 - Good Foundation',
1174 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1175 },
1176 'params': {
1177 'skip_download': True,
1178 },
1179 },
59b8ab58
PH
1180 # rtl.nl embed
1181 {
1182 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1183 'playlist_mincount': 5,
1184 'info_dict': {
1185 'id': 'aanslagen-kopenhagen',
2637fadc 1186 'title': 'Aanslagen Kopenhagen',
59b8ab58 1187 }
255fca5e
S
1188 },
1189 # Zapiks embed
1190 {
1191 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1192 'info_dict': {
1193 'id': '118046',
1194 'ext': 'mp4',
1195 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1196 }
1197 },
66e568de
S
1198 # Kaltura embed (different embed code)
1199 {
1200 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1201 'info_dict': {
1202 'id': '1_a52wc67y',
1203 'ext': 'flv',
1204 'upload_date': '20150127',
1205 'uploader_id': 'PremierMedia',
1206 'timestamp': int,
1207 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1208 },
1209 },
87703231
YCH
1210 # Kaltura embed with single quotes
1211 {
1212 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1213 'info_dict': {
1214 'id': '0_izeg5utt',
1215 'ext': 'mp4',
1216 'title': '35871',
1217 'timestamp': 1355743100,
1218 'upload_date': '20121217',
1219 'uploader_id': 'batchUser',
1220 },
1221 'add_ie': ['Kaltura'],
1222 },
427cd050
S
1223 {
1224 # Kaltura embedded via quoted entry_id
1225 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1226 'info_dict': {
1227 'id': '0_utuok90b',
1228 'ext': 'mp4',
1229 'title': '06_matthew_brender_raj_dutt',
1230 'timestamp': 1466638791,
1231 'upload_date': '20160622',
1232 },
1233 'add_ie': ['Kaltura'],
1234 'expected_warnings': [
1235 'Could not send HEAD request'
1236 ],
1237 'params': {
1238 'skip_download': True,
1239 }
1240 },
8ab7e6c4
YCH
1241 {
1242 # Kaltura embedded, some fileExt broken (#11480)
1243 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1244 'info_dict': {
1245 'id': '1_sgtvehim',
1246 'ext': 'mp4',
1247 'title': 'Our "Standard Models" of particle physics and cosmology',
1248 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1249 'timestamp': 1321158993,
1250 'upload_date': '20111113',
1251 'uploader_id': 'kps1',
1252 },
1253 'add_ie': ['Kaltura'],
1254 },
a01825a5
JH
1255 {
1256 # Kaltura iframe embed
1257 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1258 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1259 'info_dict': {
1260 'id': '0_f2cfbpwy',
1261 'ext': 'mp4',
1262 'title': 'I. M. Pei: A Centennial Celebration',
1263 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1264 'upload_date': '20170403',
1265 'uploader_id': 'batchUser',
1266 'timestamp': 1491232186,
1267 },
1268 'add_ie': ['Kaltura'],
1269 },
665e9452 1270 # EaglePlatform embed (generic URL)
135c9c42
S
1271 {
1272 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
4645432d 1273 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
135c9c42
S
1274 'info_dict': {
1275 'id': '227304',
1276 'ext': 'mp4',
1277 'title': 'Навальный вышел на свободу',
1278 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
ec85ded8 1279 'thumbnail': r're:^https?://.*\.jpg$',
135c9c42
S
1280 'duration': 87,
1281 'view_count': int,
1282 'age_limit': 0,
1283 },
250b042c
S
1284 'params': {
1285 'skip_download': True,
1286 },
1287 },
1288 # referrer protected EaglePlatform embed
1289 {
1290 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1291 'info_dict': {
1292 'id': '582306',
1293 'ext': 'mp4',
1294 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1295 'thumbnail': r're:^https?://.*\.jpg$',
1296 'duration': 3382,
1297 'view_count': int,
1298 },
1299 'params': {
1300 'skip_download': True,
1301 },
135c9c42 1302 },
665e9452 1303 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1304 {
1305 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1306 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1307 'info_dict': {
1308 'id': '12820',
1309 'ext': 'mp4',
1310 'title': "'O Sole Mio",
ec85ded8 1311 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1312 'duration': 216,
1313 'view_count': int,
1314 },
250b042c
S
1315 'params': {
1316 'skip_download': True,
1317 },
2637fadc 1318 'skip': 'This video is unavailable.',
d47ae7f6 1319 },
f8388757
S
1320 # Pladform embed
1321 {
1322 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1323 'info_dict': {
1324 'id': '100183293',
1325 'ext': 'mp4',
62259846 1326 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1327 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1328 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1329 'duration': 694,
1330 'age_limit': 0,
1331 },
2637fadc 1332 'skip': 'HTTP Error 404: Not Found',
f8388757 1333 },
c798f15b
S
1334 # Playwire embed
1335 {
1336 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1337 'info_dict': {
1338 'id': '3519514',
1339 'ext': 'mp4',
1340 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1341 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1342 'duration': 45.115,
1343 },
1344 },
ad320e9b
NJ
1345 # 5min embed
1346 {
1347 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1348 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1349 'info_dict': {
1350 'id': '518726732',
1351 'ext': 'mp4',
1352 'title': 'Facebook Creates "On This Day" | Crunch Report',
2637fadc
RA
1353 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1354 'timestamp': 1427237531,
1355 'uploader': 'Crunch Report',
1356 'upload_date': '20150324',
1357 },
1358 'params': {
1359 # m3u8 download
1360 'skip_download': True,
ad320e9b
NJ
1361 },
1362 },
dc455a5f
S
1363 # SVT embed
1364 {
1365 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1366 'info_dict': {
1367 'id': '2900353',
1368 'ext': 'flv',
1369 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1370 'duration': 27,
1371 'age_limit': 0,
1372 },
1373 },
a4257017
S
1374 # Crooks and Liars embed
1375 {
1376 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1377 'info_dict': {
1378 'id': '8RUoRhRi',
1379 'ext': 'mp4',
1380 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1381 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1382 'timestamp': 1428207000,
1383 'upload_date': '20150405',
1384 'uploader': 'Heather',
1385 },
1386 },
1387 # Crooks and Liars external embed
1388 {
1389 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1390 'info_dict': {
1391 'id': 'MTE3MjUtMzQ2MzA',
1392 'ext': 'mp4',
1393 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1394 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1395 'timestamp': 1265032391,
1396 'upload_date': '20100201',
1397 'uploader': 'Heather',
1398 },
1399 },
facecb84 1400 # NBC Sports vplayer embed
a2edf2e7 1401 {
facecb84 1402 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1403 'info_dict': {
facecb84
S
1404 'id': 'ln7x1qSThw4k',
1405 'ext': 'flv',
1406 'title': "PFT Live: New leader in the 'new-look' defense",
1407 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1408 'uploader': 'NBCU-SPORTS',
1409 'upload_date': '20140107',
1410 'timestamp': 1389118457,
a2edf2e7 1411 },
2637fadc 1412 'skip': 'Invalid Page URL',
418c5cc3 1413 },
de3eb07e
YCH
1414 # NBC News embed
1415 {
1416 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1417 'md5': '1aa589c675898ae6d37a17913cf68d66',
1418 'info_dict': {
2637fadc 1419 'id': 'x_dtl_oa_LettermanliftPR_160608',
de3eb07e 1420 'ext': 'mp4',
2637fadc 1421 'title': 'David Letterman: A Preview',
de3eb07e 1422 '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
1423 'upload_date': '20160609',
1424 'timestamp': 1465431544,
1425 'uploader': 'NBCU-NEWS',
de3eb07e
YCH
1426 },
1427 },
418c5cc3
YCH
1428 # UDN embed
1429 {
811586eb 1430 'url': 'https://video.udn.com/news/300346',
01c58f84 1431 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1432 'info_dict': {
01c58f84 1433 'id': '300346',
418c5cc3 1434 'ext': 'mp4',
01c58f84 1435 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1436 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1437 },
1438 'params': {
1439 # m3u8 download
1440 'skip_download': True,
1441 },
2637fadc 1442 'expected_warnings': ['Failed to parse JSON Expecting value'],
edfcf7ab
YCH
1443 },
1444 # Ooyala embed
1445 {
1446 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1447 'info_dict': {
1448 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1449 'ext': 'mp4',
2637fadc 1450 'description': 'Index/Match versus VLOOKUP.',
edfcf7ab 1451 'title': 'This is what separates the Excel masters from the wannabes',
53e06b25 1452 'duration': 191.933,
edfcf7ab
YCH
1453 },
1454 'params': {
1455 # m3u8 downloads
1456 'skip_download': True,
1457 }
d6fd958c 1458 },
b26733ba
YCH
1459 # Brightcove URL in single quotes
1460 {
1461 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1462 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1463 'info_dict': {
1464 'id': '4255764656001',
1465 'ext': 'mp4',
1466 'title': 'SN Presents: Russell Martin, World Citizen',
1467 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1468 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1469 'uploader_id': '1704050871',
1470 'upload_date': '20150525',
1471 'timestamp': 1432570283,
b26733ba 1472 },
756f574e
YCH
1473 },
1474 # Dailymotion Cloud video
1475 {
1476 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
7d52c052 1477 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
756f574e 1478 'info_dict': {
7d52c052 1479 'id': 'x2uy8t3',
756f574e 1480 'ext': 'mp4',
7d52c052
YCH
1481 'title': 'Sauvons les abeilles ! - Le débat',
1482 'description': 'md5:d9082128b1c5277987825d684939ca26',
ec85ded8 1483 'thumbnail': r're:^https?://.*\.jpe?g$',
7d52c052
YCH
1484 'timestamp': 1434970506,
1485 'upload_date': '20150622',
1486 'uploader': 'Public Sénat',
1487 'uploader_id': 'xa9gza',
2637fadc
RA
1488 },
1489 'skip': 'File not found.',
a5158f38 1490 },
8084be78
S
1491 # OnionStudios embed
1492 {
1493 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1494 'info_dict': {
1495 'id': '2855',
1496 'ext': 'mp4',
1497 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
ec85ded8 1498 'thumbnail': r're:^https?://.*\.jpe?g$',
8084be78
S
1499 'uploader': 'ClickHole',
1500 'uploader_id': 'clickhole',
1501 }
1502 },
b8c1cc1a
S
1503 # SnagFilms embed
1504 {
1505 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1506 'info_dict': {
1507 'id': '74849a00-85a9-11e1-9660-123139220831',
1508 'ext': 'mp4',
1509 'title': '#whilewewatch',
1510 }
1511 },
a5158f38
YCH
1512 # AdobeTVVideo embed
1513 {
1514 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1515 'md5': '43662b577c018ad707a63766462b1e87',
1516 'info_dict': {
1517 'id': '2456',
1518 'ext': 'mp4',
1519 'title': 'New experience with Acrobat DC',
1520 'description': 'New experience with Acrobat DC',
1521 'duration': 248.667,
1522 },
1f812580 1523 },
ed126900 1524 # BrightcoveInPageEmbed embed
1525 {
1526 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1527 'info_dict': {
1528 'id': '4238694884001',
1529 'ext': 'flv',
1530 'title': 'Tabletop: Dread, Last Thoughts',
1531 'description': 'Tabletop: Dread, Last Thoughts',
1532 'duration': 51690,
1533 },
750b9ff0 1534 },
d10fe835
YCH
1535 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1536 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1537 {
1538 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1539 'info_dict': {
1540 'id': '4785848093001',
1541 'ext': 'mp4',
1542 'title': 'The Cardinal Pell Interview',
1543 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1544 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1545 'uploader_id': '2733773828001',
1546 'upload_date': '20160304',
1547 'timestamp': 1457083087,
d10fe835
YCH
1548 },
1549 'params': {
1550 # m3u8 downloads
1551 'skip_download': True,
1552 },
1553 },
9edf47df
S
1554 {
1555 # Brightcove embed with whitespace around attribute names
1556 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1557 'info_dict': {
1558 'id': '3167554373001',
1559 'ext': 'mp4',
1560 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1561 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1562 'uploader_id': '1079349493',
1563 'upload_date': '20140207',
1564 'timestamp': 1391810548,
1565 },
1566 'params': {
1567 'skip_download': True,
1568 },
1569 },
134c207e
YCH
1570 # Another form of arte.tv embed
1571 {
1572 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1573 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1574 'info_dict': {
1575 'id': '030273-562_PLUS7-F',
1576 'ext': 'mp4',
1577 'title': 'ARTE Reportage - Nulle part, en France',
1578 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1579 'upload_date': '20160409',
1580 },
1581 },
b8f67449
KM
1582 # LiveLeak embed
1583 {
1584 'url': 'http://www.wykop.pl/link/3088787/',
09747ba7 1585 'md5': '7619da8c820e835bef21a1efa2a0fc71',
b8f67449
KM
1586 'info_dict': {
1587 'id': '874_1459135191',
1588 'ext': 'mp4',
1589 'title': 'Man shows poor quality of new apartment building',
1590 'description': 'The wall is like a sand pile.',
1591 'uploader': 'Lake8737',
09747ba7
YCH
1592 },
1593 'add_ie': [LiveLeakIE.ie_key()],
1594 },
1595 # Another LiveLeak embed pattern (#13336)
1596 {
1597 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1598 'info_dict': {
1599 'id': '2eb_1496309988',
1600 'ext': 'mp4',
1601 'title': 'Thief robs place where everyone was armed',
1602 'description': 'md5:694d73ee79e535953cf2488562288eee',
1603 'uploader': 'brazilwtf',
1604 },
1605 'add_ie': [LiveLeakIE.ie_key()],
b8f67449 1606 },
4a120778
YCH
1607 # Duplicated embedded video URLs
1608 {
1609 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1610 'info_dict': {
1611 'id': '149298443_480_16c25b74_2',
1612 'ext': 'mp4',
1613 'title': 'vs. Blue Orange Spring Game',
1614 'uploader': 'www.hudl.com',
1615 },
1616 },
371ddb14
S
1617 # twitter:player:stream embed
1618 {
1619 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1620 'info_dict': {
1621 'id': 'master',
1622 'ext': 'mp4',
1623 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1624 'uploader': 'www.rtl.be',
1625 },
1626 'params': {
1627 # m3u8 downloads
1628 'skip_download': True,
1629 },
1630 },
32917907
RA
1631 # twitter:player embed
1632 {
1633 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1634 'md5': 'a3e0df96369831de324f0778e126653c',
1635 'info_dict': {
1636 'id': '4909620399001',
1637 'ext': 'mp4',
1638 'title': 'What Do Black Holes Sound Like?',
1639 'description': 'what do black holes sound like',
1640 'upload_date': '20160524',
1641 'uploader_id': '29913724001',
1642 'timestamp': 1464107587,
1643 'uploader': 'TheAtlantic',
1644 },
1645 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1646 },
1647 # Facebook <iframe> embed
1648 {
1649 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1650 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1651 'info_dict': {
1652 'id': '599637780109885',
1653 'ext': 'mp4',
1654 'title': 'Facebook video #599637780109885',
1655 },
1656 },
fd1c5fba
S
1657 # Facebook <iframe> embed, plugin video
1658 {
1659 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1660 'info_dict': {
1661 'id': '1754168231264132',
1662 'ext': 'mp4',
1663 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1664 'uploader': 'Tariq Ramadan (official)',
1665 'timestamp': 1496758379,
1666 'upload_date': '20170606',
1667 },
1668 'params': {
1669 'skip_download': True,
1670 },
1671 },
fd6ca382
YCH
1672 # Facebook API embed
1673 {
1674 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1675 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1676 'info_dict': {
1677 'id': '10153467542406923',
1678 'ext': 'mp4',
1679 'title': 'Facebook video #10153467542406923',
1680 },
7deef1ba
YCH
1681 },
1682 # Wordpress "YouTube Video Importer" plugin
1683 {
1684 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1685 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1686 'info_dict': {
1687 'id': 'HNTXWDXV9Is',
1688 'ext': 'mp4',
1689 'title': 'Blue Devils Drumline Stanford lot 2016',
1690 'upload_date': '20160627',
1691 'uploader_id': 'GENOCIDE8GENERAL10',
1692 'uploader': 'cylus cyrus',
1693 },
1694 },
81953d1a
RA
1695 {
1696 # video stored on custom kaltura server
1697 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1698 'md5': '537617d06e64dfed891fa1593c4b30cc',
1699 'info_dict': {
1700 'id': '0_1iotm5bh',
1701 'ext': 'mp4',
1702 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1703 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1704 'uploader_id': 'videos.expansion@el-mundo.net',
1705 'upload_date': '20150429',
1706 'timestamp': 1430303472,
1707 },
1708 'add_ie': ['Kaltura'],
1709 },
c03adf90
YCH
1710 {
1711 # Non-standard Vimeo embed
1712 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1713 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1714 'info_dict': {
1715 'id': '148867247',
1716 'ext': 'mp4',
1717 'title': 'Understanding the web - Teaser',
1718 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1719 'upload_date': '20151214',
1720 'uploader': 'OpenClassrooms',
1721 'uploader_id': 'openclassrooms',
1722 },
1723 'add_ie': ['Vimeo'],
1724 },
a5ff05df
S
1725 {
1726 # generic vimeo embed that requires original URL passed as Referer
1727 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1728 'only_matching': True,
1729 },
1979969f
S
1730 {
1731 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1732 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1733 'info_dict': {
1734 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1735 'ext': 'mp4',
1736 'title': 'Big Buck Bunny',
1737 'description': 'Royalty free test video',
1738 'timestamp': 1432816365,
1739 'upload_date': '20150528',
1740 'is_live': False,
1741 },
1742 'params': {
1743 'skip_download': True,
1744 },
1745 'add_ie': [ArkenaIE.ie_key()],
1746 },
2a1321a2
S
1747 {
1748 '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/',
1749 'info_dict': {
1750 'id': '1c7141f46c',
1751 'ext': 'mp4',
1752 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1753 },
1754 'params': {
1755 'skip_download': True,
1756 },
1757 'add_ie': [Vbox7IE.ie_key()],
1758 },
b0c8f2e9
DR
1759 {
1760 # DBTV embeds
1761 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1762 'info_dict': {
1763 'id': '43254897',
1764 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1765 },
b0c8f2e9
DR
1766 'playlist_mincount': 3,
1767 },
e186a9ec
S
1768 {
1769 # Videa embeds
1770 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1771 'info_dict': {
1772 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1773 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1774 },
1775 'playlist_mincount': 2,
1776 },
b687c85e
S
1777 {
1778 # 20 minuten embed
1779 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1780 'info_dict': {
1781 'id': '523629',
1782 'ext': 'mp4',
1783 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1784 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1785 },
1786 'params': {
1787 'skip_download': True,
1788 },
1789 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1790 },
1791 {
1792 # VideoPress embed
1793 'url': 'https://en.support.wordpress.com/videopress/',
1794 'info_dict': {
1795 'id': 'OcobLTqC',
1796 'ext': 'm4v',
1797 'title': 'IMG_5786',
1798 'timestamp': 1435711927,
1799 'upload_date': '20150701',
1800 },
1801 'params': {
1802 'skip_download': True,
1803 },
1804 'add_ie': [VideoPressIE.ie_key()],
fef51645 1805 },
eb3079b6
S
1806 {
1807 # Rutube embed
1808 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1809 'info_dict': {
1810 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1811 'ext': 'flv',
1812 'title': 'Магаззино: Казань 2',
1813 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1814 'uploader': 'Магаззино',
1815 'upload_date': '20170228',
1816 'uploader_id': '996642',
1817 },
1818 'params': {
1819 'skip_download': True,
1820 },
1821 'add_ie': [RutubeIE.ie_key()],
1822 },
fef51645
YCH
1823 {
1824 # ThePlatform embedded with whitespaces in URLs
1825 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1826 'only_matching': True,
1827 },
97952bdb
JH
1828 {
1829 # Senate ISVP iframe https
1830 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1831 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1832 'info_dict': {
1833 'id': 'govtaff020316',
1834 'ext': 'mp4',
1835 'title': 'Integrated Senate Video Player',
1836 },
1837 'add_ie': [SenateISVPIE.ie_key()],
1838 },
ab87c260
S
1839 {
1840 # Limelight embeds (1 channel embed + 4 media embeds)
1841 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1842 'info_dict': {
1843 'id': 'FacilitatorTraining2017',
1844 'title': 'Facilitator Training 2017',
1845 },
1846 'playlist_mincount': 5,
1847 },
eb02940c
S
1848 {
1849 # Limelight embed (LimelightPlayerUtil.embed)
1850 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1851 'info_dict': {
1852 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1853 'ext': 'mp4',
1854 'title': '07448641',
1855 'timestamp': 1499890639,
1856 'upload_date': '20170712',
1857 },
1858 'params': {
1859 'skip_download': True,
1860 },
1861 'add_ie': ['LimelightMedia'],
1862 },
7986c3ab
S
1863 {
1864 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1865 'info_dict': {
1866 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1867 'title': 'Standoff with Walnut Creek murder suspect ends',
1868 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1869 },
1870 'playlist_mincount': 4,
1871 },
55719459
JH
1872 {
1873 # WashingtonPost embed
1874 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1875 'info_dict': {
1876 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1877 'ext': 'mp4',
1878 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1879 '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.',
1880 'timestamp': 1455216756,
1881 'uploader': 'The Washington Post',
1882 'upload_date': '20160211',
1883 },
1884 'add_ie': [WashingtonPostIE.ie_key()],
1885 },
2b8e6a68
S
1886 {
1887 # Mediaset embed
1888 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1889 'info_dict': {
1890 'id': '720642',
1891 'ext': 'mp4',
1892 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1893 },
1894 'params': {
1895 'skip_download': True,
1896 },
1897 'add_ie': [MediasetIE.ie_key()],
1898 },
73cf76a9
S
1899 {
1900 # JOJ.sk embeds
1901 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1902 'info_dict': {
1903 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1904 'title': 'Slovenskom sa prehnala vlna silných búrok',
1905 },
1906 'playlist_mincount': 5,
1907 'add_ie': [JojIE.ie_key()],
1908 },
4328ddf8
S
1909 {
1910 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1911 'url': 'https://tvrain.ru/amp/418921/',
1912 'md5': 'cc00413936695987e8de148b67d14f1d',
1913 'info_dict': {
1914 'id': '418921',
1915 'ext': 'mp4',
1916 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1917 },
1918 },
41918eaa 1919 {
1920 # vzaar embed
1663bd6e
S
1921 'url': 'http://help.vzaar.com/article/165-embedding-video',
1922 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1923 'info_dict': {
1663bd6e 1924 'id': '8707641',
41918eaa 1925 'ext': 'mp4',
1663bd6e 1926 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1927 },
1928 },
9ce1ac40 1929 {
1930 # multiple HTML5 videos on one page
1931 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1932 'info_dict': {
1933 'id': 'keyscenarios',
1934 'title': 'Rescue Kit 14 Free Edition - Getting started',
1935 },
1936 'playlist_count': 4,
0987f2dd
T
1937 },
1938 {
1939 # vshare embed
1940 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1941 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1942 'info_dict': {
1943 'id': '0f64ce6',
1944 'title': 'vl14062007715967',
1945 'ext': 'mp4',
1946 }
9ce1ac40 1947 }
6e6b70d6
S
1948 # {
1949 # # TODO: find another test
1950 # # http://schema.org/VideoObject
1951 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1952 # 'md5': '888dcf08b7ea671381f00fab74692755',
1953 # 'info_dict': {
1954 # 'id': 'nyvTSJMKId',
1955 # 'ext': 'mp4',
1956 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1957 # 'description': '#love for cats.',
1958 # 'timestamp': 1461244995,
1959 # 'upload_date': '20160421',
1960 # },
1961 # 'params': {
1962 # 'force_generic_extractor': True,
1963 # },
1964 # }
cfe50f04 1965 ]
9b122384 1966
9b122384
PH
1967 def report_following_redirect(self, new_url):
1968 """Report information extraction."""
79649588 1969 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 1970
4fc946b5
PH
1971 def _extract_rss(self, url, video_id, doc):
1972 playlist_title = doc.find('./channel/title').text
1973 playlist_desc_el = doc.find('./channel/description')
1974 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1975
76c73715
PH
1976 entries = []
1977 for it in doc.findall('./channel/item'):
1978 next_url = xpath_text(it, 'link', fatal=False)
1979 if not next_url:
1980 enclosure_nodes = it.findall('./enclosure')
1981 for e in enclosure_nodes:
1982 next_url = e.attrib.get('url')
1983 if next_url:
1984 break
1985
1986 if not next_url:
1987 continue
1988
1989 entries.append({
413c1f8e 1990 '_type': 'url_transparent',
76c73715
PH
1991 'url': next_url,
1992 'title': it.find('title').text,
1993 })
4fc946b5
PH
1994
1995 return {
1996 '_type': 'playlist',
1997 'id': url,
1998 'title': playlist_title,
1999 'description': playlist_desc,
2000 'entries': entries,
2001 }
2002
c8e9a235
PH
2003 def _extract_camtasia(self, url, video_id, webpage):
2004 """ Returns None if no camtasia video can be found. """
2005
2006 camtasia_cfg = self._search_regex(
2007 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2008 webpage, 'camtasia configuration file', default=None)
2009 if camtasia_cfg is None:
2010 return None
2011
2012 title = self._html_search_meta('DC.title', webpage, fatal=True)
2013
2014 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2015 camtasia_cfg = self._download_xml(
2016 camtasia_url, video_id,
2017 note='Downloading camtasia configuration',
2018 errnote='Failed to download camtasia configuration')
2019 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2020
2021 entries = []
2022 for n in fileset_node.getchildren():
2023 url_n = n.find('./uri')
2024 if url_n is None:
2025 continue
2026
2027 entries.append({
2028 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2029 'title': '%s - %s' % (title, n.tag),
2030 'url': compat_urlparse.urljoin(url, url_n.text),
2031 'duration': float_or_none(n.find('./duration').text),
2032 })
2033
2034 return {
2035 '_type': 'playlist',
2036 'entries': entries,
2037 'title': title,
2038 }
2039
9b122384 2040 def _real_extract(self, url):
ebd3c7b3
PH
2041 if url.startswith('//'):
2042 return {
2043 '_type': 'url',
20991253 2044 'url': self.http_scheme() + url,
ebd3c7b3
PH
2045 }
2046
a7130543
JMF
2047 parsed_url = compat_urlparse.urlparse(url)
2048 if not parsed_url.scheme:
04b4d394
PH
2049 default_search = self._downloader.params.get('default_search')
2050 if default_search is None:
1f7ccb90 2051 default_search = 'fixup_error'
04b4d394 2052
1f7ccb90 2053 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
2054 if '/' in url:
2055 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2056 return self.url_result('http://' + url)
1f7ccb90 2057 elif default_search != 'fixup_error':
9c1fc022 2058 if default_search == 'auto_warning':
0e67ab0d
PH
2059 if re.match(r'^(?:url|URL)$', url):
2060 raise ExtractorError(
2061 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2062 expected=True)
2063 else:
2064 self._downloader.report_warning(
7571c02c 2065 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2066 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2067
2068 if default_search in ('error', 'fixup_error'):
7571c02c 2069 raise ExtractorError(
b74e86f4
PH
2070 '%r is not a valid URL. '
2071 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2072 % (url, url), expected=True)
04b4d394 2073 else:
f2f2c0c2
PH
2074 if ':' not in default_search:
2075 default_search += ':'
04b4d394 2076 return self.url_result(default_search + url)
4d54ef20
PH
2077
2078 url, smuggled_data = unsmuggle_url(url)
2079 force_videoid = None
d6e6a422 2080 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2081 if smuggled_data and 'force_videoid' in smuggled_data:
2082 force_videoid = smuggled_data['force_videoid']
2083 video_id = force_videoid
2084 else:
9dcd6fd3 2085 video_id = self._generic_id(url)
3d83a1ae 2086
79649588 2087 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2088
ebab4520 2089 head_req = HEADRequest(url)
23be51d8 2090 head_response = self._request_webpage(
ebab4520
PH
2091 head_req, video_id,
2092 note=False, errnote='Could not send HEAD request to %s' % url,
2093 fatal=False)
42393ce2 2094
23be51d8 2095 if head_response is not False:
42393ce2 2096 # Check for redirect
5551d771 2097 new_url = compat_str(head_response.geturl())
42393ce2
PH
2098 if url != new_url:
2099 self.report_following_redirect(new_url)
4d54ef20
PH
2100 if force_videoid:
2101 new_url = smuggle_url(
2102 new_url, {'force_videoid': force_videoid})
cecaaf3f 2103 return self.url_result(new_url)
42393ce2 2104
23be51d8
PH
2105 full_response = None
2106 if head_response is False:
5c2266df 2107 request = sanitized_Request(url)
58bde34a
S
2108 request.add_header('Accept-Encoding', '*')
2109 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2110 head_response = full_response
2111
f930e0c7
S
2112 info_dict = {
2113 'id': video_id,
9dcd6fd3 2114 'title': self._generic_title(url),
303dcdb9 2115 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
2116 }
2117
23be51d8 2118 # Check for direct link to a video
955737b2 2119 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2120 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2121 if m:
4e363703 2122 format_id = compat_str(m.group('format_id'))
f930e0c7 2123 if format_id.endswith('mpegurl'):
eadc3ccd 2124 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
2125 elif format_id == 'f4m':
2126 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2127 else:
2128 formats = [{
4e363703 2129 'format_id': format_id,
eadc3ccd 2130 'url': url,
2131 'vcodec': 'none' if m.group('type') == 'audio' else None
2132 }]
de6c51e8 2133 info_dict['direct'] = True
19dbaeec 2134 self._sort_formats(formats)
de6c51e8 2135 info_dict['formats'] = formats
f930e0c7 2136 return info_dict
42393ce2 2137
d6e6a422 2138 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
2139 force = self._downloader.params.get('force_generic_extractor', False)
2140 self._downloader.report_warning(
2141 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2142
4e262a88 2143 if not full_response:
5c2266df 2144 request = sanitized_Request(url)
58bde34a
S
2145 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2146 # making it impossible to download only chunk of the file (yet we need only 512kB to
2147 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2148 # that will always result in downloading the whole file that is not desirable.
2149 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2150 # to accept raw bytes and being able to download only a chunk.
2151 # It may probably better to solve this by checking Content-Type for application/octet-stream
2152 # after HEAD request finishes, but not sure if we can rely on this.
2153 request.add_header('Accept-Encoding', '*')
2154 full_response = self._request_webpage(request, video_id)
4e262a88 2155
5940862d
S
2156 first_bytes = full_response.read(512)
2157
2158 # Is it an M3U playlist?
0d769bcb 2159 if first_bytes.startswith(b'#EXTM3U'):
5940862d 2160 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 2161 self._sort_formats(info_dict['formats'])
5940862d
S
2162 return info_dict
2163
4e262a88
PH
2164 # Maybe it's a direct link to a video?
2165 # Be careful not to download the whole thing!
61ca9a80 2166 if not is_html(first_bytes):
4e262a88
PH
2167 self._downloader.report_warning(
2168 'URL could be a direct video link, returning it as such.')
f930e0c7 2169 info_dict.update({
4e262a88
PH
2170 'direct': True,
2171 'url': url,
f930e0c7
S
2172 })
2173 return info_dict
4e262a88
PH
2174
2175 webpage = self._webpage_read_content(
2176 full_response, url, video_id, prefix=first_bytes)
2177
9b122384 2178 self.report_extraction(video_id)
887c6acd 2179
1b840245 2180 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2181 try:
f7854627 2182 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
2183 if doc.tag == 'rss':
2184 return self._extract_rss(url, video_id, doc)
cc99a77a
S
2185 elif doc.tag == 'SmoothStreamingMedia':
2186 info_dict['formats'] = self._parse_ism_formats(doc, url)
2187 self._sort_formats(info_dict['formats'])
2188 return info_dict
e5e8d20a 2189 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
2190 smil = self._parse_smil(doc, url, video_id)
2191 self._sort_formats(smil['formats'])
2192 return smil
729accb4
S
2193 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2194 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1b840245 2195 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7 2196 info_dict['formats'] = self._parse_mpd_formats(
86f4d14f 2197 doc, video_id,
5551d771 2198 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
86f4d14f 2199 mpd_url=url)
19dbaeec 2200 self._sort_formats(info_dict['formats'])
f930e0c7
S
2201 return info_dict
2202 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2203 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 2204 self._sort_formats(info_dict['formats'])
f930e0c7 2205 return info_dict
f7300c5c 2206 except compat_xml_parse_error:
4fc946b5
PH
2207 pass
2208
c8e9a235
PH
2209 # Is it a Camtasia project?
2210 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2211 if camtasia_res is not None:
2212 return camtasia_res
2213
14390730
S
2214 # Sometimes embedded video player is hidden behind percent encoding
2215 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2216 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 2217 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2218
887c6acd
PH
2219 # it's tempting to parse this further, but you would
2220 # have to take into account all the variations like
2221 # Video Title - Site Name
2222 # Site Name | Video Title
2223 # Video Title - Tagline | Site Name
2224 # and so on and so forth; it's just not practical
6f41b2bc
S
2225 video_title = self._og_search_title(
2226 webpage, default=None) or self._html_search_regex(
79649588
PH
2227 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2228 default='video')
ef4fd848 2229
4d805e06
PH
2230 # Try to detect age limit automatically
2231 age_limit = self._rta_search(webpage)
2232 # And then there are the jokers who advertise that they use RTA,
2233 # but actually don't.
2234 AGE_LIMIT_MARKERS = [
197224b7 2235 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
4d805e06
PH
2236 ]
2237 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2238 age_limit = 18
2239
ef4fd848
PH
2240 # video uploader is domain name
2241 video_uploader = self._search_regex(
79649588 2242 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2243
6f41b2bc
S
2244 video_description = self._og_search_description(webpage, default=None)
2245 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2246
b311b0ea
S
2247 info_dict.update({
2248 'title': video_title,
2249 'description': video_description,
2250 'thumbnail': video_thumbnail,
2251 'age_limit': age_limit,
2252 })
2253
1f4b722b 2254 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2255 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2256 if bc_urls:
99877772
PH
2257 entries = [{
2258 '_type': 'url',
2259 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2260 'ie_key': 'BrightcoveLegacy'
99877772
PH
2261 } for bc_url in bc_urls]
2262
2263 return {
2264 '_type': 'playlist',
2265 'title': video_title,
2266 'id': video_id,
2267 'entries': entries,
2268 }
cfe50f04 2269
f6519f89 2270 # Look for Brightcove New Studio embeds
0254f93b 2271 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2272 if bc_urls:
46b18f23 2273 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
ed126900 2274
4e826cd9
S
2275 # Look for Nexx embeds
2276 nexx_urls = NexxIE._extract_urls(webpage)
2277 if nexx_urls:
2278 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2279
3f59b015
S
2280 # Look for Nexx iFrame embeds
2281 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2282 if nexx_embed_urls:
2283 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2284
4d8819d2
S
2285 # Look for ThePlatform embeds
2286 tp_urls = ThePlatformIE._extract_urls(webpage)
2287 if tp_urls:
46b18f23 2288 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2289
48a5eabc
S
2290 # Look for Vessel embeds
2291 vessel_urls = VesselIE._extract_urls(webpage)
2292 if vessel_urls:
46b18f23 2293 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
48a5eabc 2294
59b8ab58
PH
2295 # Look for embedded rtl.nl player
2296 matches = re.findall(
2637fadc 2297 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
59b8ab58
PH
2298 webpage)
2299 if matches:
46b18f23 2300 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2301
09b9c45e
S
2302 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2303 if vimeo_urls:
46b18f23 2304 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2305
a1b85269
YCH
2306 vid_me_embed_url = self._search_regex(
2307 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2308 webpage, 'vid.me embed', default=None)
2309 if vid_me_embed_url is not None:
2310 return self.url_result(vid_me_embed_url, 'Vidme')
2311
66c9fa36
S
2312 # Look for YouTube embeds
2313 youtube_urls = YoutubeIE._extract_urls(webpage)
2314 if youtube_urls:
46b18f23 2315 return self.playlist_from_matches(
66c9fa36 2316 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2317
ad213a1d 2318 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2319 if matches:
46b18f23 2320 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2321
8489578d
NJ
2322 # Look for embedded Dailymotion playlist player (#3822)
2323 m = re.search(
2324 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2325 if m:
2326 playlists = re.findall(
2327 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2328 if playlists:
46b18f23
JH
2329 return self.playlist_from_matches(
2330 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2331
71a1db89
S
2332 # Look for DailyMail embeds
2333 dailymail_urls = DailyMailIE._extract_urls(webpage)
2334 if dailymail_urls:
2335 return self.playlist_from_matches(
2336 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2337
ef4fd848 2338 # Look for embedded Wistia player
58bb4402
S
2339 wistia_url = WistiaIE._extract_url(webpage)
2340 if wistia_url:
ef4fd848
PH
2341 return {
2342 '_type': 'url_transparent',
58bb4402
S
2343 'url': self._proto_relative_url(wistia_url),
2344 'ie_key': WistiaIE.ie_key(),
ef4fd848 2345 'uploader': video_uploader,
ef4fd848 2346 }
5f6a1245 2347
bab19a8e
S
2348 # Look for SVT player
2349 svt_url = SVTIE._extract_url(webpage)
2350 if svt_url:
2351 return self.url_result(svt_url, 'SVT')
2352
c19f7764
JMF
2353 # Look for Bandcamp pages with custom domain
2354 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2355 if mobj is not None:
2356 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2357 # Don't set the extractor because it can be a track url or an album
2358 return self.url_result(burl)
c19f7764 2359
f25571ff
PH
2360 # Look for embedded Vevo player
2361 mobj = re.search(
2362 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2363 if mobj is not None:
2364 return self.url_result(mobj.group('url'))
796df3c6
S
2365
2366 # Look for embedded Viddler player
cb454b33
S
2367 mobj = re.search(
2368 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2369 webpage)
796df3c6
S
2370 if mobj is not None:
2371 return self.url_result(mobj.group('url'))
f25571ff 2372
3378d67a
S
2373 # Look for NYTimes player
2374 mobj = re.search(
2375 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2376 webpage)
2377 if mobj is not None:
2378 return self.url_result(mobj.group('url'))
2379
cefdf970
S
2380 # Look for Libsyn player
2381 mobj = re.search(
2382 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2383 if mobj is not None:
2384 return self.url_result(mobj.group('url'))
2385
c0d0b01f 2386 # Look for Ooyala videos
8a37aa15 2387 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 2388 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
198d4cb4 2389 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
2390 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2391 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2392 if mobj is not None:
9837cb75
RA
2393 embed_token = self._search_regex(
2394 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2395 webpage, 'ooyala embed token', default=None)
2396 return OoyalaIE._build_url_result(smuggle_url(
2397 mobj.group('ec'), {
2398 'domain': url,
2399 'embed_token': embed_token,
2400 }))
c0d0b01f 2401
f076b638 2402 # Look for multiple Ooyala embeds on SBN network websites
2403 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2404 if mobj is not None:
2405 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2406 if embeds:
46b18f23
JH
2407 return self.playlist_from_matches(
2408 embeds, video_id, video_title,
2409 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2410
aa94a6d3 2411 # Look for Aparat videos
48099643 2412 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2413 if mobj is not None:
2414 return self.url_result(mobj.group(1), 'Aparat')
2415
c93c2ab1 2416 # Look for MPORA videos
c3f51436 2417 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2418 if mobj is not None:
2419 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2420
15c0e8e7 2421 # Look for embedded NovaMov-based player
8f89e687 2422 mobj = re.search(
8dfa187b 2423 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
2424 (?P<url>http://(?:(?:embed|www)\.)?
2425 (?:novamov\.com|
2426 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2427 videoweed\.(?:es|com)|
2428 movshare\.(?:net|sx|ag)|
2429 divxstage\.(?:eu|net|ch|co|at|ag))
2430 /embed\.php.+?)\1''', webpage)
8f89e687 2431 if mobj is not None:
15c0e8e7 2432 return self.url_result(mobj.group('url'))
50f56607 2433
9834872b 2434 # Look for embedded Facebook player
0646e34c
S
2435 facebook_urls = FacebookIE._extract_urls(webpage)
2436 if facebook_urls:
2437 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2438
ca97a56e
S
2439 # Look for embedded VK player
2440 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2441 if mobj is not None:
2442 return self.url_result(mobj.group('url'), 'VK')
2443
33d4fdab
S
2444 # Look for embedded Odnoklassniki player
2445 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2446 if mobj is not None:
2447 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2448
0364fa8b
S
2449 # Look for embedded ivi player
2450 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2451 if mobj is not None:
2452 return self.url_result(mobj.group('url'), 'Ivi')
2453
db1f3888
PH
2454 # Look for embedded Huffington Post player
2455 mobj = re.search(
c3f51436 2456 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2457 if mobj is not None:
2458 return self.url_result(mobj.group('url'), 'HuffPost')
2459
1b86cc41 2460 # Look for embed.ly
2461 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2462 if mobj is not None:
2463 return self.url_result(mobj.group('url'))
2464 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2465 if mobj is not None:
f7e6f7fa 2466 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2467
60cc4dc4
PH
2468 # Look for funnyordie embed
2469 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2470 if matches:
46b18f23
JH
2471 return self.playlist_from_matches(
2472 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2473
db546cf8
S
2474 # Look for BBC iPlayer embed
2475 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2476 if matches:
46b18f23 2477 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2478
93d020dd
S
2479 # Look for embedded RUTV player
2480 rutv_url = RUTVIE._extract_url(webpage)
2481 if rutv_url:
2482 return self.url_result(rutv_url, 'RUTV')
2483
494f20cb 2484 # Look for embedded TVC player
b8599718
S
2485 tvc_url = TVCIE._extract_url(webpage)
2486 if tvc_url:
2487 return self.url_result(tvc_url, 'TVC')
494f20cb 2488
d40a3b5b
S
2489 # Look for embedded SportBox player
2490 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2491 if sportbox_urls:
46b18f23 2492 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
d40a3b5b 2493
2bb5b6d0
S
2494 # Look for embedded XHamster player
2495 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2496 if xhamster_urls:
46b18f23 2497 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2498
2c9ca782
S
2499 # Look for embedded TNAFlixNetwork player
2500 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2501 if tnaflix_urls:
46b18f23 2502 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2503
b52c9ef1
S
2504 # Look for embedded PornHub player
2505 pornhub_urls = PornHubIE._extract_urls(webpage)
2506 if pornhub_urls:
46b18f23 2507 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2508
37e7a71c
S
2509 # Look for embedded DrTuber player
2510 drtuber_urls = DrTuberIE._extract_urls(webpage)
2511 if drtuber_urls:
46b18f23 2512 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2513
e28ed498
S
2514 # Look for embedded RedTube player
2515 redtube_urls = RedTubeIE._extract_urls(webpage)
2516 if redtube_urls:
46b18f23 2517 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 2518
9872d311
S
2519 # Look for embedded Tvigle player
2520 mobj = re.search(
2521 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2522 if mobj is not None:
2523 return self.url_result(mobj.group('url'), 'Tvigle')
2524
7e2ede98
JMF
2525 # Look for embedded TED player
2526 mobj = re.search(
d7cc31b6 2527 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
2528 if mobj is not None:
2529 return self.url_result(mobj.group('url'), 'TED')
2530
5c386252 2531 # Look for embedded Ustream videos
d77ac737
YCH
2532 ustream_url = UstreamIE._extract_url(webpage)
2533 if ustream_url:
2534 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 2535
893f8832
PH
2536 # Look for embedded arte.tv player
2537 mobj = re.search(
134c207e 2538 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
893f8832
PH
2539 webpage)
2540 if mobj is not None:
2541 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2542
cbd55ade
S
2543 # Look for embedded francetv player
2544 mobj = re.search(
2545 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2546 webpage)
2547 if mobj is not None:
2548 return self.url_result(mobj.group('url'))
2549
cb3ac1c6
S
2550 # Look for embedded smotri.com player
2551 smotri_url = SmotriIE._extract_url(webpage)
2552 if smotri_url:
2553 return self.url_result(smotri_url, 'Smotri')
2554
e6c2d9ad 2555 # Look for embedded Myvi.ru player
6dd94d3a 2556 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
2557 if myvi_url:
2558 return self.url_result(myvi_url)
2559
dfb1b146 2560 # Look for embedded soundcloud player
94aae015
S
2561 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2562 if soundcloud_urls:
46b18f23 2563 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
20991253 2564
027e2312
S
2565 # Look for tunein player
2566 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2567 if tunein_urls:
46b18f23 2568 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 2569
c5cd249e 2570 # Look for embedded mtvservices player
46fde8a1
S
2571 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2572 if mtvservices_url:
2573 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 2574
49807b4a
S
2575 # Look for embedded yahoo player
2576 mobj = re.search(
2577 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2578 webpage)
2579 if mobj is not None:
2580 return self.url_result(mobj.group('url'), 'Yahoo')
2581
2ef6fcb5
PH
2582 # Look for embedded sbs.com.au player
2583 mobj = re.search(
e98b8e79
PH
2584 r'''(?x)
2585 (?:
2586 <meta\s+property="og:video"\s+content=|
2587 <iframe[^>]+?src=
2588 )
2589 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
2590 webpage)
2591 if mobj is not None:
2592 return self.url_result(mobj.group('url'), 'SBS')
2593
42bdd9d0
PH
2594 # Look for embedded Cinchcast player
2595 mobj = re.search(
2596 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2597 webpage)
2598 if mobj is not None:
2599 return self.url_result(mobj.group('url'), 'Cinchcast')
2600
1a94ff68 2601 mobj = re.search(
5263cdfc 2602 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 2603 webpage)
8001607e
YCH
2604 if not mobj:
2605 mobj = re.search(
2606 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2607 webpage)
1a94ff68
S
2608 if mobj is not None:
2609 return self.url_result(mobj.group('url'), 'MLB')
2610
1419fafd 2611 mobj = re.search(
dd467d33 2612 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
2613 webpage)
2614 if mobj is not None:
2615 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2616
af63fed7 2617 mobj = re.search(
78d3b3e2 2618 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
2619 webpage)
2620 if mobj is not None:
2621 return self.url_result(mobj.group('url'), 'Livestream')
2622
255fca5e
S
2623 # Look for Zapiks embed
2624 mobj = re.search(
2625 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2626 if mobj is not None:
2627 return self.url_result(mobj.group('url'), 'Zapiks')
2628
e3216b82 2629 # Look for Kaltura embeds
c287f2bc
S
2630 kaltura_url = KalturaIE._extract_url(webpage)
2631 if kaltura_url:
2632 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
e3216b82 2633
665e9452 2634 # Look for EaglePlatform embeds
06a96da1
S
2635 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2636 if eagleplatform_url:
665e9452 2637 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 2638
665e9452 2639 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
2640 mobj = re.search(
2641 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2642 if mobj is not None:
2643 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2644
f8388757 2645 # Look for Pladform embeds
45dad7ba
S
2646 pladform_url = PladformIE._extract_url(webpage)
2647 if pladform_url:
2648 return self.url_result(pladform_url)
f8388757 2649
ff18735c
S
2650 # Look for Videomore embeds
2651 videomore_url = VideomoreIE._extract_url(webpage)
2652 if videomore_url:
2653 return self.url_result(videomore_url)
2654
83f1481b
S
2655 # Look for Webcaster embeds
2656 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2657 if webcaster_url:
2658 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2659
2dcc114f
S
2660 # Look for Playwire embeds
2661 mobj = re.search(
2662 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2663 if mobj is not None:
2664 return self.url_result(mobj.group('url'))
2665
ad320e9b
NJ
2666 # Look for 5min embeds
2667 mobj = re.search(
2668 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2669 if mobj is not None:
2670 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2671
18153f1b
S
2672 # Look for Crooks and Liars embeds
2673 mobj = re.search(
2674 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2675 if mobj is not None:
2676 return self.url_result(mobj.group('url'))
2677
a2edf2e7
YCH
2678 # Look for NBC Sports VPlayer embeds
2679 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2680 if nbc_sports_url:
2681 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2682
de3eb07e
YCH
2683 # Look for NBC News embeds
2684 nbc_news_embed_url = re.search(
2685 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2686 if nbc_news_embed_url:
2687 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2688
653789af 2689 # Look for Google Drive embeds
5b251628 2690 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 2691 if google_drive_url:
2692 return self.url_result(google_drive_url, 'GoogleDrive')
2693
418c5cc3
YCH
2694 # Look for UDN embeds
2695 mobj = re.search(
2637fadc 2696 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
2697 if mobj is not None:
2698 return self.url_result(
0a160363 2699 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 2700
2fe1b5bd
YCH
2701 # Look for Senate ISVP iframe
2702 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2703 if senate_isvp_url:
25c3a734 2704 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 2705
756f574e
YCH
2706 # Look for Dailymotion Cloud videos
2707 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2708 if dmcloud_url:
2709 return self.url_result(dmcloud_url, 'DailymotionCloud')
2710
1ac1c4c2
S
2711 # Look for OnionStudios embeds
2712 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2713 if onionstudios_url:
2714 return self.url_result(onionstudios_url)
2715
67167920 2716 # Look for ViewLift embeds
2717 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2718 if viewlift_url:
2719 return self.url_result(viewlift_url)
eedd20ef 2720
7cb09524 2721 # Look for JWPlatform embeds
2722 jwplatform_url = JWPlatformIE._extract_url(webpage)
2723 if jwplatform_url:
2724 return self.url_result(jwplatform_url, 'JWPlatform')
2725
aecfcd4e
S
2726 # Look for Digiteka embeds
2727 digiteka_url = DigitekaIE._extract_url(webpage)
2728 if digiteka_url:
2729 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 2730
1979969f
S
2731 # Look for Arkena embeds
2732 arkena_url = ArkenaIE._extract_url(webpage)
2733 if arkena_url:
2734 return self.url_result(arkena_url, ArkenaIE.ie_key())
2735
b1c35797
RA
2736 # Look for Piksel embeds
2737 piksel_url = PikselIE._extract_url(webpage)
2738 if piksel_url:
2739 return self.url_result(piksel_url, PikselIE.ie_key())
2740
1bf996fa 2741 # Look for Limelight embeds
e5d39886
S
2742 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2743 if limelight_urls:
2744 return self.playlist_result(
2745 limelight_urls, video_id, video_title, video_description)
2746
7986c3ab
S
2747 # Look for Anvato embeds
2748 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2749 if anvato_urls:
2750 return self.playlist_result(
2751 anvato_urls, video_id, video_title, video_description)
2752
a5158f38
YCH
2753 # Look for AdobeTVVideo embeds
2754 mobj = re.search(
2755 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2756 webpage)
2757 if mobj is not None:
2758 return self.url_result(
2759 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2760 'AdobeTVVideo')
2761
088e1aac
YCH
2762 # Look for Vine embeds
2763 mobj = re.search(
2764 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2765 webpage)
2766 if mobj is not None:
2767 return self.url_result(
2768 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2769
217d5ae0
RA
2770 # Look for VODPlatform embeds
2771 mobj = re.search(
93b84045 2772 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
217d5ae0
RA
2773 webpage)
2774 if mobj is not None:
2775 return self.url_result(
93b84045 2776 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 2777
7d273a38
RA
2778 # Look for Mangomolo embeds
2779 mobj = re.search(
d05ef09d 2780 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
7d273a38
RA
2781 (?:
2782 video\?.*?\bid=(?P<video_id>\d+)|
2783 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2784 ).+?)\1''', webpage)
2785 if mobj is not None:
2786 info = {
2787 '_type': 'url_transparent',
2788 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2789 'title': video_title,
2790 'description': video_description,
2791 'thumbnail': video_thumbnail,
2792 'uploader': video_uploader,
2793 }
2794 video_id = mobj.group('video_id')
2795 if video_id:
2796 info.update({
2797 'ie_key': 'MangomoloVideo',
2798 'id': video_id,
2799 })
2800 else:
2801 info.update({
2802 'ie_key': 'MangomoloLive',
2803 'id': mobj.group('channel_id'),
2804 })
2805 return info
2806
5a51775a
YCH
2807 # Look for Instagram embeds
2808 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2809 if instagram_embed_url is not None:
11e60fca
S
2810 return self.url_result(
2811 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 2812
b8f67449 2813 # Look for LiveLeak embeds
09747ba7
YCH
2814 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2815 if liveleak_urls:
2816 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
b8f67449 2817
5d39176f
S
2818 # Look for 3Q SDN embeds
2819 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2820 if threeqsdn_url:
6f41b2bc
S
2821 return {
2822 '_type': 'url_transparent',
2823 'ie_key': ThreeQSDNIE.ie_key(),
2824 'url': self._proto_relative_url(threeqsdn_url),
2825 'title': video_title,
2826 'description': video_description,
2827 'thumbnail': video_thumbnail,
2828 'uploader': video_uploader,
2829 }
5d39176f 2830
2a1321a2
S
2831 # Look for VBOX7 embeds
2832 vbox7_url = Vbox7IE._extract_url(webpage)
2833 if vbox7_url:
2834 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2835
b0c8f2e9
DR
2836 # Look for DBTV embeds
2837 dbtv_urls = DBTVIE._extract_urls(webpage)
2838 if dbtv_urls:
46b18f23 2839 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 2840
e186a9ec
S
2841 # Look for Videa embeds
2842 videa_urls = VideaIE._extract_urls(webpage)
2843 if videa_urls:
46b18f23 2844 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 2845
b687c85e
S
2846 # Look for 20 minuten embeds
2847 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2848 if twentymin_urls:
46b18f23
JH
2849 return self.playlist_from_matches(
2850 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 2851
17f8deeb
S
2852 # Look for Openload embeds
2853 openload_urls = OpenloadIE._extract_urls(webpage)
2854 if openload_urls:
46b18f23
JH
2855 return self.playlist_from_matches(
2856 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
17f8deeb 2857
6ef3e65a
S
2858 # Look for VideoPress embeds
2859 videopress_urls = VideoPressIE._extract_urls(webpage)
2860 if videopress_urls:
46b18f23
JH
2861 return self.playlist_from_matches(
2862 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 2863
eb3079b6
S
2864 # Look for Rutube embeds
2865 rutube_urls = RutubeIE._extract_urls(webpage)
2866 if rutube_urls:
46b18f23 2867 return self.playlist_from_matches(
2583c0b5 2868 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 2869
55719459
JH
2870 # Look for WashingtonPost embeds
2871 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2872 if wapo_urls:
2873 return self.playlist_from_matches(
2874 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2875
5d29af3d
S
2876 # Look for Mediaset embeds
2877 mediaset_urls = MediasetIE._extract_urls(webpage)
2878 if mediaset_urls:
2879 return self.playlist_from_matches(
2880 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2881
73cf76a9
S
2882 # Look for JOJ.sk embeds
2883 joj_urls = JojIE._extract_urls(webpage)
2884 if joj_urls:
2885 return self.playlist_from_matches(
2886 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2887
24e966e8
PH
2888 # Look for megaphone.fm embeds
2889 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2890 if mpfn_urls:
2891 return self.playlist_from_matches(
2892 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2893
1663bd6e
S
2894 # Look for vzaar embeds
2895 vzaar_urls = VzaarIE._extract_urls(webpage)
2896 if vzaar_urls:
2897 return self.playlist_from_matches(
2898 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2899
26bae2d9
S
2900 channel9_urls = Channel9IE._extract_urls(webpage)
2901 if channel9_urls:
2902 return self.playlist_from_matches(
2903 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2904
0987f2dd
T
2905 vshare_urls = VShareIE._extract_urls(webpage)
2906 if vshare_urls:
2907 return self.playlist_from_matches(
2908 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2909
b311b0ea
S
2910 def merge_dicts(dict1, dict2):
2911 merged = {}
2912 for k, v in dict1.items():
2913 if v is not None:
2914 merged[k] = v
2915 for k, v in dict2.items():
2916 if v is None:
2917 continue
2918 if (k not in merged or
2919 (isinstance(v, compat_str) and v and
2920 isinstance(merged[k], compat_str) and
2921 not merged[k])):
2922 merged[k] = v
2923 return merged
2924
bd264412
YCH
2925 # Look for HTML5 media
2926 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2927 if entries:
9ce1ac40 2928 if len(entries) == 1:
2929 entries[0].update({
bd264412
YCH
2930 'id': video_id,
2931 'title': video_title,
2932 })
9ce1ac40 2933 else:
2934 for num, entry in enumerate(entries, start=1):
2935 entry.update({
2936 'id': '%s-%s' % (video_id, num),
2937 'title': '%s (%d)' % (video_title, num),
2938 })
2939 for entry in entries:
bd264412 2940 self._sort_formats(entry['formats'])
9ce1ac40 2941 return self.playlist_result(entries, video_id, video_title)
bd264412 2942
c73e330e
RU
2943 jwplayer_data = self._find_jwplayer_data(
2944 webpage, video_id, transform_source=js_to_json)
2945 if jwplayer_data:
4f06c1c9 2946 info = self._parse_jwplayer_data(
3e943cfe 2947 jwplayer_data, video_id, require_title=False, base_url=url)
b311b0ea 2948 return merge_dicts(info, info_dict)
a4a554a7 2949
63d990d2
S
2950 # Video.js embed
2951 mobj = re.search(
c5b7014a 2952 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
2953 webpage)
2954 if mobj is not None:
2955 sources = self._parse_json(
2956 mobj.group(1), video_id, transform_source=js_to_json,
2957 fatal=False) or []
c5b7014a
S
2958 if not isinstance(sources, list):
2959 sources = [sources]
63d990d2
S
2960 formats = []
2961 for source in sources:
2962 src = source.get('src')
2963 if not src or not isinstance(src, compat_str):
2964 continue
2965 src = compat_urlparse.urljoin(url, src)
2966 src_type = source.get('type')
2967 if isinstance(src_type, compat_str):
2968 src_type = src_type.lower()
2969 ext = determine_ext(src).lower()
2970 if src_type == 'video/youtube':
2971 return self.url_result(src, YoutubeIE.ie_key())
2972 if src_type == 'application/dash+xml' or ext == 'mpd':
2973 formats.extend(self._extract_mpd_formats(
2974 src, video_id, mpd_id='dash', fatal=False))
2975 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
2976 formats.extend(self._extract_m3u8_formats(
2977 src, video_id, 'mp4', entry_protocol='m3u8_native',
2978 m3u8_id='hls', fatal=False))
2979 else:
2980 formats.append({
2981 'url': src,
2982 'ext': (mimetype2ext(src_type) or
2983 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
2984 })
2985 if formats:
2986 self._sort_formats(formats)
2987 info_dict['formats'] = formats
2988 return info_dict
2989
ff17be3a
S
2990 # Looking for http://schema.org/VideoObject
2991 json_ld = self._search_json_ld(
2992 webpage, video_id, default={}, expected_type='VideoObject')
2993 if json_ld.get('url'):
2994 return merge_dicts(json_ld, info_dict)
2995
ced659bb 2996 def check_video(vurl):
a0f71985
PH
2997 if YoutubeIE.suitable(vurl):
2998 return True
b7a8c1bc
S
2999 if RtmpIE.suitable(vurl):
3000 return True
ced659bb
S
3001 vpath = compat_urlparse.urlparse(vurl).path
3002 vext = determine_ext(vpath)
0ee79a37 3003 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
3004
3005 def filter_video(urls):
3006 return list(filter(check_video, urls))
3007
9b122384 3008 # Start with something easy: JW Player in SWFObject
ced659bb 3009 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 3010 if not found:
d981cef6 3011 # Look for gorilla-vid style embedding
ced659bb 3012 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
3013 (?:
3014 jw_plugins|
3015 JWPlayerOptions|
3016 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3017 )
a0f71985
PH
3018 .*?
3019 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 3020 if not found:
9b122384 3021 # Broaden the search a little bit
ced659bb 3022 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
3023 if not found:
3024 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 3025 found = filter_video(re.findall(
54a9328b 3026 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
3027 if not found:
3028 # Flow player
ced659bb 3029 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
3030 flowplayer\("[^"]+",\s*
3031 \{[^}]+?\}\s*,
52585fd6 3032 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 3033 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 3034 ''', webpage))
501f13fb
PH
3035 if not found:
3036 # Cinerama player
3037 found = re.findall(
3038 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 3039 if not found:
9b122384 3040 # Try to find twitter cards info
371ddb14
S
3041 # twitter:player:stream should be checked before twitter:player since
3042 # it is expected to contain a raw stream (see
3043 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3044 found = filter_video(re.findall(
3045 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 3046 if not found:
9b122384
PH
3047 # We look for Open Graph info:
3048 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3049 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3050 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3051 if m_video_type is not None:
ced659bb 3052 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 3053 if not found:
ed9a25dd 3054 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3055 found = re.search(
89ef304b 3056 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3057 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3058 webpage)
84f81016
S
3059 if not found:
3060 # Look also in Refresh HTTP header
3061 refresh_header = head_response.headers.get('Refresh')
3062 if refresh_header:
6c91a5a7
S
3063 # In python 2 response HTTP headers are bytestrings
3064 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3065 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3066 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3067 if found:
b37317d8 3068 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3069 if new_url != url:
3070 self.report_following_redirect(new_url)
3071 return {
3072 '_type': 'url',
3073 'url': new_url,
3074 }
3075 else:
3076 found = None
371ddb14
S
3077
3078 if not found:
3079 # twitter:player is a https URL to iframe player that may or may not
3080 # be supported by youtube-dl thus this is checked the very last (see
3081 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3082 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3083 if embed_url and embed_url != url:
371ddb14
S
3084 return self.url_result(embed_url)
3085
b30b8698 3086 if not found:
416c7fcb 3087 raise UnsupportedError(url)
9b122384 3088
b30b8698 3089 entries = []
4a120778 3090 for video_url in orderedSet(found):
949b6497 3091 video_url = unescapeHTML(video_url)
6cc37c69 3092 video_url = video_url.replace('\\/', '/')
b30b8698 3093 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3094 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3095
b30b8698
PH
3096 # Sometimes, jwplayer extraction will result in a YouTube URL
3097 if YoutubeIE.suitable(video_url):
3098 entries.append(self.url_result(video_url, 'Youtube'))
3099 continue
9b122384 3100
b30b8698
PH
3101 # here's a fun little line of code for you:
3102 video_id = os.path.splitext(video_id)[0]
fc9713a1 3103
28602e74
YCH
3104 entry_info_dict = {
3105 'id': video_id,
3106 'uploader': video_uploader,
3107 'title': video_title,
3108 'age_limit': age_limit,
3109 }
3110
5620f840
S
3111 if RtmpIE.suitable(video_url):
3112 entry_info_dict.update({
3113 '_type': 'url_transparent',
3114 'ie_key': RtmpIE.ie_key(),
3115 'url': video_url,
3116 })
3117 entries.append(entry_info_dict)
3118 continue
3119
729accb4
S
3120 ext = determine_ext(video_url)
3121 if ext == 'smil':
28602e74 3122 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
3123 elif ext == 'xspf':
3124 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
3125 elif ext == 'm3u8':
3126 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
3127 elif ext == 'mpd':
3128 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
3129 elif ext == 'f4m':
3130 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3131 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3132 # Just matching .ism/manifest is not enough to be reliably sure
3133 # whether it's actually an ISM manifest or some other streaming
3134 # manifest since there are various streaming URL formats
3135 # possible (see [1]) as well as some other shenanigans like
3136 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3137 # so on.
3138 # Thus the most reasonable way to solve this is to delegate
3139 # to generic extractor in order to look into the contents of
3140 # the manifest itself.
3141 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3142 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3143 entry_info_dict = self.url_result(
3144 smuggle_url(video_url, {'to_generic': True}),
3145 GenericIE.ie_key())
d6fd958c 3146 else:
28602e74
YCH
3147 entry_info_dict['url'] = video_url
3148
19dbaeec
S
3149 if entry_info_dict.get('formats'):
3150 self._sort_formats(entry_info_dict['formats'])
3151
28602e74 3152 entries.append(entry_info_dict)
b30b8698
PH
3153
3154 if len(entries) == 1:
669f0e7c 3155 return entries[0]
b30b8698
PH
3156 else:
3157 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3158 # 'url' results don't have a title
3159 if e.get('title') is not None:
3160 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3161 return {
3162 '_type': 'playlist',
3163 'entries': entries,
3164 }