]>
Commit | Line | Data |
---|---|---|
cfe50f04 JMF |
1 | # encoding: utf-8 |
2 | ||
79649588 PH |
3 | from __future__ import unicode_literals |
4 | ||
9b122384 PH |
5 | import os |
6 | import re | |
6c91a5a7 | 7 | import sys |
9b122384 PH |
8 | |
9 | from .common import InfoExtractor | |
fc9713a1 | 10 | from .youtube import YoutubeIE |
8c25f81b | 11 | from ..compat import ( |
f7854627 | 12 | compat_etree_fromstring, |
1ddb9456 | 13 | compat_urllib_parse_unquote, |
a5caba1e | 14 | compat_urlparse, |
f7300c5c | 15 | compat_xml_parse_error, |
8c25f81b PH |
16 | ) |
17 | from ..utils import ( | |
b759a0d4 | 18 | determine_ext, |
9b122384 | 19 | ExtractorError, |
c8e9a235 | 20 | float_or_none, |
aa94a6d3 | 21 | HEADRequest, |
61ca9a80 | 22 | is_html, |
ed2d6a19 | 23 | orderedSet, |
5c2266df | 24 | sanitized_Request, |
9d4660ca PH |
25 | smuggle_url, |
26 | unescapeHTML, | |
42393ce2 | 27 | unified_strdate, |
4d54ef20 | 28 | unsmuggle_url, |
416c7fcb | 29 | UnsupportedError, |
42393ce2 | 30 | url_basename, |
76c73715 | 31 | xpath_text, |
9b122384 | 32 | ) |
ed126900 | 33 | from .brightcove import ( |
4fcaa4f4 | 34 | BrightcoveLegacyIE, |
5c17f0a6 | 35 | BrightcoveNewIE, |
ed126900 | 36 | ) |
a2edf2e7 | 37 | from .nbc import NBCSportsVPlayerIE |
c0d0b01f | 38 | from .ooyala import OoyalaIE |
93d020dd | 39 | from .rutv import RUTVIE |
954c1d05 | 40 | from .tvc import TVCIE |
d40a3b5b | 41 | from .sportbox import SportBoxEmbedIE |
cb3ac1c6 | 42 | from .smotri import SmotriIE |
6dd94d3a | 43 | from .myvi import MyviIE |
1419fafd | 44 | from .condenast import CondeNastIE |
418c5cc3 | 45 | from .udn import UDNEmbedIE |
2fe1b5bd | 46 | from .senateisvp import SenateISVPIE |
bab19a8e | 47 | from .svt import SVTIE |
65d161c4 | 48 | from .pornhub import PornHubIE |
2bb5b6d0 | 49 | from .xhamster import XHamsterEmbedIE |
2c9ca782 | 50 | from .tnaflix import TNAFlixNetworkEmbedIE |
b407e173 | 51 | from .vimeo import VimeoIE |
756f574e | 52 | from .dailymotion import DailymotionCloudIE |
1ac1c4c2 | 53 | from .onionstudios import OnionStudiosIE |
eedd20ef | 54 | from .snagfilms import SnagFilmsEmbedIE |
efd712c6 | 55 | from .screenwavemedia import ScreenwaveMediaIE |
46fde8a1 | 56 | from .mtv import MTVServicesEmbeddedIE |
45dad7ba | 57 | from .pladform import PladformIE |
ff18735c | 58 | from .videomore import VideomoreIE |
5b251628 | 59 | from .googledrive import GoogleDriveIE |
7cb09524 | 60 | from .jwplatform import JWPlatformIE |
aecfcd4e | 61 | from .digiteka import DigitekaIE |
9b122384 | 62 | |
0838239e | 63 | |
9b122384 | 64 | class GenericIE(InfoExtractor): |
79649588 | 65 | IE_DESC = 'Generic downloader that works on some sites' |
9b122384 | 66 | _VALID_URL = r'.*' |
79649588 | 67 | IE_NAME = 'generic' |
cfe50f04 | 68 | _TESTS = [ |
c5fa81fe S |
69 | # Direct link to a video |
70 | { | |
71 | 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', | |
72 | 'md5': '67d406c2bcb6af27fa886f31aa934bbe', | |
73 | 'info_dict': { | |
74 | 'id': 'trailer', | |
75 | 'ext': 'mp4', | |
76 | 'title': 'trailer', | |
77 | 'upload_date': '20100513', | |
78 | } | |
79 | }, | |
c5138a7c | 80 | # Direct link to media delivered compressed (until Accept-Encoding is *) |
c5fa81fe S |
81 | { |
82 | 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac', | |
83 | 'md5': '128c42e68b13950268b648275386fc74', | |
84 | 'info_dict': { | |
85 | 'id': 'FictionJunction-Parallel_Hearts', | |
86 | 'ext': 'flac', | |
87 | 'title': 'FictionJunction-Parallel_Hearts', | |
88 | 'upload_date': '20140522', | |
89 | }, | |
90 | 'expected_warnings': [ | |
91 | 'URL could be a direct video link, returning it as such.' | |
92 | ] | |
93 | }, | |
94 | # Direct download with broken HEAD | |
95 | { | |
96 | 'url': 'http://ai-radio.org:8000/radio.opus', | |
97 | 'info_dict': { | |
98 | 'id': 'radio', | |
99 | 'ext': 'opus', | |
100 | 'title': 'radio', | |
101 | }, | |
102 | 'params': { | |
103 | 'skip_download': True, # infinite live stream | |
104 | }, | |
105 | 'expected_warnings': [ | |
106 | r'501.*Not Implemented' | |
107 | ], | |
108 | }, | |
109 | # Direct link with incorrect MIME type | |
110 | { | |
111 | 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', | |
112 | 'md5': '4ccbebe5f36706d85221f204d7eb5913', | |
113 | 'info_dict': { | |
114 | 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', | |
115 | 'id': '5_Lennart_Poettering_-_Systemd', | |
116 | 'ext': 'webm', | |
117 | 'title': '5_Lennart_Poettering_-_Systemd', | |
118 | 'upload_date': '20141120', | |
119 | }, | |
120 | 'expected_warnings': [ | |
121 | 'URL could be a direct video link, returning it as such.' | |
122 | ] | |
123 | }, | |
124 | # RSS feed | |
125 | { | |
126 | 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml', | |
127 | 'info_dict': { | |
128 | 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml', | |
129 | 'title': 'Zero Punctuation', | |
130 | 'description': 're:.*groundbreaking video review series.*' | |
131 | }, | |
132 | 'playlist_mincount': 11, | |
133 | }, | |
134 | # RSS feed with enclosure | |
135 | { | |
136 | 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml', | |
137 | 'info_dict': { | |
138 | 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624', | |
139 | 'ext': 'm4v', | |
140 | 'upload_date': '20150228', | |
141 | 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624', | |
142 | } | |
143 | }, | |
8765222d S |
144 | # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng |
145 | { | |
146 | 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml', | |
147 | 'info_dict': { | |
148 | 'id': 'smil', | |
149 | 'ext': 'mp4', | |
150 | 'title': 'Automatics, robotics and biocybernetics', | |
151 | 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482', | |
e327b736 | 152 | 'upload_date': '20130627', |
8765222d S |
153 | 'formats': 'mincount:16', |
154 | 'subtitles': 'mincount:1', | |
155 | }, | |
156 | 'params': { | |
157 | 'force_generic_extractor': True, | |
158 | 'skip_download': True, | |
159 | }, | |
160 | }, | |
161 | # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html | |
162 | { | |
163 | 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil', | |
164 | 'info_dict': { | |
165 | 'id': 'hds', | |
166 | 'ext': 'flv', | |
167 | 'title': 'hds', | |
168 | 'formats': 'mincount:1', | |
169 | }, | |
170 | 'params': { | |
171 | 'skip_download': True, | |
172 | }, | |
173 | }, | |
174 | # SMIL from https://www.restudy.dk/video/play/id/1637 | |
175 | { | |
176 | 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml', | |
177 | 'info_dict': { | |
178 | 'id': 'video_1637', | |
179 | 'ext': 'flv', | |
180 | 'title': 'video_1637', | |
181 | 'formats': 'mincount:3', | |
182 | }, | |
183 | 'params': { | |
184 | 'skip_download': True, | |
185 | }, | |
186 | }, | |
187 | # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm | |
188 | { | |
189 | 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil', | |
190 | 'info_dict': { | |
191 | 'id': 'smil-service', | |
192 | 'ext': 'flv', | |
193 | 'title': 'smil-service', | |
194 | 'formats': 'mincount:1', | |
195 | }, | |
196 | 'params': { | |
197 | 'skip_download': True, | |
198 | }, | |
199 | }, | |
200 | # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370 | |
201 | { | |
202 | 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil', | |
203 | 'info_dict': { | |
204 | 'id': '4719370', | |
205 | 'ext': 'mp4', | |
206 | 'title': '571de1fd-47bc-48db-abf9-238872a58d1f', | |
207 | 'formats': 'mincount:3', | |
208 | }, | |
209 | 'params': { | |
210 | 'skip_download': True, | |
211 | }, | |
212 | }, | |
1de5cd3b S |
213 | # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html |
214 | { | |
215 | 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf', | |
216 | 'info_dict': { | |
217 | 'id': 'mZlp2ctYIUEB', | |
218 | 'ext': 'mp4', | |
219 | 'title': 'Tikibad ontruimd wegens brand', | |
220 | 'description': 'md5:05ca046ff47b931f9b04855015e163a4', | |
221 | 'thumbnail': 're:^https?://.*\.jpg$', | |
222 | 'duration': 33, | |
223 | }, | |
224 | 'params': { | |
225 | 'skip_download': True, | |
226 | }, | |
227 | }, | |
9d939cec S |
228 | # MPD from http://dash-mse-test.appspot.com/media.html |
229 | { | |
230 | 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd', | |
231 | 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53', | |
232 | 'info_dict': { | |
233 | 'id': 'car-20120827-manifest', | |
234 | 'ext': 'mp4', | |
235 | 'title': 'car-20120827-manifest', | |
236 | 'formats': 'mincount:9', | |
237 | }, | |
238 | 'params': { | |
239 | 'format': 'bestvideo', | |
240 | }, | |
241 | }, | |
c5fa81fe S |
242 | # google redirect |
243 | { | |
244 | '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', | |
245 | 'info_dict': { | |
246 | 'id': 'cmQHVoWB5FY', | |
247 | 'ext': 'mp4', | |
248 | 'upload_date': '20130224', | |
249 | 'uploader_id': 'TheVerge', | |
250 | 'description': 're:^Chris Ziegler takes a look at the\.*', | |
251 | 'uploader': 'The Verge', | |
252 | 'title': 'First Firefox OS phones side-by-side', | |
253 | }, | |
254 | 'params': { | |
255 | 'skip_download': False, | |
256 | } | |
257 | }, | |
6c91a5a7 S |
258 | { |
259 | # redirect in Refresh HTTP header | |
260 | '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', | |
261 | 'info_dict': { | |
262 | 'id': 'pO8h3EaFRdo', | |
263 | 'ext': 'mp4', | |
264 | 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set', | |
265 | 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5', | |
266 | 'upload_date': '20150917', | |
267 | 'uploader_id': 'brtvofficial', | |
268 | 'uploader': 'Boiler Room', | |
269 | }, | |
270 | 'params': { | |
271 | 'skip_download': False, | |
272 | }, | |
273 | }, | |
cfe50f04 | 274 | { |
79649588 | 275 | 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html', |
d360a146 | 276 | 'md5': '85b90ccc9d73b4acd9138d3af4c27f89', |
79649588 | 277 | 'info_dict': { |
d360a146 S |
278 | 'id': '13601338388002', |
279 | 'ext': 'mp4', | |
79649588 PH |
280 | 'uploader': 'www.hodiho.fr', |
281 | 'title': 'R\u00e9gis plante sa Jeep', | |
cfe50f04 JMF |
282 | } |
283 | }, | |
c19f7764 JMF |
284 | # bandcamp page with custom domain |
285 | { | |
79649588 PH |
286 | 'add_ie': ['Bandcamp'], |
287 | 'url': 'http://bronyrock.com/track/the-pony-mash', | |
79649588 | 288 | 'info_dict': { |
fd50bf62 S |
289 | 'id': '3235767654', |
290 | 'ext': 'mp3', | |
79649588 PH |
291 | 'title': 'The Pony Mash', |
292 | 'uploader': 'M_Pallante', | |
c19f7764 | 293 | }, |
79649588 | 294 | 'skip': 'There is a limit of 200 free downloads / month for the test song', |
c19f7764 | 295 | }, |
eeb165e6 | 296 | # embedded brightcove video |
dd5bcdc4 JMF |
297 | # it also tests brightcove videos that need to set the 'Referer' in the |
298 | # http requests | |
eeb165e6 | 299 | { |
3b7d9aa4 | 300 | 'add_ie': ['BrightcoveLegacy'], |
79649588 PH |
301 | 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/', |
302 | 'info_dict': { | |
303 | 'id': '2765128793001', | |
304 | 'ext': 'mp4', | |
305 | 'title': 'Le cours de bourse : l’analyse technique', | |
306 | 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9', | |
307 | 'uploader': 'BFM BUSINESS', | |
eeb165e6 | 308 | }, |
79649588 PH |
309 | 'params': { |
310 | 'skip_download': True, | |
eeb165e6 JMF |
311 | }, |
312 | }, | |
17ab4d3b PH |
313 | { |
314 | # https://github.com/rg3/youtube-dl/issues/2253 | |
315 | 'url': 'http://bcove.me/i6nfkrc3', | |
17ab4d3b PH |
316 | 'md5': '0ba9446db037002366bab3b3eb30c88c', |
317 | 'info_dict': { | |
fd50bf62 S |
318 | 'id': '3101154703001', |
319 | 'ext': 'mp4', | |
17ab4d3b PH |
320 | 'title': 'Still no power', |
321 | 'uploader': 'thestar.com', | |
322 | '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.', | |
323 | }, | |
3b7d9aa4 | 324 | 'add_ie': ['BrightcoveLegacy'], |
17ab4d3b | 325 | }, |
0479c625 S |
326 | { |
327 | 'url': 'http://www.championat.com/video/football/v/87/87499.html', | |
328 | 'md5': 'fb973ecf6e4a78a67453647444222983', | |
329 | 'info_dict': { | |
330 | 'id': '3414141473001', | |
331 | 'ext': 'mp4', | |
332 | 'title': 'Видео. Удаление Дзагоева (ЦСКА)', | |
333 | 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"', | |
334 | 'uploader': 'Championat', | |
335 | }, | |
336 | }, | |
bdf97017 | 337 | { |
37aab278 | 338 | # https://github.com/rg3/youtube-dl/issues/3541 |
3b7d9aa4 | 339 | 'add_ie': ['BrightcoveLegacy'], |
bdf97017 NJ |
340 | 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1', |
341 | 'info_dict': { | |
342 | 'id': '3866516442001', | |
37aab278 | 343 | 'ext': 'mp4', |
bdf97017 NJ |
344 | 'title': 'Leer mij vrouwen kennen: Aflevering 1', |
345 | 'description': 'Leer mij vrouwen kennen: Aflevering 1', | |
346 | 'uploader': 'SBS Broadcasting', | |
347 | }, | |
37aab278 | 348 | 'skip': 'Restricted to Netherlands', |
bdf97017 | 349 | 'params': { |
37aab278 | 350 | 'skip_download': True, # m3u8 download |
bdf97017 NJ |
351 | }, |
352 | }, | |
c0d0b01f JMF |
353 | # ooyala video |
354 | { | |
79649588 | 355 | 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219', |
87830900 | 356 | 'md5': '166dd577b433b4d4ebfee10b0824d8ff', |
79649588 PH |
357 | 'info_dict': { |
358 | 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ', | |
359 | 'ext': 'mp4', | |
3486df38 | 360 | 'title': '2cc213299525360.mov', # that's what we get |
53e06b25 | 361 | 'duration': 238.231, |
c0d0b01f | 362 | }, |
87830900 | 363 | 'add_ie': ['Ooyala'], |
c0d0b01f | 364 | }, |
bf94d763 S |
365 | { |
366 | # ooyala video embedded with http://player.ooyala.com/iframe.js | |
367 | 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/', | |
368 | 'info_dict': { | |
369 | 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB', | |
370 | 'ext': 'mp4', | |
371 | 'title': '"Steve Jobs: Man in the Machine" trailer', | |
372 | 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."', | |
53e06b25 | 373 | 'duration': 135.427, |
bf94d763 S |
374 | }, |
375 | 'params': { | |
376 | 'skip_download': True, | |
377 | }, | |
378 | }, | |
f076b638 | 379 | # multiple ooyala embeds on SBN network websites |
380 | { | |
381 | 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok', | |
382 | 'info_dict': { | |
383 | 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok', | |
384 | 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com', | |
385 | }, | |
386 | 'playlist_mincount': 3, | |
387 | 'params': { | |
388 | 'skip_download': True, | |
389 | }, | |
390 | 'add_ie': ['Ooyala'], | |
391 | }, | |
1b86cc41 | 392 | # embed.ly video |
393 | { | |
394 | 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/', | |
395 | 'info_dict': { | |
396 | 'id': '9ODmcdjQcHQ', | |
397 | 'ext': 'mp4', | |
0a5bce56 PH |
398 | 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second', |
399 | 'upload_date': '20140225', | |
400 | 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff', | |
401 | 'uploader': 'Tested', | |
402 | 'uploader_id': 'testedcom', | |
1b86cc41 | 403 | }, |
404 | # No need to test YoutubeIE here | |
405 | 'params': { | |
406 | 'skip_download': True, | |
407 | }, | |
408 | }, | |
60cc4dc4 PH |
409 | # funnyordie embed |
410 | { | |
411 | 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns', | |
60cc4dc4 PH |
412 | 'info_dict': { |
413 | 'id': '18e820ec3f', | |
414 | 'ext': 'mp4', | |
415 | 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama', | |
416 | 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.', | |
93d020dd | 417 | }, |
60cc4dc4 | 418 | }, |
93d020dd S |
419 | # RUTV embed |
420 | { | |
421 | 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html', | |
422 | 'info_dict': { | |
423 | 'id': '776940', | |
424 | 'ext': 'mp4', | |
425 | 'title': 'Охотское море стало целиком российским', | |
426 | 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43', | |
427 | }, | |
428 | 'params': { | |
429 | # m3u8 download | |
430 | 'skip_download': True, | |
431 | }, | |
aab74fa1 | 432 | }, |
f37bdbe5 S |
433 | # TVC embed |
434 | { | |
435 | '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/', | |
436 | 'info_dict': { | |
437 | 'id': '55304', | |
438 | 'ext': 'mp4', | |
439 | 'title': 'Дошкольное воспитание', | |
440 | }, | |
441 | }, | |
b827a601 S |
442 | # SportBox embed |
443 | { | |
444 | 'url': 'http://www.vestifinance.ru/articles/25753', | |
445 | 'info_dict': { | |
446 | 'id': '25753', | |
447 | 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"', | |
448 | }, | |
449 | 'playlist': [{ | |
450 | 'info_dict': { | |
451 | 'id': '370908', | |
452 | 'title': 'Госзаказ. День 3', | |
453 | 'ext': 'mp4', | |
454 | } | |
455 | }, { | |
456 | 'info_dict': { | |
457 | 'id': '370905', | |
458 | 'title': 'Госзаказ. День 2', | |
459 | 'ext': 'mp4', | |
460 | } | |
461 | }, { | |
462 | 'info_dict': { | |
463 | 'id': '370902', | |
464 | 'title': 'Госзаказ. День 1', | |
465 | 'ext': 'mp4', | |
466 | } | |
467 | }], | |
468 | 'params': { | |
469 | # m3u8 download | |
470 | 'skip_download': True, | |
471 | }, | |
472 | }, | |
bf20b9c5 S |
473 | # Myvi.ru embed |
474 | { | |
475 | 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1', | |
476 | 'info_dict': { | |
477 | 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e', | |
478 | 'ext': 'mp4', | |
479 | 'title': 'Ужастики, русский трейлер (2015)', | |
480 | 'thumbnail': 're:^https?://.*\.jpg$', | |
481 | 'duration': 153, | |
482 | } | |
483 | }, | |
c76799c5 S |
484 | # XHamster embed |
485 | { | |
486 | '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', | |
487 | 'info_dict': { | |
488 | 'id': 'showthread', | |
489 | 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )', | |
490 | }, | |
491 | 'playlist_mincount': 7, | |
492 | }, | |
aab74fa1 PH |
493 | # Embedded TED video |
494 | { | |
495 | 'url': 'http://en.support.wordpress.com/videos/ted-talks/', | |
a8eb5a8e | 496 | 'md5': '65fdff94098e4a607385a60c5177c638', |
aab74fa1 | 497 | 'info_dict': { |
a8eb5a8e | 498 | 'id': '1969', |
aab74fa1 | 499 | 'ext': 'mp4', |
a8eb5a8e PH |
500 | 'title': 'Hidden miracles of the natural world', |
501 | 'uploader': 'Louie Schwartzberg', | |
502 | 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9', | |
aab74fa1 | 503 | } |
60cc4dc4 | 504 | }, |
dfb1b146 | 505 | # Embedded Ustream video |
5c386252 | 506 | { |
507 | 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm', | |
508 | 'md5': '27b99cdb639c9b12a79bca876a073417', | |
509 | 'info_dict': { | |
ca6aada4 | 510 | 'id': '45734260', |
511 | 'ext': 'flv', | |
512 | 'uploader': 'AU SPA: The NSA and Privacy', | |
5c386252 | 513 | 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman' |
514 | } | |
515 | }, | |
d95e35d6 S |
516 | # nowvideo embed hidden behind percent encoding |
517 | { | |
518 | 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/', | |
519 | 'md5': '2baf4ddd70f697d94b1c18cf796d5107', | |
520 | 'info_dict': { | |
521 | 'id': '06e53103ca9aa', | |
522 | 'ext': 'flv', | |
523 | 'title': 'Macross Episode 001 Watch Macross Episode 001 onl', | |
524 | 'description': 'No description', | |
525 | }, | |
0f2a2ba1 | 526 | }, |
893f8832 PH |
527 | # arte embed |
528 | { | |
529 | 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html', | |
530 | 'md5': '7653032cbb25bf6c80d80f217055fa43', | |
531 | 'info_dict': { | |
532 | 'id': '048195-004_PLUS7-F', | |
533 | 'ext': 'flv', | |
534 | 'title': 'X:enius', | |
535 | 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168', | |
536 | 'upload_date': '20140320', | |
537 | }, | |
538 | 'params': { | |
539 | 'skip_download': 'Requires rtmpdump' | |
540 | } | |
541 | }, | |
cbd55ade S |
542 | # francetv embed |
543 | { | |
544 | 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero', | |
545 | 'info_dict': { | |
546 | 'id': 'EV_30231', | |
547 | 'ext': 'mp4', | |
548 | 'title': 'Alcaline, le concert avec Calogero', | |
549 | 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff', | |
550 | 'upload_date': '20150226', | |
551 | 'timestamp': 1424989860, | |
552 | 'duration': 5400, | |
553 | }, | |
554 | 'params': { | |
555 | # m3u8 downloads | |
556 | 'skip_download': True, | |
557 | }, | |
558 | 'expected_warnings': [ | |
559 | 'Forbidden' | |
560 | ] | |
561 | }, | |
fa35cdad PH |
562 | # Condé Nast embed |
563 | { | |
564 | 'url': 'http://www.wired.com/2014/04/honda-asimo/', | |
565 | 'md5': 'ba0dfe966fa007657bd1443ee672db0f', | |
566 | 'info_dict': { | |
567 | 'id': '53501be369702d3275860000', | |
568 | 'ext': 'mp4', | |
569 | 'title': 'Honda’s New Asimo Robot Is More Human Than Ever', | |
570 | } | |
ebd3c7b3 PH |
571 | }, |
572 | # Dailymotion embed | |
573 | { | |
574 | 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/', | |
575 | 'md5': '441aeeb82eb72c422c7f14ec533999cd', | |
576 | 'info_dict': { | |
577 | 'id': 'k2mm4bCdJ6CQ2i7c8o2', | |
578 | 'ext': 'mp4', | |
579 | 'title': 'Le Zap de Spi0n n°216 - Zapping du Web', | |
580 | 'uploader': 'Spi0n', | |
581 | }, | |
582 | 'add_ie': ['Dailymotion'], | |
2b88feed PH |
583 | }, |
584 | # YouTube embed | |
585 | { | |
586 | 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html', | |
587 | 'info_dict': { | |
588 | 'id': 'FXRb4ykk4S0', | |
589 | 'ext': 'mp4', | |
590 | 'title': 'The NBL Auction 2014', | |
591 | 'uploader': 'BADMINTON England', | |
592 | 'uploader_id': 'BADMINTONEvents', | |
593 | 'upload_date': '20140603', | |
594 | 'description': 'md5:9ef128a69f1e262a700ed83edb163a73', | |
595 | }, | |
596 | 'add_ie': ['Youtube'], | |
597 | 'params': { | |
598 | 'skip_download': True, | |
599 | } | |
600 | }, | |
c5cd249e JMF |
601 | # MTVSercices embed |
602 | { | |
603 | 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too', | |
604 | 'md5': '35727f82f58c76d996fc188f9755b0d5', | |
605 | 'info_dict': { | |
606 | 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9', | |
607 | 'ext': 'mp4', | |
608 | 'title': 'Review', | |
609 | 'description': 'Mario\'s life in the fast lane has never looked so good.', | |
610 | }, | |
611 | }, | |
61013473 | 612 | # YouTube embed via <data-embed-url=""> |
613 | { | |
614 | 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM', | |
61013473 | 615 | 'info_dict': { |
a8eb5a8e | 616 | 'id': '4vAffPZIT44', |
61013473 | 617 | 'ext': 'mp4', |
a8eb5a8e | 618 | 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!', |
ed2d6a19 PH |
619 | 'uploader': 'Gameloft', |
620 | 'uploader_id': 'gameloft', | |
a8eb5a8e PH |
621 | 'upload_date': '20140828', |
622 | 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4', | |
ed2d6a19 PH |
623 | }, |
624 | 'params': { | |
625 | 'skip_download': True, | |
61013473 | 626 | } |
c8e9a235 PH |
627 | }, |
628 | # Camtasia studio | |
629 | { | |
630 | 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/', | |
631 | 'playlist': [{ | |
632 | 'md5': '0c5e352edabf715d762b0ad4e6d9ee67', | |
633 | 'info_dict': { | |
634 | 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final', | |
635 | 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1', | |
636 | 'ext': 'flv', | |
637 | 'duration': 2235.90, | |
638 | } | |
639 | }, { | |
640 | 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63', | |
641 | 'info_dict': { | |
642 | 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP', | |
643 | 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip', | |
644 | 'ext': 'flv', | |
645 | 'duration': 2235.93, | |
646 | } | |
647 | }], | |
648 | 'info_dict': { | |
649 | 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final', | |
650 | } | |
4d805e06 PH |
651 | }, |
652 | # Flowplayer | |
653 | { | |
654 | 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html', | |
655 | 'md5': '9d65602bf31c6e20014319c7d07fba27', | |
656 | 'info_dict': { | |
657 | 'id': '5123ea6d5e5a7', | |
658 | 'ext': 'mp4', | |
659 | 'age_limit': 18, | |
660 | 'uploader': 'www.handjobhub.com', | |
d6d9186f | 661 | 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com', |
4d805e06 | 662 | } |
0990305d | 663 | }, |
22a6f150 PH |
664 | # Multiple brightcove videos |
665 | # https://github.com/rg3/youtube-dl/issues/2283 | |
666 | { | |
667 | 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html', | |
668 | 'info_dict': { | |
669 | 'id': 'always-never', | |
670 | 'title': 'Always / Never - The New Yorker', | |
671 | }, | |
672 | 'playlist_count': 3, | |
673 | 'params': { | |
674 | 'extract_flat': False, | |
675 | 'skip_download': True, | |
676 | } | |
1a94ff68 S |
677 | }, |
678 | # MLB embed | |
679 | { | |
680 | 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/', | |
681 | 'md5': '96f09a37e44da40dd083e12d9a683327', | |
682 | 'info_dict': { | |
683 | 'id': '33322633', | |
684 | 'ext': 'mp4', | |
685 | 'title': 'Ump changes call to ball', | |
686 | 'description': 'md5:71c11215384298a172a6dcb4c2e20685', | |
687 | 'duration': 48, | |
688 | 'timestamp': 1401537900, | |
689 | 'upload_date': '20140531', | |
690 | 'thumbnail': 're:^https?://.*\.jpg$', | |
691 | }, | |
692 | }, | |
746c67d7 NJ |
693 | # Wistia embed |
694 | { | |
695 | 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson', | |
696 | 'md5': '8788b683c777a5cf25621eaf286d0c23', | |
697 | 'info_dict': { | |
698 | 'id': '1cfaf6b7ea', | |
699 | 'ext': 'mov', | |
700 | 'title': 'md5:51364a8d3d009997ba99656004b5e20d', | |
701 | 'duration': 643.0, | |
702 | 'filesize': 182808282, | |
703 | 'uploader': 'education-portal.com', | |
704 | }, | |
705 | }, | |
52cffcb1 | 706 | { |
707 | 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz', | |
708 | 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4', | |
709 | 'info_dict': { | |
710 | 'id': 'uxjb0lwrcz', | |
711 | 'ext': 'mp4', | |
85d7b765 | 712 | 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks', |
52cffcb1 | 713 | 'duration': 1715.0, |
85d7b765 | 714 | 'uploader': 'thoughtworks.wistia.com', |
70b7e3fb | 715 | }, |
52cffcb1 | 716 | }, |
ac645ac7 PH |
717 | # Soundcloud embed |
718 | { | |
719 | 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/', | |
720 | 'info_dict': { | |
721 | 'id': '174391317', | |
722 | 'ext': 'mp3', | |
723 | 'description': 'md5:ff867d6b555488ad3c52572bb33d432c', | |
724 | 'uploader': 'Sophos Security', | |
725 | 'title': 'Chet Chat 171 - Oct 29, 2014', | |
726 | 'upload_date': '20141029', | |
727 | } | |
af63fed7 PH |
728 | }, |
729 | # Livestream embed | |
730 | { | |
731 | 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast', | |
732 | 'info_dict': { | |
733 | 'id': '67864563', | |
734 | 'ext': 'flv', | |
735 | 'upload_date': '20141112', | |
736 | 'title': 'Rosetta #CometLanding webcast HL 10', | |
737 | } | |
738 | }, | |
65f3a228 PH |
739 | # LazyYT |
740 | { | |
741 | 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986', | |
742 | 'info_dict': { | |
11e611a7 | 743 | 'id': '1986', |
65f3a228 PH |
744 | 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse', |
745 | }, | |
746 | 'playlist_mincount': 2, | |
4e262a88 | 747 | }, |
42bdd9d0 PH |
748 | # Cinchcast embed |
749 | { | |
750 | 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/', | |
751 | 'info_dict': { | |
752 | 'id': '7141703', | |
753 | 'ext': 'mp3', | |
754 | 'upload_date': '20141126', | |
755 | 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing', | |
756 | } | |
757 | }, | |
501f13fb PH |
758 | # Cinerama player |
759 | { | |
760 | 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm', | |
761 | 'info_dict': { | |
762 | 'id': '730m_DandD_1901_512k', | |
763 | 'ext': 'mp4', | |
764 | 'uploader': 'www.abc.net.au', | |
765 | 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015', | |
766 | } | |
796df3c6 S |
767 | }, |
768 | # embedded viddler video | |
769 | { | |
770 | 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597', | |
771 | 'info_dict': { | |
772 | 'id': '4d03aad9', | |
773 | 'ext': 'mp4', | |
774 | 'uploader': 'deadspin', | |
775 | 'title': 'WALL-TO-GORTAT', | |
776 | 'timestamp': 1422285291, | |
777 | 'upload_date': '20150126', | |
778 | }, | |
779 | 'add_ie': ['Viddler'], | |
a0f71985 | 780 | }, |
2051acde S |
781 | # Libsyn embed |
782 | { | |
783 | 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve', | |
784 | 'info_dict': { | |
785 | 'id': '3377616', | |
786 | 'ext': 'mp3', | |
787 | 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart", | |
788 | 'description': 'md5:601cb790edd05908957dae8aaa866465', | |
789 | 'upload_date': '20150220', | |
790 | }, | |
791 | }, | |
a0f71985 PH |
792 | # jwplayer YouTube |
793 | { | |
794 | 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/', | |
795 | 'info_dict': { | |
796 | 'id': 'Mrj4DVp2zeA', | |
797 | 'ext': 'mp4', | |
f37e3f99 | 798 | 'upload_date': '20150212', |
a0f71985 PH |
799 | 'uploader': 'The National Archives UK', |
800 | 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6', | |
801 | 'uploader_id': 'NationalArchives08', | |
802 | 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue', | |
803 | }, | |
59b8ab58 PH |
804 | }, |
805 | # rtl.nl embed | |
806 | { | |
807 | 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen', | |
808 | 'playlist_mincount': 5, | |
809 | 'info_dict': { | |
810 | 'id': 'aanslagen-kopenhagen', | |
811 | 'title': 'Aanslagen Kopenhagen | RTL Nieuws', | |
812 | } | |
255fca5e S |
813 | }, |
814 | # Zapiks embed | |
815 | { | |
816 | 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html', | |
817 | 'info_dict': { | |
818 | 'id': '118046', | |
819 | 'ext': 'mp4', | |
820 | 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !', | |
821 | } | |
822 | }, | |
e3216b82 NJ |
823 | # Kaltura embed |
824 | { | |
825 | 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15', | |
826 | 'info_dict': { | |
827 | 'id': '1_eergr3h1', | |
828 | 'ext': 'mp4', | |
829 | 'upload_date': '20150226', | |
830 | 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com', | |
831 | 'timestamp': int, | |
832 | 'title': 'John Carlson Postgame 2/25/15', | |
833 | }, | |
834 | }, | |
66e568de S |
835 | # Kaltura embed (different embed code) |
836 | { | |
837 | 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014', | |
838 | 'info_dict': { | |
839 | 'id': '1_a52wc67y', | |
840 | 'ext': 'flv', | |
841 | 'upload_date': '20150127', | |
842 | 'uploader_id': 'PremierMedia', | |
843 | 'timestamp': int, | |
844 | 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014', | |
845 | }, | |
846 | }, | |
6da620de S |
847 | # Kaltura embed protected with referrer |
848 | { | |
849 | 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero', | |
850 | 'info_dict': { | |
851 | 'id': '1_g4fbemnq', | |
852 | 'ext': 'mp4', | |
853 | 'title': 'Violetta - Achter De Schermen - Ruggero', | |
854 | 'description': 'Achter de schermen met Ruggero', | |
855 | 'timestamp': 1435133761, | |
856 | 'upload_date': '20150624', | |
857 | 'uploader_id': 'echojecka', | |
858 | }, | |
859 | }, | |
135c9c42 S |
860 | # Eagle.Platform embed (generic URL) |
861 | { | |
862 | 'url': 'http://lenta.ru/news/2015/03/06/navalny/', | |
863 | 'info_dict': { | |
864 | 'id': '227304', | |
865 | 'ext': 'mp4', | |
866 | 'title': 'Навальный вышел на свободу', | |
867 | 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5', | |
868 | 'thumbnail': 're:^https?://.*\.jpg$', | |
869 | 'duration': 87, | |
870 | 'view_count': int, | |
871 | 'age_limit': 0, | |
872 | }, | |
873 | }, | |
d47ae7f6 S |
874 | # ClipYou (Eagle.Platform) embed (custom URL) |
875 | { | |
876 | 'url': 'http://muz-tv.ru/play/7129/', | |
877 | 'info_dict': { | |
878 | 'id': '12820', | |
879 | 'ext': 'mp4', | |
880 | 'title': "'O Sole Mio", | |
881 | 'thumbnail': 're:^https?://.*\.jpg$', | |
882 | 'duration': 216, | |
883 | 'view_count': int, | |
884 | }, | |
885 | }, | |
f8388757 S |
886 | # Pladform embed |
887 | { | |
888 | 'url': 'http://muz-tv.ru/kinozal/view/7400/', | |
889 | 'info_dict': { | |
890 | 'id': '100183293', | |
891 | 'ext': 'mp4', | |
62259846 | 892 | 'title': 'Тайны перевала Дятлова • 1 серия 2 часть', |
f8388757 S |
893 | 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века', |
894 | 'thumbnail': 're:^https?://.*\.jpg$', | |
895 | 'duration': 694, | |
896 | 'age_limit': 0, | |
897 | }, | |
898 | }, | |
c798f15b S |
899 | # Playwire embed |
900 | { | |
901 | 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html', | |
902 | 'info_dict': { | |
903 | 'id': '3519514', | |
904 | 'ext': 'mp4', | |
905 | 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer', | |
906 | 'thumbnail': 're:^https?://.*\.png$', | |
907 | 'duration': 45.115, | |
908 | }, | |
909 | }, | |
ad320e9b NJ |
910 | # 5min embed |
911 | { | |
912 | 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/', | |
913 | 'md5': '4c6f127a30736b59b3e2c19234ee2bf7', | |
914 | 'info_dict': { | |
915 | 'id': '518726732', | |
916 | 'ext': 'mp4', | |
917 | 'title': 'Facebook Creates "On This Day" | Crunch Report', | |
918 | }, | |
919 | }, | |
dc455a5f S |
920 | # SVT embed |
921 | { | |
922 | 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun', | |
923 | 'info_dict': { | |
924 | 'id': '2900353', | |
925 | 'ext': 'flv', | |
926 | 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)', | |
927 | 'duration': 27, | |
928 | 'age_limit': 0, | |
929 | }, | |
930 | }, | |
a4257017 S |
931 | # Crooks and Liars embed |
932 | { | |
933 | 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists', | |
934 | 'info_dict': { | |
935 | 'id': '8RUoRhRi', | |
936 | 'ext': 'mp4', | |
937 | 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!", | |
938 | 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f', | |
939 | 'timestamp': 1428207000, | |
940 | 'upload_date': '20150405', | |
941 | 'uploader': 'Heather', | |
942 | }, | |
943 | }, | |
944 | # Crooks and Liars external embed | |
945 | { | |
946 | 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/', | |
947 | 'info_dict': { | |
948 | 'id': 'MTE3MjUtMzQ2MzA', | |
949 | 'ext': 'mp4', | |
950 | 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5', | |
951 | 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec', | |
952 | 'timestamp': 1265032391, | |
953 | 'upload_date': '20100201', | |
954 | 'uploader': 'Heather', | |
955 | }, | |
956 | }, | |
facecb84 | 957 | # NBC Sports vplayer embed |
a2edf2e7 | 958 | { |
facecb84 | 959 | 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a', |
a2edf2e7 | 960 | 'info_dict': { |
facecb84 S |
961 | 'id': 'ln7x1qSThw4k', |
962 | 'ext': 'flv', | |
963 | 'title': "PFT Live: New leader in the 'new-look' defense", | |
964 | 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e', | |
a2edf2e7 | 965 | }, |
418c5cc3 YCH |
966 | }, |
967 | # UDN embed | |
968 | { | |
969 | 'url': 'http://www.udn.com/news/story/7314/822787', | |
01c58f84 | 970 | 'md5': 'fd2060e988c326991037b9aff9df21a6', |
418c5cc3 | 971 | 'info_dict': { |
01c58f84 | 972 | 'id': '300346', |
418c5cc3 | 973 | 'ext': 'mp4', |
01c58f84 | 974 | 'title': '中一中男師變性 全校師生力挺', |
418c5cc3 YCH |
975 | 'thumbnail': 're:^https?://.*\.jpg$', |
976 | } | |
edfcf7ab YCH |
977 | }, |
978 | # Ooyala embed | |
979 | { | |
980 | 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T', | |
981 | 'info_dict': { | |
982 | 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs', | |
983 | 'ext': 'mp4', | |
cce9d15d | 984 | 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.', |
edfcf7ab | 985 | 'title': 'This is what separates the Excel masters from the wannabes', |
53e06b25 | 986 | 'duration': 191.933, |
edfcf7ab YCH |
987 | }, |
988 | 'params': { | |
989 | # m3u8 downloads | |
990 | 'skip_download': True, | |
991 | } | |
d6fd958c YCH |
992 | }, |
993 | # Contains a SMIL manifest | |
994 | { | |
995 | 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html', | |
996 | 'info_dict': { | |
997 | 'id': 'file', | |
998 | 'ext': 'flv', | |
999 | 'title': '+ Football: Lottery Champions League Europe', | |
1000 | 'uploader': 'www.telewebion.com', | |
1001 | }, | |
1002 | 'params': { | |
1003 | # rtmpe downloads | |
1004 | 'skip_download': True, | |
1005 | } | |
b26733ba YCH |
1006 | }, |
1007 | # Brightcove URL in single quotes | |
1008 | { | |
1009 | 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/', | |
1010 | 'md5': '4ae374f1f8b91c889c4b9203c8c752af', | |
1011 | 'info_dict': { | |
1012 | 'id': '4255764656001', | |
1013 | 'ext': 'mp4', | |
1014 | 'title': 'SN Presents: Russell Martin, World Citizen', | |
1015 | '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.', | |
1016 | 'uploader': 'Rogers Sportsnet', | |
1017 | }, | |
756f574e YCH |
1018 | }, |
1019 | # Dailymotion Cloud video | |
1020 | { | |
1021 | 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910', | |
1022 | 'md5': '49444254273501a64675a7e68c502681', | |
1023 | 'info_dict': { | |
1024 | 'id': '5585de919473990de4bee11b', | |
1025 | 'ext': 'mp4', | |
1026 | 'title': 'Le débat', | |
1027 | 'thumbnail': 're:^https?://.*\.jpe?g$', | |
1028 | } | |
a5158f38 | 1029 | }, |
8084be78 S |
1030 | # OnionStudios embed |
1031 | { | |
1032 | 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537', | |
1033 | 'info_dict': { | |
1034 | 'id': '2855', | |
1035 | 'ext': 'mp4', | |
1036 | 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You', | |
1037 | 'thumbnail': 're:^https?://.*\.jpe?g$', | |
1038 | 'uploader': 'ClickHole', | |
1039 | 'uploader_id': 'clickhole', | |
1040 | } | |
1041 | }, | |
b8c1cc1a S |
1042 | # SnagFilms embed |
1043 | { | |
1044 | 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html', | |
1045 | 'info_dict': { | |
1046 | 'id': '74849a00-85a9-11e1-9660-123139220831', | |
1047 | 'ext': 'mp4', | |
1048 | 'title': '#whilewewatch', | |
1049 | } | |
1050 | }, | |
a5158f38 YCH |
1051 | # AdobeTVVideo embed |
1052 | { | |
1053 | 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners', | |
1054 | 'md5': '43662b577c018ad707a63766462b1e87', | |
1055 | 'info_dict': { | |
1056 | 'id': '2456', | |
1057 | 'ext': 'mp4', | |
1058 | 'title': 'New experience with Acrobat DC', | |
1059 | 'description': 'New experience with Acrobat DC', | |
1060 | 'duration': 248.667, | |
1061 | }, | |
1f812580 S |
1062 | }, |
1063 | # ScreenwaveMedia embed | |
1064 | { | |
1065 | 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1', | |
1066 | 'md5': '24ace5baba0d35d55c6810b51f34e9e0', | |
1067 | 'info_dict': { | |
1068 | 'id': 'cinemasnob-55d26273809dd', | |
1069 | 'ext': 'mp4', | |
1070 | 'title': 'cinemasnob', | |
1071 | }, | |
ed126900 | 1072 | }, |
1073 | # BrightcoveInPageEmbed embed | |
1074 | { | |
1075 | 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/', | |
1076 | 'info_dict': { | |
1077 | 'id': '4238694884001', | |
1078 | 'ext': 'flv', | |
1079 | 'title': 'Tabletop: Dread, Last Thoughts', | |
1080 | 'description': 'Tabletop: Dread, Last Thoughts', | |
1081 | 'duration': 51690, | |
1082 | }, | |
750b9ff0 YCH |
1083 | }, |
1084 | # JWPlayer with M3U8 | |
1085 | { | |
1086 | 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video', | |
1087 | 'info_dict': { | |
1088 | 'id': 'playlist', | |
1089 | 'ext': 'mp4', | |
1090 | 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ', | |
1091 | 'uploader': 'ren.tv', | |
1092 | }, | |
1093 | 'params': { | |
1094 | # m3u8 downloads | |
1095 | 'skip_download': True, | |
1096 | } | |
76c73715 | 1097 | } |
cfe50f04 | 1098 | ] |
9b122384 | 1099 | |
9b122384 PH |
1100 | def report_following_redirect(self, new_url): |
1101 | """Report information extraction.""" | |
79649588 | 1102 | self._downloader.to_screen('[redirect] Following redirect to %s' % new_url) |
9b122384 | 1103 | |
4fc946b5 PH |
1104 | def _extract_rss(self, url, video_id, doc): |
1105 | playlist_title = doc.find('./channel/title').text | |
1106 | playlist_desc_el = doc.find('./channel/description') | |
1107 | playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text | |
1108 | ||
76c73715 PH |
1109 | entries = [] |
1110 | for it in doc.findall('./channel/item'): | |
1111 | next_url = xpath_text(it, 'link', fatal=False) | |
1112 | if not next_url: | |
1113 | enclosure_nodes = it.findall('./enclosure') | |
1114 | for e in enclosure_nodes: | |
1115 | next_url = e.attrib.get('url') | |
1116 | if next_url: | |
1117 | break | |
1118 | ||
1119 | if not next_url: | |
1120 | continue | |
1121 | ||
1122 | entries.append({ | |
1123 | '_type': 'url', | |
1124 | 'url': next_url, | |
1125 | 'title': it.find('title').text, | |
1126 | }) | |
4fc946b5 PH |
1127 | |
1128 | return { | |
1129 | '_type': 'playlist', | |
1130 | 'id': url, | |
1131 | 'title': playlist_title, | |
1132 | 'description': playlist_desc, | |
1133 | 'entries': entries, | |
1134 | } | |
1135 | ||
c8e9a235 PH |
1136 | def _extract_camtasia(self, url, video_id, webpage): |
1137 | """ Returns None if no camtasia video can be found. """ | |
1138 | ||
1139 | camtasia_cfg = self._search_regex( | |
1140 | r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);', | |
1141 | webpage, 'camtasia configuration file', default=None) | |
1142 | if camtasia_cfg is None: | |
1143 | return None | |
1144 | ||
1145 | title = self._html_search_meta('DC.title', webpage, fatal=True) | |
1146 | ||
1147 | camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg) | |
1148 | camtasia_cfg = self._download_xml( | |
1149 | camtasia_url, video_id, | |
1150 | note='Downloading camtasia configuration', | |
1151 | errnote='Failed to download camtasia configuration') | |
1152 | fileset_node = camtasia_cfg.find('./playlist/array/fileset') | |
1153 | ||
1154 | entries = [] | |
1155 | for n in fileset_node.getchildren(): | |
1156 | url_n = n.find('./uri') | |
1157 | if url_n is None: | |
1158 | continue | |
1159 | ||
1160 | entries.append({ | |
1161 | 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0], | |
1162 | 'title': '%s - %s' % (title, n.tag), | |
1163 | 'url': compat_urlparse.urljoin(url, url_n.text), | |
1164 | 'duration': float_or_none(n.find('./duration').text), | |
1165 | }) | |
1166 | ||
1167 | return { | |
1168 | '_type': 'playlist', | |
1169 | 'entries': entries, | |
1170 | 'title': title, | |
1171 | } | |
1172 | ||
9b122384 | 1173 | def _real_extract(self, url): |
ebd3c7b3 PH |
1174 | if url.startswith('//'): |
1175 | return { | |
1176 | '_type': 'url', | |
20991253 | 1177 | 'url': self.http_scheme() + url, |
ebd3c7b3 PH |
1178 | } |
1179 | ||
a7130543 JMF |
1180 | parsed_url = compat_urlparse.urlparse(url) |
1181 | if not parsed_url.scheme: | |
04b4d394 PH |
1182 | default_search = self._downloader.params.get('default_search') |
1183 | if default_search is None: | |
1f7ccb90 | 1184 | default_search = 'fixup_error' |
04b4d394 | 1185 | |
1f7ccb90 | 1186 | if default_search in ('auto', 'auto_warning', 'fixup_error'): |
04b4d394 PH |
1187 | if '/' in url: |
1188 | self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') | |
1189 | return self.url_result('http://' + url) | |
1f7ccb90 | 1190 | elif default_search != 'fixup_error': |
9c1fc022 | 1191 | if default_search == 'auto_warning': |
0e67ab0d PH |
1192 | if re.match(r'^(?:url|URL)$', url): |
1193 | raise ExtractorError( | |
1194 | 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url, | |
1195 | expected=True) | |
1196 | else: | |
1197 | self._downloader.report_warning( | |
7571c02c | 1198 | 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url) |
04b4d394 | 1199 | return self.url_result('ytsearch:' + url) |
1f7ccb90 PH |
1200 | |
1201 | if default_search in ('error', 'fixup_error'): | |
7571c02c | 1202 | raise ExtractorError( |
b74e86f4 PH |
1203 | '%r is not a valid URL. ' |
1204 | 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube' | |
1205 | % (url, url), expected=True) | |
04b4d394 | 1206 | else: |
f2f2c0c2 PH |
1207 | if ':' not in default_search: |
1208 | default_search += ':' | |
04b4d394 | 1209 | return self.url_result(default_search + url) |
4d54ef20 PH |
1210 | |
1211 | url, smuggled_data = unsmuggle_url(url) | |
1212 | force_videoid = None | |
d6e6a422 | 1213 | is_intentional = smuggled_data and smuggled_data.get('to_generic') |
4d54ef20 PH |
1214 | if smuggled_data and 'force_videoid' in smuggled_data: |
1215 | force_videoid = smuggled_data['force_videoid'] | |
1216 | video_id = force_videoid | |
1217 | else: | |
1ddb9456 | 1218 | video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0]) |
a7130543 | 1219 | |
79649588 | 1220 | self.to_screen('%s: Requesting header' % video_id) |
c1d1facd | 1221 | |
ebab4520 | 1222 | head_req = HEADRequest(url) |
23be51d8 | 1223 | head_response = self._request_webpage( |
ebab4520 PH |
1224 | head_req, video_id, |
1225 | note=False, errnote='Could not send HEAD request to %s' % url, | |
1226 | fatal=False) | |
42393ce2 | 1227 | |
23be51d8 | 1228 | if head_response is not False: |
42393ce2 | 1229 | # Check for redirect |
23be51d8 | 1230 | new_url = head_response.geturl() |
42393ce2 PH |
1231 | if url != new_url: |
1232 | self.report_following_redirect(new_url) | |
4d54ef20 PH |
1233 | if force_videoid: |
1234 | new_url = smuggle_url( | |
1235 | new_url, {'force_videoid': force_videoid}) | |
cecaaf3f | 1236 | return self.url_result(new_url) |
42393ce2 | 1237 | |
23be51d8 PH |
1238 | full_response = None |
1239 | if head_response is False: | |
5c2266df | 1240 | request = sanitized_Request(url) |
58bde34a S |
1241 | request.add_header('Accept-Encoding', '*') |
1242 | full_response = self._request_webpage(request, video_id) | |
23be51d8 PH |
1243 | head_response = full_response |
1244 | ||
f930e0c7 S |
1245 | info_dict = { |
1246 | 'id': video_id, | |
1247 | 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), | |
1248 | } | |
1249 | ||
23be51d8 | 1250 | # Check for direct link to a video |
955737b2 | 1251 | content_type = head_response.headers.get('Content-Type', '').lower() |
263eff95 | 1252 | m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type) |
23be51d8 PH |
1253 | if m: |
1254 | upload_date = unified_strdate( | |
1255 | head_response.headers.get('Last-Modified')) | |
f930e0c7 S |
1256 | format_id = m.group('format_id') |
1257 | if format_id.endswith('mpegurl'): | |
eadc3ccd | 1258 | formats = self._extract_m3u8_formats(url, video_id, 'mp4') |
f930e0c7 S |
1259 | elif format_id == 'f4m': |
1260 | formats = self._extract_f4m_formats(url, video_id) | |
eadc3ccd | 1261 | else: |
1262 | formats = [{ | |
1263 | 'format_id': m.group('format_id'), | |
1264 | 'url': url, | |
1265 | 'vcodec': 'none' if m.group('type') == 'audio' else None | |
1266 | }] | |
f930e0c7 | 1267 | info_dict.update({ |
ccdd0ffb | 1268 | 'direct': True, |
eadc3ccd | 1269 | 'formats': formats, |
23be51d8 | 1270 | 'upload_date': upload_date, |
f930e0c7 S |
1271 | }) |
1272 | return info_dict | |
42393ce2 | 1273 | |
d6e6a422 | 1274 | if not self._downloader.params.get('test', False) and not is_intentional: |
2fece970 S |
1275 | force = self._downloader.params.get('force_generic_extractor', False) |
1276 | self._downloader.report_warning( | |
1277 | '%s on generic information extractor.' % ('Forcing' if force else 'Falling back')) | |
d6e6a422 | 1278 | |
4e262a88 | 1279 | if not full_response: |
5c2266df | 1280 | request = sanitized_Request(url) |
58bde34a S |
1281 | # Some webservers may serve compressed content of rather big size (e.g. gzipped flac) |
1282 | # making it impossible to download only chunk of the file (yet we need only 512kB to | |
1283 | # test whether it's HTML or not). According to youtube-dl default Accept-Encoding | |
1284 | # that will always result in downloading the whole file that is not desirable. | |
1285 | # Therefore for extraction pass we have to override Accept-Encoding to any in order | |
1286 | # to accept raw bytes and being able to download only a chunk. | |
1287 | # It may probably better to solve this by checking Content-Type for application/octet-stream | |
1288 | # after HEAD request finishes, but not sure if we can rely on this. | |
1289 | request.add_header('Accept-Encoding', '*') | |
1290 | full_response = self._request_webpage(request, video_id) | |
4e262a88 PH |
1291 | |
1292 | # Maybe it's a direct link to a video? | |
1293 | # Be careful not to download the whole thing! | |
1294 | first_bytes = full_response.read(512) | |
61ca9a80 | 1295 | if not is_html(first_bytes): |
4e262a88 PH |
1296 | self._downloader.report_warning( |
1297 | 'URL could be a direct video link, returning it as such.') | |
1298 | upload_date = unified_strdate( | |
1299 | head_response.headers.get('Last-Modified')) | |
f930e0c7 | 1300 | info_dict.update({ |
4e262a88 PH |
1301 | 'direct': True, |
1302 | 'url': url, | |
1303 | 'upload_date': upload_date, | |
f930e0c7 S |
1304 | }) |
1305 | return info_dict | |
4e262a88 PH |
1306 | |
1307 | webpage = self._webpage_read_content( | |
1308 | full_response, url, video_id, prefix=first_bytes) | |
1309 | ||
9b122384 | 1310 | self.report_extraction(video_id) |
887c6acd | 1311 | |
1b840245 | 1312 | # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest? |
4fc946b5 | 1313 | try: |
f7854627 | 1314 | doc = compat_etree_fromstring(webpage.encode('utf-8')) |
4fc946b5 PH |
1315 | if doc.tag == 'rss': |
1316 | return self._extract_rss(url, video_id, doc) | |
e5e8d20a S |
1317 | elif re.match(r'^(?:{[^}]+})?smil$', doc.tag): |
1318 | return self._parse_smil(doc, url, video_id) | |
729accb4 S |
1319 | elif doc.tag == '{http://xspf.org/ns/0/}playlist': |
1320 | return self.playlist_result(self._parse_xspf(doc, video_id), video_id) | |
1b840245 | 1321 | elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): |
f930e0c7 S |
1322 | info_dict['formats'] = self._parse_mpd_formats( |
1323 | doc, video_id, mpd_base_url=url.rpartition('/')[0]) | |
1324 | return info_dict | |
1325 | elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag): | |
1326 | info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id) | |
1327 | return info_dict | |
f7300c5c | 1328 | except compat_xml_parse_error: |
4fc946b5 PH |
1329 | pass |
1330 | ||
c8e9a235 PH |
1331 | # Is it a Camtasia project? |
1332 | camtasia_res = self._extract_camtasia(url, video_id, webpage) | |
1333 | if camtasia_res is not None: | |
1334 | return camtasia_res | |
1335 | ||
14390730 S |
1336 | # Sometimes embedded video player is hidden behind percent encoding |
1337 | # (e.g. https://github.com/rg3/youtube-dl/issues/2448) | |
1338 | # Unescaping the whole page allows to handle those cases in a generic way | |
45eedbe5 | 1339 | webpage = compat_urllib_parse_unquote(webpage) |
1f7659db | 1340 | |
887c6acd PH |
1341 | # it's tempting to parse this further, but you would |
1342 | # have to take into account all the variations like | |
1343 | # Video Title - Site Name | |
1344 | # Site Name | Video Title | |
1345 | # Video Title - Tagline | Site Name | |
1346 | # and so on and so forth; it's just not practical | |
ef4fd848 | 1347 | video_title = self._html_search_regex( |
79649588 PH |
1348 | r'(?s)<title>(.*?)</title>', webpage, 'video title', |
1349 | default='video') | |
ef4fd848 | 1350 | |
4d805e06 PH |
1351 | # Try to detect age limit automatically |
1352 | age_limit = self._rta_search(webpage) | |
1353 | # And then there are the jokers who advertise that they use RTA, | |
1354 | # but actually don't. | |
1355 | AGE_LIMIT_MARKERS = [ | |
1356 | r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>', | |
1357 | ] | |
1358 | if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS): | |
1359 | age_limit = 18 | |
1360 | ||
ef4fd848 PH |
1361 | # video uploader is domain name |
1362 | video_uploader = self._search_regex( | |
79649588 | 1363 | r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') |
887c6acd | 1364 | |
ed2d6a19 | 1365 | # Helper method |
83992676 | 1366 | def _playlist_from_matches(matches, getter=None, ie=None): |
3b2f933b | 1367 | urlrs = orderedSet( |
83992676 | 1368 | self.url_result(self._proto_relative_url(getter(m) if getter else m), ie) |
3b2f933b | 1369 | for m in matches) |
ed2d6a19 PH |
1370 | return self.playlist_result( |
1371 | urlrs, playlist_id=video_id, playlist_title=video_title) | |
1372 | ||
1f4b722b | 1373 | # Look for Brightcove Legacy Studio embeds |
4fcaa4f4 | 1374 | bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage) |
99877772 | 1375 | if bc_urls: |
79649588 | 1376 | self.to_screen('Brightcove video detected.') |
99877772 PH |
1377 | entries = [{ |
1378 | '_type': 'url', | |
1379 | 'url': smuggle_url(bc_url, {'Referer': url}), | |
3b7d9aa4 | 1380 | 'ie_key': 'BrightcoveLegacy' |
99877772 PH |
1381 | } for bc_url in bc_urls] |
1382 | ||
1383 | return { | |
1384 | '_type': 'playlist', | |
1385 | 'title': video_title, | |
1386 | 'id': video_id, | |
1387 | 'entries': entries, | |
1388 | } | |
cfe50f04 | 1389 | |
f6519f89 S |
1390 | # Look for Brightcove New Studio embeds |
1391 | bc_urls = BrightcoveNewIE._extract_urls(webpage) | |
1392 | if bc_urls: | |
1393 | return _playlist_from_matches(bc_urls, ie='BrightcoveNew') | |
ed126900 | 1394 | |
59b8ab58 PH |
1395 | # Look for embedded rtl.nl player |
1396 | matches = re.findall( | |
97b570a9 | 1397 | r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"', |
59b8ab58 PH |
1398 | webpage) |
1399 | if matches: | |
1400 | return _playlist_from_matches(matches, ie='RtlNl') | |
1401 | ||
b407e173 YCH |
1402 | vimeo_url = VimeoIE._extract_vimeo_url(url, webpage) |
1403 | if vimeo_url is not None: | |
1404 | return self.url_result(vimeo_url) | |
7115ca84 | 1405 | |
a1b85269 YCH |
1406 | vid_me_embed_url = self._search_regex( |
1407 | r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]', | |
1408 | webpage, 'vid.me embed', default=None) | |
1409 | if vid_me_embed_url is not None: | |
1410 | return self.url_result(vid_me_embed_url, 'Vidme') | |
1411 | ||
53c1d3ef | 1412 | # Look for embedded YouTube player |
1f9da904 | 1413 | matches = re.findall(r'''(?x) |
2b88feed PH |
1414 | (?: |
1415 | <iframe[^>]+?src=| | |
c71dfccc | 1416 | data-video-url=| |
2b88feed | 1417 | <embed[^>]+?src=| |
a7e97f6d PH |
1418 | embedSWF\(?:\s*| |
1419 | new\s+SWFObject\( | |
2b88feed PH |
1420 | ) |
1421 | (["\']) | |
1bf5423e | 1422 | (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ |
6b08cdf6 | 1423 | (?:embed|v|p)/.+?) |
1f9da904 | 1424 | \1''', webpage) |
887c6acd | 1425 | if matches: |
ed2d6a19 | 1426 | return _playlist_from_matches( |
3b2f933b | 1427 | matches, lambda m: unescapeHTML(m[1])) |
53c1d3ef | 1428 | |
65f3a228 PH |
1429 | # Look for lazyYT YouTube embed |
1430 | matches = re.findall( | |
1431 | r'class="lazyYT" data-youtube-id="([^"]+)"', webpage) | |
1432 | if matches: | |
1433 | return _playlist_from_matches(matches, lambda m: unescapeHTML(m)) | |
1434 | ||
355e4fd0 PH |
1435 | # Look for embedded Dailymotion player |
1436 | matches = re.findall( | |
5a490592 | 1437 | r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage) |
355e4fd0 | 1438 | if matches: |
ed2d6a19 PH |
1439 | return _playlist_from_matches( |
1440 | matches, lambda m: unescapeHTML(m[1])) | |
355e4fd0 | 1441 | |
8489578d NJ |
1442 | # Look for embedded Dailymotion playlist player (#3822) |
1443 | m = re.search( | |
1444 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage) | |
1445 | if m: | |
1446 | playlists = re.findall( | |
1447 | r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url'))) | |
1448 | if playlists: | |
1449 | return _playlist_from_matches( | |
1450 | playlists, lambda p: '//dailymotion.com/playlist/%s' % p) | |
1451 | ||
ef4fd848 PH |
1452 | # Look for embedded Wistia player |
1453 | match = re.search( | |
281d3f1d | 1454 | r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) |
ef4fd848 | 1455 | if match: |
9471c444 NJ |
1456 | embed_url = self._proto_relative_url( |
1457 | unescapeHTML(match.group('url'))) | |
ef4fd848 PH |
1458 | return { |
1459 | '_type': 'url_transparent', | |
9471c444 | 1460 | 'url': embed_url, |
ef4fd848 PH |
1461 | 'ie_key': 'Wistia', |
1462 | 'uploader': video_uploader, | |
1463 | 'title': video_title, | |
1464 | 'id': video_id, | |
1465 | } | |
5f6a1245 | 1466 | |
9471c444 | 1467 | match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage) |
746c67d7 NJ |
1468 | if match: |
1469 | return { | |
1470 | '_type': 'url_transparent', | |
1471 | 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')), | |
1472 | 'ie_key': 'Wistia', | |
1473 | 'uploader': video_uploader, | |
1474 | 'title': video_title, | |
1475 | 'id': match.group('id') | |
1476 | } | |
ef4fd848 | 1477 | |
bab19a8e S |
1478 | # Look for SVT player |
1479 | svt_url = SVTIE._extract_url(webpage) | |
1480 | if svt_url: | |
1481 | return self.url_result(svt_url, 'SVT') | |
1482 | ||
fa35cdad PH |
1483 | # Look for embedded condenast player |
1484 | matches = re.findall( | |
1485 | r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")', | |
1486 | webpage) | |
1487 | if matches: | |
1488 | return { | |
1489 | '_type': 'playlist', | |
1490 | 'entries': [{ | |
1491 | '_type': 'url', | |
1492 | 'ie_key': 'CondeNast', | |
1493 | 'url': ma, | |
1494 | } for ma in matches], | |
1495 | 'title': video_title, | |
1496 | 'id': video_id, | |
1497 | } | |
1498 | ||
c19f7764 JMF |
1499 | # Look for Bandcamp pages with custom domain |
1500 | mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage) | |
1501 | if mobj is not None: | |
1502 | burl = unescapeHTML(mobj.group(1)) | |
09804265 JMF |
1503 | # Don't set the extractor because it can be a track url or an album |
1504 | return self.url_result(burl) | |
c19f7764 | 1505 | |
f25571ff PH |
1506 | # Look for embedded Vevo player |
1507 | mobj = re.search( | |
1508 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage) | |
1509 | if mobj is not None: | |
1510 | return self.url_result(mobj.group('url')) | |
796df3c6 S |
1511 | |
1512 | # Look for embedded Viddler player | |
cb454b33 S |
1513 | mobj = re.search( |
1514 | r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1', | |
1515 | webpage) | |
796df3c6 S |
1516 | if mobj is not None: |
1517 | return self.url_result(mobj.group('url')) | |
f25571ff | 1518 | |
3378d67a S |
1519 | # Look for NYTimes player |
1520 | mobj = re.search( | |
1521 | r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>', | |
1522 | webpage) | |
1523 | if mobj is not None: | |
1524 | return self.url_result(mobj.group('url')) | |
1525 | ||
cefdf970 S |
1526 | # Look for Libsyn player |
1527 | mobj = re.search( | |
1528 | r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage) | |
1529 | if mobj is not None: | |
1530 | return self.url_result(mobj.group('url')) | |
1531 | ||
c0d0b01f | 1532 | # Look for Ooyala videos |
8a37aa15 | 1533 | mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or |
f076b638 | 1534 | re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or |
edfcf7ab YCH |
1535 | re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or |
1536 | re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage)) | |
c0d0b01f | 1537 | if mobj is not None: |
cce9d15d | 1538 | return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url})) |
c0d0b01f | 1539 | |
f076b638 | 1540 | # Look for multiple Ooyala embeds on SBN network websites |
1541 | mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage) | |
1542 | if mobj is not None: | |
1543 | embeds = self._parse_json(mobj.group(1), video_id, fatal=False) | |
1544 | if embeds: | |
1545 | return _playlist_from_matches( | |
cce9d15d | 1546 | embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala') |
f076b638 | 1547 | |
aa94a6d3 | 1548 | # Look for Aparat videos |
48099643 | 1549 | mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage) |
aa94a6d3 PH |
1550 | if mobj is not None: |
1551 | return self.url_result(mobj.group(1), 'Aparat') | |
1552 | ||
c93c2ab1 | 1553 | # Look for MPORA videos |
c3f51436 | 1554 | mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage) |
c93c2ab1 PH |
1555 | if mobj is not None: |
1556 | return self.url_result(mobj.group(1), 'Mpora') | |
5f59ee79 | 1557 | |
15c0e8e7 | 1558 | # Look for embedded NovaMov-based player |
8f89e687 | 1559 | mobj = re.search( |
8dfa187b | 1560 | r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\']) |
15c0e8e7 S |
1561 | (?P<url>http://(?:(?:embed|www)\.)? |
1562 | (?:novamov\.com| | |
1563 | nowvideo\.(?:ch|sx|eu|at|ag|co)| | |
1564 | videoweed\.(?:es|com)| | |
1565 | movshare\.(?:net|sx|ag)| | |
1566 | divxstage\.(?:eu|net|ch|co|at|ag)) | |
1567 | /embed\.php.+?)\1''', webpage) | |
8f89e687 | 1568 | if mobj is not None: |
15c0e8e7 | 1569 | return self.url_result(mobj.group('url')) |
50f56607 | 1570 | |
9834872b PH |
1571 | # Look for embedded Facebook player |
1572 | mobj = re.search( | |
db1f3888 | 1573 | r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage) |
9834872b PH |
1574 | if mobj is not None: |
1575 | return self.url_result(mobj.group('url'), 'Facebook') | |
1576 | ||
ca97a56e S |
1577 | # Look for embedded VK player |
1578 | mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage) | |
1579 | if mobj is not None: | |
1580 | return self.url_result(mobj.group('url'), 'VK') | |
1581 | ||
33d4fdab S |
1582 | # Look for embedded Odnoklassniki player |
1583 | mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage) | |
1584 | if mobj is not None: | |
1585 | return self.url_result(mobj.group('url'), 'Odnoklassniki') | |
1586 | ||
0364fa8b S |
1587 | # Look for embedded ivi player |
1588 | mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage) | |
1589 | if mobj is not None: | |
1590 | return self.url_result(mobj.group('url'), 'Ivi') | |
1591 | ||
db1f3888 PH |
1592 | # Look for embedded Huffington Post player |
1593 | mobj = re.search( | |
c3f51436 | 1594 | r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage) |
db1f3888 PH |
1595 | if mobj is not None: |
1596 | return self.url_result(mobj.group('url'), 'HuffPost') | |
1597 | ||
1b86cc41 | 1598 | # Look for embed.ly |
1599 | mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage) | |
1600 | if mobj is not None: | |
1601 | return self.url_result(mobj.group('url')) | |
1602 | mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage) | |
1603 | if mobj is not None: | |
f7e6f7fa | 1604 | return self.url_result(compat_urllib_parse_unquote(mobj.group('url'))) |
1b86cc41 | 1605 | |
60cc4dc4 PH |
1606 | # Look for funnyordie embed |
1607 | matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage) | |
1608 | if matches: | |
ed2d6a19 PH |
1609 | return _playlist_from_matches( |
1610 | matches, getter=unescapeHTML, ie='FunnyOrDie') | |
60cc4dc4 | 1611 | |
db546cf8 S |
1612 | # Look for BBC iPlayer embed |
1613 | matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage) | |
1614 | if matches: | |
476eae0c | 1615 | return _playlist_from_matches(matches, ie='BBCCoUk') |
db546cf8 | 1616 | |
93d020dd S |
1617 | # Look for embedded RUTV player |
1618 | rutv_url = RUTVIE._extract_url(webpage) | |
1619 | if rutv_url: | |
1620 | return self.url_result(rutv_url, 'RUTV') | |
1621 | ||
494f20cb | 1622 | # Look for embedded TVC player |
b8599718 S |
1623 | tvc_url = TVCIE._extract_url(webpage) |
1624 | if tvc_url: | |
1625 | return self.url_result(tvc_url, 'TVC') | |
494f20cb | 1626 | |
d40a3b5b S |
1627 | # Look for embedded SportBox player |
1628 | sportbox_urls = SportBoxEmbedIE._extract_urls(webpage) | |
1629 | if sportbox_urls: | |
1630 | return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed') | |
1631 | ||
78e2b74b | 1632 | # Look for embedded PornHub player |
65d161c4 S |
1633 | pornhub_url = PornHubIE._extract_url(webpage) |
1634 | if pornhub_url: | |
1635 | return self.url_result(pornhub_url, 'PornHub') | |
1636 | ||
2bb5b6d0 S |
1637 | # Look for embedded XHamster player |
1638 | xhamster_urls = XHamsterEmbedIE._extract_urls(webpage) | |
1639 | if xhamster_urls: | |
1640 | return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed') | |
1641 | ||
2c9ca782 S |
1642 | # Look for embedded TNAFlixNetwork player |
1643 | tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage) | |
1644 | if tnaflix_urls: | |
1645 | return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key()) | |
1646 | ||
9872d311 S |
1647 | # Look for embedded Tvigle player |
1648 | mobj = re.search( | |
1649 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage) | |
1650 | if mobj is not None: | |
1651 | return self.url_result(mobj.group('url'), 'Tvigle') | |
1652 | ||
7e2ede98 JMF |
1653 | # Look for embedded TED player |
1654 | mobj = re.search( | |
d7cc31b6 | 1655 | r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage) |
7e2ede98 JMF |
1656 | if mobj is not None: |
1657 | return self.url_result(mobj.group('url'), 'TED') | |
1658 | ||
5c386252 | 1659 | # Look for embedded Ustream videos |
1660 | mobj = re.search( | |
1661 | r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage) | |
1662 | if mobj is not None: | |
1663 | return self.url_result(mobj.group('url'), 'Ustream') | |
1664 | ||
893f8832 PH |
1665 | # Look for embedded arte.tv player |
1666 | mobj = re.search( | |
1667 | r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"', | |
1668 | webpage) | |
1669 | if mobj is not None: | |
1670 | return self.url_result(mobj.group('url'), 'ArteTVEmbed') | |
1671 | ||
cbd55ade S |
1672 | # Look for embedded francetv player |
1673 | mobj = re.search( | |
1674 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1', | |
1675 | webpage) | |
1676 | if mobj is not None: | |
1677 | return self.url_result(mobj.group('url')) | |
1678 | ||
cb3ac1c6 S |
1679 | # Look for embedded smotri.com player |
1680 | smotri_url = SmotriIE._extract_url(webpage) | |
1681 | if smotri_url: | |
1682 | return self.url_result(smotri_url, 'Smotri') | |
1683 | ||
e6c2d9ad | 1684 | # Look for embedded Myvi.ru player |
6dd94d3a | 1685 | myvi_url = MyviIE._extract_url(webpage) |
e6c2d9ad S |
1686 | if myvi_url: |
1687 | return self.url_result(myvi_url) | |
1688 | ||
dfb1b146 | 1689 | # Look for embedded soundcloud player |
20991253 | 1690 | mobj = re.search( |
ac645ac7 | 1691 | r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"', |
20991253 PH |
1692 | webpage) |
1693 | if mobj is not None: | |
1694 | url = unescapeHTML(mobj.group('url')) | |
1695 | return self.url_result(url) | |
1696 | ||
826ec77f PH |
1697 | # Look for embedded vulture.com player |
1698 | mobj = re.search( | |
1699 | r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"', | |
1700 | webpage) | |
1701 | if mobj is not None: | |
1702 | url = unescapeHTML(mobj.group('url')) | |
1703 | return self.url_result(url, ie='Vulture') | |
1704 | ||
c5cd249e | 1705 | # Look for embedded mtvservices player |
46fde8a1 S |
1706 | mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage) |
1707 | if mtvservices_url: | |
1708 | return self.url_result(mtvservices_url, ie='MTVServicesEmbedded') | |
c5cd249e | 1709 | |
49807b4a S |
1710 | # Look for embedded yahoo player |
1711 | mobj = re.search( | |
1712 | r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1', | |
1713 | webpage) | |
1714 | if mobj is not None: | |
1715 | return self.url_result(mobj.group('url'), 'Yahoo') | |
1716 | ||
2ef6fcb5 PH |
1717 | # Look for embedded sbs.com.au player |
1718 | mobj = re.search( | |
e98b8e79 PH |
1719 | r'''(?x) |
1720 | (?: | |
1721 | <meta\s+property="og:video"\s+content=| | |
1722 | <iframe[^>]+?src= | |
1723 | ) | |
1724 | (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''', | |
2ef6fcb5 PH |
1725 | webpage) |
1726 | if mobj is not None: | |
1727 | return self.url_result(mobj.group('url'), 'SBS') | |
1728 | ||
42bdd9d0 PH |
1729 | # Look for embedded Cinchcast player |
1730 | mobj = re.search( | |
1731 | r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1', | |
1732 | webpage) | |
1733 | if mobj is not None: | |
1734 | return self.url_result(mobj.group('url'), 'Cinchcast') | |
1735 | ||
1a94ff68 | 1736 | mobj = re.search( |
5263cdfc | 1737 | r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1', |
1a94ff68 | 1738 | webpage) |
8001607e YCH |
1739 | if not mobj: |
1740 | mobj = re.search( | |
1741 | r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)', | |
1742 | webpage) | |
1a94ff68 S |
1743 | if mobj is not None: |
1744 | return self.url_result(mobj.group('url'), 'MLB') | |
1745 | ||
1419fafd | 1746 | mobj = re.search( |
dd467d33 | 1747 | r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL, |
1419fafd S |
1748 | webpage) |
1749 | if mobj is not None: | |
1750 | return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast') | |
1751 | ||
af63fed7 PH |
1752 | mobj = re.search( |
1753 | r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"', | |
1754 | webpage) | |
1755 | if mobj is not None: | |
1756 | return self.url_result(mobj.group('url'), 'Livestream') | |
1757 | ||
255fca5e S |
1758 | # Look for Zapiks embed |
1759 | mobj = re.search( | |
1760 | r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage) | |
1761 | if mobj is not None: | |
1762 | return self.url_result(mobj.group('url'), 'Zapiks') | |
1763 | ||
e3216b82 | 1764 | # Look for Kaltura embeds |
6a5d6de1 | 1765 | mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or |
1c31a5b0 | 1766 | re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage)) |
e3216b82 | 1767 | if mobj is not None: |
5b5fae5f S |
1768 | return self.url_result(smuggle_url( |
1769 | 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), | |
1770 | {'source_url': url}), 'Kaltura') | |
e3216b82 | 1771 | |
135c9c42 S |
1772 | # Look for Eagle.Platform embeds |
1773 | mobj = re.search( | |
1774 | r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage) | |
1775 | if mobj is not None: | |
1776 | return self.url_result(mobj.group('url'), 'EaglePlatform') | |
1777 | ||
d47ae7f6 S |
1778 | # Look for ClipYou (uses Eagle.Platform) embeds |
1779 | mobj = re.search( | |
1780 | r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage) | |
1781 | if mobj is not None: | |
1782 | return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform') | |
1783 | ||
f8388757 | 1784 | # Look for Pladform embeds |
45dad7ba S |
1785 | pladform_url = PladformIE._extract_url(webpage) |
1786 | if pladform_url: | |
1787 | return self.url_result(pladform_url) | |
f8388757 | 1788 | |
ff18735c S |
1789 | # Look for Videomore embeds |
1790 | videomore_url = VideomoreIE._extract_url(webpage) | |
1791 | if videomore_url: | |
1792 | return self.url_result(videomore_url) | |
1793 | ||
2dcc114f S |
1794 | # Look for Playwire embeds |
1795 | mobj = re.search( | |
1796 | r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage) | |
1797 | if mobj is not None: | |
1798 | return self.url_result(mobj.group('url')) | |
1799 | ||
ad320e9b NJ |
1800 | # Look for 5min embeds |
1801 | mobj = re.search( | |
1802 | r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage) | |
1803 | if mobj is not None: | |
1804 | return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin') | |
1805 | ||
18153f1b S |
1806 | # Look for Crooks and Liars embeds |
1807 | mobj = re.search( | |
1808 | r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage) | |
1809 | if mobj is not None: | |
1810 | return self.url_result(mobj.group('url')) | |
1811 | ||
a2edf2e7 YCH |
1812 | # Look for NBC Sports VPlayer embeds |
1813 | nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage) | |
1814 | if nbc_sports_url: | |
1815 | return self.url_result(nbc_sports_url, 'NBCSportsVPlayer') | |
1816 | ||
653789af | 1817 | # Look for Google Drive embeds |
5b251628 | 1818 | google_drive_url = GoogleDriveIE._extract_url(webpage) |
653789af | 1819 | if google_drive_url: |
1820 | return self.url_result(google_drive_url, 'GoogleDrive') | |
1821 | ||
418c5cc3 YCH |
1822 | # Look for UDN embeds |
1823 | mobj = re.search( | |
c39fd7b1 | 1824 | r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage) |
418c5cc3 YCH |
1825 | if mobj is not None: |
1826 | return self.url_result( | |
0a160363 | 1827 | compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed') |
418c5cc3 | 1828 | |
2fe1b5bd YCH |
1829 | # Look for Senate ISVP iframe |
1830 | senate_isvp_url = SenateISVPIE._search_iframe_url(webpage) | |
1831 | if senate_isvp_url: | |
25c3a734 | 1832 | return self.url_result(senate_isvp_url, 'SenateISVP') |
2fe1b5bd | 1833 | |
756f574e YCH |
1834 | # Look for Dailymotion Cloud videos |
1835 | dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage) | |
1836 | if dmcloud_url: | |
1837 | return self.url_result(dmcloud_url, 'DailymotionCloud') | |
1838 | ||
1ac1c4c2 S |
1839 | # Look for OnionStudios embeds |
1840 | onionstudios_url = OnionStudiosIE._extract_url(webpage) | |
1841 | if onionstudios_url: | |
1842 | return self.url_result(onionstudios_url) | |
1843 | ||
eedd20ef S |
1844 | # Look for SnagFilms embeds |
1845 | snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage) | |
1846 | if snagfilms_url: | |
1847 | return self.url_result(snagfilms_url) | |
1848 | ||
7cb09524 | 1849 | # Look for JWPlatform embeds |
1850 | jwplatform_url = JWPlatformIE._extract_url(webpage) | |
1851 | if jwplatform_url: | |
1852 | return self.url_result(jwplatform_url, 'JWPlatform') | |
1853 | ||
8ca31a0e | 1854 | # Look for ScreenwaveMedia embeds |
efd712c6 | 1855 | mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage) |
8ca31a0e | 1856 | if mobj is not None: |
efd712c6 | 1857 | return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia') |
8ca31a0e | 1858 | |
aecfcd4e S |
1859 | # Look for Digiteka embeds |
1860 | digiteka_url = DigitekaIE._extract_url(webpage) | |
1861 | if digiteka_url: | |
1862 | return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key()) | |
6aeba407 | 1863 | |
1bf996fa | 1864 | # Look for Limelight embeds |
1865 | mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage) | |
1866 | if mobj: | |
1867 | lm = { | |
1868 | 'Media': 'media', | |
1869 | 'Channel': 'channel', | |
1870 | 'ChannelList': 'channel_list', | |
1871 | } | |
1872 | return self.url_result('limelight:%s:%s' % ( | |
1873 | lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2)) | |
1874 | ||
a5158f38 YCH |
1875 | # Look for AdobeTVVideo embeds |
1876 | mobj = re.search( | |
1877 | r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]', | |
1878 | webpage) | |
1879 | if mobj is not None: | |
1880 | return self.url_result( | |
1881 | self._proto_relative_url(unescapeHTML(mobj.group(1))), | |
1882 | 'AdobeTVVideo') | |
1883 | ||
ced659bb | 1884 | def check_video(vurl): |
a0f71985 PH |
1885 | if YoutubeIE.suitable(vurl): |
1886 | return True | |
ced659bb S |
1887 | vpath = compat_urlparse.urlparse(vurl).path |
1888 | vext = determine_ext(vpath) | |
1889 | return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml') | |
1890 | ||
1891 | def filter_video(urls): | |
1892 | return list(filter(check_video, urls)) | |
1893 | ||
9b122384 | 1894 | # Start with something easy: JW Player in SWFObject |
ced659bb | 1895 | found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)) |
b30b8698 | 1896 | if not found: |
d981cef6 | 1897 | # Look for gorilla-vid style embedding |
ced659bb | 1898 | found = filter_video(re.findall(r'''(?sx) |
c0292e8a PH |
1899 | (?: |
1900 | jw_plugins| | |
1901 | JWPlayerOptions| | |
1902 | jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup | |
1903 | ) | |
a0f71985 PH |
1904 | .*? |
1905 | ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage)) | |
b30b8698 | 1906 | if not found: |
9b122384 | 1907 | # Broaden the search a little bit |
ced659bb | 1908 | found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)) |
b30b8698 PH |
1909 | if not found: |
1910 | # Broaden the findall a little bit: JWPlayer JS loader | |
ced659bb | 1911 | found = filter_video(re.findall( |
54a9328b | 1912 | r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)) |
4d805e06 PH |
1913 | if not found: |
1914 | # Flow player | |
ced659bb | 1915 | found = filter_video(re.findall(r'''(?xs) |
4d805e06 PH |
1916 | flowplayer\("[^"]+",\s* |
1917 | \{[^}]+?\}\s*, | |
52585fd6 | 1918 | \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s* |
4d805e06 | 1919 | ["']?url["']?\s*:\s*["']([^"']+)["'] |
ced659bb | 1920 | ''', webpage)) |
501f13fb PH |
1921 | if not found: |
1922 | # Cinerama player | |
1923 | found = re.findall( | |
1924 | r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage) | |
b30b8698 | 1925 | if not found: |
9b122384 | 1926 | # Try to find twitter cards info |
ced659bb S |
1927 | found = filter_video(re.findall( |
1928 | r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)) | |
b30b8698 | 1929 | if not found: |
9b122384 PH |
1930 | # We look for Open Graph info: |
1931 | # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am) | |
b30b8698 | 1932 | m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage) |
9b122384 PH |
1933 | # We only look in og:video if the MIME type is a video, don't try if it's a Flash player: |
1934 | if m_video_type is not None: | |
ced659bb | 1935 | found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)) |
b30b8698 | 1936 | if not found: |
7fea7156 | 1937 | # HTML5 video |
12439dd5 | 1938 | found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage) |
b30b8698 | 1939 | if not found: |
ed9a25dd | 1940 | REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)' |
a5a45015 | 1941 | found = re.search( |
89ef304b | 1942 | r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")' |
ed9a25dd | 1943 | r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX, |
89ef304b | 1944 | webpage) |
84f81016 S |
1945 | if not found: |
1946 | # Look also in Refresh HTTP header | |
1947 | refresh_header = head_response.headers.get('Refresh') | |
1948 | if refresh_header: | |
6c91a5a7 S |
1949 | # In python 2 response HTTP headers are bytestrings |
1950 | if sys.version_info < (3, 0) and isinstance(refresh_header, str): | |
1951 | refresh_header = refresh_header.decode('iso-8859-1') | |
ed9a25dd | 1952 | found = re.search(REDIRECT_REGEX, refresh_header) |
b30b8698 | 1953 | if found: |
b37317d8 | 1954 | new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1))) |
89ef304b PH |
1955 | self.report_following_redirect(new_url) |
1956 | return { | |
1957 | '_type': 'url', | |
1958 | 'url': new_url, | |
1959 | } | |
b30b8698 | 1960 | if not found: |
416c7fcb | 1961 | raise UnsupportedError(url) |
9b122384 | 1962 | |
b30b8698 PH |
1963 | entries = [] |
1964 | for video_url in found: | |
6cc37c69 | 1965 | video_url = video_url.replace('\\/', '/') |
b30b8698 | 1966 | video_url = compat_urlparse.urljoin(url, video_url) |
f7e6f7fa | 1967 | video_id = compat_urllib_parse_unquote(os.path.basename(video_url)) |
9b122384 | 1968 | |
b30b8698 PH |
1969 | # Sometimes, jwplayer extraction will result in a YouTube URL |
1970 | if YoutubeIE.suitable(video_url): | |
1971 | entries.append(self.url_result(video_url, 'Youtube')) | |
1972 | continue | |
9b122384 | 1973 | |
b30b8698 PH |
1974 | # here's a fun little line of code for you: |
1975 | video_id = os.path.splitext(video_id)[0] | |
fc9713a1 | 1976 | |
28602e74 YCH |
1977 | entry_info_dict = { |
1978 | 'id': video_id, | |
1979 | 'uploader': video_uploader, | |
1980 | 'title': video_title, | |
1981 | 'age_limit': age_limit, | |
1982 | } | |
1983 | ||
729accb4 S |
1984 | ext = determine_ext(video_url) |
1985 | if ext == 'smil': | |
28602e74 | 1986 | entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id) |
729accb4 S |
1987 | elif ext == 'xspf': |
1988 | return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id) | |
750b9ff0 YCH |
1989 | elif ext == 'm3u8': |
1990 | entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4') | |
79a35085 S |
1991 | elif ext == 'mpd': |
1992 | entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id) | |
3f2f4a94 S |
1993 | elif ext == 'f4m': |
1994 | entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id) | |
d6fd958c | 1995 | else: |
28602e74 YCH |
1996 | entry_info_dict['url'] = video_url |
1997 | ||
1998 | entries.append(entry_info_dict) | |
b30b8698 PH |
1999 | |
2000 | if len(entries) == 1: | |
669f0e7c | 2001 | return entries[0] |
b30b8698 PH |
2002 | else: |
2003 | for num, e in enumerate(entries, start=1): | |
13d8fbef JMF |
2004 | # 'url' results don't have a title |
2005 | if e.get('title') is not None: | |
2006 | e['title'] = '%s (%d)' % (e['title'], num) | |
b30b8698 PH |
2007 | return { |
2008 | '_type': 'playlist', | |
2009 | 'entries': entries, | |
2010 | } |