]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
[izlesene] Improve extraction and fix issues (closes #16407, closes #16271)
[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,
76c73715 35 xpath_text,
9b122384 36)
b7a8c1bc 37from .commonprotocols import RtmpIE
ed126900 38from .brightcove import (
4fcaa4f4 39 BrightcoveLegacyIE,
5c17f0a6 40 BrightcoveNewIE,
ed126900 41)
3f59b015
S
42from .nexx import (
43 NexxIE,
44 NexxEmbedIE,
45)
a2edf2e7 46from .nbc import NBCSportsVPlayerIE
c0d0b01f 47from .ooyala import OoyalaIE
93d020dd 48from .rutv import RUTVIE
954c1d05 49from .tvc import TVCIE
d40a3b5b 50from .sportbox import SportBoxEmbedIE
cb3ac1c6 51from .smotri import SmotriIE
6dd94d3a 52from .myvi import MyviIE
1419fafd 53from .condenast import CondeNastIE
418c5cc3 54from .udn import UDNEmbedIE
2fe1b5bd 55from .senateisvp import SenateISVPIE
bab19a8e 56from .svt import SVTIE
65d161c4 57from .pornhub import PornHubIE
2bb5b6d0 58from .xhamster import XHamsterEmbedIE
2c9ca782 59from .tnaflix import TNAFlixNetworkEmbedIE
37e7a71c 60from .drtuber import DrTuberIE
e28ed498 61from .redtube import RedTubeIE
06993715 62from .tube8 import Tube8IE
b407e173 63from .vimeo import VimeoIE
3c4fbfec 64from .dailymotion import DailymotionIE
71a1db89 65from .dailymail import DailyMailIE
1ac1c4c2 66from .onionstudios import OnionStudiosIE
67167920 67from .viewlift import ViewLiftEmbedIE
46fde8a1 68from .mtv import MTVServicesEmbeddedIE
45dad7ba 69from .pladform import PladformIE
ff18735c 70from .videomore import VideomoreIE
83f1481b 71from .webcaster import WebcasterFeedIE
5b251628 72from .googledrive import GoogleDriveIE
7cb09524 73from .jwplatform import JWPlatformIE
aecfcd4e 74from .digiteka import DigitekaIE
1979969f 75from .arkena import ArkenaIE
5a51775a 76from .instagram import InstagramIE
b8f67449 77from .liveleak import LiveLeakIE
5d39176f 78from .threeqsdn import ThreeQSDNIE
4d8819d2 79from .theplatform import ThePlatformIE
48a5eabc 80from .vessel import VesselIE
c287f2bc 81from .kaltura import KalturaIE
06a96da1 82from .eagleplatform import EaglePlatformIE
fd6ca382 83from .facebook import FacebookIE
94aae015 84from .soundcloud import SoundcloudIE
027e2312 85from .tunein import TuneInBaseIE
2a1321a2 86from .vbox7 import Vbox7IE
b0c8f2e9 87from .dbtv import DBTVIE
b1c35797 88from .piksel import PikselIE
e186a9ec 89from .videa import VideaIE
b687c85e 90from .twentymin import TwentyMinutenIE
d77ac737 91from .ustream import UstreamIE
17f8deeb 92from .openload import OpenloadIE
6ef3e65a 93from .videopress import VideoPressIE
eb3079b6 94from .rutube import RutubeIE
e5d39886 95from .limelight import LimelightBaseIE
7986c3ab 96from .anvato import AnvatoIE
55719459 97from .washingtonpost import WashingtonPostIE
58bb4402 98from .wistia import WistiaIE
5d29af3d 99from .mediaset import MediasetIE
73cf76a9 100from .joj import JojIE
24e966e8 101from .megaphone import MegaphoneIE
41918eaa 102from .vzaar import VzaarIE
26bae2d9 103from .channel9 import Channel9IE
0987f2dd 104from .vshare import VShareIE
2ca7ed41 105from .mediasite import MediasiteIE
7d540621 106from .springboardplatform import SpringboardPlatformIE
4c780fbd 107from .yapfiles import YapFilesIE
86c8cfc5 108from .vice import ViceIE
178ee883 109from .xfileshare import XFileShareIE
660a230b 110from .cloudflarestream import CloudflareStreamIE
6bd499e8 111from .peertube import PeerTubeIE
aee36ca8 112from .indavideo import IndavideoEmbedIE
9b122384 113
0838239e 114
9b122384 115class GenericIE(InfoExtractor):
79649588 116 IE_DESC = 'Generic downloader that works on some sites'
9b122384 117 _VALID_URL = r'.*'
79649588 118 IE_NAME = 'generic'
cfe50f04 119 _TESTS = [
c5fa81fe
S
120 # Direct link to a video
121 {
122 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
123 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
124 'info_dict': {
125 'id': 'trailer',
126 'ext': 'mp4',
127 'title': 'trailer',
128 'upload_date': '20100513',
129 }
130 },
c5138a7c 131 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
132 {
133 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
134 'md5': '128c42e68b13950268b648275386fc74',
135 'info_dict': {
136 'id': 'FictionJunction-Parallel_Hearts',
137 'ext': 'flac',
138 'title': 'FictionJunction-Parallel_Hearts',
139 'upload_date': '20140522',
140 },
141 'expected_warnings': [
142 'URL could be a direct video link, returning it as such.'
39efc6e3
YCH
143 ],
144 'skip': 'URL invalid',
c5fa81fe
S
145 },
146 # Direct download with broken HEAD
147 {
148 'url': 'http://ai-radio.org:8000/radio.opus',
149 'info_dict': {
150 'id': 'radio',
151 'ext': 'opus',
152 'title': 'radio',
153 },
154 'params': {
155 'skip_download': True, # infinite live stream
156 },
157 'expected_warnings': [
ef0e4e7b
YCH
158 r'501.*Not Implemented',
159 r'400.*Bad Request',
c5fa81fe
S
160 ],
161 },
162 # Direct link with incorrect MIME type
163 {
164 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
165 'md5': '4ccbebe5f36706d85221f204d7eb5913',
166 'info_dict': {
167 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
168 'id': '5_Lennart_Poettering_-_Systemd',
169 'ext': 'webm',
170 'title': '5_Lennart_Poettering_-_Systemd',
171 'upload_date': '20141120',
172 },
173 'expected_warnings': [
174 'URL could be a direct video link, returning it as such.'
175 ]
176 },
177 # RSS feed
178 {
179 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
180 'info_dict': {
181 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
182 'title': 'Zero Punctuation',
183 'description': 're:.*groundbreaking video review series.*'
184 },
185 'playlist_mincount': 11,
186 },
187 # RSS feed with enclosure
188 {
189 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
190 'info_dict': {
191 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
192 'ext': 'm4v',
193 'upload_date': '20150228',
194 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
195 }
196 },
01aec848
BG
197 # RSS feed with enclosures and unsupported link URLs
198 {
199 'url': 'http://www.hellointernet.fm/podcast?format=rss',
200 'info_dict': {
201 'id': 'http://www.hellointernet.fm/podcast?format=rss',
202 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
203 'title': 'Hello Internet',
204 },
205 'playlist_mincount': 100,
206 },
8765222d
S
207 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
208 {
209 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
210 'info_dict': {
211 'id': 'smil',
212 'ext': 'mp4',
213 'title': 'Automatics, robotics and biocybernetics',
214 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 215 'upload_date': '20130627',
8765222d
S
216 'formats': 'mincount:16',
217 'subtitles': 'mincount:1',
218 },
219 'params': {
220 'force_generic_extractor': True,
221 'skip_download': True,
222 },
223 },
224 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
225 {
226 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
227 'info_dict': {
228 'id': 'hds',
229 'ext': 'flv',
230 'title': 'hds',
231 'formats': 'mincount:1',
232 },
233 'params': {
234 'skip_download': True,
235 },
236 },
237 # SMIL from https://www.restudy.dk/video/play/id/1637
238 {
239 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
240 'info_dict': {
241 'id': 'video_1637',
242 'ext': 'flv',
243 'title': 'video_1637',
244 'formats': 'mincount:3',
245 },
246 'params': {
247 'skip_download': True,
248 },
249 },
250 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
251 {
252 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
253 'info_dict': {
254 'id': 'smil-service',
255 'ext': 'flv',
256 'title': 'smil-service',
257 'formats': 'mincount:1',
258 },
259 'params': {
260 'skip_download': True,
261 },
262 },
263 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
264 {
265 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
266 'info_dict': {
267 'id': '4719370',
268 'ext': 'mp4',
269 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
270 'formats': 'mincount:3',
271 },
272 'params': {
273 'skip_download': True,
274 },
275 },
1de5cd3b
S
276 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
277 {
278 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
279 'info_dict': {
280 'id': 'mZlp2ctYIUEB',
281 'ext': 'mp4',
282 'title': 'Tikibad ontruimd wegens brand',
283 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
ec85ded8 284 'thumbnail': r're:^https?://.*\.jpg$',
1de5cd3b
S
285 'duration': 33,
286 },
287 'params': {
288 'skip_download': True,
289 },
290 },
9d939cec
S
291 # MPD from http://dash-mse-test.appspot.com/media.html
292 {
293 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
294 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
295 'info_dict': {
296 'id': 'car-20120827-manifest',
297 'ext': 'mp4',
298 'title': 'car-20120827-manifest',
299 'formats': 'mincount:9',
0738187f 300 'upload_date': '20130904',
9d939cec
S
301 },
302 'params': {
303 'format': 'bestvideo',
304 },
305 },
20938f76
S
306 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
307 {
308 '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',
309 'info_dict': {
310 'id': 'content',
311 'ext': 'mp4',
312 'title': 'content',
313 'formats': 'mincount:8',
314 },
315 'params': {
316 # m3u8 downloads
317 'skip_download': True,
39efc6e3
YCH
318 },
319 'skip': 'video gone',
20938f76 320 },
edd9b71c
S
321 # m3u8 served with Content-Type: text/plain
322 {
323 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
324 'info_dict': {
325 'id': 'index',
326 'ext': 'mp4',
327 'title': 'index',
328 'upload_date': '20140720',
329 'formats': 'mincount:11',
330 },
331 'params': {
332 # m3u8 downloads
333 'skip_download': True,
39efc6e3
YCH
334 },
335 'skip': 'video gone',
edd9b71c 336 },
c5fa81fe
S
337 # google redirect
338 {
339 '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',
340 'info_dict': {
341 'id': 'cmQHVoWB5FY',
342 'ext': 'mp4',
343 'upload_date': '20130224',
344 'uploader_id': 'TheVerge',
ec85ded8 345 'description': r're:^Chris Ziegler takes a look at the\.*',
c5fa81fe
S
346 'uploader': 'The Verge',
347 'title': 'First Firefox OS phones side-by-side',
348 },
349 'params': {
350 'skip_download': False,
351 }
352 },
6c91a5a7
S
353 {
354 # redirect in Refresh HTTP header
355 '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',
356 'info_dict': {
357 'id': 'pO8h3EaFRdo',
358 'ext': 'mp4',
359 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
360 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
361 'upload_date': '20150917',
362 'uploader_id': 'brtvofficial',
363 'uploader': 'Boiler Room',
364 },
365 'params': {
366 'skip_download': False,
367 },
368 },
cfe50f04 369 {
79649588 370 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 371 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 372 'info_dict': {
d360a146
S
373 'id': '13601338388002',
374 'ext': 'mp4',
79649588
PH
375 'uploader': 'www.hodiho.fr',
376 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
377 }
378 },
c19f7764
JMF
379 # bandcamp page with custom domain
380 {
79649588
PH
381 'add_ie': ['Bandcamp'],
382 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 383 'info_dict': {
fd50bf62
S
384 'id': '3235767654',
385 'ext': 'mp3',
79649588
PH
386 'title': 'The Pony Mash',
387 'uploader': 'M_Pallante',
c19f7764 388 },
79649588 389 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 390 },
eeb165e6 391 {
53a664ed
S
392 # embedded brightcove video
393 # it also tests brightcove videos that need to set the 'Referer'
394 # in the http requests
3b7d9aa4 395 'add_ie': ['BrightcoveLegacy'],
79649588
PH
396 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
397 'info_dict': {
398 'id': '2765128793001',
399 'ext': 'mp4',
400 'title': 'Le cours de bourse : l’analyse technique',
401 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
402 'uploader': 'BFM BUSINESS',
eeb165e6 403 },
79649588
PH
404 'params': {
405 'skip_download': True,
eeb165e6
JMF
406 },
407 },
53a664ed
S
408 {
409 # embedded with itemprop embedURL and video id spelled as `idVideo`
410 'add_id': ['BrightcoveLegacy'],
411 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
412 'info_dict': {
413 'id': '5255628253001',
414 'ext': 'mp4',
415 'title': 'md5:37c519b1128915607601e75a87995fc0',
416 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
417 'uploader': 'BFM BUSINESS',
418 'uploader_id': '876450612001',
419 'timestamp': 1482255315,
420 'upload_date': '20161220',
421 },
422 'params': {
423 'skip_download': True,
424 },
425 },
17ab4d3b
PH
426 {
427 # https://github.com/rg3/youtube-dl/issues/2253
428 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
429 'md5': '0ba9446db037002366bab3b3eb30c88c',
430 'info_dict': {
fd50bf62
S
431 'id': '3101154703001',
432 'ext': 'mp4',
17ab4d3b
PH
433 'title': 'Still no power',
434 'uploader': 'thestar.com',
435 '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.',
436 },
3b7d9aa4 437 'add_ie': ['BrightcoveLegacy'],
39efc6e3 438 'skip': 'video gone',
17ab4d3b 439 },
0479c625
S
440 {
441 'url': 'http://www.championat.com/video/football/v/87/87499.html',
442 'md5': 'fb973ecf6e4a78a67453647444222983',
443 'info_dict': {
444 'id': '3414141473001',
445 'ext': 'mp4',
446 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
447 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
448 'uploader': 'Championat',
449 },
450 },
bdf97017 451 {
37aab278 452 # https://github.com/rg3/youtube-dl/issues/3541
3b7d9aa4 453 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
454 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
455 'info_dict': {
456 'id': '3866516442001',
37aab278 457 'ext': 'mp4',
bdf97017
NJ
458 'title': 'Leer mij vrouwen kennen: Aflevering 1',
459 'description': 'Leer mij vrouwen kennen: Aflevering 1',
460 'uploader': 'SBS Broadcasting',
461 },
37aab278 462 'skip': 'Restricted to Netherlands',
bdf97017 463 'params': {
37aab278 464 'skip_download': True, # m3u8 download
bdf97017
NJ
465 },
466 },
06d0ad9a
YCH
467 {
468 # Brightcove video in <iframe>
469 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
470 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
471 'info_dict': {
472 'id': '5360463607001',
473 'ext': 'mp4',
474 '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',
475 '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。',
476 'uploader': 'United Nations',
477 'uploader_id': '1362235914001',
478 'timestamp': 1489593889,
479 'upload_date': '20170315',
480 },
481 'add_ie': ['BrightcoveLegacy'],
482 },
16e2c8f7
YCH
483 {
484 # Brightcove with alternative playerID key
485 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
486 'info_dict': {
487 'id': 'nmeth.2062_SV1',
488 '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',
489 },
490 'playlist': [{
491 'info_dict': {
492 'id': '2228375078001',
493 'ext': 'mp4',
494 'title': 'nmeth.2062-sv1',
495 'description': 'nmeth.2062-sv1',
496 'timestamp': 1363357591,
497 'upload_date': '20130315',
498 'uploader': 'Nature Publishing Group',
499 'uploader_id': '1964492299001',
500 },
501 }],
502 },
40158f55
JH
503 {
504 # Brightcove with UUID in videoPlayer
505 'url': 'http://www8.hp.com/cn/zh/home.html',
506 'info_dict': {
507 'id': '5255815316001',
508 'ext': 'mp4',
509 'title': 'Sprocket Video - China',
510 'description': 'Sprocket Video - China',
511 'uploader': 'HP-Video Gallery',
512 'timestamp': 1482263210,
513 'upload_date': '20161220',
514 'uploader_id': '1107601872001',
515 },
516 'params': {
517 'skip_download': True, # m3u8 download
518 },
519 'skip': 'video rotates...weekly?',
520 },
521 {
522 # Brightcove:new type [2].
523 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
524 'md5': '2b35148fcf48da41c9fb4591650784f3',
525 'info_dict': {
526 'id': '5348741021001',
527 'ext': 'mp4',
528 'upload_date': '20170306',
529 'uploader_id': '4191638492001',
530 'timestamp': 1488769918,
531 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
532
533 },
534 },
535 {
536 # Alternative brightcove <video> attributes
537 '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/',
538 'info_dict': {
539 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
540 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
541 },
542 'playlist': [{
543 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
544 'info_dict': {
545 'id': '5311302538001',
546 'ext': 'mp4',
547 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
548 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
549 'timestamp': 1486321708,
550 'upload_date': '20170205',
551 'uploader_id': '800000640001',
552 },
553 'only_matching': True,
554 }],
555 },
b68a812e
S
556 {
557 # Brightcove with UUID in videoPlayer
558 'url': 'http://www8.hp.com/cn/zh/home.html',
559 'info_dict': {
560 'id': '5255815316001',
561 'ext': 'mp4',
562 'title': 'Sprocket Video - China',
563 'description': 'Sprocket Video - China',
564 'uploader': 'HP-Video Gallery',
565 'timestamp': 1482263210,
566 'upload_date': '20161220',
567 'uploader_id': '1107601872001',
568 },
569 'params': {
570 'skip_download': True, # m3u8 download
571 },
572 },
c0d0b01f
JMF
573 # ooyala video
574 {
79649588 575 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 576 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
577 'info_dict': {
578 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
579 'ext': 'mp4',
3486df38 580 'title': '2cc213299525360.mov', # that's what we get
53e06b25 581 'duration': 238.231,
c0d0b01f 582 },
87830900 583 'add_ie': ['Ooyala'],
c0d0b01f 584 },
bf94d763
S
585 {
586 # ooyala video embedded with http://player.ooyala.com/iframe.js
587 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
588 'info_dict': {
589 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
590 'ext': 'mp4',
591 'title': '"Steve Jobs: Man in the Machine" trailer',
592 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 593 'duration': 135.427,
bf94d763
S
594 },
595 'params': {
596 'skip_download': True,
597 },
39efc6e3 598 'skip': 'movie expired',
bf94d763 599 },
198d4cb4
GR
600 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
601 {
602 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
603 'info_dict': {
604 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
605 'ext': 'mp4',
606 'title': 'Steampunk Fest Comes to Honesdale',
607 'duration': 43.276,
608 },
609 'params': {
610 'skip_download': True,
611 }
612 },
1b86cc41 613 # embed.ly video
614 {
615 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
616 'info_dict': {
617 'id': '9ODmcdjQcHQ',
618 'ext': 'mp4',
0a5bce56
PH
619 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
620 'upload_date': '20140225',
621 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
622 'uploader': 'Tested',
623 'uploader_id': 'testedcom',
1b86cc41 624 },
625 # No need to test YoutubeIE here
626 'params': {
627 'skip_download': True,
628 },
629 },
60cc4dc4
PH
630 # funnyordie embed
631 {
632 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
633 'info_dict': {
634 'id': '18e820ec3f',
635 'ext': 'mp4',
636 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
637 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 638 },
39efc6e3
YCH
639 # HEAD requests lead to endless 301, while GET is OK
640 'expected_warnings': ['301'],
60cc4dc4 641 },
93d020dd
S
642 # RUTV embed
643 {
644 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
645 'info_dict': {
646 'id': '776940',
647 'ext': 'mp4',
648 'title': 'Охотское море стало целиком российским',
649 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
650 },
651 'params': {
652 # m3u8 download
653 'skip_download': True,
654 },
aab74fa1 655 },
f37bdbe5
S
656 # TVC embed
657 {
658 '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/',
659 'info_dict': {
660 'id': '55304',
661 'ext': 'mp4',
662 'title': 'Дошкольное воспитание',
663 },
664 },
b827a601
S
665 # SportBox embed
666 {
667 'url': 'http://www.vestifinance.ru/articles/25753',
668 'info_dict': {
669 'id': '25753',
05d1e7aa 670 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
b827a601
S
671 },
672 'playlist': [{
673 'info_dict': {
674 'id': '370908',
675 'title': 'Госзаказ. День 3',
676 'ext': 'mp4',
677 }
678 }, {
679 'info_dict': {
680 'id': '370905',
681 'title': 'Госзаказ. День 2',
682 'ext': 'mp4',
683 }
684 }, {
685 'info_dict': {
686 'id': '370902',
687 'title': 'Госзаказ. День 1',
688 'ext': 'mp4',
689 }
690 }],
691 'params': {
692 # m3u8 download
693 'skip_download': True,
694 },
695 },
bf20b9c5
S
696 # Myvi.ru embed
697 {
698 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
699 'info_dict': {
700 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
701 'ext': 'mp4',
702 'title': 'Ужастики, русский трейлер (2015)',
ec85ded8 703 'thumbnail': r're:^https?://.*\.jpg$',
bf20b9c5
S
704 'duration': 153,
705 }
706 },
c76799c5
S
707 # XHamster embed
708 {
709 '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',
710 'info_dict': {
711 'id': 'showthread',
712 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
713 },
714 'playlist_mincount': 7,
39efc6e3
YCH
715 # This forum does not allow <iframe> syntaxes anymore
716 # Now HTML tags are displayed as-is
717 'skip': 'No videos on this page',
c76799c5 718 },
aab74fa1
PH
719 # Embedded TED video
720 {
721 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 722 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 723 'info_dict': {
a8eb5a8e 724 'id': '1969',
aab74fa1 725 'ext': 'mp4',
a8eb5a8e
PH
726 'title': 'Hidden miracles of the natural world',
727 'uploader': 'Louie Schwartzberg',
728 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 729 }
60cc4dc4 730 },
d95e35d6
S
731 # nowvideo embed hidden behind percent encoding
732 {
733 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
734 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
735 'info_dict': {
736 'id': '06e53103ca9aa',
737 'ext': 'flv',
738 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
739 'description': 'No description',
740 },
0f2a2ba1 741 },
893f8832
PH
742 # arte embed
743 {
744 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
745 'md5': '7653032cbb25bf6c80d80f217055fa43',
746 'info_dict': {
747 'id': '048195-004_PLUS7-F',
748 'ext': 'flv',
749 'title': 'X:enius',
750 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
751 'upload_date': '20140320',
752 },
753 'params': {
754 'skip_download': 'Requires rtmpdump'
39efc6e3
YCH
755 },
756 'skip': 'video gone',
893f8832 757 },
cbd55ade
S
758 # francetv embed
759 {
760 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
761 'info_dict': {
762 'id': 'EV_30231',
763 'ext': 'mp4',
764 'title': 'Alcaline, le concert avec Calogero',
765 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
766 'upload_date': '20150226',
767 'timestamp': 1424989860,
768 'duration': 5400,
769 },
770 'params': {
771 # m3u8 downloads
772 'skip_download': True,
773 },
774 'expected_warnings': [
775 'Forbidden'
776 ]
777 },
fa35cdad
PH
778 # Condé Nast embed
779 {
780 'url': 'http://www.wired.com/2014/04/honda-asimo/',
781 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
782 'info_dict': {
783 'id': '53501be369702d3275860000',
784 'ext': 'mp4',
785 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
786 }
ebd3c7b3
PH
787 },
788 # Dailymotion embed
789 {
790 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
791 'md5': '441aeeb82eb72c422c7f14ec533999cd',
792 'info_dict': {
793 'id': 'k2mm4bCdJ6CQ2i7c8o2',
794 'ext': 'mp4',
795 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 796 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 797 'uploader': 'Spi0n',
0738187f
YCH
798 'uploader_id': 'xgditw',
799 'upload_date': '20140425',
800 'timestamp': 1398441542,
ebd3c7b3
PH
801 },
802 'add_ie': ['Dailymotion'],
2b88feed 803 },
71a1db89
S
804 # DailyMail embed
805 {
806 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
807 'info_dict': {
808 'id': '1495629',
809 'ext': 'mp4',
810 'title': 'Care worker punches elderly dementia patient in head 11 times',
811 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
812 },
813 'add_ie': ['DailyMail'],
814 'params': {
815 'skip_download': True,
816 },
817 },
2b88feed
PH
818 # YouTube embed
819 {
820 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
821 'info_dict': {
822 'id': 'FXRb4ykk4S0',
823 'ext': 'mp4',
824 'title': 'The NBL Auction 2014',
825 'uploader': 'BADMINTON England',
826 'uploader_id': 'BADMINTONEvents',
827 'upload_date': '20140603',
828 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
829 },
830 'add_ie': ['Youtube'],
831 'params': {
832 'skip_download': True,
833 }
834 },
c5cd249e
JMF
835 # MTVSercices embed
836 {
1fa309da
YCH
837 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
838 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 839 'info_dict': {
1fa309da 840 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 841 'ext': 'mp4',
1fa309da
YCH
842 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
843 'description': 'Two valets share their love for movie star Liam Neesons.',
05d1e7aa
YCH
844 'timestamp': 1349922600,
845 'upload_date': '20121011',
c5cd249e
JMF
846 },
847 },
61013473 848 # YouTube embed via <data-embed-url="">
849 {
850 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 851 'info_dict': {
a8eb5a8e 852 'id': '4vAffPZIT44',
61013473 853 'ext': 'mp4',
a8eb5a8e 854 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
855 'uploader': 'Gameloft',
856 'uploader_id': 'gameloft',
a8eb5a8e
PH
857 'upload_date': '20140828',
858 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
859 },
860 'params': {
861 'skip_download': True,
61013473 862 }
c8e9a235 863 },
61568e50
JH
864 # YouTube <object> embed
865 {
866 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
867 'md5': '516718101ec834f74318df76259fb3cc',
868 'info_dict': {
869 'id': 'msN87y-iEx0',
870 'ext': 'webm',
871 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
872 'upload_date': '20080526',
873 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
874 'uploader': 'Christopher Sykes',
875 'uploader_id': 'ChristopherJSykes',
876 },
877 'add_ie': ['Youtube'],
878 },
c8e9a235
PH
879 # Camtasia studio
880 {
881 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
882 'playlist': [{
883 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
884 'info_dict': {
885 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
886 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
887 'ext': 'flv',
888 'duration': 2235.90,
889 }
890 }, {
891 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
892 'info_dict': {
893 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
894 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
895 'ext': 'flv',
896 'duration': 2235.93,
897 }
898 }],
899 'info_dict': {
900 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
901 }
4d805e06
PH
902 },
903 # Flowplayer
904 {
905 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
906 'md5': '9d65602bf31c6e20014319c7d07fba27',
907 'info_dict': {
908 'id': '5123ea6d5e5a7',
909 'ext': 'mp4',
910 'age_limit': 18,
911 'uploader': 'www.handjobhub.com',
d6d9186f 912 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 913 }
0990305d 914 },
22a6f150
PH
915 # Multiple brightcove videos
916 # https://github.com/rg3/youtube-dl/issues/2283
917 {
918 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
919 'info_dict': {
920 'id': 'always-never',
921 'title': 'Always / Never - The New Yorker',
922 },
923 'playlist_count': 3,
924 'params': {
925 'extract_flat': False,
926 'skip_download': True,
927 }
1a94ff68
S
928 },
929 # MLB embed
930 {
931 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
932 'md5': '96f09a37e44da40dd083e12d9a683327',
933 'info_dict': {
934 'id': '33322633',
935 'ext': 'mp4',
936 'title': 'Ump changes call to ball',
937 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
938 'duration': 48,
939 'timestamp': 1401537900,
940 'upload_date': '20140531',
ec85ded8 941 'thumbnail': r're:^https?://.*\.jpg$',
1a94ff68
S
942 },
943 },
746c67d7
NJ
944 # Wistia embed
945 {
6c114b12
S
946 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
947 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 948 'info_dict': {
6c114b12 949 'id': '6e2wtrbdaf',
746c67d7 950 'ext': 'mov',
6c114b12
S
951 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
952 'description': 'a Paywall Videos video from Remilon',
953 'duration': 644.072,
954 'uploader': 'study.com',
955 'timestamp': 1459678540,
956 'upload_date': '20160403',
957 'filesize': 24687186,
746c67d7
NJ
958 },
959 },
52cffcb1 960 {
961 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
962 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
963 'info_dict': {
964 'id': 'uxjb0lwrcz',
965 'ext': 'mp4',
6c114b12 966 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 967 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 968 'duration': 1715.0,
85d7b765 969 'uploader': 'thoughtworks.wistia.com',
0738187f 970 'timestamp': 1401832161,
6c114b12 971 'upload_date': '20140603',
70b7e3fb 972 },
52cffcb1 973 },
7ded6545
S
974 # Wistia standard embed (async)
975 {
976 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
977 'info_dict': {
978 'id': '807fafadvk',
979 'ext': 'mp4',
980 'title': 'Drip Brennan Dunn Workshop',
981 'description': 'a JV Webinars video from getdrip-1',
982 'duration': 4986.95,
7ded6545 983 'timestamp': 1463607249,
6c114b12 984 'upload_date': '20160518',
7ded6545
S
985 },
986 'params': {
987 'skip_download': True,
988 }
989 },
ac645ac7
PH
990 # Soundcloud embed
991 {
992 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
993 'info_dict': {
994 'id': '174391317',
995 'ext': 'mp3',
996 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
997 'uploader': 'Sophos Security',
998 'title': 'Chet Chat 171 - Oct 29, 2014',
999 'upload_date': '20141029',
1000 }
af63fed7 1001 },
db19df6c
S
1002 # Soundcloud multiple embeds
1003 {
1004 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1005 'info_dict': {
1006 'id': '52809',
1007 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1008 },
1009 'playlist_mincount': 7,
1010 },
027e2312
S
1011 # TuneIn station embed
1012 {
1013 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1014 'info_dict': {
1015 'id': '204146',
1016 'ext': 'mp3',
1017 'title': 'CNRV',
1018 'location': 'Paris, France',
1019 'is_live': True,
1020 },
1021 'params': {
1022 # Live stream
1023 'skip_download': True,
1024 },
1025 },
af63fed7
PH
1026 # Livestream embed
1027 {
1028 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1029 'info_dict': {
1030 'id': '67864563',
1031 'ext': 'flv',
1032 'upload_date': '20141112',
1033 'title': 'Rosetta #CometLanding webcast HL 10',
1034 }
1035 },
78d3b3e2
YCH
1036 # Another Livestream embed, without 'new.' in URL
1037 {
1038 'url': 'https://www.freespeech.org/',
1039 'info_dict': {
1040 'id': '123537347',
1041 'ext': 'mp4',
1042 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1043 },
1044 'params': {
1045 # Live stream
1046 'skip_download': True,
1047 },
1048 },
65f3a228
PH
1049 # LazyYT
1050 {
e8e4cc5a 1051 'url': 'https://skiplagged.com/',
65f3a228 1052 'info_dict': {
e8e4cc5a
JH
1053 'id': 'skiplagged',
1054 'title': 'Skiplagged: The smart way to find cheap flights',
65f3a228 1055 },
e8e4cc5a
JH
1056 'playlist_mincount': 1,
1057 'add_ie': ['Youtube'],
4e262a88 1058 },
42bdd9d0
PH
1059 # Cinchcast embed
1060 {
1061 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1062 'info_dict': {
1063 'id': '7141703',
1064 'ext': 'mp3',
1065 'upload_date': '20141126',
1066 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1067 }
1068 },
501f13fb
PH
1069 # Cinerama player
1070 {
1071 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1072 'info_dict': {
1073 'id': '730m_DandD_1901_512k',
1074 'ext': 'mp4',
1075 'uploader': 'www.abc.net.au',
1076 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1077 }
796df3c6
S
1078 },
1079 # embedded viddler video
1080 {
1081 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1082 'info_dict': {
1083 'id': '4d03aad9',
1084 'ext': 'mp4',
1085 'uploader': 'deadspin',
1086 'title': 'WALL-TO-GORTAT',
1087 'timestamp': 1422285291,
1088 'upload_date': '20150126',
1089 },
1090 'add_ie': ['Viddler'],
a0f71985 1091 },
2051acde
S
1092 # Libsyn embed
1093 {
1094 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1095 'info_dict': {
1096 'id': '3377616',
1097 'ext': 'mp3',
1098 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1099 'description': 'md5:601cb790edd05908957dae8aaa866465',
1100 'upload_date': '20150220',
1101 },
326fa4e6 1102 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
2051acde 1103 },
a0f71985
PH
1104 # jwplayer YouTube
1105 {
1106 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1107 'info_dict': {
1108 'id': 'Mrj4DVp2zeA',
1109 'ext': 'mp4',
f37e3f99 1110 'upload_date': '20150212',
a0f71985 1111 'uploader': 'The National Archives UK',
2637fadc 1112 'description': 'md5:8078af856dca76edc42910b61273dbbf',
a0f71985
PH
1113 'uploader_id': 'NationalArchives08',
1114 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1115 },
59b8ab58 1116 },
5620f840
S
1117 # jwplayer rtmp
1118 {
6899b1d9 1119 'url': 'http://www.suffolk.edu/sjc/live.php',
5620f840 1120 'info_dict': {
6899b1d9 1121 'id': 'live',
5620f840
S
1122 'ext': 'flv',
1123 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1124 'uploader': 'www.suffolk.edu',
1125 },
1126 'params': {
1127 'skip_download': True,
2637fadc 1128 },
6899b1d9 1129 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
5620f840 1130 },
a4a554a7
YCH
1131 # Complex jwplayer
1132 {
1133 'url': 'http://www.indiedb.com/games/king-machine/videos',
1134 'info_dict': {
1135 'id': 'videos',
1136 'ext': 'mp4',
1137 'title': 'king machine trailer 1',
2637fadc 1138 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
a4a554a7
YCH
1139 'thumbnail': r're:^https?://.*\.jpg$',
1140 },
1141 },
03486dbb
RU
1142 {
1143 # JWPlayer config passed as variable
1144 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1145 'info_dict': {
1146 'id': '3326530_hq',
1147 'ext': 'mp4',
1148 'title': 'ARIELE | Tube Cup',
1149 'uploader': 'www.txxx.com',
1150 'age_limit': 18,
1151 },
1152 'params': {
1153 'skip_download': True,
1154 }
1155 },
939be9ad
JH
1156 {
1157 # JWPlatform iframe
1158 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1159 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1160 'info_dict': {
1161 'id': 'O0c5JcKT',
1162 'ext': 'mp4',
1163 'upload_date': '20171122',
1164 'timestamp': 1511366290,
1165 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1166 },
805f5bf7 1167 'add_ie': [JWPlatformIE.ie_key()],
939be9ad 1168 },
63d990d2 1169 {
c5b7014a 1170 # Video.js embed, multiple formats
63d990d2
S
1171 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1172 'info_dict': {
1173 'id': 'yygqldloqIk',
1174 'ext': 'mp4',
1175 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1176 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1177 'upload_date': '20130314',
1178 'uploader': 'PROстое3D',
1179 'uploader_id': 'PROstoe3D',
1180 },
1181 'params': {
1182 'skip_download': True,
1183 },
1184 },
c5b7014a
S
1185 {
1186 # Video.js embed, single format
1187 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1188 'info_dict': {
1189 'id': 'watch',
1190 'ext': 'mp4',
1191 'title': 'Step 1 - Good Foundation',
1192 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1193 },
1194 'params': {
1195 'skip_download': True,
1196 },
1197 },
59b8ab58
PH
1198 # rtl.nl embed
1199 {
1200 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1201 'playlist_mincount': 5,
1202 'info_dict': {
1203 'id': 'aanslagen-kopenhagen',
2637fadc 1204 'title': 'Aanslagen Kopenhagen',
59b8ab58 1205 }
255fca5e
S
1206 },
1207 # Zapiks embed
1208 {
1209 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1210 'info_dict': {
1211 'id': '118046',
1212 'ext': 'mp4',
1213 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1214 }
1215 },
66e568de
S
1216 # Kaltura embed (different embed code)
1217 {
1218 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1219 'info_dict': {
1220 'id': '1_a52wc67y',
1221 'ext': 'flv',
1222 'upload_date': '20150127',
1223 'uploader_id': 'PremierMedia',
1224 'timestamp': int,
1225 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1226 },
1227 },
87703231
YCH
1228 # Kaltura embed with single quotes
1229 {
1230 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1231 'info_dict': {
1232 'id': '0_izeg5utt',
1233 'ext': 'mp4',
1234 'title': '35871',
1235 'timestamp': 1355743100,
1236 'upload_date': '20121217',
e30991f9 1237 'uploader_id': 'cplapp@learn360.com',
87703231
YCH
1238 },
1239 'add_ie': ['Kaltura'],
1240 },
427cd050
S
1241 {
1242 # Kaltura embedded via quoted entry_id
1243 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1244 'info_dict': {
1245 'id': '0_utuok90b',
1246 'ext': 'mp4',
1247 'title': '06_matthew_brender_raj_dutt',
1248 'timestamp': 1466638791,
1249 'upload_date': '20160622',
1250 },
1251 'add_ie': ['Kaltura'],
1252 'expected_warnings': [
1253 'Could not send HEAD request'
1254 ],
1255 'params': {
1256 'skip_download': True,
1257 }
1258 },
8ab7e6c4
YCH
1259 {
1260 # Kaltura embedded, some fileExt broken (#11480)
1261 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1262 'info_dict': {
1263 'id': '1_sgtvehim',
1264 'ext': 'mp4',
1265 'title': 'Our "Standard Models" of particle physics and cosmology',
1266 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1267 'timestamp': 1321158993,
1268 'upload_date': '20111113',
1269 'uploader_id': 'kps1',
1270 },
1271 'add_ie': ['Kaltura'],
1272 },
a01825a5
JH
1273 {
1274 # Kaltura iframe embed
1275 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1276 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1277 'info_dict': {
1278 'id': '0_f2cfbpwy',
1279 'ext': 'mp4',
1280 'title': 'I. M. Pei: A Centennial Celebration',
1281 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1282 'upload_date': '20170403',
1283 'uploader_id': 'batchUser',
1284 'timestamp': 1491232186,
1285 },
1286 'add_ie': ['Kaltura'],
1287 },
c21692fa
S
1288 {
1289 # Kaltura iframe embed, more sophisticated
1290 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1291 'info_dict': {
1292 'id': '1_9gzouybz',
1293 'ext': 'mp4',
1294 'title': 'lecture-05sep2017',
1295 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1296 'upload_date': '20170913',
1297 'uploader_id': 'eps2',
1298 'timestamp': 1505340777,
1299 },
1300 'params': {
1301 'skip_download': True,
1302 },
1303 'add_ie': ['Kaltura'],
1304 },
e30991f9
S
1305 {
1306 # meta twitter:player
1307 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1308 'info_dict': {
1309 'id': '0_01b42zps',
1310 'ext': 'mp4',
1311 'title': 'Main Twerk (Video)',
1312 'upload_date': '20171208',
1313 'uploader_id': 'sebastian.salinas@thechive.com',
1314 'timestamp': 1512713057,
1315 },
1316 'params': {
1317 'skip_download': True,
1318 },
1319 'add_ie': ['Kaltura'],
1320 },
250b042c
S
1321 # referrer protected EaglePlatform embed
1322 {
1323 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1324 'info_dict': {
1325 'id': '582306',
1326 'ext': 'mp4',
1327 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1328 'thumbnail': r're:^https?://.*\.jpg$',
1329 'duration': 3382,
1330 'view_count': int,
1331 },
1332 'params': {
1333 'skip_download': True,
1334 },
135c9c42 1335 },
665e9452 1336 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1337 {
1338 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1339 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1340 'info_dict': {
1341 'id': '12820',
1342 'ext': 'mp4',
1343 'title': "'O Sole Mio",
ec85ded8 1344 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1345 'duration': 216,
1346 'view_count': int,
1347 },
250b042c
S
1348 'params': {
1349 'skip_download': True,
1350 },
2637fadc 1351 'skip': 'This video is unavailable.',
d47ae7f6 1352 },
f8388757
S
1353 # Pladform embed
1354 {
1355 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1356 'info_dict': {
1357 'id': '100183293',
1358 'ext': 'mp4',
62259846 1359 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1360 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1361 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1362 'duration': 694,
1363 'age_limit': 0,
1364 },
2637fadc 1365 'skip': 'HTTP Error 404: Not Found',
f8388757 1366 },
c798f15b
S
1367 # Playwire embed
1368 {
1369 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1370 'info_dict': {
1371 'id': '3519514',
1372 'ext': 'mp4',
1373 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1374 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1375 'duration': 45.115,
1376 },
1377 },
ad320e9b
NJ
1378 # 5min embed
1379 {
1380 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1381 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1382 'info_dict': {
1383 'id': '518726732',
1384 'ext': 'mp4',
1385 'title': 'Facebook Creates "On This Day" | Crunch Report',
2637fadc
RA
1386 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1387 'timestamp': 1427237531,
1388 'uploader': 'Crunch Report',
1389 'upload_date': '20150324',
1390 },
1391 'params': {
1392 # m3u8 download
1393 'skip_download': True,
ad320e9b
NJ
1394 },
1395 },
dc455a5f
S
1396 # SVT embed
1397 {
1398 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1399 'info_dict': {
1400 'id': '2900353',
1401 'ext': 'flv',
1402 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1403 'duration': 27,
1404 'age_limit': 0,
1405 },
1406 },
a4257017
S
1407 # Crooks and Liars embed
1408 {
1409 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1410 'info_dict': {
1411 'id': '8RUoRhRi',
1412 'ext': 'mp4',
1413 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1414 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1415 'timestamp': 1428207000,
1416 'upload_date': '20150405',
1417 'uploader': 'Heather',
1418 },
1419 },
1420 # Crooks and Liars external embed
1421 {
1422 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1423 'info_dict': {
1424 'id': 'MTE3MjUtMzQ2MzA',
1425 'ext': 'mp4',
1426 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1427 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1428 'timestamp': 1265032391,
1429 'upload_date': '20100201',
1430 'uploader': 'Heather',
1431 },
1432 },
facecb84 1433 # NBC Sports vplayer embed
a2edf2e7 1434 {
facecb84 1435 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1436 'info_dict': {
facecb84
S
1437 'id': 'ln7x1qSThw4k',
1438 'ext': 'flv',
1439 'title': "PFT Live: New leader in the 'new-look' defense",
1440 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1441 'uploader': 'NBCU-SPORTS',
1442 'upload_date': '20140107',
1443 'timestamp': 1389118457,
a2edf2e7 1444 },
2637fadc 1445 'skip': 'Invalid Page URL',
418c5cc3 1446 },
de3eb07e
YCH
1447 # NBC News embed
1448 {
1449 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1450 'md5': '1aa589c675898ae6d37a17913cf68d66',
1451 'info_dict': {
2637fadc 1452 'id': 'x_dtl_oa_LettermanliftPR_160608',
de3eb07e 1453 'ext': 'mp4',
2637fadc 1454 'title': 'David Letterman: A Preview',
de3eb07e 1455 '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
1456 'upload_date': '20160609',
1457 'timestamp': 1465431544,
1458 'uploader': 'NBCU-NEWS',
de3eb07e
YCH
1459 },
1460 },
418c5cc3
YCH
1461 # UDN embed
1462 {
811586eb 1463 'url': 'https://video.udn.com/news/300346',
01c58f84 1464 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1465 'info_dict': {
01c58f84 1466 'id': '300346',
418c5cc3 1467 'ext': 'mp4',
01c58f84 1468 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1469 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1470 },
1471 'params': {
1472 # m3u8 download
1473 'skip_download': True,
1474 },
2637fadc 1475 'expected_warnings': ['Failed to parse JSON Expecting value'],
edfcf7ab 1476 },
b26733ba
YCH
1477 # Brightcove URL in single quotes
1478 {
1479 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1480 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1481 'info_dict': {
1482 'id': '4255764656001',
1483 'ext': 'mp4',
1484 'title': 'SN Presents: Russell Martin, World Citizen',
1485 '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.',
1486 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1487 'uploader_id': '1704050871',
1488 'upload_date': '20150525',
1489 'timestamp': 1432570283,
b26733ba 1490 },
756f574e 1491 },
8084be78
S
1492 # OnionStudios embed
1493 {
1494 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1495 'info_dict': {
1496 'id': '2855',
1497 'ext': 'mp4',
1498 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
ec85ded8 1499 'thumbnail': r're:^https?://.*\.jpe?g$',
8084be78
S
1500 'uploader': 'ClickHole',
1501 'uploader_id': 'clickhole',
1502 }
1503 },
b8c1cc1a
S
1504 # SnagFilms embed
1505 {
1506 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1507 'info_dict': {
1508 'id': '74849a00-85a9-11e1-9660-123139220831',
1509 'ext': 'mp4',
1510 'title': '#whilewewatch',
1511 }
1512 },
a5158f38
YCH
1513 # AdobeTVVideo embed
1514 {
1515 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1516 'md5': '43662b577c018ad707a63766462b1e87',
1517 'info_dict': {
1518 'id': '2456',
1519 'ext': 'mp4',
1520 'title': 'New experience with Acrobat DC',
1521 'description': 'New experience with Acrobat DC',
1522 'duration': 248.667,
1523 },
1f812580 1524 },
ed126900 1525 # BrightcoveInPageEmbed embed
1526 {
1527 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1528 'info_dict': {
1529 'id': '4238694884001',
1530 'ext': 'flv',
1531 'title': 'Tabletop: Dread, Last Thoughts',
1532 'description': 'Tabletop: Dread, Last Thoughts',
1533 'duration': 51690,
1534 },
750b9ff0 1535 },
d10fe835
YCH
1536 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1537 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1538 {
1539 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1540 'info_dict': {
1541 'id': '4785848093001',
1542 'ext': 'mp4',
1543 'title': 'The Cardinal Pell Interview',
1544 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1545 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1546 'uploader_id': '2733773828001',
1547 'upload_date': '20160304',
1548 'timestamp': 1457083087,
d10fe835
YCH
1549 },
1550 'params': {
1551 # m3u8 downloads
1552 'skip_download': True,
1553 },
1554 },
9edf47df
S
1555 {
1556 # Brightcove embed with whitespace around attribute names
1557 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1558 'info_dict': {
1559 'id': '3167554373001',
1560 'ext': 'mp4',
1561 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1562 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1563 'uploader_id': '1079349493',
1564 'upload_date': '20140207',
1565 'timestamp': 1391810548,
1566 },
1567 'params': {
1568 'skip_download': True,
1569 },
1570 },
134c207e
YCH
1571 # Another form of arte.tv embed
1572 {
1573 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1574 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1575 'info_dict': {
1576 'id': '030273-562_PLUS7-F',
1577 'ext': 'mp4',
1578 'title': 'ARTE Reportage - Nulle part, en France',
1579 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1580 'upload_date': '20160409',
1581 },
1582 },
b8f67449
KM
1583 # LiveLeak embed
1584 {
1585 'url': 'http://www.wykop.pl/link/3088787/',
09747ba7 1586 'md5': '7619da8c820e835bef21a1efa2a0fc71',
b8f67449
KM
1587 'info_dict': {
1588 'id': '874_1459135191',
1589 'ext': 'mp4',
1590 'title': 'Man shows poor quality of new apartment building',
1591 'description': 'The wall is like a sand pile.',
1592 'uploader': 'Lake8737',
09747ba7
YCH
1593 },
1594 'add_ie': [LiveLeakIE.ie_key()],
1595 },
1596 # Another LiveLeak embed pattern (#13336)
1597 {
1598 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1599 'info_dict': {
1600 'id': '2eb_1496309988',
1601 'ext': 'mp4',
1602 'title': 'Thief robs place where everyone was armed',
1603 'description': 'md5:694d73ee79e535953cf2488562288eee',
1604 'uploader': 'brazilwtf',
1605 },
1606 'add_ie': [LiveLeakIE.ie_key()],
b8f67449 1607 },
4a120778
YCH
1608 # Duplicated embedded video URLs
1609 {
1610 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1611 'info_dict': {
1612 'id': '149298443_480_16c25b74_2',
1613 'ext': 'mp4',
1614 'title': 'vs. Blue Orange Spring Game',
1615 'uploader': 'www.hudl.com',
1616 },
1617 },
371ddb14
S
1618 # twitter:player:stream embed
1619 {
1620 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1621 'info_dict': {
1622 'id': 'master',
1623 'ext': 'mp4',
1624 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1625 'uploader': 'www.rtl.be',
1626 },
1627 'params': {
1628 # m3u8 downloads
1629 'skip_download': True,
1630 },
1631 },
32917907
RA
1632 # twitter:player embed
1633 {
1634 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1635 'md5': 'a3e0df96369831de324f0778e126653c',
1636 'info_dict': {
1637 'id': '4909620399001',
1638 'ext': 'mp4',
1639 'title': 'What Do Black Holes Sound Like?',
1640 'description': 'what do black holes sound like',
1641 'upload_date': '20160524',
1642 'uploader_id': '29913724001',
1643 'timestamp': 1464107587,
1644 'uploader': 'TheAtlantic',
1645 },
1646 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1647 },
1648 # Facebook <iframe> embed
1649 {
1650 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1651 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1652 'info_dict': {
1653 'id': '599637780109885',
1654 'ext': 'mp4',
1655 'title': 'Facebook video #599637780109885',
1656 },
1657 },
fd1c5fba
S
1658 # Facebook <iframe> embed, plugin video
1659 {
1660 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1661 'info_dict': {
1662 'id': '1754168231264132',
1663 'ext': 'mp4',
1664 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1665 'uploader': 'Tariq Ramadan (official)',
1666 'timestamp': 1496758379,
1667 'upload_date': '20170606',
1668 },
1669 'params': {
1670 'skip_download': True,
1671 },
1672 },
fd6ca382
YCH
1673 # Facebook API embed
1674 {
1675 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1676 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1677 'info_dict': {
1678 'id': '10153467542406923',
1679 'ext': 'mp4',
1680 'title': 'Facebook video #10153467542406923',
1681 },
7deef1ba
YCH
1682 },
1683 # Wordpress "YouTube Video Importer" plugin
1684 {
1685 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1686 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1687 'info_dict': {
1688 'id': 'HNTXWDXV9Is',
1689 'ext': 'mp4',
1690 'title': 'Blue Devils Drumline Stanford lot 2016',
1691 'upload_date': '20160627',
1692 'uploader_id': 'GENOCIDE8GENERAL10',
1693 'uploader': 'cylus cyrus',
1694 },
1695 },
81953d1a
RA
1696 {
1697 # video stored on custom kaltura server
1698 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1699 'md5': '537617d06e64dfed891fa1593c4b30cc',
1700 'info_dict': {
1701 'id': '0_1iotm5bh',
1702 'ext': 'mp4',
1703 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1704 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1705 'uploader_id': 'videos.expansion@el-mundo.net',
1706 'upload_date': '20150429',
1707 'timestamp': 1430303472,
1708 },
1709 'add_ie': ['Kaltura'],
1710 },
c03adf90
YCH
1711 {
1712 # Non-standard Vimeo embed
1713 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1714 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1715 'info_dict': {
1716 'id': '148867247',
1717 'ext': 'mp4',
1718 'title': 'Understanding the web - Teaser',
1719 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1720 'upload_date': '20151214',
1721 'uploader': 'OpenClassrooms',
1722 'uploader_id': 'openclassrooms',
1723 },
1724 'add_ie': ['Vimeo'],
1725 },
a5ff05df
S
1726 {
1727 # generic vimeo embed that requires original URL passed as Referer
1728 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1729 'only_matching': True,
1730 },
1979969f
S
1731 {
1732 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1733 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1734 'info_dict': {
1735 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1736 'ext': 'mp4',
1737 'title': 'Big Buck Bunny',
1738 'description': 'Royalty free test video',
1739 'timestamp': 1432816365,
1740 'upload_date': '20150528',
1741 'is_live': False,
1742 },
1743 'params': {
1744 'skip_download': True,
1745 },
1746 'add_ie': [ArkenaIE.ie_key()],
1747 },
2a1321a2
S
1748 {
1749 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1750 'info_dict': {
1751 'id': '1c7141f46c',
1752 'ext': 'mp4',
1753 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1754 },
1755 'params': {
1756 'skip_download': True,
1757 },
1758 'add_ie': [Vbox7IE.ie_key()],
1759 },
b0c8f2e9
DR
1760 {
1761 # DBTV embeds
1762 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1763 'info_dict': {
1764 'id': '43254897',
1765 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1766 },
b0c8f2e9
DR
1767 'playlist_mincount': 3,
1768 },
e186a9ec
S
1769 {
1770 # Videa embeds
1771 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1772 'info_dict': {
1773 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1774 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1775 },
1776 'playlist_mincount': 2,
1777 },
b687c85e
S
1778 {
1779 # 20 minuten embed
1780 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1781 'info_dict': {
1782 'id': '523629',
1783 'ext': 'mp4',
1784 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1785 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1786 },
1787 'params': {
1788 'skip_download': True,
1789 },
1790 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1791 },
1792 {
1793 # VideoPress embed
1794 'url': 'https://en.support.wordpress.com/videopress/',
1795 'info_dict': {
1796 'id': 'OcobLTqC',
1797 'ext': 'm4v',
1798 'title': 'IMG_5786',
1799 'timestamp': 1435711927,
1800 'upload_date': '20150701',
1801 },
1802 'params': {
1803 'skip_download': True,
1804 },
1805 'add_ie': [VideoPressIE.ie_key()],
fef51645 1806 },
eb3079b6
S
1807 {
1808 # Rutube embed
1809 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1810 'info_dict': {
1811 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1812 'ext': 'flv',
1813 'title': 'Магаззино: Казань 2',
1814 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1815 'uploader': 'Магаззино',
1816 'upload_date': '20170228',
1817 'uploader_id': '996642',
1818 },
1819 'params': {
1820 'skip_download': True,
1821 },
1822 'add_ie': [RutubeIE.ie_key()],
1823 },
fef51645
YCH
1824 {
1825 # ThePlatform embedded with whitespaces in URLs
1826 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1827 'only_matching': True,
1828 },
97952bdb
JH
1829 {
1830 # Senate ISVP iframe https
1831 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1832 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1833 'info_dict': {
1834 'id': 'govtaff020316',
1835 'ext': 'mp4',
1836 'title': 'Integrated Senate Video Player',
1837 },
1838 'add_ie': [SenateISVPIE.ie_key()],
1839 },
ab87c260
S
1840 {
1841 # Limelight embeds (1 channel embed + 4 media embeds)
1842 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1843 'info_dict': {
1844 'id': 'FacilitatorTraining2017',
1845 'title': 'Facilitator Training 2017',
1846 },
1847 'playlist_mincount': 5,
1848 },
eb02940c
S
1849 {
1850 # Limelight embed (LimelightPlayerUtil.embed)
1851 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1852 'info_dict': {
1853 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1854 'ext': 'mp4',
1855 'title': '07448641',
1856 'timestamp': 1499890639,
1857 'upload_date': '20170712',
1858 },
1859 'params': {
1860 'skip_download': True,
1861 },
1862 'add_ie': ['LimelightMedia'],
1863 },
7986c3ab
S
1864 {
1865 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1866 'info_dict': {
1867 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1868 'title': 'Standoff with Walnut Creek murder suspect ends',
1869 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1870 },
1871 'playlist_mincount': 4,
1872 },
55719459
JH
1873 {
1874 # WashingtonPost embed
1875 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1876 'info_dict': {
1877 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1878 'ext': 'mp4',
1879 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1880 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1881 'timestamp': 1455216756,
1882 'uploader': 'The Washington Post',
1883 'upload_date': '20160211',
1884 },
1885 'add_ie': [WashingtonPostIE.ie_key()],
1886 },
2b8e6a68
S
1887 {
1888 # Mediaset embed
1889 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1890 'info_dict': {
1891 'id': '720642',
1892 'ext': 'mp4',
1893 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1894 },
1895 'params': {
1896 'skip_download': True,
1897 },
1898 'add_ie': [MediasetIE.ie_key()],
1899 },
73cf76a9
S
1900 {
1901 # JOJ.sk embeds
1902 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1903 'info_dict': {
1904 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1905 'title': 'Slovenskom sa prehnala vlna silných búrok',
1906 },
1907 'playlist_mincount': 5,
1908 'add_ie': [JojIE.ie_key()],
1909 },
4328ddf8
S
1910 {
1911 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1912 'url': 'https://tvrain.ru/amp/418921/',
1913 'md5': 'cc00413936695987e8de148b67d14f1d',
1914 'info_dict': {
1915 'id': '418921',
1916 'ext': 'mp4',
1917 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1918 },
1919 },
41918eaa 1920 {
1921 # vzaar embed
1663bd6e
S
1922 'url': 'http://help.vzaar.com/article/165-embedding-video',
1923 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1924 'info_dict': {
1663bd6e 1925 'id': '8707641',
41918eaa 1926 'ext': 'mp4',
1663bd6e 1927 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1928 },
1929 },
9ce1ac40 1930 {
1931 # multiple HTML5 videos on one page
1932 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1933 'info_dict': {
1934 'id': 'keyscenarios',
1935 'title': 'Rescue Kit 14 Free Edition - Getting started',
1936 },
1937 'playlist_count': 4,
0987f2dd
T
1938 },
1939 {
1940 # vshare embed
1941 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1942 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1943 'info_dict': {
1944 'id': '0f64ce6',
1945 'title': 'vl14062007715967',
1946 'ext': 'mp4',
1947 }
2ca7ed41
S
1948 },
1949 {
1950 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1951 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1952 'info_dict': {
1953 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1954 'ext': 'mp4',
1955 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1956 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1957 'timestamp': 1474354800,
1958 'upload_date': '20160920',
1959 }
7d540621
S
1960 },
1961 {
1962 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1963 'info_dict': {
1964 'id': '1731611',
1965 'ext': 'mp4',
1966 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1967 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1968 'timestamp': 1516100691,
1969 'upload_date': '20180116',
1970 },
1971 'params': {
1972 'skip_download': True,
1973 },
1974 'add_ie': [SpringboardPlatformIE.ie_key()],
ea696249
S
1975 },
1976 {
1977 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1978 'info_dict': {
1979 'id': 'uPDB5I9wfp8',
1980 'ext': 'webm',
1981 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1982 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1983 'upload_date': '20160219',
1984 'uploader': 'Pocoyo - Português (BR)',
1985 'uploader_id': 'PocoyoBrazil',
1986 },
1987 'add_ie': [YoutubeIE.ie_key()],
1988 'params': {
1989 'skip_download': True,
1990 },
4c780fbd
S
1991 },
1992 {
1993 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1994 'info_dict': {
1995 'id': 'vMDE4NzI1Mjgt690b',
1996 'ext': 'mp4',
1997 'title': 'Котята',
1998 },
1999 'add_ie': [YapFilesIE.ie_key()],
2000 'params': {
2001 'skip_download': True,
2002 },
1fc37ca3 2003 },
660a230b
S
2004 {
2005 # CloudflareStream embed
2006 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2007 'info_dict': {
2008 'id': '31c9291ab41fac05471db4e73aa11717',
2009 'ext': 'mp4',
2010 'title': '31c9291ab41fac05471db4e73aa11717',
2011 },
2012 'add_ie': [CloudflareStreamIE.ie_key()],
2013 'params': {
2014 'skip_download': True,
2015 },
2016 },
6bd499e8
S
2017 {
2018 # PeerTube embed
2019 'url': 'https://joinpeertube.org/fr/home/',
2020 'info_dict': {
2021 'id': 'home',
2022 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2023 },
2024 'playlist_count': 2,
2025 },
aee36ca8
S
2026 {
2027 # Indavideo embed
2028 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2029 'info_dict': {
2030 'id': '1693903',
2031 'ext': 'mp4',
2032 'title': 'Így kell otthon hamburgert sütni',
2033 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2034 'timestamp': 1426330212,
2035 'upload_date': '20150314',
2036 'uploader': 'StreetKitchen',
2037 'uploader_id': '546363',
2038 },
2039 'add_ie': [IndavideoEmbedIE.ie_key()],
2040 'params': {
2041 'skip_download': True,
2042 },
2043 },
1fc37ca3
SO
2044 {
2045 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2046 'md5': 'b68d276de422ab07ee1d49388103f457',
2047 'info_dict': {
2048 'id': '83645793',
2049 'title': 'Lock up and get excited',
1fc37ca3 2050 'ext': 'mp4'
d3431dcb
S
2051 },
2052 'skip': 'TODO: fix nested playlists processing in tests',
2053 },
6e6b70d6
S
2054 # {
2055 # # TODO: find another test
2056 # # http://schema.org/VideoObject
2057 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2058 # 'md5': '888dcf08b7ea671381f00fab74692755',
2059 # 'info_dict': {
2060 # 'id': 'nyvTSJMKId',
2061 # 'ext': 'mp4',
2062 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2063 # 'description': '#love for cats.',
2064 # 'timestamp': 1461244995,
2065 # 'upload_date': '20160421',
2066 # },
2067 # 'params': {
2068 # 'force_generic_extractor': True,
2069 # },
2070 # }
cfe50f04 2071 ]
9b122384 2072
9b122384
PH
2073 def report_following_redirect(self, new_url):
2074 """Report information extraction."""
79649588 2075 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 2076
4fc946b5
PH
2077 def _extract_rss(self, url, video_id, doc):
2078 playlist_title = doc.find('./channel/title').text
2079 playlist_desc_el = doc.find('./channel/description')
2080 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2081
76c73715
PH
2082 entries = []
2083 for it in doc.findall('./channel/item'):
01aec848
BG
2084 next_url = None
2085 enclosure_nodes = it.findall('./enclosure')
2086 for e in enclosure_nodes:
2087 next_url = e.attrib.get('url')
2088 if next_url:
2089 break
2090
76c73715 2091 if not next_url:
01aec848 2092 next_url = xpath_text(it, 'link', fatal=False)
76c73715
PH
2093
2094 if not next_url:
2095 continue
2096
2097 entries.append({
413c1f8e 2098 '_type': 'url_transparent',
76c73715
PH
2099 'url': next_url,
2100 'title': it.find('title').text,
2101 })
4fc946b5
PH
2102
2103 return {
2104 '_type': 'playlist',
2105 'id': url,
2106 'title': playlist_title,
2107 'description': playlist_desc,
2108 'entries': entries,
2109 }
2110
c8e9a235
PH
2111 def _extract_camtasia(self, url, video_id, webpage):
2112 """ Returns None if no camtasia video can be found. """
2113
2114 camtasia_cfg = self._search_regex(
2115 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2116 webpage, 'camtasia configuration file', default=None)
2117 if camtasia_cfg is None:
2118 return None
2119
2120 title = self._html_search_meta('DC.title', webpage, fatal=True)
2121
2122 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2123 camtasia_cfg = self._download_xml(
2124 camtasia_url, video_id,
2125 note='Downloading camtasia configuration',
2126 errnote='Failed to download camtasia configuration')
2127 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2128
2129 entries = []
2130 for n in fileset_node.getchildren():
2131 url_n = n.find('./uri')
2132 if url_n is None:
2133 continue
2134
2135 entries.append({
2136 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2137 'title': '%s - %s' % (title, n.tag),
2138 'url': compat_urlparse.urljoin(url, url_n.text),
2139 'duration': float_or_none(n.find('./duration').text),
2140 })
2141
2142 return {
2143 '_type': 'playlist',
2144 'entries': entries,
2145 'title': title,
2146 }
2147
9b122384 2148 def _real_extract(self, url):
ebd3c7b3
PH
2149 if url.startswith('//'):
2150 return {
2151 '_type': 'url',
20991253 2152 'url': self.http_scheme() + url,
ebd3c7b3
PH
2153 }
2154
a7130543
JMF
2155 parsed_url = compat_urlparse.urlparse(url)
2156 if not parsed_url.scheme:
04b4d394
PH
2157 default_search = self._downloader.params.get('default_search')
2158 if default_search is None:
1f7ccb90 2159 default_search = 'fixup_error'
04b4d394 2160
1f7ccb90 2161 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
2162 if '/' in url:
2163 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2164 return self.url_result('http://' + url)
1f7ccb90 2165 elif default_search != 'fixup_error':
9c1fc022 2166 if default_search == 'auto_warning':
0e67ab0d
PH
2167 if re.match(r'^(?:url|URL)$', url):
2168 raise ExtractorError(
2169 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2170 expected=True)
2171 else:
2172 self._downloader.report_warning(
7571c02c 2173 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2174 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2175
2176 if default_search in ('error', 'fixup_error'):
7571c02c 2177 raise ExtractorError(
b74e86f4
PH
2178 '%r is not a valid URL. '
2179 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2180 % (url, url), expected=True)
04b4d394 2181 else:
f2f2c0c2
PH
2182 if ':' not in default_search:
2183 default_search += ':'
04b4d394 2184 return self.url_result(default_search + url)
4d54ef20
PH
2185
2186 url, smuggled_data = unsmuggle_url(url)
2187 force_videoid = None
d6e6a422 2188 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2189 if smuggled_data and 'force_videoid' in smuggled_data:
2190 force_videoid = smuggled_data['force_videoid']
2191 video_id = force_videoid
2192 else:
9dcd6fd3 2193 video_id = self._generic_id(url)
3d83a1ae 2194
79649588 2195 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2196
ebab4520 2197 head_req = HEADRequest(url)
23be51d8 2198 head_response = self._request_webpage(
ebab4520
PH
2199 head_req, video_id,
2200 note=False, errnote='Could not send HEAD request to %s' % url,
2201 fatal=False)
42393ce2 2202
23be51d8 2203 if head_response is not False:
42393ce2 2204 # Check for redirect
5551d771 2205 new_url = compat_str(head_response.geturl())
42393ce2
PH
2206 if url != new_url:
2207 self.report_following_redirect(new_url)
4d54ef20
PH
2208 if force_videoid:
2209 new_url = smuggle_url(
2210 new_url, {'force_videoid': force_videoid})
cecaaf3f 2211 return self.url_result(new_url)
42393ce2 2212
23be51d8
PH
2213 full_response = None
2214 if head_response is False:
5c2266df 2215 request = sanitized_Request(url)
58bde34a
S
2216 request.add_header('Accept-Encoding', '*')
2217 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2218 head_response = full_response
2219
f930e0c7
S
2220 info_dict = {
2221 'id': video_id,
9dcd6fd3 2222 'title': self._generic_title(url),
303dcdb9 2223 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
2224 }
2225
23be51d8 2226 # Check for direct link to a video
955737b2 2227 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2228 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2229 if m:
4e363703 2230 format_id = compat_str(m.group('format_id'))
f930e0c7 2231 if format_id.endswith('mpegurl'):
eadc3ccd 2232 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
2233 elif format_id == 'f4m':
2234 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2235 else:
2236 formats = [{
4e363703 2237 'format_id': format_id,
eadc3ccd 2238 'url': url,
2239 'vcodec': 'none' if m.group('type') == 'audio' else None
2240 }]
de6c51e8 2241 info_dict['direct'] = True
19dbaeec 2242 self._sort_formats(formats)
de6c51e8 2243 info_dict['formats'] = formats
f930e0c7 2244 return info_dict
42393ce2 2245
d6e6a422 2246 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
2247 force = self._downloader.params.get('force_generic_extractor', False)
2248 self._downloader.report_warning(
2249 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2250
4e262a88 2251 if not full_response:
5c2266df 2252 request = sanitized_Request(url)
58bde34a
S
2253 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2254 # making it impossible to download only chunk of the file (yet we need only 512kB to
2255 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2256 # that will always result in downloading the whole file that is not desirable.
2257 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2258 # to accept raw bytes and being able to download only a chunk.
2259 # It may probably better to solve this by checking Content-Type for application/octet-stream
2260 # after HEAD request finishes, but not sure if we can rely on this.
2261 request.add_header('Accept-Encoding', '*')
2262 full_response = self._request_webpage(request, video_id)
4e262a88 2263
5940862d
S
2264 first_bytes = full_response.read(512)
2265
2266 # Is it an M3U playlist?
0d769bcb 2267 if first_bytes.startswith(b'#EXTM3U'):
5940862d 2268 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 2269 self._sort_formats(info_dict['formats'])
5940862d
S
2270 return info_dict
2271
4e262a88
PH
2272 # Maybe it's a direct link to a video?
2273 # Be careful not to download the whole thing!
61ca9a80 2274 if not is_html(first_bytes):
4e262a88
PH
2275 self._downloader.report_warning(
2276 'URL could be a direct video link, returning it as such.')
f930e0c7 2277 info_dict.update({
4e262a88
PH
2278 'direct': True,
2279 'url': url,
f930e0c7
S
2280 })
2281 return info_dict
4e262a88
PH
2282
2283 webpage = self._webpage_read_content(
2284 full_response, url, video_id, prefix=first_bytes)
2285
9b122384 2286 self.report_extraction(video_id)
887c6acd 2287
1b840245 2288 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2289 try:
f7854627 2290 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
2291 if doc.tag == 'rss':
2292 return self._extract_rss(url, video_id, doc)
cc99a77a
S
2293 elif doc.tag == 'SmoothStreamingMedia':
2294 info_dict['formats'] = self._parse_ism_formats(doc, url)
2295 self._sort_formats(info_dict['formats'])
2296 return info_dict
e5e8d20a 2297 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
2298 smil = self._parse_smil(doc, url, video_id)
2299 self._sort_formats(smil['formats'])
2300 return smil
729accb4 2301 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
96b8b9ab 2302 return self.playlist_result(
47a5cb77
S
2303 self._parse_xspf(
2304 doc, video_id, xspf_url=url,
2305 xspf_base_url=compat_str(full_response.geturl())),
96b8b9ab 2306 video_id)
1b840245 2307 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7 2308 info_dict['formats'] = self._parse_mpd_formats(
d3f8b76b 2309 doc,
5551d771 2310 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
86f4d14f 2311 mpd_url=url)
19dbaeec 2312 self._sort_formats(info_dict['formats'])
f930e0c7
S
2313 return info_dict
2314 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2315 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 2316 self._sort_formats(info_dict['formats'])
f930e0c7 2317 return info_dict
f7300c5c 2318 except compat_xml_parse_error:
4fc946b5
PH
2319 pass
2320
c8e9a235
PH
2321 # Is it a Camtasia project?
2322 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2323 if camtasia_res is not None:
2324 return camtasia_res
2325
14390730
S
2326 # Sometimes embedded video player is hidden behind percent encoding
2327 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2328 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 2329 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2330
887c6acd
PH
2331 # it's tempting to parse this further, but you would
2332 # have to take into account all the variations like
2333 # Video Title - Site Name
2334 # Site Name | Video Title
2335 # Video Title - Tagline | Site Name
2336 # and so on and so forth; it's just not practical
6f41b2bc
S
2337 video_title = self._og_search_title(
2338 webpage, default=None) or self._html_search_regex(
79649588
PH
2339 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2340 default='video')
ef4fd848 2341
4d805e06
PH
2342 # Try to detect age limit automatically
2343 age_limit = self._rta_search(webpage)
2344 # And then there are the jokers who advertise that they use RTA,
2345 # but actually don't.
2346 AGE_LIMIT_MARKERS = [
197224b7 2347 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
4d805e06
PH
2348 ]
2349 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2350 age_limit = 18
2351
ef4fd848
PH
2352 # video uploader is domain name
2353 video_uploader = self._search_regex(
79649588 2354 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2355
6f41b2bc
S
2356 video_description = self._og_search_description(webpage, default=None)
2357 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2358
b311b0ea
S
2359 info_dict.update({
2360 'title': video_title,
2361 'description': video_description,
2362 'thumbnail': video_thumbnail,
2363 'age_limit': age_limit,
2364 })
2365
1f4b722b 2366 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2367 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2368 if bc_urls:
99877772
PH
2369 entries = [{
2370 '_type': 'url',
2371 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2372 'ie_key': 'BrightcoveLegacy'
99877772
PH
2373 } for bc_url in bc_urls]
2374
2375 return {
2376 '_type': 'playlist',
2377 'title': video_title,
2378 'id': video_id,
2379 'entries': entries,
2380 }
cfe50f04 2381
f6519f89 2382 # Look for Brightcove New Studio embeds
0254f93b 2383 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2384 if bc_urls:
5399ab3f
S
2385 return self.playlist_from_matches(
2386 bc_urls, video_id, video_title,
2387 getter=lambda x: smuggle_url(x, {'referrer': url}),
2388 ie='BrightcoveNew')
ed126900 2389
4e826cd9
S
2390 # Look for Nexx embeds
2391 nexx_urls = NexxIE._extract_urls(webpage)
2392 if nexx_urls:
2393 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2394
3f59b015
S
2395 # Look for Nexx iFrame embeds
2396 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2397 if nexx_embed_urls:
2398 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2399
4d8819d2
S
2400 # Look for ThePlatform embeds
2401 tp_urls = ThePlatformIE._extract_urls(webpage)
2402 if tp_urls:
46b18f23 2403 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2404
48a5eabc
S
2405 # Look for Vessel embeds
2406 vessel_urls = VesselIE._extract_urls(webpage)
2407 if vessel_urls:
46b18f23 2408 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
48a5eabc 2409
59b8ab58
PH
2410 # Look for embedded rtl.nl player
2411 matches = re.findall(
2637fadc 2412 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
59b8ab58
PH
2413 webpage)
2414 if matches:
46b18f23 2415 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2416
09b9c45e
S
2417 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2418 if vimeo_urls:
46b18f23 2419 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2420
a1b85269
YCH
2421 vid_me_embed_url = self._search_regex(
2422 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2423 webpage, 'vid.me embed', default=None)
2424 if vid_me_embed_url is not None:
2425 return self.url_result(vid_me_embed_url, 'Vidme')
2426
66c9fa36
S
2427 # Look for YouTube embeds
2428 youtube_urls = YoutubeIE._extract_urls(webpage)
2429 if youtube_urls:
46b18f23 2430 return self.playlist_from_matches(
66c9fa36 2431 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2432
ad213a1d 2433 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2434 if matches:
46b18f23 2435 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2436
8489578d
NJ
2437 # Look for embedded Dailymotion playlist player (#3822)
2438 m = re.search(
2439 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2440 if m:
2441 playlists = re.findall(
2442 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2443 if playlists:
46b18f23
JH
2444 return self.playlist_from_matches(
2445 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2446
71a1db89
S
2447 # Look for DailyMail embeds
2448 dailymail_urls = DailyMailIE._extract_urls(webpage)
2449 if dailymail_urls:
2450 return self.playlist_from_matches(
2451 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2452
ef4fd848 2453 # Look for embedded Wistia player
58bb4402
S
2454 wistia_url = WistiaIE._extract_url(webpage)
2455 if wistia_url:
ef4fd848
PH
2456 return {
2457 '_type': 'url_transparent',
58bb4402
S
2458 'url': self._proto_relative_url(wistia_url),
2459 'ie_key': WistiaIE.ie_key(),
ef4fd848 2460 'uploader': video_uploader,
ef4fd848 2461 }
5f6a1245 2462
bab19a8e
S
2463 # Look for SVT player
2464 svt_url = SVTIE._extract_url(webpage)
2465 if svt_url:
2466 return self.url_result(svt_url, 'SVT')
2467
c19f7764
JMF
2468 # Look for Bandcamp pages with custom domain
2469 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2470 if mobj is not None:
2471 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2472 # Don't set the extractor because it can be a track url or an album
2473 return self.url_result(burl)
c19f7764 2474
f25571ff
PH
2475 # Look for embedded Vevo player
2476 mobj = re.search(
2477 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2478 if mobj is not None:
2479 return self.url_result(mobj.group('url'))
796df3c6
S
2480
2481 # Look for embedded Viddler player
cb454b33
S
2482 mobj = re.search(
2483 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2484 webpage)
796df3c6
S
2485 if mobj is not None:
2486 return self.url_result(mobj.group('url'))
f25571ff 2487
3378d67a
S
2488 # Look for NYTimes player
2489 mobj = re.search(
2490 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2491 webpage)
2492 if mobj is not None:
2493 return self.url_result(mobj.group('url'))
2494
cefdf970
S
2495 # Look for Libsyn player
2496 mobj = re.search(
2497 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2498 if mobj is not None:
2499 return self.url_result(mobj.group('url'))
2500
c0d0b01f 2501 # Look for Ooyala videos
8a37aa15 2502 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 2503 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
198d4cb4 2504 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
2505 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2506 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2507 if mobj is not None:
9837cb75
RA
2508 embed_token = self._search_regex(
2509 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2510 webpage, 'ooyala embed token', default=None)
2511 return OoyalaIE._build_url_result(smuggle_url(
2512 mobj.group('ec'), {
2513 'domain': url,
2514 'embed_token': embed_token,
2515 }))
c0d0b01f 2516
f076b638 2517 # Look for multiple Ooyala embeds on SBN network websites
2518 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2519 if mobj is not None:
2520 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2521 if embeds:
46b18f23
JH
2522 return self.playlist_from_matches(
2523 embeds, video_id, video_title,
2524 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2525
aa94a6d3 2526 # Look for Aparat videos
48099643 2527 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2528 if mobj is not None:
2529 return self.url_result(mobj.group(1), 'Aparat')
2530
c93c2ab1 2531 # Look for MPORA videos
c3f51436 2532 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2533 if mobj is not None:
2534 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2535
15c0e8e7 2536 # Look for embedded NovaMov-based player
8f89e687 2537 mobj = re.search(
8dfa187b 2538 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
2539 (?P<url>http://(?:(?:embed|www)\.)?
2540 (?:novamov\.com|
2541 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2542 videoweed\.(?:es|com)|
2543 movshare\.(?:net|sx|ag)|
2544 divxstage\.(?:eu|net|ch|co|at|ag))
2545 /embed\.php.+?)\1''', webpage)
8f89e687 2546 if mobj is not None:
15c0e8e7 2547 return self.url_result(mobj.group('url'))
50f56607 2548
9834872b 2549 # Look for embedded Facebook player
0646e34c
S
2550 facebook_urls = FacebookIE._extract_urls(webpage)
2551 if facebook_urls:
2552 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2553
ca97a56e
S
2554 # Look for embedded VK player
2555 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2556 if mobj is not None:
2557 return self.url_result(mobj.group('url'), 'VK')
2558
33d4fdab
S
2559 # Look for embedded Odnoklassniki player
2560 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2561 if mobj is not None:
2562 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2563
0364fa8b
S
2564 # Look for embedded ivi player
2565 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2566 if mobj is not None:
2567 return self.url_result(mobj.group('url'), 'Ivi')
2568
db1f3888
PH
2569 # Look for embedded Huffington Post player
2570 mobj = re.search(
c3f51436 2571 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2572 if mobj is not None:
2573 return self.url_result(mobj.group('url'), 'HuffPost')
2574
1b86cc41 2575 # Look for embed.ly
2576 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2577 if mobj is not None:
2578 return self.url_result(mobj.group('url'))
2579 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2580 if mobj is not None:
f7e6f7fa 2581 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2582
60cc4dc4
PH
2583 # Look for funnyordie embed
2584 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2585 if matches:
46b18f23
JH
2586 return self.playlist_from_matches(
2587 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2588
db546cf8
S
2589 # Look for BBC iPlayer embed
2590 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2591 if matches:
46b18f23 2592 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2593
93d020dd
S
2594 # Look for embedded RUTV player
2595 rutv_url = RUTVIE._extract_url(webpage)
2596 if rutv_url:
2597 return self.url_result(rutv_url, 'RUTV')
2598
494f20cb 2599 # Look for embedded TVC player
b8599718
S
2600 tvc_url = TVCIE._extract_url(webpage)
2601 if tvc_url:
2602 return self.url_result(tvc_url, 'TVC')
494f20cb 2603
d40a3b5b
S
2604 # Look for embedded SportBox player
2605 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2606 if sportbox_urls:
46b18f23 2607 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
d40a3b5b 2608
2bb5b6d0
S
2609 # Look for embedded XHamster player
2610 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2611 if xhamster_urls:
46b18f23 2612 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2613
2c9ca782
S
2614 # Look for embedded TNAFlixNetwork player
2615 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2616 if tnaflix_urls:
46b18f23 2617 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2618
b52c9ef1
S
2619 # Look for embedded PornHub player
2620 pornhub_urls = PornHubIE._extract_urls(webpage)
2621 if pornhub_urls:
46b18f23 2622 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2623
37e7a71c
S
2624 # Look for embedded DrTuber player
2625 drtuber_urls = DrTuberIE._extract_urls(webpage)
2626 if drtuber_urls:
46b18f23 2627 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2628
e28ed498
S
2629 # Look for embedded RedTube player
2630 redtube_urls = RedTubeIE._extract_urls(webpage)
2631 if redtube_urls:
46b18f23 2632 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 2633
06993715
S
2634 # Look for embedded Tube8 player
2635 tube8_urls = Tube8IE._extract_urls(webpage)
2636 if tube8_urls:
2637 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2638
9872d311
S
2639 # Look for embedded Tvigle player
2640 mobj = re.search(
2641 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2642 if mobj is not None:
2643 return self.url_result(mobj.group('url'), 'Tvigle')
2644
7e2ede98
JMF
2645 # Look for embedded TED player
2646 mobj = re.search(
d7cc31b6 2647 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
2648 if mobj is not None:
2649 return self.url_result(mobj.group('url'), 'TED')
2650
5c386252 2651 # Look for embedded Ustream videos
d77ac737
YCH
2652 ustream_url = UstreamIE._extract_url(webpage)
2653 if ustream_url:
2654 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 2655
893f8832
PH
2656 # Look for embedded arte.tv player
2657 mobj = re.search(
134c207e 2658 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
893f8832
PH
2659 webpage)
2660 if mobj is not None:
2661 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2662
cbd55ade
S
2663 # Look for embedded francetv player
2664 mobj = re.search(
2665 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2666 webpage)
2667 if mobj is not None:
2668 return self.url_result(mobj.group('url'))
2669
cb3ac1c6
S
2670 # Look for embedded smotri.com player
2671 smotri_url = SmotriIE._extract_url(webpage)
2672 if smotri_url:
2673 return self.url_result(smotri_url, 'Smotri')
2674
e6c2d9ad 2675 # Look for embedded Myvi.ru player
6dd94d3a 2676 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
2677 if myvi_url:
2678 return self.url_result(myvi_url)
2679
dfb1b146 2680 # Look for embedded soundcloud player
94aae015
S
2681 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2682 if soundcloud_urls:
46b18f23 2683 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
20991253 2684
027e2312
S
2685 # Look for tunein player
2686 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2687 if tunein_urls:
46b18f23 2688 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 2689
c5cd249e 2690 # Look for embedded mtvservices player
46fde8a1
S
2691 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2692 if mtvservices_url:
2693 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 2694
49807b4a
S
2695 # Look for embedded yahoo player
2696 mobj = re.search(
2697 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2698 webpage)
2699 if mobj is not None:
2700 return self.url_result(mobj.group('url'), 'Yahoo')
2701
2ef6fcb5
PH
2702 # Look for embedded sbs.com.au player
2703 mobj = re.search(
e98b8e79
PH
2704 r'''(?x)
2705 (?:
2706 <meta\s+property="og:video"\s+content=|
2707 <iframe[^>]+?src=
2708 )
2709 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
2710 webpage)
2711 if mobj is not None:
2712 return self.url_result(mobj.group('url'), 'SBS')
2713
42bdd9d0
PH
2714 # Look for embedded Cinchcast player
2715 mobj = re.search(
2716 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2717 webpage)
2718 if mobj is not None:
2719 return self.url_result(mobj.group('url'), 'Cinchcast')
2720
1a94ff68 2721 mobj = re.search(
5263cdfc 2722 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 2723 webpage)
8001607e
YCH
2724 if not mobj:
2725 mobj = re.search(
2726 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2727 webpage)
1a94ff68
S
2728 if mobj is not None:
2729 return self.url_result(mobj.group('url'), 'MLB')
2730
1419fafd 2731 mobj = re.search(
dd467d33 2732 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
2733 webpage)
2734 if mobj is not None:
2735 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2736
af63fed7 2737 mobj = re.search(
78d3b3e2 2738 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
2739 webpage)
2740 if mobj is not None:
2741 return self.url_result(mobj.group('url'), 'Livestream')
2742
255fca5e
S
2743 # Look for Zapiks embed
2744 mobj = re.search(
2745 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2746 if mobj is not None:
2747 return self.url_result(mobj.group('url'), 'Zapiks')
2748
e3216b82 2749 # Look for Kaltura embeds
c287f2bc
S
2750 kaltura_url = KalturaIE._extract_url(webpage)
2751 if kaltura_url:
2752 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
e3216b82 2753
665e9452 2754 # Look for EaglePlatform embeds
06a96da1
S
2755 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2756 if eagleplatform_url:
665e9452 2757 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 2758
665e9452 2759 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
2760 mobj = re.search(
2761 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2762 if mobj is not None:
2763 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2764
f8388757 2765 # Look for Pladform embeds
45dad7ba
S
2766 pladform_url = PladformIE._extract_url(webpage)
2767 if pladform_url:
2768 return self.url_result(pladform_url)
f8388757 2769
ff18735c
S
2770 # Look for Videomore embeds
2771 videomore_url = VideomoreIE._extract_url(webpage)
2772 if videomore_url:
2773 return self.url_result(videomore_url)
2774
83f1481b
S
2775 # Look for Webcaster embeds
2776 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2777 if webcaster_url:
2778 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2779
2dcc114f
S
2780 # Look for Playwire embeds
2781 mobj = re.search(
2782 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2783 if mobj is not None:
2784 return self.url_result(mobj.group('url'))
2785
ad320e9b
NJ
2786 # Look for 5min embeds
2787 mobj = re.search(
2788 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2789 if mobj is not None:
2790 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2791
18153f1b
S
2792 # Look for Crooks and Liars embeds
2793 mobj = re.search(
2794 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2795 if mobj is not None:
2796 return self.url_result(mobj.group('url'))
2797
a2edf2e7
YCH
2798 # Look for NBC Sports VPlayer embeds
2799 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2800 if nbc_sports_url:
2801 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2802
de3eb07e
YCH
2803 # Look for NBC News embeds
2804 nbc_news_embed_url = re.search(
2805 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2806 if nbc_news_embed_url:
2807 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2808
653789af 2809 # Look for Google Drive embeds
5b251628 2810 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 2811 if google_drive_url:
2812 return self.url_result(google_drive_url, 'GoogleDrive')
2813
418c5cc3
YCH
2814 # Look for UDN embeds
2815 mobj = re.search(
2637fadc 2816 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
2817 if mobj is not None:
2818 return self.url_result(
0a160363 2819 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 2820
2fe1b5bd
YCH
2821 # Look for Senate ISVP iframe
2822 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2823 if senate_isvp_url:
25c3a734 2824 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 2825
1ac1c4c2
S
2826 # Look for OnionStudios embeds
2827 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2828 if onionstudios_url:
2829 return self.url_result(onionstudios_url)
2830
67167920 2831 # Look for ViewLift embeds
2832 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2833 if viewlift_url:
2834 return self.url_result(viewlift_url)
eedd20ef 2835
7cb09524 2836 # Look for JWPlatform embeds
b0ead0e0
S
2837 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2838 if jwplatform_urls:
2839 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
7cb09524 2840
aecfcd4e
S
2841 # Look for Digiteka embeds
2842 digiteka_url = DigitekaIE._extract_url(webpage)
2843 if digiteka_url:
2844 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 2845
1979969f
S
2846 # Look for Arkena embeds
2847 arkena_url = ArkenaIE._extract_url(webpage)
2848 if arkena_url:
2849 return self.url_result(arkena_url, ArkenaIE.ie_key())
2850
b1c35797
RA
2851 # Look for Piksel embeds
2852 piksel_url = PikselIE._extract_url(webpage)
2853 if piksel_url:
2854 return self.url_result(piksel_url, PikselIE.ie_key())
2855
1bf996fa 2856 # Look for Limelight embeds
e5d39886
S
2857 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2858 if limelight_urls:
2859 return self.playlist_result(
2860 limelight_urls, video_id, video_title, video_description)
2861
7986c3ab
S
2862 # Look for Anvato embeds
2863 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2864 if anvato_urls:
2865 return self.playlist_result(
2866 anvato_urls, video_id, video_title, video_description)
2867
a5158f38
YCH
2868 # Look for AdobeTVVideo embeds
2869 mobj = re.search(
2870 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2871 webpage)
2872 if mobj is not None:
2873 return self.url_result(
2874 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2875 'AdobeTVVideo')
2876
088e1aac
YCH
2877 # Look for Vine embeds
2878 mobj = re.search(
2879 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2880 webpage)
2881 if mobj is not None:
2882 return self.url_result(
2883 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2884
217d5ae0
RA
2885 # Look for VODPlatform embeds
2886 mobj = re.search(
93b84045 2887 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
217d5ae0
RA
2888 webpage)
2889 if mobj is not None:
2890 return self.url_result(
93b84045 2891 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 2892
7d273a38
RA
2893 # Look for Mangomolo embeds
2894 mobj = re.search(
d05ef09d 2895 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
7d273a38
RA
2896 (?:
2897 video\?.*?\bid=(?P<video_id>\d+)|
2898 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2899 ).+?)\1''', webpage)
2900 if mobj is not None:
2901 info = {
2902 '_type': 'url_transparent',
2903 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2904 'title': video_title,
2905 'description': video_description,
2906 'thumbnail': video_thumbnail,
2907 'uploader': video_uploader,
2908 }
2909 video_id = mobj.group('video_id')
2910 if video_id:
2911 info.update({
2912 'ie_key': 'MangomoloVideo',
2913 'id': video_id,
2914 })
2915 else:
2916 info.update({
2917 'ie_key': 'MangomoloLive',
2918 'id': mobj.group('channel_id'),
2919 })
2920 return info
2921
5a51775a
YCH
2922 # Look for Instagram embeds
2923 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2924 if instagram_embed_url is not None:
11e60fca
S
2925 return self.url_result(
2926 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 2927
b8f67449 2928 # Look for LiveLeak embeds
09747ba7
YCH
2929 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2930 if liveleak_urls:
2931 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
b8f67449 2932
5d39176f
S
2933 # Look for 3Q SDN embeds
2934 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2935 if threeqsdn_url:
6f41b2bc
S
2936 return {
2937 '_type': 'url_transparent',
2938 'ie_key': ThreeQSDNIE.ie_key(),
2939 'url': self._proto_relative_url(threeqsdn_url),
2940 'title': video_title,
2941 'description': video_description,
2942 'thumbnail': video_thumbnail,
2943 'uploader': video_uploader,
2944 }
5d39176f 2945
2a1321a2
S
2946 # Look for VBOX7 embeds
2947 vbox7_url = Vbox7IE._extract_url(webpage)
2948 if vbox7_url:
2949 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2950
b0c8f2e9
DR
2951 # Look for DBTV embeds
2952 dbtv_urls = DBTVIE._extract_urls(webpage)
2953 if dbtv_urls:
46b18f23 2954 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 2955
e186a9ec
S
2956 # Look for Videa embeds
2957 videa_urls = VideaIE._extract_urls(webpage)
2958 if videa_urls:
46b18f23 2959 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 2960
b687c85e
S
2961 # Look for 20 minuten embeds
2962 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2963 if twentymin_urls:
46b18f23
JH
2964 return self.playlist_from_matches(
2965 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 2966
17f8deeb
S
2967 # Look for Openload embeds
2968 openload_urls = OpenloadIE._extract_urls(webpage)
2969 if openload_urls:
46b18f23
JH
2970 return self.playlist_from_matches(
2971 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
17f8deeb 2972
6ef3e65a
S
2973 # Look for VideoPress embeds
2974 videopress_urls = VideoPressIE._extract_urls(webpage)
2975 if videopress_urls:
46b18f23
JH
2976 return self.playlist_from_matches(
2977 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 2978
eb3079b6
S
2979 # Look for Rutube embeds
2980 rutube_urls = RutubeIE._extract_urls(webpage)
2981 if rutube_urls:
46b18f23 2982 return self.playlist_from_matches(
2583c0b5 2983 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 2984
55719459
JH
2985 # Look for WashingtonPost embeds
2986 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2987 if wapo_urls:
2988 return self.playlist_from_matches(
2989 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2990
5d29af3d
S
2991 # Look for Mediaset embeds
2992 mediaset_urls = MediasetIE._extract_urls(webpage)
2993 if mediaset_urls:
2994 return self.playlist_from_matches(
2995 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2996
73cf76a9
S
2997 # Look for JOJ.sk embeds
2998 joj_urls = JojIE._extract_urls(webpage)
2999 if joj_urls:
3000 return self.playlist_from_matches(
3001 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3002
24e966e8
PH
3003 # Look for megaphone.fm embeds
3004 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3005 if mpfn_urls:
3006 return self.playlist_from_matches(
3007 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3008
1663bd6e
S
3009 # Look for vzaar embeds
3010 vzaar_urls = VzaarIE._extract_urls(webpage)
3011 if vzaar_urls:
3012 return self.playlist_from_matches(
3013 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3014
26bae2d9
S
3015 channel9_urls = Channel9IE._extract_urls(webpage)
3016 if channel9_urls:
3017 return self.playlist_from_matches(
3018 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3019
0987f2dd
T
3020 vshare_urls = VShareIE._extract_urls(webpage)
3021 if vshare_urls:
3022 return self.playlist_from_matches(
3023 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3024
8056c854 3025 # Look for Mediasite embeds
2ca7ed41
S
3026 mediasite_urls = MediasiteIE._extract_urls(webpage)
3027 if mediasite_urls:
3028 entries = [
3029 self.url_result(smuggle_url(
3030 compat_urlparse.urljoin(url, mediasite_url),
3031 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3032 for mediasite_url in mediasite_urls]
3033 return self.playlist_result(entries, video_id, video_title)
8056c854 3034
7d540621
S
3035 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3036 if springboardplatform_urls:
3037 return self.playlist_from_matches(
3038 springboardplatform_urls, video_id, video_title,
3039 ie=SpringboardPlatformIE.ie_key())
3040
4c780fbd
S
3041 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3042 if yapfiles_urls:
3043 return self.playlist_from_matches(
3044 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3045
86c8cfc5
S
3046 vice_urls = ViceIE._extract_urls(webpage)
3047 if vice_urls:
3048 return self.playlist_from_matches(
3049 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3050
178ee883
S
3051 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3052 if xfileshare_urls:
3053 return self.playlist_from_matches(
3054 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3055
660a230b
S
3056 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3057 if cloudflarestream_urls:
3058 return self.playlist_from_matches(
3059 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3060
6bd499e8
S
3061 peertube_urls = PeerTubeIE._extract_urls(webpage)
3062 if peertube_urls:
3063 return self.playlist_from_matches(
3064 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3065
aee36ca8
S
3066 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3067 if indavideo_urls:
3068 return self.playlist_from_matches(
3069 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3070
d3431dcb
S
3071 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
3072 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3073 webpage)]
3074 if sharevideos_urls:
3075 return self.playlist_from_matches(
3076 sharevideos_urls, video_id, video_title)
3077
bd264412
YCH
3078 # Look for HTML5 media
3079 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3080 if entries:
9ce1ac40 3081 if len(entries) == 1:
3082 entries[0].update({
bd264412
YCH
3083 'id': video_id,
3084 'title': video_title,
3085 })
9ce1ac40 3086 else:
3087 for num, entry in enumerate(entries, start=1):
3088 entry.update({
3089 'id': '%s-%s' % (video_id, num),
3090 'title': '%s (%d)' % (video_title, num),
3091 })
3092 for entry in entries:
bd264412 3093 self._sort_formats(entry['formats'])
9ce1ac40 3094 return self.playlist_result(entries, video_id, video_title)
bd264412 3095
c73e330e
RU
3096 jwplayer_data = self._find_jwplayer_data(
3097 webpage, video_id, transform_source=js_to_json)
3098 if jwplayer_data:
4f06c1c9 3099 info = self._parse_jwplayer_data(
3e943cfe 3100 jwplayer_data, video_id, require_title=False, base_url=url)
b311b0ea 3101 return merge_dicts(info, info_dict)
a4a554a7 3102
63d990d2
S
3103 # Video.js embed
3104 mobj = re.search(
c5b7014a 3105 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
3106 webpage)
3107 if mobj is not None:
3108 sources = self._parse_json(
3109 mobj.group(1), video_id, transform_source=js_to_json,
3110 fatal=False) or []
c5b7014a
S
3111 if not isinstance(sources, list):
3112 sources = [sources]
63d990d2
S
3113 formats = []
3114 for source in sources:
3115 src = source.get('src')
3116 if not src or not isinstance(src, compat_str):
3117 continue
3118 src = compat_urlparse.urljoin(url, src)
3119 src_type = source.get('type')
3120 if isinstance(src_type, compat_str):
3121 src_type = src_type.lower()
3122 ext = determine_ext(src).lower()
3123 if src_type == 'video/youtube':
3124 return self.url_result(src, YoutubeIE.ie_key())
3125 if src_type == 'application/dash+xml' or ext == 'mpd':
3126 formats.extend(self._extract_mpd_formats(
3127 src, video_id, mpd_id='dash', fatal=False))
3128 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3129 formats.extend(self._extract_m3u8_formats(
3130 src, video_id, 'mp4', entry_protocol='m3u8_native',
3131 m3u8_id='hls', fatal=False))
3132 else:
3133 formats.append({
3134 'url': src,
3135 'ext': (mimetype2ext(src_type) or
3136 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3137 })
3138 if formats:
3139 self._sort_formats(formats)
3140 info_dict['formats'] = formats
3141 return info_dict
3142
ff17be3a
S
3143 # Looking for http://schema.org/VideoObject
3144 json_ld = self._search_json_ld(
3145 webpage, video_id, default={}, expected_type='VideoObject')
3146 if json_ld.get('url'):
3147 return merge_dicts(json_ld, info_dict)
3148
ced659bb 3149 def check_video(vurl):
a0f71985
PH
3150 if YoutubeIE.suitable(vurl):
3151 return True
b7a8c1bc
S
3152 if RtmpIE.suitable(vurl):
3153 return True
ced659bb
S
3154 vpath = compat_urlparse.urlparse(vurl).path
3155 vext = determine_ext(vpath)
0ee79a37 3156 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
3157
3158 def filter_video(urls):
3159 return list(filter(check_video, urls))
3160
9b122384 3161 # Start with something easy: JW Player in SWFObject
ced659bb 3162 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 3163 if not found:
d981cef6 3164 # Look for gorilla-vid style embedding
ced659bb 3165 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
3166 (?:
3167 jw_plugins|
3168 JWPlayerOptions|
3169 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3170 )
a0f71985
PH
3171 .*?
3172 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 3173 if not found:
9b122384 3174 # Broaden the search a little bit
ced659bb 3175 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
3176 if not found:
3177 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 3178 found = filter_video(re.findall(
54a9328b 3179 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
3180 if not found:
3181 # Flow player
ced659bb 3182 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
3183 flowplayer\("[^"]+",\s*
3184 \{[^}]+?\}\s*,
52585fd6 3185 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 3186 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 3187 ''', webpage))
501f13fb
PH
3188 if not found:
3189 # Cinerama player
3190 found = re.findall(
3191 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 3192 if not found:
9b122384 3193 # Try to find twitter cards info
371ddb14
S
3194 # twitter:player:stream should be checked before twitter:player since
3195 # it is expected to contain a raw stream (see
3196 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3197 found = filter_video(re.findall(
3198 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 3199 if not found:
9b122384
PH
3200 # We look for Open Graph info:
3201 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3202 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3203 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3204 if m_video_type is not None:
ced659bb 3205 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 3206 if not found:
ed9a25dd 3207 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3208 found = re.search(
89ef304b 3209 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3210 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3211 webpage)
84f81016
S
3212 if not found:
3213 # Look also in Refresh HTTP header
3214 refresh_header = head_response.headers.get('Refresh')
3215 if refresh_header:
6c91a5a7
S
3216 # In python 2 response HTTP headers are bytestrings
3217 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3218 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3219 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3220 if found:
b37317d8 3221 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3222 if new_url != url:
3223 self.report_following_redirect(new_url)
3224 return {
3225 '_type': 'url',
3226 'url': new_url,
3227 }
3228 else:
3229 found = None
371ddb14
S
3230
3231 if not found:
3232 # twitter:player is a https URL to iframe player that may or may not
3233 # be supported by youtube-dl thus this is checked the very last (see
3234 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3235 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3236 if embed_url and embed_url != url:
371ddb14
S
3237 return self.url_result(embed_url)
3238
b30b8698 3239 if not found:
416c7fcb 3240 raise UnsupportedError(url)
9b122384 3241
b30b8698 3242 entries = []
4a120778 3243 for video_url in orderedSet(found):
949b6497 3244 video_url = unescapeHTML(video_url)
6cc37c69 3245 video_url = video_url.replace('\\/', '/')
b30b8698 3246 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3247 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3248
b30b8698
PH
3249 # Sometimes, jwplayer extraction will result in a YouTube URL
3250 if YoutubeIE.suitable(video_url):
3251 entries.append(self.url_result(video_url, 'Youtube'))
3252 continue
9b122384 3253
b30b8698
PH
3254 # here's a fun little line of code for you:
3255 video_id = os.path.splitext(video_id)[0]
fc9713a1 3256
28602e74
YCH
3257 entry_info_dict = {
3258 'id': video_id,
3259 'uploader': video_uploader,
3260 'title': video_title,
3261 'age_limit': age_limit,
3262 }
3263
5620f840
S
3264 if RtmpIE.suitable(video_url):
3265 entry_info_dict.update({
3266 '_type': 'url_transparent',
3267 'ie_key': RtmpIE.ie_key(),
3268 'url': video_url,
3269 })
3270 entries.append(entry_info_dict)
3271 continue
3272
729accb4
S
3273 ext = determine_ext(video_url)
3274 if ext == 'smil':
28602e74 3275 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
3276 elif ext == 'xspf':
3277 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
3278 elif ext == 'm3u8':
3279 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
3280 elif ext == 'mpd':
3281 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
3282 elif ext == 'f4m':
3283 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3284 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3285 # Just matching .ism/manifest is not enough to be reliably sure
3286 # whether it's actually an ISM manifest or some other streaming
3287 # manifest since there are various streaming URL formats
3288 # possible (see [1]) as well as some other shenanigans like
3289 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3290 # so on.
3291 # Thus the most reasonable way to solve this is to delegate
3292 # to generic extractor in order to look into the contents of
3293 # the manifest itself.
3294 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3295 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3296 entry_info_dict = self.url_result(
3297 smuggle_url(video_url, {'to_generic': True}),
3298 GenericIE.ie_key())
d6fd958c 3299 else:
28602e74
YCH
3300 entry_info_dict['url'] = video_url
3301
19dbaeec
S
3302 if entry_info_dict.get('formats'):
3303 self._sort_formats(entry_info_dict['formats'])
3304
28602e74 3305 entries.append(entry_info_dict)
b30b8698
PH
3306
3307 if len(entries) == 1:
669f0e7c 3308 return entries[0]
b30b8698
PH
3309 else:
3310 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3311 # 'url' results don't have a title
3312 if e.get('title') is not None:
3313 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3314 return {
3315 '_type': 'playlist',
3316 'entries': entries,
3317 }