]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vk.py
2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
8 from ..compat
import compat_urlparse
23 from .dailymotion
import DailymotionIE
24 from .pladform
import PladformIE
25 from .vimeo
import VimeoIE
26 from .youtube
import YoutubeIE
29 class VKBaseIE(InfoExtractor
):
33 username
, password
= self
._get
_login
_info
()
37 login_page
, url_handle
= self
._download
_webpage
_handle
(
38 'https://vk.com', None, 'Downloading login page')
40 login_form
= self
._hidden
_inputs
(login_page
)
43 'email': username
.encode('cp1251'),
44 'pass': password
.encode('cp1251'),
47 # vk serves two same remixlhk cookies in Set-Cookie header and expects
48 # first one to be actually set
49 self
._apply
_first
_set
_cookie
_header
(url_handle
, 'remixlhk')
51 login_page
= self
._download
_webpage
(
52 'https://login.vk.com/?act=login', None,
54 data
=urlencode_postdata(login_form
))
56 if re
.search(r
'onLoginFailed', login_page
):
58 'Unable to login, incorrect username and/or password', expected
=True)
60 def _real_initialize(self
):
71 (?:(?:m|new)\.)?vk\.com/video_|
74 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
76 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?video|
77 (?:www\.)?daxab.com/embed/
79 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
84 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
85 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
87 'id': '-77521_162222515',
89 'title': 'ProtivoGunz - Хуёвая песня',
90 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
91 'uploader_id': '-77521',
93 'timestamp': 1329049880,
94 'upload_date': '20120212',
98 'url': 'http://vk.com/video205387401_165548505',
99 'md5': '6c0aeb2e90396ba97035b9cbde548700',
101 'id': '205387401_165548505',
104 'uploader': 'Tom Cruise',
105 'uploader_id': '205387401',
107 'timestamp': 1374364108,
108 'upload_date': '20130720',
112 'note': 'Embedded video',
113 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
114 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
116 'id': '32194266_162925554',
118 'uploader': 'Vladimir Gavrin',
121 'upload_date': '20120730',
124 'skip': 'This video has been removed from public access.',
128 # please update if you find a video whose URL follows the same pattern
129 'url': 'http://vk.com/video-8871596_164049491',
130 'md5': 'a590bcaf3d543576c9bd162812387666',
131 'note': 'Only available for registered users',
133 'id': '-8871596_164049491',
135 'uploader': 'Триллеры',
136 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
138 'upload_date': '20121218',
141 'skip': 'Requires vk account credentials',
144 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
145 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
147 'id': '-43215063_168067957',
149 'uploader': 'Киномания - лучшее из мира кино',
152 'upload_date': '20140328',
154 'skip': 'Requires vk account credentials',
157 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
158 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
159 'note': 'ivi.ru embed',
161 'id': '-43215063_169084319',
163 'title': 'Книга Илая',
165 'upload_date': '20140626',
168 'skip': 'Only works from Russia',
171 # video (removed?) only available with list id
172 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
173 'md5': '091287af5402239a1051c37ec7b92913',
175 'id': '30481095_171201961',
177 'title': 'ТюменцевВВ_09.07.2015',
178 'uploader': 'Anton Ivanov',
180 'upload_date': '20150709',
187 'url': 'https://vk.com/video276849682_170681728',
191 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
192 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
194 'upload_date': '20130116',
195 'uploader': "Children's Joy Foundation Inc.",
196 'uploader_id': 'thecjf',
202 'url': 'https://vk.com/video-37468416_456239855',
204 'id': 'k3lz2cmXyRuJQSjGHUv',
206 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
207 # TODO: fix test by fixing dailymotion description extraction
208 'description': 'md5:c651358f03c56f1150b555c26d90a0fd',
209 'uploader': 'AniLibria.Tv',
210 'upload_date': '20160914',
211 'uploader_id': 'x1p5vl5',
212 'timestamp': 1473877246,
215 'skip_download': True,
219 # video key is extra_data not url\d+
220 'url': 'http://vk.com/video-110305615_171782105',
221 'md5': 'e13fcda136f99764872e739d13fac1d1',
223 'id': '-110305615_171782105',
225 'title': 'S-Dance, репетиции к The way show',
226 'uploader': 'THE WAY SHOW | 17 апреля',
227 'uploader_id': '-110305615',
228 'timestamp': 1454859345,
229 'upload_date': '20160207',
232 'skip_download': True,
236 # finished live stream, postlive_mp4
237 'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
239 'id': '-387766_456242764',
241 'title': 'ИгроМир 2016 День 1 — Игромания Утром',
242 'uploader': 'Игромания',
244 # TODO: use act=show to extract view_count
246 'upload_date': '20160929',
247 'uploader_id': '-387766',
248 'timestamp': 1475137527,
252 # live stream, hls and rtmp links, most likely already finished live
253 # stream by the time you are reading this comment
254 'url': 'https://vk.com/video-140332_456239111',
255 'only_matching': True,
258 # removed video, just testing that we match the pattern
259 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
260 'only_matching': True,
263 # age restricted video, requires vk account credentials
264 'url': 'https://vk.com/video205387401_164765225',
265 'only_matching': True,
269 'url': 'https://vk.com/video-76116461_171554880',
270 'only_matching': True,
273 'url': 'http://new.vk.com/video205387401_165548505',
274 'only_matching': True,
277 # This video is no longer available, because its author has been blocked.
278 'url': 'https://vk.com/video-10639516_456240611',
279 'only_matching': True,
282 # The video is not available in your region.
283 'url': 'https://vk.com/video-51812607_171445436',
284 'only_matching': True,
287 def _real_extract(self
, url
):
288 mobj
= re
.match(self
._VALID
_URL
, url
)
289 video_id
= mobj
.group('videoid')
292 info_url
= 'https://vk.com/al_video.php?act=show_inline&al=1&video=' + video_id
293 # Some videos (removed?) can only be downloaded with list id specified
294 list_id
= mobj
.group('list_id')
296 info_url
+= '&list=%s' % list_id
298 info_url
= 'http://vk.com/video_ext.php?' + mobj
.group('embed_query')
299 video_id
= '%s_%s' % (mobj
.group('oid'), mobj
.group('id'))
301 info_page
= self
._download
_webpage
(info_url
, video_id
)
303 error_message
= self
._html
_search
_regex
(
304 [r
'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
305 r
'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
306 info_page
, 'error message', default
=None)
308 raise ExtractorError(error_message
, expected
=True)
310 if re
.search(r
'<!>/login\.php\?.*\bact=security_check', info_page
):
311 raise ExtractorError(
312 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
315 ERROR_COPYRIGHT
= 'Video %s has been removed from public access due to rightholder complaint.'
318 r
'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
321 r
'>The video .*? was removed from public access by request of the copyright holder.<':
324 r
'<!>Please log in or <':
325 'Video %s is only available for registered users, '
326 'use --username and --password options to provide account credentials.',
329 'Video %s does not exist.',
331 r
'<!>Видео временно недоступно':
332 'Video %s is temporarily unavailable.',
335 'Access denied to video %s.',
337 r
'<!>Видеозапись недоступна, так как её автор был заблокирован.':
338 'Video %s is no longer available, because its author has been blocked.',
340 r
'<!>This video is no longer available, because its author has been blocked.':
341 'Video %s is no longer available, because its author has been blocked.',
343 r
'<!>This video is no longer available, because it has been deleted.':
344 'Video %s is no longer available, because it has been deleted.',
346 r
'<!>The video .+? is not available in your region.':
347 'Video %s is not available in your region.',
350 for error_re
, error_msg
in ERRORS
.items():
351 if re
.search(error_re
, info_page
):
352 raise ExtractorError(error_msg
% video_id
, expected
=True)
354 youtube_url
= YoutubeIE
._extract
_url
(info_page
)
356 return self
.url_result(youtube_url
, ie
=YoutubeIE
.ie_key())
358 vimeo_url
= VimeoIE
._extract
_url
(url
, info_page
)
359 if vimeo_url
is not None:
360 return self
.url_result(vimeo_url
)
362 pladform_url
= PladformIE
._extract
_url
(info_page
)
364 return self
.url_result(pladform_url
)
366 m_rutube
= re
.search(
367 r
'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page
)
368 if m_rutube
is not None:
369 rutube_url
= self
._proto
_relative
_url
(
370 m_rutube
.group(1).replace('\\', ''))
371 return self
.url_result(rutube_url
)
373 dailymotion_urls
= DailymotionIE
._extract
_urls
(info_page
)
375 return self
.url_result(dailymotion_urls
[0], DailymotionIE
.ie_key())
377 m_opts
= re
.search(r
'(?s)var\s+opts\s*=\s*({.+?});', info_page
)
379 m_opts_url
= re
.search(r
"url\s*:\s*'((?!/\b)[^']+)", m_opts
.group(1))
381 opts_url
= m_opts_url
.group(1)
382 if opts_url
.startswith('//'):
383 opts_url
= 'http:' + opts_url
384 return self
.url_result(opts_url
)
386 # vars does not look to be served anymore since 24.10.2016
387 data
= self
._parse
_json
(
389 r
'var\s+vars\s*=\s*({.+?});', info_page
, 'vars', default
='{}'),
390 video_id
, fatal
=False)
392 # <!json> is served instead
394 data
= self
._parse
_json
(
396 [r
'<!json>\s*({.+?})\s*<!>', r
'<!json>\s*({.+})'],
397 info_page
, 'json', default
='{}'),
400 data
= data
['player']['params'][0]
403 data
= self
._parse
_json
(
405 r
'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page
,
406 'player params', default
='{}'),
409 data
= data
['params'][0]
413 data
= self
._parse
_json
(
415 r
'<!--\s*({.+})', info_page
, 'payload'),
416 video_id
)['payload'][-1][-1]['player']['params'][0]
418 title
= unescapeHTML(data
['md_title'])
421 # 3 = post live (finished live)
422 is_live
= data
.get('live') == 2
424 title
= self
._live
_title
(title
)
426 timestamp
= unified_timestamp(self
._html
_search
_regex
(
427 r
'class=["\']mv_info_date
[^
>]+>([^
<]+)(?
:<|
from)', info_page,
428 'upload date
', default=None)) or int_or_none(data.get('date
'))
430 view_count = str_to_int(self._search_regex(
431 r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)',
432 info_page, 'view count', default=None))
435 for format_id, format_url in data.items():
436 format_url = url_or_none(format_url)
437 if not format_url or not format_url.startswith(('http', '//', 'rtmp')):
439 if (format_id.startswith(('url', 'cache'))
440 or format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
441 height = int_or_none(self._search_regex(
442 r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
444 'format_id': format_id,
448 elif format_id == 'hls':
449 formats.extend(self._extract_m3u8_formats(
450 format_url, video_id, 'mp4', 'm3u8_native',
451 m3u8_id=format_id, fatal=False, live=is_live))
452 elif format_id == 'rtmp':
454 'format_id': format_id,
458 self._sort_formats(formats)
464 'thumbnail': data.get('jpg'),
465 'uploader': data.get('md_author'),
466 'uploader_id': str_or_none(data.get('author_id')),
467 'duration': data.get('duration'),
468 'timestamp': timestamp,
469 'view_count': view_count,
470 'like_count': int_or_none(data.get('liked')),
471 'dislike_count': int_or_none(data.get('nolikes')),
476 class VKUserVideosIE(VKBaseIE):
477 IE_NAME = 'vk:uservideos'
478 IE_DESC = "VK
- User
's Videos"
479 _VALID_URL = r'https?
://(?
:(?
:m|new
)\
.)?vk\
.com
/videos(?P
<id>-?
[0-9]+)(?
!\?.*\bz
=video
)(?
:[/?
#&]|$)'
480 _TEMPLATE_URL
= 'https://vk.com/videos'
482 'url': 'http://vk.com/videos205387401',
485 'title': "Tom Cruise's Videos",
487 'playlist_mincount': 4,
489 'url': 'http://vk.com/videos-77521',
490 'only_matching': True,
492 'url': 'http://vk.com/videos-97664626?section=all',
493 'only_matching': True,
495 'url': 'http://m.vk.com/videos205387401',
496 'only_matching': True,
498 'url': 'http://new.vk.com/videos205387401',
499 'only_matching': True,
502 def _real_extract(self
, url
):
503 page_id
= self
._match
_id
(url
)
505 webpage
= self
._download
_webpage
(url
, page_id
)
509 'http://vk.com/video' + video_id
, 'VK', video_id
=video_id
)
510 for video_id
in orderedSet(re
.findall(r
'href="/video(-?[0-9_]+)"', webpage
))]
512 title
= unescapeHTML(self
._search
_regex
(
513 r
'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
514 webpage
, 'title', default
=page_id
))
516 return self
.playlist_result(entries
, page_id
, title
)
519 class VKWallPostIE(VKBaseIE
):
520 IE_NAME
= 'vk:wallpost'
521 _VALID_URL
= r
'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))'
523 # public page URL, audio playlist
524 'url': 'https://vk.com/bs.official?w=wall-23538238_35',
527 'title': 'Black Shadow - Wall post 23538238_35',
528 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
531 'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
533 'id': '135220665_111806521',
535 'title': 'Black Shadow - Слепое Верование',
537 'uploader': 'Black Shadow',
538 'artist': 'Black Shadow',
539 'track': 'Слепое Верование',
542 'md5': '4cc7e804579122b17ea95af7834c9233',
544 'id': '135220665_111802303',
546 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
548 'uploader': 'Black Shadow',
549 'artist': 'Black Shadow',
550 'track': 'Война - Негасимое Бездны Пламя!',
553 'skip_download': True,
559 'skip': 'Requires vk account credentials',
561 # single YouTube embed, no leading -
562 'url': 'https://vk.com/wall85155021_6319',
564 'id': '85155021_6319',
565 'title': 'Sergey Gorbunov - Wall post 85155021_6319',
571 'skip': 'Requires vk account credentials',
574 'url': 'https://vk.com/wall-23538238_35',
575 'only_matching': True,
577 # mobile wall page URL
578 'url': 'https://m.vk.com/wall-23538238_35',
579 'only_matching': True,
582 def _real_extract(self
, url
):
583 post_id
= self
._match
_id
(url
)
585 wall_url
= 'https://vk.com/wall%s' % post_id
587 post_id
= remove_start(post_id
, '-')
589 webpage
= self
._download
_webpage
(wall_url
, post_id
)
591 error
= self
._html
_search
_regex
(
592 r
'>Error</div>\s*<div[^>]+class=["\']body
["\'][^>]*>([^<]+)',
593 webpage, 'error', default=None)
595 raise ExtractorError('VK said: %s' % error, expected=True)
597 description = clean_html(get_element_by_class('wall_post_text', webpage))
598 uploader = clean_html(get_element_by_class('author', webpage))
599 thumbnail = self._og_search_thumbnail(webpage)
603 audio_ids = re.findall(r'data-full-id=["\'](\d
+_\d
+)', webpage)
605 al_audio = self._download_webpage(
606 'https
://vk
.com
/al_audio
.php
', post_id,
607 note='Downloading audio info
', fatal=False,
608 data=urlencode_postdata({
609 'act
': 'reload_audio
',
611 'ids
': ','.join(audio_ids)
614 Audio = collections.namedtuple(
615 'Audio
', ['id', 'user_id
', 'url
', 'track
', 'artist
', 'duration
'])
616 audios = self._parse_json(
618 r'<!json
>(.+?
)<!>', al_audio, 'audios
', default='[]'),
619 post_id, fatal=False, transform_source=unescapeHTML)
620 if isinstance(audios, list):
622 a = Audio._make(audio[:6])
624 'id': '%s_%s' % (a.user_id, a.id),
626 'title
': '%s - %s' % (a.artist, a.track) if a.artist and a.track else a.id,
627 'thumbnail
': thumbnail,
628 'duration
': a.duration,
629 'uploader
': uploader,
634 for video in re.finditer(
635 r'<a
[^
>]+href
=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):
636 entries.append(self.url_result(
637 compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key()))
639 title = 'Wall post %s' % post_id
641 return self.playlist_result(
642 orderedSet(entries), post_id,
643 '%s - %s' % (uploader, title) if uploader else title,