]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
[xfileshare] Add support for vidto.se (closes #17317)
[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 25 KNOWN_EXTENSIONS,
6cc62232 26 merge_dicts,
63d990d2 27 mimetype2ext,
ed2d6a19 28 orderedSet,
5c2266df 29 sanitized_Request,
9d4660ca
PH
30 smuggle_url,
31 unescapeHTML,
42393ce2 32 unified_strdate,
4d54ef20 33 unsmuggle_url,
416c7fcb 34 UnsupportedError,
3052a30d 35 url_or_none,
76c73715 36 xpath_text,
9b122384 37)
b7a8c1bc 38from .commonprotocols import RtmpIE
ed126900 39from .brightcove import (
4fcaa4f4 40 BrightcoveLegacyIE,
5c17f0a6 41 BrightcoveNewIE,
ed126900 42)
3f59b015
S
43from .nexx import (
44 NexxIE,
45 NexxEmbedIE,
46)
a2edf2e7 47from .nbc import NBCSportsVPlayerIE
c0d0b01f 48from .ooyala import OoyalaIE
93d020dd 49from .rutv import RUTVIE
954c1d05 50from .tvc import TVCIE
d40a3b5b 51from .sportbox import SportBoxEmbedIE
cb3ac1c6 52from .smotri import SmotriIE
6dd94d3a 53from .myvi import MyviIE
1419fafd 54from .condenast import CondeNastIE
418c5cc3 55from .udn import UDNEmbedIE
2fe1b5bd 56from .senateisvp import SenateISVPIE
bab19a8e 57from .svt import SVTIE
65d161c4 58from .pornhub import PornHubIE
2bb5b6d0 59from .xhamster import XHamsterEmbedIE
2c9ca782 60from .tnaflix import TNAFlixNetworkEmbedIE
37e7a71c 61from .drtuber import DrTuberIE
e28ed498 62from .redtube import RedTubeIE
06993715 63from .tube8 import Tube8IE
b407e173 64from .vimeo import VimeoIE
3c4fbfec 65from .dailymotion import DailymotionIE
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
2ca7ed41 106from .mediasite import MediasiteIE
7d540621 107from .springboardplatform import SpringboardPlatformIE
4c780fbd 108from .yapfiles import YapFilesIE
86c8cfc5 109from .vice import ViceIE
178ee883 110from .xfileshare import XFileShareIE
660a230b 111from .cloudflarestream import CloudflareStreamIE
6bd499e8 112from .peertube import PeerTubeIE
aee36ca8 113from .indavideo import IndavideoEmbedIE
cfd7f2a6 114from .apa import APAIE
f51f526b 115from .foxnews import FoxNewsIE
9d1b2138 116from .viqeo import ViqeoIE
57c68ec4 117from .expressen import ExpressenIE
9b122384 118
0838239e 119
9b122384 120class GenericIE(InfoExtractor):
79649588 121 IE_DESC = 'Generic downloader that works on some sites'
9b122384 122 _VALID_URL = r'.*'
79649588 123 IE_NAME = 'generic'
cfe50f04 124 _TESTS = [
c5fa81fe
S
125 # Direct link to a video
126 {
127 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
128 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
129 'info_dict': {
130 'id': 'trailer',
131 'ext': 'mp4',
132 'title': 'trailer',
133 'upload_date': '20100513',
134 }
135 },
c5138a7c 136 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
137 {
138 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
139 'md5': '128c42e68b13950268b648275386fc74',
140 'info_dict': {
141 'id': 'FictionJunction-Parallel_Hearts',
142 'ext': 'flac',
143 'title': 'FictionJunction-Parallel_Hearts',
144 'upload_date': '20140522',
145 },
146 'expected_warnings': [
147 'URL could be a direct video link, returning it as such.'
39efc6e3
YCH
148 ],
149 'skip': 'URL invalid',
c5fa81fe
S
150 },
151 # Direct download with broken HEAD
152 {
153 'url': 'http://ai-radio.org:8000/radio.opus',
154 'info_dict': {
155 'id': 'radio',
156 'ext': 'opus',
157 'title': 'radio',
158 },
159 'params': {
160 'skip_download': True, # infinite live stream
161 },
162 'expected_warnings': [
ef0e4e7b
YCH
163 r'501.*Not Implemented',
164 r'400.*Bad Request',
c5fa81fe
S
165 ],
166 },
167 # Direct link with incorrect MIME type
168 {
169 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
170 'md5': '4ccbebe5f36706d85221f204d7eb5913',
171 'info_dict': {
172 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
173 'id': '5_Lennart_Poettering_-_Systemd',
174 'ext': 'webm',
175 'title': '5_Lennart_Poettering_-_Systemd',
176 'upload_date': '20141120',
177 },
178 'expected_warnings': [
179 'URL could be a direct video link, returning it as such.'
180 ]
181 },
182 # RSS feed
183 {
184 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
185 'info_dict': {
186 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
187 'title': 'Zero Punctuation',
188 'description': 're:.*groundbreaking video review series.*'
189 },
190 'playlist_mincount': 11,
191 },
192 # RSS feed with enclosure
193 {
194 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
195 'info_dict': {
196 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
197 'ext': 'm4v',
198 'upload_date': '20150228',
199 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
200 }
201 },
01aec848
BG
202 # RSS feed with enclosures and unsupported link URLs
203 {
204 'url': 'http://www.hellointernet.fm/podcast?format=rss',
205 'info_dict': {
206 'id': 'http://www.hellointernet.fm/podcast?format=rss',
207 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
208 'title': 'Hello Internet',
209 },
210 'playlist_mincount': 100,
211 },
8765222d
S
212 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
213 {
214 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
215 'info_dict': {
216 'id': 'smil',
217 'ext': 'mp4',
218 'title': 'Automatics, robotics and biocybernetics',
219 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 220 'upload_date': '20130627',
8765222d
S
221 'formats': 'mincount:16',
222 'subtitles': 'mincount:1',
223 },
224 'params': {
225 'force_generic_extractor': True,
226 'skip_download': True,
227 },
228 },
229 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
230 {
231 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
232 'info_dict': {
233 'id': 'hds',
234 'ext': 'flv',
235 'title': 'hds',
236 'formats': 'mincount:1',
237 },
238 'params': {
239 'skip_download': True,
240 },
241 },
242 # SMIL from https://www.restudy.dk/video/play/id/1637
243 {
244 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
245 'info_dict': {
246 'id': 'video_1637',
247 'ext': 'flv',
248 'title': 'video_1637',
249 'formats': 'mincount:3',
250 },
251 'params': {
252 'skip_download': True,
253 },
254 },
255 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
256 {
257 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
258 'info_dict': {
259 'id': 'smil-service',
260 'ext': 'flv',
261 'title': 'smil-service',
262 'formats': 'mincount:1',
263 },
264 'params': {
265 'skip_download': True,
266 },
267 },
268 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
269 {
270 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
271 'info_dict': {
272 'id': '4719370',
273 'ext': 'mp4',
274 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
275 'formats': 'mincount:3',
276 },
277 'params': {
278 'skip_download': True,
279 },
280 },
1de5cd3b
S
281 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
282 {
283 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
284 'info_dict': {
285 'id': 'mZlp2ctYIUEB',
286 'ext': 'mp4',
287 'title': 'Tikibad ontruimd wegens brand',
288 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
ec85ded8 289 'thumbnail': r're:^https?://.*\.jpg$',
1de5cd3b
S
290 'duration': 33,
291 },
292 'params': {
293 'skip_download': True,
294 },
295 },
9d939cec
S
296 # MPD from http://dash-mse-test.appspot.com/media.html
297 {
298 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
299 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
300 'info_dict': {
301 'id': 'car-20120827-manifest',
302 'ext': 'mp4',
303 'title': 'car-20120827-manifest',
304 'formats': 'mincount:9',
0738187f 305 'upload_date': '20130904',
9d939cec
S
306 },
307 'params': {
308 'format': 'bestvideo',
309 },
310 },
20938f76
S
311 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
312 {
313 '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',
314 'info_dict': {
315 'id': 'content',
316 'ext': 'mp4',
317 'title': 'content',
318 'formats': 'mincount:8',
319 },
320 'params': {
321 # m3u8 downloads
322 'skip_download': True,
39efc6e3
YCH
323 },
324 'skip': 'video gone',
20938f76 325 },
edd9b71c
S
326 # m3u8 served with Content-Type: text/plain
327 {
328 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
329 'info_dict': {
330 'id': 'index',
331 'ext': 'mp4',
332 'title': 'index',
333 'upload_date': '20140720',
334 'formats': 'mincount:11',
335 },
336 'params': {
337 # m3u8 downloads
338 'skip_download': True,
39efc6e3
YCH
339 },
340 'skip': 'video gone',
edd9b71c 341 },
c5fa81fe
S
342 # google redirect
343 {
344 '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',
345 'info_dict': {
346 'id': 'cmQHVoWB5FY',
347 'ext': 'mp4',
348 'upload_date': '20130224',
349 'uploader_id': 'TheVerge',
ec85ded8 350 'description': r're:^Chris Ziegler takes a look at the\.*',
c5fa81fe
S
351 'uploader': 'The Verge',
352 'title': 'First Firefox OS phones side-by-side',
353 },
354 'params': {
355 'skip_download': False,
356 }
357 },
6c91a5a7
S
358 {
359 # redirect in Refresh HTTP header
360 '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',
361 'info_dict': {
362 'id': 'pO8h3EaFRdo',
363 'ext': 'mp4',
364 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
365 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
366 'upload_date': '20150917',
367 'uploader_id': 'brtvofficial',
368 'uploader': 'Boiler Room',
369 },
370 'params': {
371 'skip_download': False,
372 },
373 },
cfe50f04 374 {
79649588 375 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 376 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 377 'info_dict': {
d360a146
S
378 'id': '13601338388002',
379 'ext': 'mp4',
79649588
PH
380 'uploader': 'www.hodiho.fr',
381 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
382 }
383 },
c19f7764
JMF
384 # bandcamp page with custom domain
385 {
79649588
PH
386 'add_ie': ['Bandcamp'],
387 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 388 'info_dict': {
fd50bf62
S
389 'id': '3235767654',
390 'ext': 'mp3',
79649588
PH
391 'title': 'The Pony Mash',
392 'uploader': 'M_Pallante',
c19f7764 393 },
79649588 394 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 395 },
eeb165e6 396 {
53a664ed
S
397 # embedded brightcove video
398 # it also tests brightcove videos that need to set the 'Referer'
399 # in the http requests
3b7d9aa4 400 'add_ie': ['BrightcoveLegacy'],
79649588
PH
401 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
402 'info_dict': {
403 'id': '2765128793001',
404 'ext': 'mp4',
405 'title': 'Le cours de bourse : l’analyse technique',
406 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
407 'uploader': 'BFM BUSINESS',
eeb165e6 408 },
79649588
PH
409 'params': {
410 'skip_download': True,
eeb165e6
JMF
411 },
412 },
53a664ed
S
413 {
414 # embedded with itemprop embedURL and video id spelled as `idVideo`
415 'add_id': ['BrightcoveLegacy'],
416 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
417 'info_dict': {
418 'id': '5255628253001',
419 'ext': 'mp4',
420 'title': 'md5:37c519b1128915607601e75a87995fc0',
421 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
422 'uploader': 'BFM BUSINESS',
423 'uploader_id': '876450612001',
424 'timestamp': 1482255315,
425 'upload_date': '20161220',
426 },
427 'params': {
428 'skip_download': True,
429 },
430 },
17ab4d3b
PH
431 {
432 # https://github.com/rg3/youtube-dl/issues/2253
433 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
434 'md5': '0ba9446db037002366bab3b3eb30c88c',
435 'info_dict': {
fd50bf62
S
436 'id': '3101154703001',
437 'ext': 'mp4',
17ab4d3b
PH
438 'title': 'Still no power',
439 'uploader': 'thestar.com',
440 '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.',
441 },
3b7d9aa4 442 'add_ie': ['BrightcoveLegacy'],
39efc6e3 443 'skip': 'video gone',
17ab4d3b 444 },
0479c625
S
445 {
446 'url': 'http://www.championat.com/video/football/v/87/87499.html',
447 'md5': 'fb973ecf6e4a78a67453647444222983',
448 'info_dict': {
449 'id': '3414141473001',
450 'ext': 'mp4',
451 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
452 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
453 'uploader': 'Championat',
454 },
455 },
bdf97017 456 {
37aab278 457 # https://github.com/rg3/youtube-dl/issues/3541
3b7d9aa4 458 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
459 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
460 'info_dict': {
461 'id': '3866516442001',
37aab278 462 'ext': 'mp4',
bdf97017
NJ
463 'title': 'Leer mij vrouwen kennen: Aflevering 1',
464 'description': 'Leer mij vrouwen kennen: Aflevering 1',
465 'uploader': 'SBS Broadcasting',
466 },
37aab278 467 'skip': 'Restricted to Netherlands',
bdf97017 468 'params': {
37aab278 469 'skip_download': True, # m3u8 download
bdf97017
NJ
470 },
471 },
06d0ad9a
YCH
472 {
473 # Brightcove video in <iframe>
474 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
475 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
476 'info_dict': {
477 'id': '5360463607001',
478 'ext': 'mp4',
479 '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',
480 '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。',
481 'uploader': 'United Nations',
482 'uploader_id': '1362235914001',
483 'timestamp': 1489593889,
484 'upload_date': '20170315',
485 },
486 'add_ie': ['BrightcoveLegacy'],
487 },
16e2c8f7
YCH
488 {
489 # Brightcove with alternative playerID key
490 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
491 'info_dict': {
492 'id': 'nmeth.2062_SV1',
493 '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',
494 },
495 'playlist': [{
496 'info_dict': {
497 'id': '2228375078001',
498 'ext': 'mp4',
499 'title': 'nmeth.2062-sv1',
500 'description': 'nmeth.2062-sv1',
501 'timestamp': 1363357591,
502 'upload_date': '20130315',
503 'uploader': 'Nature Publishing Group',
504 'uploader_id': '1964492299001',
505 },
506 }],
507 },
40158f55
JH
508 {
509 # Brightcove with UUID in videoPlayer
510 'url': 'http://www8.hp.com/cn/zh/home.html',
511 'info_dict': {
512 'id': '5255815316001',
513 'ext': 'mp4',
514 'title': 'Sprocket Video - China',
515 'description': 'Sprocket Video - China',
516 'uploader': 'HP-Video Gallery',
517 'timestamp': 1482263210,
518 'upload_date': '20161220',
519 'uploader_id': '1107601872001',
520 },
521 'params': {
522 'skip_download': True, # m3u8 download
523 },
524 'skip': 'video rotates...weekly?',
525 },
526 {
527 # Brightcove:new type [2].
528 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
529 'md5': '2b35148fcf48da41c9fb4591650784f3',
530 'info_dict': {
531 'id': '5348741021001',
532 'ext': 'mp4',
533 'upload_date': '20170306',
534 'uploader_id': '4191638492001',
535 'timestamp': 1488769918,
536 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
537
538 },
539 },
540 {
541 # Alternative brightcove <video> attributes
542 '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/',
543 'info_dict': {
544 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
545 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
546 },
547 'playlist': [{
548 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
549 'info_dict': {
550 'id': '5311302538001',
551 'ext': 'mp4',
552 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
553 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
554 'timestamp': 1486321708,
555 'upload_date': '20170205',
556 'uploader_id': '800000640001',
557 },
558 'only_matching': True,
559 }],
560 },
b68a812e
S
561 {
562 # Brightcove with UUID in videoPlayer
563 'url': 'http://www8.hp.com/cn/zh/home.html',
564 'info_dict': {
565 'id': '5255815316001',
566 'ext': 'mp4',
567 'title': 'Sprocket Video - China',
568 'description': 'Sprocket Video - China',
569 'uploader': 'HP-Video Gallery',
570 'timestamp': 1482263210,
571 'upload_date': '20161220',
572 'uploader_id': '1107601872001',
573 },
574 'params': {
575 'skip_download': True, # m3u8 download
576 },
577 },
c0d0b01f
JMF
578 # ooyala video
579 {
79649588 580 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 581 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
582 'info_dict': {
583 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
584 'ext': 'mp4',
3486df38 585 'title': '2cc213299525360.mov', # that's what we get
53e06b25 586 'duration': 238.231,
c0d0b01f 587 },
87830900 588 'add_ie': ['Ooyala'],
c0d0b01f 589 },
bf94d763
S
590 {
591 # ooyala video embedded with http://player.ooyala.com/iframe.js
592 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
593 'info_dict': {
594 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
595 'ext': 'mp4',
596 'title': '"Steve Jobs: Man in the Machine" trailer',
597 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 598 'duration': 135.427,
bf94d763
S
599 },
600 'params': {
601 'skip_download': True,
602 },
39efc6e3 603 'skip': 'movie expired',
bf94d763 604 },
198d4cb4
GR
605 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
606 {
607 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
608 'info_dict': {
609 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
610 'ext': 'mp4',
611 'title': 'Steampunk Fest Comes to Honesdale',
612 'duration': 43.276,
613 },
614 'params': {
615 'skip_download': True,
616 }
617 },
1b86cc41 618 # embed.ly video
619 {
620 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
621 'info_dict': {
622 'id': '9ODmcdjQcHQ',
623 'ext': 'mp4',
0a5bce56
PH
624 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
625 'upload_date': '20140225',
626 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
627 'uploader': 'Tested',
628 'uploader_id': 'testedcom',
1b86cc41 629 },
630 # No need to test YoutubeIE here
631 'params': {
632 'skip_download': True,
633 },
634 },
60cc4dc4
PH
635 # funnyordie embed
636 {
637 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
638 'info_dict': {
639 'id': '18e820ec3f',
640 'ext': 'mp4',
641 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
642 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 643 },
39efc6e3
YCH
644 # HEAD requests lead to endless 301, while GET is OK
645 'expected_warnings': ['301'],
60cc4dc4 646 },
93d020dd
S
647 # RUTV embed
648 {
649 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
650 'info_dict': {
651 'id': '776940',
652 'ext': 'mp4',
653 'title': 'Охотское море стало целиком российским',
654 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
655 },
656 'params': {
657 # m3u8 download
658 'skip_download': True,
659 },
aab74fa1 660 },
f37bdbe5
S
661 # TVC embed
662 {
663 '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/',
664 'info_dict': {
665 'id': '55304',
666 'ext': 'mp4',
667 'title': 'Дошкольное воспитание',
668 },
669 },
b827a601
S
670 # SportBox embed
671 {
672 'url': 'http://www.vestifinance.ru/articles/25753',
673 'info_dict': {
674 'id': '25753',
05d1e7aa 675 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
b827a601
S
676 },
677 'playlist': [{
678 'info_dict': {
679 'id': '370908',
680 'title': 'Госзаказ. День 3',
681 'ext': 'mp4',
682 }
683 }, {
684 'info_dict': {
685 'id': '370905',
686 'title': 'Госзаказ. День 2',
687 'ext': 'mp4',
688 }
689 }, {
690 'info_dict': {
691 'id': '370902',
692 'title': 'Госзаказ. День 1',
693 'ext': 'mp4',
694 }
695 }],
696 'params': {
697 # m3u8 download
698 'skip_download': True,
699 },
700 },
bf20b9c5
S
701 # Myvi.ru embed
702 {
703 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
704 'info_dict': {
705 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
706 'ext': 'mp4',
707 'title': 'Ужастики, русский трейлер (2015)',
ec85ded8 708 'thumbnail': r're:^https?://.*\.jpg$',
bf20b9c5
S
709 'duration': 153,
710 }
711 },
c76799c5
S
712 # XHamster embed
713 {
714 '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',
715 'info_dict': {
716 'id': 'showthread',
717 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
718 },
719 'playlist_mincount': 7,
39efc6e3
YCH
720 # This forum does not allow <iframe> syntaxes anymore
721 # Now HTML tags are displayed as-is
722 'skip': 'No videos on this page',
c76799c5 723 },
aab74fa1
PH
724 # Embedded TED video
725 {
726 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 727 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 728 'info_dict': {
a8eb5a8e 729 'id': '1969',
aab74fa1 730 'ext': 'mp4',
a8eb5a8e
PH
731 'title': 'Hidden miracles of the natural world',
732 'uploader': 'Louie Schwartzberg',
733 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 734 }
60cc4dc4 735 },
d95e35d6
S
736 # nowvideo embed hidden behind percent encoding
737 {
738 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
739 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
740 'info_dict': {
741 'id': '06e53103ca9aa',
742 'ext': 'flv',
743 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
744 'description': 'No description',
745 },
0f2a2ba1 746 },
893f8832
PH
747 # arte embed
748 {
749 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
750 'md5': '7653032cbb25bf6c80d80f217055fa43',
751 'info_dict': {
752 'id': '048195-004_PLUS7-F',
753 'ext': 'flv',
754 'title': 'X:enius',
755 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
756 'upload_date': '20140320',
757 },
758 'params': {
759 'skip_download': 'Requires rtmpdump'
39efc6e3
YCH
760 },
761 'skip': 'video gone',
893f8832 762 },
cbd55ade
S
763 # francetv embed
764 {
765 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
766 'info_dict': {
767 'id': 'EV_30231',
768 'ext': 'mp4',
769 'title': 'Alcaline, le concert avec Calogero',
770 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
771 'upload_date': '20150226',
772 'timestamp': 1424989860,
773 'duration': 5400,
774 },
775 'params': {
776 # m3u8 downloads
777 'skip_download': True,
778 },
779 'expected_warnings': [
780 'Forbidden'
781 ]
782 },
fa35cdad
PH
783 # Condé Nast embed
784 {
785 'url': 'http://www.wired.com/2014/04/honda-asimo/',
786 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
787 'info_dict': {
788 'id': '53501be369702d3275860000',
789 'ext': 'mp4',
790 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
791 }
ebd3c7b3
PH
792 },
793 # Dailymotion embed
794 {
795 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
796 'md5': '441aeeb82eb72c422c7f14ec533999cd',
797 'info_dict': {
798 'id': 'k2mm4bCdJ6CQ2i7c8o2',
799 'ext': 'mp4',
800 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 801 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 802 'uploader': 'Spi0n',
0738187f
YCH
803 'uploader_id': 'xgditw',
804 'upload_date': '20140425',
805 'timestamp': 1398441542,
ebd3c7b3
PH
806 },
807 'add_ie': ['Dailymotion'],
2b88feed 808 },
71a1db89
S
809 # DailyMail embed
810 {
811 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
812 'info_dict': {
813 'id': '1495629',
814 'ext': 'mp4',
815 'title': 'Care worker punches elderly dementia patient in head 11 times',
816 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
817 },
818 'add_ie': ['DailyMail'],
819 'params': {
820 'skip_download': True,
821 },
822 },
2b88feed
PH
823 # YouTube embed
824 {
825 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
826 'info_dict': {
827 'id': 'FXRb4ykk4S0',
828 'ext': 'mp4',
829 'title': 'The NBL Auction 2014',
830 'uploader': 'BADMINTON England',
831 'uploader_id': 'BADMINTONEvents',
832 'upload_date': '20140603',
833 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
834 },
835 'add_ie': ['Youtube'],
836 'params': {
837 'skip_download': True,
838 }
839 },
c5cd249e
JMF
840 # MTVSercices embed
841 {
1fa309da
YCH
842 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
843 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 844 'info_dict': {
1fa309da 845 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 846 'ext': 'mp4',
1fa309da
YCH
847 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
848 'description': 'Two valets share their love for movie star Liam Neesons.',
05d1e7aa
YCH
849 'timestamp': 1349922600,
850 'upload_date': '20121011',
c5cd249e
JMF
851 },
852 },
61013473 853 # YouTube embed via <data-embed-url="">
854 {
855 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 856 'info_dict': {
a8eb5a8e 857 'id': '4vAffPZIT44',
61013473 858 'ext': 'mp4',
a8eb5a8e 859 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
860 'uploader': 'Gameloft',
861 'uploader_id': 'gameloft',
a8eb5a8e
PH
862 'upload_date': '20140828',
863 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
864 },
865 'params': {
866 'skip_download': True,
61013473 867 }
c8e9a235 868 },
61568e50
JH
869 # YouTube <object> embed
870 {
871 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
872 'md5': '516718101ec834f74318df76259fb3cc',
873 'info_dict': {
874 'id': 'msN87y-iEx0',
875 'ext': 'webm',
876 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
877 'upload_date': '20080526',
878 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
879 'uploader': 'Christopher Sykes',
880 'uploader_id': 'ChristopherJSykes',
881 },
882 'add_ie': ['Youtube'],
883 },
c8e9a235
PH
884 # Camtasia studio
885 {
886 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
887 'playlist': [{
888 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
889 'info_dict': {
890 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
891 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
892 'ext': 'flv',
893 'duration': 2235.90,
894 }
895 }, {
896 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
897 'info_dict': {
898 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
899 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
900 'ext': 'flv',
901 'duration': 2235.93,
902 }
903 }],
904 'info_dict': {
905 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
906 }
4d805e06
PH
907 },
908 # Flowplayer
909 {
910 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
911 'md5': '9d65602bf31c6e20014319c7d07fba27',
912 'info_dict': {
913 'id': '5123ea6d5e5a7',
914 'ext': 'mp4',
915 'age_limit': 18,
916 'uploader': 'www.handjobhub.com',
d6d9186f 917 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 918 }
0990305d 919 },
22a6f150
PH
920 # Multiple brightcove videos
921 # https://github.com/rg3/youtube-dl/issues/2283
922 {
923 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
924 'info_dict': {
925 'id': 'always-never',
926 'title': 'Always / Never - The New Yorker',
927 },
928 'playlist_count': 3,
929 'params': {
930 'extract_flat': False,
931 'skip_download': True,
932 }
1a94ff68
S
933 },
934 # MLB embed
935 {
936 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
937 'md5': '96f09a37e44da40dd083e12d9a683327',
938 'info_dict': {
939 'id': '33322633',
940 'ext': 'mp4',
941 'title': 'Ump changes call to ball',
942 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
943 'duration': 48,
944 'timestamp': 1401537900,
945 'upload_date': '20140531',
ec85ded8 946 'thumbnail': r're:^https?://.*\.jpg$',
1a94ff68
S
947 },
948 },
746c67d7
NJ
949 # Wistia embed
950 {
6c114b12
S
951 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
952 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 953 'info_dict': {
6c114b12 954 'id': '6e2wtrbdaf',
746c67d7 955 'ext': 'mov',
6c114b12
S
956 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
957 'description': 'a Paywall Videos video from Remilon',
958 'duration': 644.072,
959 'uploader': 'study.com',
960 'timestamp': 1459678540,
961 'upload_date': '20160403',
962 'filesize': 24687186,
746c67d7
NJ
963 },
964 },
52cffcb1 965 {
966 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
967 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
968 'info_dict': {
969 'id': 'uxjb0lwrcz',
970 'ext': 'mp4',
6c114b12 971 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 972 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 973 'duration': 1715.0,
85d7b765 974 'uploader': 'thoughtworks.wistia.com',
0738187f 975 'timestamp': 1401832161,
6c114b12 976 'upload_date': '20140603',
70b7e3fb 977 },
52cffcb1 978 },
7ded6545
S
979 # Wistia standard embed (async)
980 {
981 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
982 'info_dict': {
983 'id': '807fafadvk',
984 'ext': 'mp4',
985 'title': 'Drip Brennan Dunn Workshop',
986 'description': 'a JV Webinars video from getdrip-1',
987 'duration': 4986.95,
7ded6545 988 'timestamp': 1463607249,
6c114b12 989 'upload_date': '20160518',
7ded6545
S
990 },
991 'params': {
992 'skip_download': True,
993 }
994 },
ac645ac7
PH
995 # Soundcloud embed
996 {
997 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
998 'info_dict': {
999 'id': '174391317',
1000 'ext': 'mp3',
1001 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1002 'uploader': 'Sophos Security',
1003 'title': 'Chet Chat 171 - Oct 29, 2014',
1004 'upload_date': '20141029',
1005 }
af63fed7 1006 },
db19df6c
S
1007 # Soundcloud multiple embeds
1008 {
1009 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1010 'info_dict': {
1011 'id': '52809',
1012 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1013 },
1014 'playlist_mincount': 7,
1015 },
027e2312
S
1016 # TuneIn station embed
1017 {
1018 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1019 'info_dict': {
1020 'id': '204146',
1021 'ext': 'mp3',
1022 'title': 'CNRV',
1023 'location': 'Paris, France',
1024 'is_live': True,
1025 },
1026 'params': {
1027 # Live stream
1028 'skip_download': True,
1029 },
1030 },
af63fed7
PH
1031 # Livestream embed
1032 {
1033 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1034 'info_dict': {
1035 'id': '67864563',
1036 'ext': 'flv',
1037 'upload_date': '20141112',
1038 'title': 'Rosetta #CometLanding webcast HL 10',
1039 }
1040 },
78d3b3e2
YCH
1041 # Another Livestream embed, without 'new.' in URL
1042 {
1043 'url': 'https://www.freespeech.org/',
1044 'info_dict': {
1045 'id': '123537347',
1046 'ext': 'mp4',
1047 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1048 },
1049 'params': {
1050 # Live stream
1051 'skip_download': True,
1052 },
1053 },
65f3a228
PH
1054 # LazyYT
1055 {
e8e4cc5a 1056 'url': 'https://skiplagged.com/',
65f3a228 1057 'info_dict': {
e8e4cc5a
JH
1058 'id': 'skiplagged',
1059 'title': 'Skiplagged: The smart way to find cheap flights',
65f3a228 1060 },
e8e4cc5a
JH
1061 'playlist_mincount': 1,
1062 'add_ie': ['Youtube'],
4e262a88 1063 },
42bdd9d0
PH
1064 # Cinchcast embed
1065 {
1066 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1067 'info_dict': {
1068 'id': '7141703',
1069 'ext': 'mp3',
1070 'upload_date': '20141126',
1071 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1072 }
1073 },
501f13fb
PH
1074 # Cinerama player
1075 {
1076 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1077 'info_dict': {
1078 'id': '730m_DandD_1901_512k',
1079 'ext': 'mp4',
1080 'uploader': 'www.abc.net.au',
1081 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1082 }
796df3c6
S
1083 },
1084 # embedded viddler video
1085 {
1086 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1087 'info_dict': {
1088 'id': '4d03aad9',
1089 'ext': 'mp4',
1090 'uploader': 'deadspin',
1091 'title': 'WALL-TO-GORTAT',
1092 'timestamp': 1422285291,
1093 'upload_date': '20150126',
1094 },
1095 'add_ie': ['Viddler'],
a0f71985 1096 },
2051acde
S
1097 # Libsyn embed
1098 {
1099 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1100 'info_dict': {
1101 'id': '3377616',
1102 'ext': 'mp3',
1103 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1104 'description': 'md5:601cb790edd05908957dae8aaa866465',
1105 'upload_date': '20150220',
1106 },
326fa4e6 1107 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
2051acde 1108 },
a0f71985
PH
1109 # jwplayer YouTube
1110 {
1111 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1112 'info_dict': {
1113 'id': 'Mrj4DVp2zeA',
1114 'ext': 'mp4',
f37e3f99 1115 'upload_date': '20150212',
a0f71985 1116 'uploader': 'The National Archives UK',
2637fadc 1117 'description': 'md5:8078af856dca76edc42910b61273dbbf',
a0f71985
PH
1118 'uploader_id': 'NationalArchives08',
1119 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1120 },
59b8ab58 1121 },
5620f840
S
1122 # jwplayer rtmp
1123 {
6899b1d9 1124 'url': 'http://www.suffolk.edu/sjc/live.php',
5620f840 1125 'info_dict': {
6899b1d9 1126 'id': 'live',
5620f840
S
1127 'ext': 'flv',
1128 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1129 'uploader': 'www.suffolk.edu',
1130 },
1131 'params': {
1132 'skip_download': True,
2637fadc 1133 },
6899b1d9 1134 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
5620f840 1135 },
a4a554a7
YCH
1136 # Complex jwplayer
1137 {
1138 'url': 'http://www.indiedb.com/games/king-machine/videos',
1139 'info_dict': {
1140 'id': 'videos',
1141 'ext': 'mp4',
1142 'title': 'king machine trailer 1',
2637fadc 1143 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
a4a554a7
YCH
1144 'thumbnail': r're:^https?://.*\.jpg$',
1145 },
1146 },
03486dbb
RU
1147 {
1148 # JWPlayer config passed as variable
1149 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1150 'info_dict': {
1151 'id': '3326530_hq',
1152 'ext': 'mp4',
1153 'title': 'ARIELE | Tube Cup',
1154 'uploader': 'www.txxx.com',
1155 'age_limit': 18,
1156 },
1157 'params': {
1158 'skip_download': True,
1159 }
1160 },
939be9ad
JH
1161 {
1162 # JWPlatform iframe
1163 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1164 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1165 'info_dict': {
1166 'id': 'O0c5JcKT',
1167 'ext': 'mp4',
1168 'upload_date': '20171122',
1169 'timestamp': 1511366290,
1170 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1171 },
805f5bf7 1172 'add_ie': [JWPlatformIE.ie_key()],
939be9ad 1173 },
63d990d2 1174 {
c5b7014a 1175 # Video.js embed, multiple formats
63d990d2
S
1176 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1177 'info_dict': {
1178 'id': 'yygqldloqIk',
1179 'ext': 'mp4',
1180 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1181 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1182 'upload_date': '20130314',
1183 'uploader': 'PROстое3D',
1184 'uploader_id': 'PROstoe3D',
1185 },
1186 'params': {
1187 'skip_download': True,
1188 },
1189 },
c5b7014a
S
1190 {
1191 # Video.js embed, single format
1192 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1193 'info_dict': {
1194 'id': 'watch',
1195 'ext': 'mp4',
1196 'title': 'Step 1 - Good Foundation',
1197 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1198 },
1199 'params': {
1200 'skip_download': True,
1201 },
1202 },
59b8ab58
PH
1203 # rtl.nl embed
1204 {
1205 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1206 'playlist_mincount': 5,
1207 'info_dict': {
1208 'id': 'aanslagen-kopenhagen',
2637fadc 1209 'title': 'Aanslagen Kopenhagen',
59b8ab58 1210 }
255fca5e
S
1211 },
1212 # Zapiks embed
1213 {
1214 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1215 'info_dict': {
1216 'id': '118046',
1217 'ext': 'mp4',
1218 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1219 }
1220 },
66e568de
S
1221 # Kaltura embed (different embed code)
1222 {
1223 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1224 'info_dict': {
1225 'id': '1_a52wc67y',
1226 'ext': 'flv',
1227 'upload_date': '20150127',
1228 'uploader_id': 'PremierMedia',
1229 'timestamp': int,
1230 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1231 },
1232 },
87703231
YCH
1233 # Kaltura embed with single quotes
1234 {
1235 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1236 'info_dict': {
1237 'id': '0_izeg5utt',
1238 'ext': 'mp4',
1239 'title': '35871',
1240 'timestamp': 1355743100,
1241 'upload_date': '20121217',
e30991f9 1242 'uploader_id': 'cplapp@learn360.com',
87703231
YCH
1243 },
1244 'add_ie': ['Kaltura'],
1245 },
427cd050
S
1246 {
1247 # Kaltura embedded via quoted entry_id
1248 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1249 'info_dict': {
1250 'id': '0_utuok90b',
1251 'ext': 'mp4',
1252 'title': '06_matthew_brender_raj_dutt',
1253 'timestamp': 1466638791,
1254 'upload_date': '20160622',
1255 },
1256 'add_ie': ['Kaltura'],
1257 'expected_warnings': [
1258 'Could not send HEAD request'
1259 ],
1260 'params': {
1261 'skip_download': True,
1262 }
1263 },
8ab7e6c4
YCH
1264 {
1265 # Kaltura embedded, some fileExt broken (#11480)
1266 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1267 'info_dict': {
1268 'id': '1_sgtvehim',
1269 'ext': 'mp4',
1270 'title': 'Our "Standard Models" of particle physics and cosmology',
1271 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1272 'timestamp': 1321158993,
1273 'upload_date': '20111113',
1274 'uploader_id': 'kps1',
1275 },
1276 'add_ie': ['Kaltura'],
1277 },
a01825a5
JH
1278 {
1279 # Kaltura iframe embed
1280 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1281 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1282 'info_dict': {
1283 'id': '0_f2cfbpwy',
1284 'ext': 'mp4',
1285 'title': 'I. M. Pei: A Centennial Celebration',
1286 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1287 'upload_date': '20170403',
1288 'uploader_id': 'batchUser',
1289 'timestamp': 1491232186,
1290 },
1291 'add_ie': ['Kaltura'],
1292 },
c21692fa
S
1293 {
1294 # Kaltura iframe embed, more sophisticated
1295 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1296 'info_dict': {
1297 'id': '1_9gzouybz',
1298 'ext': 'mp4',
1299 'title': 'lecture-05sep2017',
1300 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1301 'upload_date': '20170913',
1302 'uploader_id': 'eps2',
1303 'timestamp': 1505340777,
1304 },
1305 'params': {
1306 'skip_download': True,
1307 },
1308 'add_ie': ['Kaltura'],
1309 },
e30991f9
S
1310 {
1311 # meta twitter:player
1312 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1313 'info_dict': {
1314 'id': '0_01b42zps',
1315 'ext': 'mp4',
1316 'title': 'Main Twerk (Video)',
1317 'upload_date': '20171208',
1318 'uploader_id': 'sebastian.salinas@thechive.com',
1319 'timestamp': 1512713057,
1320 },
1321 'params': {
1322 'skip_download': True,
1323 },
1324 'add_ie': ['Kaltura'],
1325 },
250b042c
S
1326 # referrer protected EaglePlatform embed
1327 {
1328 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1329 'info_dict': {
1330 'id': '582306',
1331 'ext': 'mp4',
1332 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1333 'thumbnail': r're:^https?://.*\.jpg$',
1334 'duration': 3382,
1335 'view_count': int,
1336 },
1337 'params': {
1338 'skip_download': True,
1339 },
135c9c42 1340 },
665e9452 1341 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1342 {
1343 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1344 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1345 'info_dict': {
1346 'id': '12820',
1347 'ext': 'mp4',
1348 'title': "'O Sole Mio",
ec85ded8 1349 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1350 'duration': 216,
1351 'view_count': int,
1352 },
250b042c
S
1353 'params': {
1354 'skip_download': True,
1355 },
2637fadc 1356 'skip': 'This video is unavailable.',
d47ae7f6 1357 },
f8388757
S
1358 # Pladform embed
1359 {
1360 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1361 'info_dict': {
1362 'id': '100183293',
1363 'ext': 'mp4',
62259846 1364 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1365 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1366 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1367 'duration': 694,
1368 'age_limit': 0,
1369 },
2637fadc 1370 'skip': 'HTTP Error 404: Not Found',
f8388757 1371 },
c798f15b
S
1372 # Playwire embed
1373 {
1374 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1375 'info_dict': {
1376 'id': '3519514',
1377 'ext': 'mp4',
1378 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1379 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1380 'duration': 45.115,
1381 },
1382 },
ad320e9b
NJ
1383 # 5min embed
1384 {
1385 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1386 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1387 'info_dict': {
1388 'id': '518726732',
1389 'ext': 'mp4',
1390 'title': 'Facebook Creates "On This Day" | Crunch Report',
2637fadc
RA
1391 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1392 'timestamp': 1427237531,
1393 'uploader': 'Crunch Report',
1394 'upload_date': '20150324',
1395 },
1396 'params': {
1397 # m3u8 download
1398 'skip_download': True,
ad320e9b
NJ
1399 },
1400 },
a4257017
S
1401 # Crooks and Liars embed
1402 {
1403 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1404 'info_dict': {
1405 'id': '8RUoRhRi',
1406 'ext': 'mp4',
1407 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1408 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1409 'timestamp': 1428207000,
1410 'upload_date': '20150405',
1411 'uploader': 'Heather',
1412 },
1413 },
1414 # Crooks and Liars external embed
1415 {
1416 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1417 'info_dict': {
1418 'id': 'MTE3MjUtMzQ2MzA',
1419 'ext': 'mp4',
1420 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1421 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1422 'timestamp': 1265032391,
1423 'upload_date': '20100201',
1424 'uploader': 'Heather',
1425 },
1426 },
facecb84 1427 # NBC Sports vplayer embed
a2edf2e7 1428 {
facecb84 1429 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1430 'info_dict': {
facecb84
S
1431 'id': 'ln7x1qSThw4k',
1432 'ext': 'flv',
1433 'title': "PFT Live: New leader in the 'new-look' defense",
1434 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1435 'uploader': 'NBCU-SPORTS',
1436 'upload_date': '20140107',
1437 'timestamp': 1389118457,
a2edf2e7 1438 },
2637fadc 1439 'skip': 'Invalid Page URL',
418c5cc3 1440 },
de3eb07e
YCH
1441 # NBC News embed
1442 {
1443 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1444 'md5': '1aa589c675898ae6d37a17913cf68d66',
1445 'info_dict': {
2637fadc 1446 'id': 'x_dtl_oa_LettermanliftPR_160608',
de3eb07e 1447 'ext': 'mp4',
2637fadc 1448 'title': 'David Letterman: A Preview',
de3eb07e 1449 '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
1450 'upload_date': '20160609',
1451 'timestamp': 1465431544,
1452 'uploader': 'NBCU-NEWS',
de3eb07e
YCH
1453 },
1454 },
418c5cc3
YCH
1455 # UDN embed
1456 {
811586eb 1457 'url': 'https://video.udn.com/news/300346',
01c58f84 1458 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1459 'info_dict': {
01c58f84 1460 'id': '300346',
418c5cc3 1461 'ext': 'mp4',
01c58f84 1462 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1463 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1464 },
1465 'params': {
1466 # m3u8 download
1467 'skip_download': True,
1468 },
2637fadc 1469 'expected_warnings': ['Failed to parse JSON Expecting value'],
edfcf7ab 1470 },
b26733ba
YCH
1471 # Brightcove URL in single quotes
1472 {
1473 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1474 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1475 'info_dict': {
1476 'id': '4255764656001',
1477 'ext': 'mp4',
1478 'title': 'SN Presents: Russell Martin, World Citizen',
1479 '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.',
1480 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1481 'uploader_id': '1704050871',
1482 'upload_date': '20150525',
1483 'timestamp': 1432570283,
b26733ba 1484 },
756f574e 1485 },
8084be78
S
1486 # OnionStudios embed
1487 {
1488 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1489 'info_dict': {
1490 'id': '2855',
1491 'ext': 'mp4',
1492 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
ec85ded8 1493 'thumbnail': r're:^https?://.*\.jpe?g$',
8084be78
S
1494 'uploader': 'ClickHole',
1495 'uploader_id': 'clickhole',
1496 }
1497 },
b8c1cc1a
S
1498 # SnagFilms embed
1499 {
1500 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1501 'info_dict': {
1502 'id': '74849a00-85a9-11e1-9660-123139220831',
1503 'ext': 'mp4',
1504 'title': '#whilewewatch',
1505 }
1506 },
a5158f38
YCH
1507 # AdobeTVVideo embed
1508 {
1509 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1510 'md5': '43662b577c018ad707a63766462b1e87',
1511 'info_dict': {
1512 'id': '2456',
1513 'ext': 'mp4',
1514 'title': 'New experience with Acrobat DC',
1515 'description': 'New experience with Acrobat DC',
1516 'duration': 248.667,
1517 },
1f812580 1518 },
ed126900 1519 # BrightcoveInPageEmbed embed
1520 {
1521 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1522 'info_dict': {
1523 'id': '4238694884001',
1524 'ext': 'flv',
1525 'title': 'Tabletop: Dread, Last Thoughts',
1526 'description': 'Tabletop: Dread, Last Thoughts',
1527 'duration': 51690,
1528 },
750b9ff0 1529 },
d10fe835
YCH
1530 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1531 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1532 {
1533 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1534 'info_dict': {
1535 'id': '4785848093001',
1536 'ext': 'mp4',
1537 'title': 'The Cardinal Pell Interview',
1538 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1539 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1540 'uploader_id': '2733773828001',
1541 'upload_date': '20160304',
1542 'timestamp': 1457083087,
d10fe835
YCH
1543 },
1544 'params': {
1545 # m3u8 downloads
1546 'skip_download': True,
1547 },
1548 },
9edf47df
S
1549 {
1550 # Brightcove embed with whitespace around attribute names
1551 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1552 'info_dict': {
1553 'id': '3167554373001',
1554 'ext': 'mp4',
1555 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1556 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1557 'uploader_id': '1079349493',
1558 'upload_date': '20140207',
1559 'timestamp': 1391810548,
1560 },
1561 'params': {
1562 'skip_download': True,
1563 },
1564 },
134c207e
YCH
1565 # Another form of arte.tv embed
1566 {
1567 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1568 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1569 'info_dict': {
1570 'id': '030273-562_PLUS7-F',
1571 'ext': 'mp4',
1572 'title': 'ARTE Reportage - Nulle part, en France',
1573 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1574 'upload_date': '20160409',
1575 },
1576 },
b8f67449
KM
1577 # LiveLeak embed
1578 {
1579 'url': 'http://www.wykop.pl/link/3088787/',
09747ba7 1580 'md5': '7619da8c820e835bef21a1efa2a0fc71',
b8f67449
KM
1581 'info_dict': {
1582 'id': '874_1459135191',
1583 'ext': 'mp4',
1584 'title': 'Man shows poor quality of new apartment building',
1585 'description': 'The wall is like a sand pile.',
1586 'uploader': 'Lake8737',
09747ba7
YCH
1587 },
1588 'add_ie': [LiveLeakIE.ie_key()],
1589 },
1590 # Another LiveLeak embed pattern (#13336)
1591 {
1592 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1593 'info_dict': {
1594 'id': '2eb_1496309988',
1595 'ext': 'mp4',
1596 'title': 'Thief robs place where everyone was armed',
1597 'description': 'md5:694d73ee79e535953cf2488562288eee',
1598 'uploader': 'brazilwtf',
1599 },
1600 'add_ie': [LiveLeakIE.ie_key()],
b8f67449 1601 },
4a120778
YCH
1602 # Duplicated embedded video URLs
1603 {
1604 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1605 'info_dict': {
1606 'id': '149298443_480_16c25b74_2',
1607 'ext': 'mp4',
1608 'title': 'vs. Blue Orange Spring Game',
1609 'uploader': 'www.hudl.com',
1610 },
1611 },
371ddb14
S
1612 # twitter:player:stream embed
1613 {
1614 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1615 'info_dict': {
1616 'id': 'master',
1617 'ext': 'mp4',
1618 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1619 'uploader': 'www.rtl.be',
1620 },
1621 'params': {
1622 # m3u8 downloads
1623 'skip_download': True,
1624 },
1625 },
32917907
RA
1626 # twitter:player embed
1627 {
1628 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1629 'md5': 'a3e0df96369831de324f0778e126653c',
1630 'info_dict': {
1631 'id': '4909620399001',
1632 'ext': 'mp4',
1633 'title': 'What Do Black Holes Sound Like?',
1634 'description': 'what do black holes sound like',
1635 'upload_date': '20160524',
1636 'uploader_id': '29913724001',
1637 'timestamp': 1464107587,
1638 'uploader': 'TheAtlantic',
1639 },
1640 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1641 },
1642 # Facebook <iframe> embed
1643 {
1644 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1645 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1646 'info_dict': {
1647 'id': '599637780109885',
1648 'ext': 'mp4',
1649 'title': 'Facebook video #599637780109885',
1650 },
1651 },
fd1c5fba
S
1652 # Facebook <iframe> embed, plugin video
1653 {
1654 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1655 'info_dict': {
1656 'id': '1754168231264132',
1657 'ext': 'mp4',
1658 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1659 'uploader': 'Tariq Ramadan (official)',
1660 'timestamp': 1496758379,
1661 'upload_date': '20170606',
1662 },
1663 'params': {
1664 'skip_download': True,
1665 },
1666 },
fd6ca382
YCH
1667 # Facebook API embed
1668 {
1669 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1670 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1671 'info_dict': {
1672 'id': '10153467542406923',
1673 'ext': 'mp4',
1674 'title': 'Facebook video #10153467542406923',
1675 },
7deef1ba
YCH
1676 },
1677 # Wordpress "YouTube Video Importer" plugin
1678 {
1679 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1680 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1681 'info_dict': {
1682 'id': 'HNTXWDXV9Is',
1683 'ext': 'mp4',
1684 'title': 'Blue Devils Drumline Stanford lot 2016',
1685 'upload_date': '20160627',
1686 'uploader_id': 'GENOCIDE8GENERAL10',
1687 'uploader': 'cylus cyrus',
1688 },
1689 },
81953d1a
RA
1690 {
1691 # video stored on custom kaltura server
1692 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1693 'md5': '537617d06e64dfed891fa1593c4b30cc',
1694 'info_dict': {
1695 'id': '0_1iotm5bh',
1696 'ext': 'mp4',
1697 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1698 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1699 'uploader_id': 'videos.expansion@el-mundo.net',
1700 'upload_date': '20150429',
1701 'timestamp': 1430303472,
1702 },
1703 'add_ie': ['Kaltura'],
1704 },
c03adf90
YCH
1705 {
1706 # Non-standard Vimeo embed
1707 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1708 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1709 'info_dict': {
1710 'id': '148867247',
1711 'ext': 'mp4',
1712 'title': 'Understanding the web - Teaser',
1713 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1714 'upload_date': '20151214',
1715 'uploader': 'OpenClassrooms',
1716 'uploader_id': 'openclassrooms',
1717 },
1718 'add_ie': ['Vimeo'],
1719 },
a5ff05df
S
1720 {
1721 # generic vimeo embed that requires original URL passed as Referer
1722 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1723 'only_matching': True,
1724 },
1979969f
S
1725 {
1726 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1727 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1728 'info_dict': {
1729 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1730 'ext': 'mp4',
1731 'title': 'Big Buck Bunny',
1732 'description': 'Royalty free test video',
1733 'timestamp': 1432816365,
1734 'upload_date': '20150528',
1735 'is_live': False,
1736 },
1737 'params': {
1738 'skip_download': True,
1739 },
1740 'add_ie': [ArkenaIE.ie_key()],
1741 },
2a1321a2
S
1742 {
1743 '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/',
1744 'info_dict': {
1745 'id': '1c7141f46c',
1746 'ext': 'mp4',
1747 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1748 },
1749 'params': {
1750 'skip_download': True,
1751 },
1752 'add_ie': [Vbox7IE.ie_key()],
1753 },
b0c8f2e9
DR
1754 {
1755 # DBTV embeds
1756 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1757 'info_dict': {
1758 'id': '43254897',
1759 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1760 },
b0c8f2e9
DR
1761 'playlist_mincount': 3,
1762 },
e186a9ec
S
1763 {
1764 # Videa embeds
1765 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1766 'info_dict': {
1767 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1768 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1769 },
1770 'playlist_mincount': 2,
1771 },
b687c85e
S
1772 {
1773 # 20 minuten embed
1774 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1775 'info_dict': {
1776 'id': '523629',
1777 'ext': 'mp4',
1778 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1779 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1780 },
1781 'params': {
1782 'skip_download': True,
1783 },
1784 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1785 },
1786 {
1787 # VideoPress embed
1788 'url': 'https://en.support.wordpress.com/videopress/',
1789 'info_dict': {
1790 'id': 'OcobLTqC',
1791 'ext': 'm4v',
1792 'title': 'IMG_5786',
1793 'timestamp': 1435711927,
1794 'upload_date': '20150701',
1795 },
1796 'params': {
1797 'skip_download': True,
1798 },
1799 'add_ie': [VideoPressIE.ie_key()],
fef51645 1800 },
eb3079b6
S
1801 {
1802 # Rutube embed
1803 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1804 'info_dict': {
1805 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1806 'ext': 'flv',
1807 'title': 'Магаззино: Казань 2',
1808 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1809 'uploader': 'Магаззино',
1810 'upload_date': '20170228',
1811 'uploader_id': '996642',
1812 },
1813 'params': {
1814 'skip_download': True,
1815 },
1816 'add_ie': [RutubeIE.ie_key()],
1817 },
fef51645
YCH
1818 {
1819 # ThePlatform embedded with whitespaces in URLs
1820 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1821 'only_matching': True,
1822 },
97952bdb
JH
1823 {
1824 # Senate ISVP iframe https
1825 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1826 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1827 'info_dict': {
1828 'id': 'govtaff020316',
1829 'ext': 'mp4',
1830 'title': 'Integrated Senate Video Player',
1831 },
1832 'add_ie': [SenateISVPIE.ie_key()],
1833 },
ab87c260
S
1834 {
1835 # Limelight embeds (1 channel embed + 4 media embeds)
1836 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1837 'info_dict': {
1838 'id': 'FacilitatorTraining2017',
1839 'title': 'Facilitator Training 2017',
1840 },
1841 'playlist_mincount': 5,
1842 },
eb02940c
S
1843 {
1844 # Limelight embed (LimelightPlayerUtil.embed)
1845 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1846 'info_dict': {
1847 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1848 'ext': 'mp4',
1849 'title': '07448641',
1850 'timestamp': 1499890639,
1851 'upload_date': '20170712',
1852 },
1853 'params': {
1854 'skip_download': True,
1855 },
1856 'add_ie': ['LimelightMedia'],
1857 },
7986c3ab
S
1858 {
1859 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1860 'info_dict': {
1861 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1862 'title': 'Standoff with Walnut Creek murder suspect ends',
1863 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1864 },
1865 'playlist_mincount': 4,
1866 },
55719459
JH
1867 {
1868 # WashingtonPost embed
1869 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1870 'info_dict': {
1871 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1872 'ext': 'mp4',
1873 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1874 '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.',
1875 'timestamp': 1455216756,
1876 'uploader': 'The Washington Post',
1877 'upload_date': '20160211',
1878 },
1879 'add_ie': [WashingtonPostIE.ie_key()],
1880 },
2b8e6a68
S
1881 {
1882 # Mediaset embed
1883 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1884 'info_dict': {
1885 'id': '720642',
1886 'ext': 'mp4',
1887 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1888 },
1889 'params': {
1890 'skip_download': True,
1891 },
1892 'add_ie': [MediasetIE.ie_key()],
1893 },
73cf76a9
S
1894 {
1895 # JOJ.sk embeds
1896 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1897 'info_dict': {
1898 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1899 'title': 'Slovenskom sa prehnala vlna silných búrok',
1900 },
1901 'playlist_mincount': 5,
1902 'add_ie': [JojIE.ie_key()],
1903 },
4328ddf8
S
1904 {
1905 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1906 'url': 'https://tvrain.ru/amp/418921/',
1907 'md5': 'cc00413936695987e8de148b67d14f1d',
1908 'info_dict': {
1909 'id': '418921',
1910 'ext': 'mp4',
1911 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1912 },
1913 },
41918eaa 1914 {
1915 # vzaar embed
1663bd6e
S
1916 'url': 'http://help.vzaar.com/article/165-embedding-video',
1917 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1918 'info_dict': {
1663bd6e 1919 'id': '8707641',
41918eaa 1920 'ext': 'mp4',
1663bd6e 1921 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1922 },
1923 },
9ce1ac40 1924 {
1925 # multiple HTML5 videos on one page
1926 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1927 'info_dict': {
1928 'id': 'keyscenarios',
1929 'title': 'Rescue Kit 14 Free Edition - Getting started',
1930 },
1931 'playlist_count': 4,
0987f2dd
T
1932 },
1933 {
1934 # vshare embed
1935 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1936 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1937 'info_dict': {
1938 'id': '0f64ce6',
1939 'title': 'vl14062007715967',
1940 'ext': 'mp4',
1941 }
2ca7ed41
S
1942 },
1943 {
1944 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1945 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1946 'info_dict': {
1947 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1948 'ext': 'mp4',
1949 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1950 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1951 'timestamp': 1474354800,
1952 'upload_date': '20160920',
1953 }
7d540621
S
1954 },
1955 {
1956 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1957 'info_dict': {
1958 'id': '1731611',
1959 'ext': 'mp4',
1960 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1961 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1962 'timestamp': 1516100691,
1963 'upload_date': '20180116',
1964 },
1965 'params': {
1966 'skip_download': True,
1967 },
1968 'add_ie': [SpringboardPlatformIE.ie_key()],
ea696249
S
1969 },
1970 {
1971 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1972 'info_dict': {
1973 'id': 'uPDB5I9wfp8',
1974 'ext': 'webm',
1975 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1976 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1977 'upload_date': '20160219',
1978 'uploader': 'Pocoyo - Português (BR)',
1979 'uploader_id': 'PocoyoBrazil',
1980 },
1981 'add_ie': [YoutubeIE.ie_key()],
1982 'params': {
1983 'skip_download': True,
1984 },
4c780fbd
S
1985 },
1986 {
1987 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1988 'info_dict': {
1989 'id': 'vMDE4NzI1Mjgt690b',
1990 'ext': 'mp4',
1991 'title': 'Котята',
1992 },
1993 'add_ie': [YapFilesIE.ie_key()],
1994 'params': {
1995 'skip_download': True,
1996 },
1fc37ca3 1997 },
660a230b
S
1998 {
1999 # CloudflareStream embed
2000 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2001 'info_dict': {
2002 'id': '31c9291ab41fac05471db4e73aa11717',
2003 'ext': 'mp4',
2004 'title': '31c9291ab41fac05471db4e73aa11717',
2005 },
2006 'add_ie': [CloudflareStreamIE.ie_key()],
2007 'params': {
2008 'skip_download': True,
2009 },
2010 },
6bd499e8
S
2011 {
2012 # PeerTube embed
2013 'url': 'https://joinpeertube.org/fr/home/',
2014 'info_dict': {
2015 'id': 'home',
2016 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2017 },
2018 'playlist_count': 2,
2019 },
aee36ca8
S
2020 {
2021 # Indavideo embed
2022 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2023 'info_dict': {
2024 'id': '1693903',
2025 'ext': 'mp4',
2026 'title': 'Így kell otthon hamburgert sütni',
2027 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2028 'timestamp': 1426330212,
2029 'upload_date': '20150314',
2030 'uploader': 'StreetKitchen',
2031 'uploader_id': '546363',
2032 },
2033 'add_ie': [IndavideoEmbedIE.ie_key()],
2034 'params': {
2035 'skip_download': True,
2036 },
2037 },
cfd7f2a6
S
2038 {
2039 # APA embed via JWPlatform embed
2040 'url': 'http://www.vol.at/blue-man-group/5593454',
2041 'info_dict': {
2042 'id': 'jjv85FdZ',
2043 'ext': 'mp4',
2044 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2045 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2046 'thumbnail': r're:^https?://.*\.jpg$',
2047 'duration': 254,
2048 'timestamp': 1519211149,
2049 'upload_date': '20180221',
2050 },
2051 'params': {
2052 'skip_download': True,
2053 },
2054 },
1fc37ca3
SO
2055 {
2056 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2057 'md5': 'b68d276de422ab07ee1d49388103f457',
2058 'info_dict': {
2059 'id': '83645793',
2060 'title': 'Lock up and get excited',
1fc37ca3 2061 'ext': 'mp4'
d3431dcb
S
2062 },
2063 'skip': 'TODO: fix nested playlists processing in tests',
2064 },
9d1b2138
S
2065 {
2066 # Viqeo embeds
2067 'url': 'https://viqeo.tv/',
2068 'info_dict': {
2069 'id': 'viqeo',
2070 'title': 'All-new video platform',
2071 },
2072 'playlist_count': 6,
2073 },
6e6b70d6
S
2074 # {
2075 # # TODO: find another test
2076 # # http://schema.org/VideoObject
2077 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2078 # 'md5': '888dcf08b7ea671381f00fab74692755',
2079 # 'info_dict': {
2080 # 'id': 'nyvTSJMKId',
2081 # 'ext': 'mp4',
2082 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2083 # 'description': '#love for cats.',
2084 # 'timestamp': 1461244995,
2085 # 'upload_date': '20160421',
2086 # },
2087 # 'params': {
2088 # 'force_generic_extractor': True,
2089 # },
2090 # }
cfe50f04 2091 ]
9b122384 2092
9b122384
PH
2093 def report_following_redirect(self, new_url):
2094 """Report information extraction."""
79649588 2095 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 2096
4fc946b5
PH
2097 def _extract_rss(self, url, video_id, doc):
2098 playlist_title = doc.find('./channel/title').text
2099 playlist_desc_el = doc.find('./channel/description')
2100 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2101
76c73715
PH
2102 entries = []
2103 for it in doc.findall('./channel/item'):
01aec848
BG
2104 next_url = None
2105 enclosure_nodes = it.findall('./enclosure')
2106 for e in enclosure_nodes:
2107 next_url = e.attrib.get('url')
2108 if next_url:
2109 break
2110
76c73715 2111 if not next_url:
01aec848 2112 next_url = xpath_text(it, 'link', fatal=False)
76c73715
PH
2113
2114 if not next_url:
2115 continue
2116
2117 entries.append({
413c1f8e 2118 '_type': 'url_transparent',
76c73715
PH
2119 'url': next_url,
2120 'title': it.find('title').text,
2121 })
4fc946b5
PH
2122
2123 return {
2124 '_type': 'playlist',
2125 'id': url,
2126 'title': playlist_title,
2127 'description': playlist_desc,
2128 'entries': entries,
2129 }
2130
c8e9a235
PH
2131 def _extract_camtasia(self, url, video_id, webpage):
2132 """ Returns None if no camtasia video can be found. """
2133
2134 camtasia_cfg = self._search_regex(
2135 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2136 webpage, 'camtasia configuration file', default=None)
2137 if camtasia_cfg is None:
2138 return None
2139
2140 title = self._html_search_meta('DC.title', webpage, fatal=True)
2141
2142 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2143 camtasia_cfg = self._download_xml(
2144 camtasia_url, video_id,
2145 note='Downloading camtasia configuration',
2146 errnote='Failed to download camtasia configuration')
2147 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2148
2149 entries = []
2150 for n in fileset_node.getchildren():
2151 url_n = n.find('./uri')
2152 if url_n is None:
2153 continue
2154
2155 entries.append({
2156 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2157 'title': '%s - %s' % (title, n.tag),
2158 'url': compat_urlparse.urljoin(url, url_n.text),
2159 'duration': float_or_none(n.find('./duration').text),
2160 })
2161
2162 return {
2163 '_type': 'playlist',
2164 'entries': entries,
2165 'title': title,
2166 }
2167
9b122384 2168 def _real_extract(self, url):
ebd3c7b3
PH
2169 if url.startswith('//'):
2170 return {
2171 '_type': 'url',
20991253 2172 'url': self.http_scheme() + url,
ebd3c7b3
PH
2173 }
2174
a7130543
JMF
2175 parsed_url = compat_urlparse.urlparse(url)
2176 if not parsed_url.scheme:
04b4d394
PH
2177 default_search = self._downloader.params.get('default_search')
2178 if default_search is None:
1f7ccb90 2179 default_search = 'fixup_error'
04b4d394 2180
1f7ccb90 2181 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
2182 if '/' in url:
2183 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2184 return self.url_result('http://' + url)
1f7ccb90 2185 elif default_search != 'fixup_error':
9c1fc022 2186 if default_search == 'auto_warning':
0e67ab0d
PH
2187 if re.match(r'^(?:url|URL)$', url):
2188 raise ExtractorError(
2189 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2190 expected=True)
2191 else:
2192 self._downloader.report_warning(
7571c02c 2193 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2194 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2195
2196 if default_search in ('error', 'fixup_error'):
7571c02c 2197 raise ExtractorError(
b74e86f4
PH
2198 '%r is not a valid URL. '
2199 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2200 % (url, url), expected=True)
04b4d394 2201 else:
f2f2c0c2
PH
2202 if ':' not in default_search:
2203 default_search += ':'
04b4d394 2204 return self.url_result(default_search + url)
4d54ef20
PH
2205
2206 url, smuggled_data = unsmuggle_url(url)
2207 force_videoid = None
d6e6a422 2208 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2209 if smuggled_data and 'force_videoid' in smuggled_data:
2210 force_videoid = smuggled_data['force_videoid']
2211 video_id = force_videoid
2212 else:
9dcd6fd3 2213 video_id = self._generic_id(url)
3d83a1ae 2214
79649588 2215 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2216
ebab4520 2217 head_req = HEADRequest(url)
23be51d8 2218 head_response = self._request_webpage(
ebab4520
PH
2219 head_req, video_id,
2220 note=False, errnote='Could not send HEAD request to %s' % url,
2221 fatal=False)
42393ce2 2222
23be51d8 2223 if head_response is not False:
42393ce2 2224 # Check for redirect
5551d771 2225 new_url = compat_str(head_response.geturl())
42393ce2
PH
2226 if url != new_url:
2227 self.report_following_redirect(new_url)
4d54ef20
PH
2228 if force_videoid:
2229 new_url = smuggle_url(
2230 new_url, {'force_videoid': force_videoid})
cecaaf3f 2231 return self.url_result(new_url)
42393ce2 2232
23be51d8
PH
2233 full_response = None
2234 if head_response is False:
5c2266df 2235 request = sanitized_Request(url)
58bde34a
S
2236 request.add_header('Accept-Encoding', '*')
2237 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2238 head_response = full_response
2239
f930e0c7
S
2240 info_dict = {
2241 'id': video_id,
9dcd6fd3 2242 'title': self._generic_title(url),
303dcdb9 2243 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
2244 }
2245
23be51d8 2246 # Check for direct link to a video
955737b2 2247 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2248 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2249 if m:
4e363703 2250 format_id = compat_str(m.group('format_id'))
f930e0c7 2251 if format_id.endswith('mpegurl'):
eadc3ccd 2252 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
2253 elif format_id == 'f4m':
2254 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2255 else:
2256 formats = [{
4e363703 2257 'format_id': format_id,
eadc3ccd 2258 'url': url,
2259 'vcodec': 'none' if m.group('type') == 'audio' else None
2260 }]
de6c51e8 2261 info_dict['direct'] = True
19dbaeec 2262 self._sort_formats(formats)
de6c51e8 2263 info_dict['formats'] = formats
f930e0c7 2264 return info_dict
42393ce2 2265
d6e6a422 2266 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
2267 force = self._downloader.params.get('force_generic_extractor', False)
2268 self._downloader.report_warning(
2269 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2270
4e262a88 2271 if not full_response:
5c2266df 2272 request = sanitized_Request(url)
58bde34a
S
2273 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2274 # making it impossible to download only chunk of the file (yet we need only 512kB to
2275 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2276 # that will always result in downloading the whole file that is not desirable.
2277 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2278 # to accept raw bytes and being able to download only a chunk.
2279 # It may probably better to solve this by checking Content-Type for application/octet-stream
2280 # after HEAD request finishes, but not sure if we can rely on this.
2281 request.add_header('Accept-Encoding', '*')
2282 full_response = self._request_webpage(request, video_id)
4e262a88 2283
5940862d
S
2284 first_bytes = full_response.read(512)
2285
2286 # Is it an M3U playlist?
0d769bcb 2287 if first_bytes.startswith(b'#EXTM3U'):
5940862d 2288 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 2289 self._sort_formats(info_dict['formats'])
5940862d
S
2290 return info_dict
2291
4e262a88
PH
2292 # Maybe it's a direct link to a video?
2293 # Be careful not to download the whole thing!
61ca9a80 2294 if not is_html(first_bytes):
4e262a88
PH
2295 self._downloader.report_warning(
2296 'URL could be a direct video link, returning it as such.')
f930e0c7 2297 info_dict.update({
4e262a88
PH
2298 'direct': True,
2299 'url': url,
f930e0c7
S
2300 })
2301 return info_dict
4e262a88
PH
2302
2303 webpage = self._webpage_read_content(
2304 full_response, url, video_id, prefix=first_bytes)
2305
9b122384 2306 self.report_extraction(video_id)
887c6acd 2307
1b840245 2308 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2309 try:
f7854627 2310 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
2311 if doc.tag == 'rss':
2312 return self._extract_rss(url, video_id, doc)
cc99a77a
S
2313 elif doc.tag == 'SmoothStreamingMedia':
2314 info_dict['formats'] = self._parse_ism_formats(doc, url)
2315 self._sort_formats(info_dict['formats'])
2316 return info_dict
e5e8d20a 2317 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
2318 smil = self._parse_smil(doc, url, video_id)
2319 self._sort_formats(smil['formats'])
2320 return smil
729accb4 2321 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
96b8b9ab 2322 return self.playlist_result(
47a5cb77
S
2323 self._parse_xspf(
2324 doc, video_id, xspf_url=url,
2325 xspf_base_url=compat_str(full_response.geturl())),
96b8b9ab 2326 video_id)
1b840245 2327 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7 2328 info_dict['formats'] = self._parse_mpd_formats(
d3f8b76b 2329 doc,
5551d771 2330 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
86f4d14f 2331 mpd_url=url)
19dbaeec 2332 self._sort_formats(info_dict['formats'])
f930e0c7
S
2333 return info_dict
2334 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2335 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 2336 self._sort_formats(info_dict['formats'])
f930e0c7 2337 return info_dict
f7300c5c 2338 except compat_xml_parse_error:
4fc946b5
PH
2339 pass
2340
c8e9a235
PH
2341 # Is it a Camtasia project?
2342 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2343 if camtasia_res is not None:
2344 return camtasia_res
2345
14390730
S
2346 # Sometimes embedded video player is hidden behind percent encoding
2347 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2348 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 2349 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2350
887c6acd
PH
2351 # it's tempting to parse this further, but you would
2352 # have to take into account all the variations like
2353 # Video Title - Site Name
2354 # Site Name | Video Title
2355 # Video Title - Tagline | Site Name
2356 # and so on and so forth; it's just not practical
6f41b2bc
S
2357 video_title = self._og_search_title(
2358 webpage, default=None) or self._html_search_regex(
79649588
PH
2359 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2360 default='video')
ef4fd848 2361
4d805e06
PH
2362 # Try to detect age limit automatically
2363 age_limit = self._rta_search(webpage)
2364 # And then there are the jokers who advertise that they use RTA,
2365 # but actually don't.
2366 AGE_LIMIT_MARKERS = [
197224b7 2367 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
4d805e06
PH
2368 ]
2369 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2370 age_limit = 18
2371
ef4fd848
PH
2372 # video uploader is domain name
2373 video_uploader = self._search_regex(
79649588 2374 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2375
6f41b2bc
S
2376 video_description = self._og_search_description(webpage, default=None)
2377 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2378
b311b0ea
S
2379 info_dict.update({
2380 'title': video_title,
2381 'description': video_description,
2382 'thumbnail': video_thumbnail,
2383 'age_limit': age_limit,
2384 })
2385
1f4b722b 2386 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2387 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2388 if bc_urls:
99877772
PH
2389 entries = [{
2390 '_type': 'url',
2391 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2392 'ie_key': 'BrightcoveLegacy'
99877772
PH
2393 } for bc_url in bc_urls]
2394
2395 return {
2396 '_type': 'playlist',
2397 'title': video_title,
2398 'id': video_id,
2399 'entries': entries,
2400 }
cfe50f04 2401
f6519f89 2402 # Look for Brightcove New Studio embeds
0254f93b 2403 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2404 if bc_urls:
5399ab3f
S
2405 return self.playlist_from_matches(
2406 bc_urls, video_id, video_title,
2407 getter=lambda x: smuggle_url(x, {'referrer': url}),
2408 ie='BrightcoveNew')
ed126900 2409
4e826cd9
S
2410 # Look for Nexx embeds
2411 nexx_urls = NexxIE._extract_urls(webpage)
2412 if nexx_urls:
2413 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2414
3f59b015
S
2415 # Look for Nexx iFrame embeds
2416 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2417 if nexx_embed_urls:
2418 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2419
4d8819d2
S
2420 # Look for ThePlatform embeds
2421 tp_urls = ThePlatformIE._extract_urls(webpage)
2422 if tp_urls:
46b18f23 2423 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2424
48a5eabc
S
2425 # Look for Vessel embeds
2426 vessel_urls = VesselIE._extract_urls(webpage)
2427 if vessel_urls:
46b18f23 2428 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
48a5eabc 2429
59b8ab58
PH
2430 # Look for embedded rtl.nl player
2431 matches = re.findall(
2637fadc 2432 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
59b8ab58
PH
2433 webpage)
2434 if matches:
46b18f23 2435 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2436
09b9c45e
S
2437 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2438 if vimeo_urls:
46b18f23 2439 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2440
a1b85269
YCH
2441 vid_me_embed_url = self._search_regex(
2442 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2443 webpage, 'vid.me embed', default=None)
2444 if vid_me_embed_url is not None:
2445 return self.url_result(vid_me_embed_url, 'Vidme')
2446
66c9fa36
S
2447 # Look for YouTube embeds
2448 youtube_urls = YoutubeIE._extract_urls(webpage)
2449 if youtube_urls:
46b18f23 2450 return self.playlist_from_matches(
66c9fa36 2451 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2452
ad213a1d 2453 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2454 if matches:
46b18f23 2455 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2456
8489578d
NJ
2457 # Look for embedded Dailymotion playlist player (#3822)
2458 m = re.search(
2459 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2460 if m:
2461 playlists = re.findall(
2462 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2463 if playlists:
46b18f23
JH
2464 return self.playlist_from_matches(
2465 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2466
71a1db89
S
2467 # Look for DailyMail embeds
2468 dailymail_urls = DailyMailIE._extract_urls(webpage)
2469 if dailymail_urls:
2470 return self.playlist_from_matches(
2471 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2472
ef4fd848 2473 # Look for embedded Wistia player
58bb4402
S
2474 wistia_url = WistiaIE._extract_url(webpage)
2475 if wistia_url:
ef4fd848
PH
2476 return {
2477 '_type': 'url_transparent',
58bb4402
S
2478 'url': self._proto_relative_url(wistia_url),
2479 'ie_key': WistiaIE.ie_key(),
ef4fd848 2480 'uploader': video_uploader,
ef4fd848 2481 }
5f6a1245 2482
bab19a8e
S
2483 # Look for SVT player
2484 svt_url = SVTIE._extract_url(webpage)
2485 if svt_url:
2486 return self.url_result(svt_url, 'SVT')
2487
c19f7764
JMF
2488 # Look for Bandcamp pages with custom domain
2489 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2490 if mobj is not None:
2491 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2492 # Don't set the extractor because it can be a track url or an album
2493 return self.url_result(burl)
c19f7764 2494
f25571ff
PH
2495 # Look for embedded Vevo player
2496 mobj = re.search(
2497 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2498 if mobj is not None:
2499 return self.url_result(mobj.group('url'))
796df3c6
S
2500
2501 # Look for embedded Viddler player
cb454b33
S
2502 mobj = re.search(
2503 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2504 webpage)
796df3c6
S
2505 if mobj is not None:
2506 return self.url_result(mobj.group('url'))
f25571ff 2507
3378d67a
S
2508 # Look for NYTimes player
2509 mobj = re.search(
2510 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2511 webpage)
2512 if mobj is not None:
2513 return self.url_result(mobj.group('url'))
2514
cefdf970
S
2515 # Look for Libsyn player
2516 mobj = re.search(
2517 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2518 if mobj is not None:
2519 return self.url_result(mobj.group('url'))
2520
c0d0b01f 2521 # Look for Ooyala videos
8a37aa15 2522 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 2523 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
198d4cb4 2524 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
2525 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2526 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2527 if mobj is not None:
9837cb75
RA
2528 embed_token = self._search_regex(
2529 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2530 webpage, 'ooyala embed token', default=None)
2531 return OoyalaIE._build_url_result(smuggle_url(
2532 mobj.group('ec'), {
2533 'domain': url,
2534 'embed_token': embed_token,
2535 }))
c0d0b01f 2536
f076b638 2537 # Look for multiple Ooyala embeds on SBN network websites
2538 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2539 if mobj is not None:
2540 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2541 if embeds:
46b18f23
JH
2542 return self.playlist_from_matches(
2543 embeds, video_id, video_title,
2544 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2545
aa94a6d3 2546 # Look for Aparat videos
48099643 2547 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2548 if mobj is not None:
2549 return self.url_result(mobj.group(1), 'Aparat')
2550
c93c2ab1 2551 # Look for MPORA videos
c3f51436 2552 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2553 if mobj is not None:
2554 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2555
15c0e8e7 2556 # Look for embedded NovaMov-based player
8f89e687 2557 mobj = re.search(
8dfa187b 2558 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
2559 (?P<url>http://(?:(?:embed|www)\.)?
2560 (?:novamov\.com|
2561 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2562 videoweed\.(?:es|com)|
2563 movshare\.(?:net|sx|ag)|
2564 divxstage\.(?:eu|net|ch|co|at|ag))
2565 /embed\.php.+?)\1''', webpage)
8f89e687 2566 if mobj is not None:
15c0e8e7 2567 return self.url_result(mobj.group('url'))
50f56607 2568
9834872b 2569 # Look for embedded Facebook player
0646e34c
S
2570 facebook_urls = FacebookIE._extract_urls(webpage)
2571 if facebook_urls:
2572 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2573
ca97a56e
S
2574 # Look for embedded VK player
2575 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2576 if mobj is not None:
2577 return self.url_result(mobj.group('url'), 'VK')
2578
33d4fdab
S
2579 # Look for embedded Odnoklassniki player
2580 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2581 if mobj is not None:
2582 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2583
0364fa8b
S
2584 # Look for embedded ivi player
2585 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2586 if mobj is not None:
2587 return self.url_result(mobj.group('url'), 'Ivi')
2588
db1f3888
PH
2589 # Look for embedded Huffington Post player
2590 mobj = re.search(
c3f51436 2591 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2592 if mobj is not None:
2593 return self.url_result(mobj.group('url'), 'HuffPost')
2594
1b86cc41 2595 # Look for embed.ly
2596 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2597 if mobj is not None:
2598 return self.url_result(mobj.group('url'))
2599 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2600 if mobj is not None:
f7e6f7fa 2601 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2602
60cc4dc4
PH
2603 # Look for funnyordie embed
2604 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2605 if matches:
46b18f23
JH
2606 return self.playlist_from_matches(
2607 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2608
db546cf8
S
2609 # Look for BBC iPlayer embed
2610 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2611 if matches:
46b18f23 2612 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2613
93d020dd
S
2614 # Look for embedded RUTV player
2615 rutv_url = RUTVIE._extract_url(webpage)
2616 if rutv_url:
2617 return self.url_result(rutv_url, 'RUTV')
2618
494f20cb 2619 # Look for embedded TVC player
b8599718
S
2620 tvc_url = TVCIE._extract_url(webpage)
2621 if tvc_url:
2622 return self.url_result(tvc_url, 'TVC')
494f20cb 2623
d40a3b5b
S
2624 # Look for embedded SportBox player
2625 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2626 if sportbox_urls:
46b18f23 2627 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
d40a3b5b 2628
2bb5b6d0
S
2629 # Look for embedded XHamster player
2630 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2631 if xhamster_urls:
46b18f23 2632 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2633
2c9ca782
S
2634 # Look for embedded TNAFlixNetwork player
2635 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2636 if tnaflix_urls:
46b18f23 2637 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2638
b52c9ef1
S
2639 # Look for embedded PornHub player
2640 pornhub_urls = PornHubIE._extract_urls(webpage)
2641 if pornhub_urls:
46b18f23 2642 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2643
37e7a71c
S
2644 # Look for embedded DrTuber player
2645 drtuber_urls = DrTuberIE._extract_urls(webpage)
2646 if drtuber_urls:
46b18f23 2647 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2648
e28ed498
S
2649 # Look for embedded RedTube player
2650 redtube_urls = RedTubeIE._extract_urls(webpage)
2651 if redtube_urls:
46b18f23 2652 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 2653
06993715
S
2654 # Look for embedded Tube8 player
2655 tube8_urls = Tube8IE._extract_urls(webpage)
2656 if tube8_urls:
2657 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2658
9872d311
S
2659 # Look for embedded Tvigle player
2660 mobj = re.search(
2661 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2662 if mobj is not None:
2663 return self.url_result(mobj.group('url'), 'Tvigle')
2664
7e2ede98
JMF
2665 # Look for embedded TED player
2666 mobj = re.search(
d7cc31b6 2667 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
2668 if mobj is not None:
2669 return self.url_result(mobj.group('url'), 'TED')
2670
5c386252 2671 # Look for embedded Ustream videos
d77ac737
YCH
2672 ustream_url = UstreamIE._extract_url(webpage)
2673 if ustream_url:
2674 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 2675
893f8832
PH
2676 # Look for embedded arte.tv player
2677 mobj = re.search(
134c207e 2678 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
893f8832
PH
2679 webpage)
2680 if mobj is not None:
2681 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2682
cbd55ade
S
2683 # Look for embedded francetv player
2684 mobj = re.search(
2685 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2686 webpage)
2687 if mobj is not None:
2688 return self.url_result(mobj.group('url'))
2689
cb3ac1c6
S
2690 # Look for embedded smotri.com player
2691 smotri_url = SmotriIE._extract_url(webpage)
2692 if smotri_url:
2693 return self.url_result(smotri_url, 'Smotri')
2694
e6c2d9ad 2695 # Look for embedded Myvi.ru player
6dd94d3a 2696 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
2697 if myvi_url:
2698 return self.url_result(myvi_url)
2699
dfb1b146 2700 # Look for embedded soundcloud player
94aae015
S
2701 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2702 if soundcloud_urls:
46b18f23 2703 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
20991253 2704
027e2312
S
2705 # Look for tunein player
2706 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2707 if tunein_urls:
46b18f23 2708 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 2709
c5cd249e 2710 # Look for embedded mtvservices player
46fde8a1
S
2711 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2712 if mtvservices_url:
2713 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 2714
49807b4a
S
2715 # Look for embedded yahoo player
2716 mobj = re.search(
2717 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2718 webpage)
2719 if mobj is not None:
2720 return self.url_result(mobj.group('url'), 'Yahoo')
2721
2ef6fcb5
PH
2722 # Look for embedded sbs.com.au player
2723 mobj = re.search(
e98b8e79
PH
2724 r'''(?x)
2725 (?:
2726 <meta\s+property="og:video"\s+content=|
2727 <iframe[^>]+?src=
2728 )
2729 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
2730 webpage)
2731 if mobj is not None:
2732 return self.url_result(mobj.group('url'), 'SBS')
2733
42bdd9d0
PH
2734 # Look for embedded Cinchcast player
2735 mobj = re.search(
2736 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2737 webpage)
2738 if mobj is not None:
2739 return self.url_result(mobj.group('url'), 'Cinchcast')
2740
1a94ff68 2741 mobj = re.search(
5263cdfc 2742 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 2743 webpage)
8001607e
YCH
2744 if not mobj:
2745 mobj = re.search(
2746 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2747 webpage)
1a94ff68
S
2748 if mobj is not None:
2749 return self.url_result(mobj.group('url'), 'MLB')
2750
1419fafd 2751 mobj = re.search(
dd467d33 2752 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
2753 webpage)
2754 if mobj is not None:
2755 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2756
af63fed7 2757 mobj = re.search(
78d3b3e2 2758 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
2759 webpage)
2760 if mobj is not None:
2761 return self.url_result(mobj.group('url'), 'Livestream')
2762
255fca5e
S
2763 # Look for Zapiks embed
2764 mobj = re.search(
2765 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2766 if mobj is not None:
2767 return self.url_result(mobj.group('url'), 'Zapiks')
2768
e3216b82 2769 # Look for Kaltura embeds
c287f2bc
S
2770 kaltura_url = KalturaIE._extract_url(webpage)
2771 if kaltura_url:
2772 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
e3216b82 2773
665e9452 2774 # Look for EaglePlatform embeds
06a96da1
S
2775 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2776 if eagleplatform_url:
665e9452 2777 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 2778
665e9452 2779 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
2780 mobj = re.search(
2781 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2782 if mobj is not None:
2783 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2784
f8388757 2785 # Look for Pladform embeds
45dad7ba
S
2786 pladform_url = PladformIE._extract_url(webpage)
2787 if pladform_url:
2788 return self.url_result(pladform_url)
f8388757 2789
ff18735c
S
2790 # Look for Videomore embeds
2791 videomore_url = VideomoreIE._extract_url(webpage)
2792 if videomore_url:
2793 return self.url_result(videomore_url)
2794
83f1481b
S
2795 # Look for Webcaster embeds
2796 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2797 if webcaster_url:
2798 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2799
2dcc114f
S
2800 # Look for Playwire embeds
2801 mobj = re.search(
2802 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2803 if mobj is not None:
2804 return self.url_result(mobj.group('url'))
2805
ad320e9b
NJ
2806 # Look for 5min embeds
2807 mobj = re.search(
2808 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2809 if mobj is not None:
2810 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2811
18153f1b
S
2812 # Look for Crooks and Liars embeds
2813 mobj = re.search(
2814 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2815 if mobj is not None:
2816 return self.url_result(mobj.group('url'))
2817
a2edf2e7
YCH
2818 # Look for NBC Sports VPlayer embeds
2819 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2820 if nbc_sports_url:
2821 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2822
de3eb07e
YCH
2823 # Look for NBC News embeds
2824 nbc_news_embed_url = re.search(
2825 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2826 if nbc_news_embed_url:
2827 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2828
653789af 2829 # Look for Google Drive embeds
5b251628 2830 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 2831 if google_drive_url:
2832 return self.url_result(google_drive_url, 'GoogleDrive')
2833
418c5cc3
YCH
2834 # Look for UDN embeds
2835 mobj = re.search(
2637fadc 2836 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
2837 if mobj is not None:
2838 return self.url_result(
0a160363 2839 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 2840
2fe1b5bd
YCH
2841 # Look for Senate ISVP iframe
2842 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2843 if senate_isvp_url:
25c3a734 2844 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 2845
1ac1c4c2
S
2846 # Look for OnionStudios embeds
2847 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2848 if onionstudios_url:
2849 return self.url_result(onionstudios_url)
2850
67167920 2851 # Look for ViewLift embeds
2852 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2853 if viewlift_url:
2854 return self.url_result(viewlift_url)
eedd20ef 2855
7cb09524 2856 # Look for JWPlatform embeds
b0ead0e0
S
2857 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2858 if jwplatform_urls:
2859 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
7cb09524 2860
aecfcd4e
S
2861 # Look for Digiteka embeds
2862 digiteka_url = DigitekaIE._extract_url(webpage)
2863 if digiteka_url:
2864 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 2865
1979969f
S
2866 # Look for Arkena embeds
2867 arkena_url = ArkenaIE._extract_url(webpage)
2868 if arkena_url:
2869 return self.url_result(arkena_url, ArkenaIE.ie_key())
2870
b1c35797
RA
2871 # Look for Piksel embeds
2872 piksel_url = PikselIE._extract_url(webpage)
2873 if piksel_url:
2874 return self.url_result(piksel_url, PikselIE.ie_key())
2875
1bf996fa 2876 # Look for Limelight embeds
e5d39886
S
2877 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2878 if limelight_urls:
2879 return self.playlist_result(
2880 limelight_urls, video_id, video_title, video_description)
2881
7986c3ab
S
2882 # Look for Anvato embeds
2883 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2884 if anvato_urls:
2885 return self.playlist_result(
2886 anvato_urls, video_id, video_title, video_description)
2887
a5158f38
YCH
2888 # Look for AdobeTVVideo embeds
2889 mobj = re.search(
2890 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2891 webpage)
2892 if mobj is not None:
2893 return self.url_result(
2894 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2895 'AdobeTVVideo')
2896
088e1aac
YCH
2897 # Look for Vine embeds
2898 mobj = re.search(
2899 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2900 webpage)
2901 if mobj is not None:
2902 return self.url_result(
2903 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2904
217d5ae0
RA
2905 # Look for VODPlatform embeds
2906 mobj = re.search(
93b84045 2907 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
217d5ae0
RA
2908 webpage)
2909 if mobj is not None:
2910 return self.url_result(
93b84045 2911 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 2912
7d273a38
RA
2913 # Look for Mangomolo embeds
2914 mobj = re.search(
d05ef09d 2915 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
7d273a38
RA
2916 (?:
2917 video\?.*?\bid=(?P<video_id>\d+)|
2918 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2919 ).+?)\1''', webpage)
2920 if mobj is not None:
2921 info = {
2922 '_type': 'url_transparent',
2923 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2924 'title': video_title,
2925 'description': video_description,
2926 'thumbnail': video_thumbnail,
2927 'uploader': video_uploader,
2928 }
2929 video_id = mobj.group('video_id')
2930 if video_id:
2931 info.update({
2932 'ie_key': 'MangomoloVideo',
2933 'id': video_id,
2934 })
2935 else:
2936 info.update({
2937 'ie_key': 'MangomoloLive',
2938 'id': mobj.group('channel_id'),
2939 })
2940 return info
2941
5a51775a
YCH
2942 # Look for Instagram embeds
2943 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2944 if instagram_embed_url is not None:
11e60fca
S
2945 return self.url_result(
2946 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 2947
b8f67449 2948 # Look for LiveLeak embeds
09747ba7
YCH
2949 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2950 if liveleak_urls:
2951 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
b8f67449 2952
5d39176f
S
2953 # Look for 3Q SDN embeds
2954 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2955 if threeqsdn_url:
6f41b2bc
S
2956 return {
2957 '_type': 'url_transparent',
2958 'ie_key': ThreeQSDNIE.ie_key(),
2959 'url': self._proto_relative_url(threeqsdn_url),
2960 'title': video_title,
2961 'description': video_description,
2962 'thumbnail': video_thumbnail,
2963 'uploader': video_uploader,
2964 }
5d39176f 2965
2a1321a2
S
2966 # Look for VBOX7 embeds
2967 vbox7_url = Vbox7IE._extract_url(webpage)
2968 if vbox7_url:
2969 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2970
b0c8f2e9
DR
2971 # Look for DBTV embeds
2972 dbtv_urls = DBTVIE._extract_urls(webpage)
2973 if dbtv_urls:
46b18f23 2974 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 2975
e186a9ec
S
2976 # Look for Videa embeds
2977 videa_urls = VideaIE._extract_urls(webpage)
2978 if videa_urls:
46b18f23 2979 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 2980
b687c85e
S
2981 # Look for 20 minuten embeds
2982 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2983 if twentymin_urls:
46b18f23
JH
2984 return self.playlist_from_matches(
2985 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 2986
17f8deeb
S
2987 # Look for Openload embeds
2988 openload_urls = OpenloadIE._extract_urls(webpage)
2989 if openload_urls:
46b18f23
JH
2990 return self.playlist_from_matches(
2991 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
17f8deeb 2992
6ef3e65a
S
2993 # Look for VideoPress embeds
2994 videopress_urls = VideoPressIE._extract_urls(webpage)
2995 if videopress_urls:
46b18f23
JH
2996 return self.playlist_from_matches(
2997 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 2998
eb3079b6
S
2999 # Look for Rutube embeds
3000 rutube_urls = RutubeIE._extract_urls(webpage)
3001 if rutube_urls:
46b18f23 3002 return self.playlist_from_matches(
2583c0b5 3003 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 3004
55719459
JH
3005 # Look for WashingtonPost embeds
3006 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3007 if wapo_urls:
3008 return self.playlist_from_matches(
3009 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3010
5d29af3d
S
3011 # Look for Mediaset embeds
3012 mediaset_urls = MediasetIE._extract_urls(webpage)
3013 if mediaset_urls:
3014 return self.playlist_from_matches(
3015 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3016
73cf76a9
S
3017 # Look for JOJ.sk embeds
3018 joj_urls = JojIE._extract_urls(webpage)
3019 if joj_urls:
3020 return self.playlist_from_matches(
3021 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3022
24e966e8
PH
3023 # Look for megaphone.fm embeds
3024 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3025 if mpfn_urls:
3026 return self.playlist_from_matches(
3027 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3028
1663bd6e
S
3029 # Look for vzaar embeds
3030 vzaar_urls = VzaarIE._extract_urls(webpage)
3031 if vzaar_urls:
3032 return self.playlist_from_matches(
3033 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3034
26bae2d9
S
3035 channel9_urls = Channel9IE._extract_urls(webpage)
3036 if channel9_urls:
3037 return self.playlist_from_matches(
3038 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3039
0987f2dd
T
3040 vshare_urls = VShareIE._extract_urls(webpage)
3041 if vshare_urls:
3042 return self.playlist_from_matches(
3043 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3044
8056c854 3045 # Look for Mediasite embeds
2ca7ed41
S
3046 mediasite_urls = MediasiteIE._extract_urls(webpage)
3047 if mediasite_urls:
3048 entries = [
3049 self.url_result(smuggle_url(
3050 compat_urlparse.urljoin(url, mediasite_url),
3051 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3052 for mediasite_url in mediasite_urls]
3053 return self.playlist_result(entries, video_id, video_title)
8056c854 3054
7d540621
S
3055 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3056 if springboardplatform_urls:
3057 return self.playlist_from_matches(
3058 springboardplatform_urls, video_id, video_title,
3059 ie=SpringboardPlatformIE.ie_key())
3060
4c780fbd
S
3061 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3062 if yapfiles_urls:
3063 return self.playlist_from_matches(
3064 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3065
86c8cfc5
S
3066 vice_urls = ViceIE._extract_urls(webpage)
3067 if vice_urls:
3068 return self.playlist_from_matches(
3069 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3070
178ee883
S
3071 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3072 if xfileshare_urls:
3073 return self.playlist_from_matches(
3074 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3075
660a230b
S
3076 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3077 if cloudflarestream_urls:
3078 return self.playlist_from_matches(
3079 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3080
8b4b400a 3081 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
6bd499e8
S
3082 if peertube_urls:
3083 return self.playlist_from_matches(
3084 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3085
aee36ca8
S
3086 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3087 if indavideo_urls:
3088 return self.playlist_from_matches(
3089 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3090
cfd7f2a6
S
3091 apa_urls = APAIE._extract_urls(webpage)
3092 if apa_urls:
3093 return self.playlist_from_matches(
3094 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3095
f51f526b
S
3096 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3097 if foxnews_urls:
3098 return self.playlist_from_matches(
3099 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3100
d3431dcb
S
3101 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
3102 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3103 webpage)]
3104 if sharevideos_urls:
3105 return self.playlist_from_matches(
3106 sharevideos_urls, video_id, video_title)
3107
9d1b2138
S
3108 viqeo_urls = ViqeoIE._extract_urls(webpage)
3109 if viqeo_urls:
3110 return self.playlist_from_matches(
3111 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
57c68ec4
S
3112
3113 expressen_urls = ExpressenIE._extract_urls(webpage)
3114 if expressen_urls:
3115 return self.playlist_from_matches(
3116 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
9d1b2138 3117
bd264412
YCH
3118 # Look for HTML5 media
3119 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3120 if entries:
9ce1ac40 3121 if len(entries) == 1:
3122 entries[0].update({
bd264412
YCH
3123 'id': video_id,
3124 'title': video_title,
3125 })
9ce1ac40 3126 else:
3127 for num, entry in enumerate(entries, start=1):
3128 entry.update({
3129 'id': '%s-%s' % (video_id, num),
3130 'title': '%s (%d)' % (video_title, num),
3131 })
3132 for entry in entries:
bd264412 3133 self._sort_formats(entry['formats'])
9ce1ac40 3134 return self.playlist_result(entries, video_id, video_title)
bd264412 3135
c73e330e
RU
3136 jwplayer_data = self._find_jwplayer_data(
3137 webpage, video_id, transform_source=js_to_json)
3138 if jwplayer_data:
4f06c1c9 3139 info = self._parse_jwplayer_data(
3e943cfe 3140 jwplayer_data, video_id, require_title=False, base_url=url)
b311b0ea 3141 return merge_dicts(info, info_dict)
a4a554a7 3142
63d990d2
S
3143 # Video.js embed
3144 mobj = re.search(
c5b7014a 3145 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
3146 webpage)
3147 if mobj is not None:
3148 sources = self._parse_json(
3149 mobj.group(1), video_id, transform_source=js_to_json,
3150 fatal=False) or []
c5b7014a
S
3151 if not isinstance(sources, list):
3152 sources = [sources]
63d990d2
S
3153 formats = []
3154 for source in sources:
3052a30d
S
3155 src = url_or_none(source.get('src'))
3156 if not src:
63d990d2
S
3157 continue
3158 src = compat_urlparse.urljoin(url, src)
3159 src_type = source.get('type')
3160 if isinstance(src_type, compat_str):
3161 src_type = src_type.lower()
3162 ext = determine_ext(src).lower()
3163 if src_type == 'video/youtube':
3164 return self.url_result(src, YoutubeIE.ie_key())
3165 if src_type == 'application/dash+xml' or ext == 'mpd':
3166 formats.extend(self._extract_mpd_formats(
3167 src, video_id, mpd_id='dash', fatal=False))
3168 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3169 formats.extend(self._extract_m3u8_formats(
3170 src, video_id, 'mp4', entry_protocol='m3u8_native',
3171 m3u8_id='hls', fatal=False))
3172 else:
3173 formats.append({
3174 'url': src,
3175 'ext': (mimetype2ext(src_type) or
3176 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3177 })
3178 if formats:
3179 self._sort_formats(formats)
3180 info_dict['formats'] = formats
3181 return info_dict
3182
ff17be3a
S
3183 # Looking for http://schema.org/VideoObject
3184 json_ld = self._search_json_ld(
3185 webpage, video_id, default={}, expected_type='VideoObject')
3186 if json_ld.get('url'):
3187 return merge_dicts(json_ld, info_dict)
3188
ced659bb 3189 def check_video(vurl):
a0f71985
PH
3190 if YoutubeIE.suitable(vurl):
3191 return True
b7a8c1bc
S
3192 if RtmpIE.suitable(vurl):
3193 return True
ced659bb
S
3194 vpath = compat_urlparse.urlparse(vurl).path
3195 vext = determine_ext(vpath)
0ee79a37 3196 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
3197
3198 def filter_video(urls):
3199 return list(filter(check_video, urls))
3200
9b122384 3201 # Start with something easy: JW Player in SWFObject
ced659bb 3202 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 3203 if not found:
d981cef6 3204 # Look for gorilla-vid style embedding
ced659bb 3205 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
3206 (?:
3207 jw_plugins|
3208 JWPlayerOptions|
3209 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3210 )
a0f71985
PH
3211 .*?
3212 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 3213 if not found:
9b122384 3214 # Broaden the search a little bit
ced659bb 3215 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
3216 if not found:
3217 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 3218 found = filter_video(re.findall(
54a9328b 3219 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
3220 if not found:
3221 # Flow player
ced659bb 3222 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
3223 flowplayer\("[^"]+",\s*
3224 \{[^}]+?\}\s*,
52585fd6 3225 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 3226 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 3227 ''', webpage))
501f13fb
PH
3228 if not found:
3229 # Cinerama player
3230 found = re.findall(
3231 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 3232 if not found:
9b122384 3233 # Try to find twitter cards info
371ddb14
S
3234 # twitter:player:stream should be checked before twitter:player since
3235 # it is expected to contain a raw stream (see
3236 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3237 found = filter_video(re.findall(
3238 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 3239 if not found:
9b122384
PH
3240 # We look for Open Graph info:
3241 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3242 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3243 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3244 if m_video_type is not None:
ced659bb 3245 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 3246 if not found:
ed9a25dd 3247 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3248 found = re.search(
89ef304b 3249 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3250 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3251 webpage)
84f81016
S
3252 if not found:
3253 # Look also in Refresh HTTP header
3254 refresh_header = head_response.headers.get('Refresh')
3255 if refresh_header:
6c91a5a7
S
3256 # In python 2 response HTTP headers are bytestrings
3257 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3258 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3259 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3260 if found:
b37317d8 3261 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3262 if new_url != url:
3263 self.report_following_redirect(new_url)
3264 return {
3265 '_type': 'url',
3266 'url': new_url,
3267 }
3268 else:
3269 found = None
371ddb14
S
3270
3271 if not found:
3272 # twitter:player is a https URL to iframe player that may or may not
3273 # be supported by youtube-dl thus this is checked the very last (see
3274 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3275 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3276 if embed_url and embed_url != url:
371ddb14
S
3277 return self.url_result(embed_url)
3278
b30b8698 3279 if not found:
416c7fcb 3280 raise UnsupportedError(url)
9b122384 3281
b30b8698 3282 entries = []
4a120778 3283 for video_url in orderedSet(found):
949b6497 3284 video_url = unescapeHTML(video_url)
6cc37c69 3285 video_url = video_url.replace('\\/', '/')
b30b8698 3286 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3287 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3288
b30b8698
PH
3289 # Sometimes, jwplayer extraction will result in a YouTube URL
3290 if YoutubeIE.suitable(video_url):
3291 entries.append(self.url_result(video_url, 'Youtube'))
3292 continue
9b122384 3293
b30b8698
PH
3294 # here's a fun little line of code for you:
3295 video_id = os.path.splitext(video_id)[0]
fc9713a1 3296
28602e74
YCH
3297 entry_info_dict = {
3298 'id': video_id,
3299 'uploader': video_uploader,
3300 'title': video_title,
3301 'age_limit': age_limit,
3302 }
3303
5620f840
S
3304 if RtmpIE.suitable(video_url):
3305 entry_info_dict.update({
3306 '_type': 'url_transparent',
3307 'ie_key': RtmpIE.ie_key(),
3308 'url': video_url,
3309 })
3310 entries.append(entry_info_dict)
3311 continue
3312
729accb4
S
3313 ext = determine_ext(video_url)
3314 if ext == 'smil':
28602e74 3315 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
3316 elif ext == 'xspf':
3317 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
3318 elif ext == 'm3u8':
3319 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
3320 elif ext == 'mpd':
3321 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
3322 elif ext == 'f4m':
3323 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3324 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3325 # Just matching .ism/manifest is not enough to be reliably sure
3326 # whether it's actually an ISM manifest or some other streaming
3327 # manifest since there are various streaming URL formats
3328 # possible (see [1]) as well as some other shenanigans like
3329 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3330 # so on.
3331 # Thus the most reasonable way to solve this is to delegate
3332 # to generic extractor in order to look into the contents of
3333 # the manifest itself.
3334 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3335 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3336 entry_info_dict = self.url_result(
3337 smuggle_url(video_url, {'to_generic': True}),
3338 GenericIE.ie_key())
d6fd958c 3339 else:
28602e74
YCH
3340 entry_info_dict['url'] = video_url
3341
19dbaeec
S
3342 if entry_info_dict.get('formats'):
3343 self._sort_formats(entry_info_dict['formats'])
3344
28602e74 3345 entries.append(entry_info_dict)
b30b8698
PH
3346
3347 if len(entries) == 1:
669f0e7c 3348 return entries[0]
b30b8698
PH
3349 else:
3350 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3351 # 'url' results don't have a title
3352 if e.get('title') is not None:
3353 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3354 return {
3355 '_type': 'playlist',
3356 'entries': entries,
3357 }