2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
8 from ..compat
import compat_urlparse
22 from .dailymotion
import DailymotionIE
23 from .odnoklassniki
import OdnoklassnikiIE
24 from .pladform
import PladformIE
25 from .vimeo
import VimeoIE
26 from .youtube
import YoutubeIE
29 class VKBaseIE(InfoExtractor
):
32 def _perform_login(self
, username
, password
):
33 login_page
, url_handle
= self
._download
_webpage
_handle
(
34 'https://vk.com', None, 'Downloading login page')
36 login_form
= self
._hidden
_inputs
(login_page
)
39 'email': username
.encode('cp1251'),
40 'pass': password
.encode('cp1251'),
43 # vk serves two same remixlhk cookies in Set-Cookie header and expects
44 # first one to be actually set
45 self
._apply
_first
_set
_cookie
_header
(url_handle
, 'remixlhk')
47 login_page
= self
._download
_webpage
(
48 'https://vk.com/login', None,
50 data
=urlencode_postdata(login_form
))
52 if re
.search(r
'onLoginFailed', login_page
):
54 'Unable to login, incorrect username and/or password', expected
=True)
56 def _download_payload(self
, path
, video_id
, data
, fatal
=True):
58 code
, payload
= self
._download
_json
(
59 'https://vk.com/%s.php' % path
, video_id
,
60 data
=urlencode_postdata(data
), fatal
=fatal
,
61 headers
={'X-Requested-With': 'XMLHttpRequest'}
)['payload']
63 self
.raise_login_required()
65 raise ExtractorError(clean_html(payload
[0][1:-1]), expected
=True)
76 (?:(?:m|new)\.)?vk\.com/video_|
79 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
81 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?(?:video|clip)|
82 (?:www\.)?daxab.com/embed/
84 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>([\da-f]+)|(ln-[\da-zA-Z]+)))?
89 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
90 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
92 'id': '-77521_162222515',
94 'title': 'ProtivoGunz - Хуёвая песня',
95 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
96 'uploader_id': '-77521',
98 'timestamp': 1329049880,
99 'upload_date': '20120212',
103 'url': 'http://vk.com/video205387401_165548505',
105 'id': '205387401_165548505',
108 'uploader': 'Tom Cruise',
109 'uploader_id': '205387401',
111 'timestamp': 1374364108,
112 'upload_date': '20130720',
116 'note': 'Embedded video',
117 'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa',
118 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
120 'id': '-77521_162222515',
122 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
123 'title': 'ProtivoGunz - Хуёвая песня',
125 'upload_date': '20120212',
126 'timestamp': 1329049880,
127 'uploader_id': '-77521',
132 # please update if you find a video whose URL follows the same pattern
133 'url': 'http://vk.com/video-8871596_164049491',
134 'md5': 'a590bcaf3d543576c9bd162812387666',
135 'note': 'Only available for registered users',
137 'id': '-8871596_164049491',
139 'uploader': 'Триллеры',
140 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
142 'upload_date': '20121218',
148 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
150 'id': '-43215063_168067957',
152 'uploader': 'Bro Mazter',
155 'upload_date': '20140328',
156 'uploader_id': '223413403',
157 'timestamp': 1396018030,
159 'skip': 'Requires vk account credentials',
162 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
163 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
164 'note': 'ivi.ru embed',
166 'id': '-43215063_169084319',
168 'title': 'Книга Илая',
170 'upload_date': '20140626',
176 'url': 'https://vk.com/video-93049196_456239755?list=ln-cBjJ7S4jYYx3ADnmDT',
178 'id': '-93049196_456239755',
180 'title': '8 серия (озвучка)',
182 'upload_date': '20211222',
187 # video (removed?) only available with list id
188 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
189 'md5': '091287af5402239a1051c37ec7b92913',
191 'id': '30481095_171201961',
193 'title': 'ТюменцевВВ_09.07.2015',
194 'uploader': 'Anton Ivanov',
196 'upload_date': '20150709',
203 'url': 'https://vk.com/video276849682_170681728',
207 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
208 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
210 'upload_date': '20130116',
211 'uploader': "Children's Joy Foundation Inc.",
212 'uploader_id': 'thecjf',
218 'url': 'https://vk.com/video-37468416_456239855',
220 'id': 'k3lz2cmXyRuJQSjGHUv',
222 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
223 'description': 'md5:424b8e88cc873217f520e582ba28bb36',
224 'uploader': 'AniLibria.Tv',
225 'upload_date': '20160914',
226 'uploader_id': 'x1p5vl5',
227 'timestamp': 1473877246,
230 'skip_download': True,
234 # video key is extra_data not url\d+
235 'url': 'http://vk.com/video-110305615_171782105',
236 'md5': 'e13fcda136f99764872e739d13fac1d1',
238 'id': '-110305615_171782105',
240 'title': 'S-Dance, репетиции к The way show',
241 'uploader': 'THE WAY SHOW | 17 апреля',
242 'uploader_id': '-110305615',
243 'timestamp': 1454859345,
244 'upload_date': '20160207',
247 'skip_download': True,
251 # finished live stream, postlive_mp4
252 'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
254 'id': '-387766_456242764',
256 'title': 'ИгроМир 2016 День 1 — Игромания Утром',
257 'uploader': 'Игромания',
259 # TODO: use act=show to extract view_count
261 'upload_date': '20160929',
262 'uploader_id': '-387766',
263 'timestamp': 1475137527,
266 'skip_download': True,
270 # live stream, hls and rtmp links, most likely already finished live
271 # stream by the time you are reading this comment
272 'url': 'https://vk.com/video-140332_456239111',
273 'only_matching': True,
276 # removed video, just testing that we match the pattern
277 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
278 'only_matching': True,
281 # age restricted video, requires vk account credentials
282 'url': 'https://vk.com/video205387401_164765225',
283 'only_matching': True,
287 'url': 'https://vk.com/video-76116461_171554880',
288 'only_matching': True,
291 'url': 'http://new.vk.com/video205387401_165548505',
292 'only_matching': True,
295 # This video is no longer available, because its author has been blocked.
296 'url': 'https://vk.com/video-10639516_456240611',
297 'only_matching': True,
300 # The video is not available in your region.
301 'url': 'https://vk.com/video-51812607_171445436',
302 'only_matching': True,
305 'url': 'https://vk.com/clip30014565_456240946',
306 'only_matching': True,
310 def _extract_sibnet_urls(webpage
):
311 # https://help.sibnet.ru/?sibnet_video_embed
312 return [unescapeHTML(mobj
.group('url')) for mobj
in re
.finditer(
313 r
'<iframe\b[^>]+\bsrc=(["\'])(?P
<url
>(?
:https?
:)?
//video\
.sibnet\
.ru
/shell\
.php
\?.*?
\bvideoid
=\d
+.*?
)\
1',
316 def _real_extract(self, url):
317 mobj = self._match_valid_url(url)
318 video_id = mobj.group('videoid
')
323 'act
': 'show_inline
',
326 # Some videos (removed?) can only be downloaded with list id specified
327 list_id = mobj.group('list_id
')
329 data['list'] = list_id
331 payload = self._download_payload('al_video
', video_id, data)
332 info_page = payload[1]
334 mv_data = opts.get('mvData
') or {}
335 player = opts.get('player
') or {}
337 video_id = '%s_%s' % (mobj.group('oid
'), mobj.group('id'))
339 info_page = self._download_webpage(
340 'http
://vk
.com
/video_ext
.php?
' + mobj.group('embed_query
'), video_id)
342 error_message = self._html_search_regex(
343 [r'(?s
)<!><div
[^
>]+class="video_layer_message"[^
>]*>(.+?
)</div
>',
344 r'(?s
)<div
[^
>]+id="video_ext_msg"[^
>]*>(.+?
)</div
>'],
345 info_page, 'error message
', default=None)
347 raise ExtractorError(error_message, expected=True)
349 if re.search(r'<!>/login\
.php
\?.*\bact
=security_check
', info_page):
350 raise ExtractorError(
351 'You are trying to log
in from an unusual location
. You should confirm ownership at vk
.com to log
in with this IP
.',
354 ERROR_COPYRIGHT = 'Video
%s has been removed
from public access due to rightholder complaint
.'
357 r'>Видеозапись
.*? была изъята из публичного доступа в связи с обращением правообладателя
.<':
360 r'>The video
.*? was removed
from public access by request of the copyright holder
.<':
363 r'<!>Please log
in or <':
364 'Video
%s is only available
for registered users
, '
365 'use
--username
and --password options to provide account credentials
.',
368 'Video
%s does
not exist
.',
370 r'<!>Видео временно недоступно
':
371 'Video
%s is temporarily unavailable
.',
374 'Access denied to video
%s.',
376 r'<!>Видеозапись недоступна
, так как её автор был заблокирован
.':
377 'Video
%s is no longer available
, because its author has been blocked
.',
379 r'<!>This video
is no longer available
, because its author has been blocked
.':
380 'Video
%s is no longer available
, because its author has been blocked
.',
382 r'<!>This video
is no longer available
, because it has been deleted
.':
383 'Video
%s is no longer available
, because it has been deleted
.',
385 r'<!>The video
.+?
is not available
in your region
.':
386 'Video
%s is not available
in your region
.',
389 for error_re, error_msg in ERRORS.items():
390 if re.search(error_re, info_page):
391 raise ExtractorError(error_msg % video_id, expected=True)
393 player = self._parse_json(self._search_regex(
394 r'var\s
+playerParams\s
*=\s
*({.+?}
)\s
*;\s
*\n',
395 info_page, 'player params
'), video_id)
397 youtube_url = YoutubeIE._extract_url(info_page)
399 return self.url_result(youtube_url, YoutubeIE.ie_key())
401 vimeo_url = VimeoIE._extract_url(url, info_page)
402 if vimeo_url is not None:
403 return self.url_result(vimeo_url, VimeoIE.ie_key())
405 pladform_url = PladformIE._extract_url(info_page)
407 return self.url_result(pladform_url, PladformIE.ie_key())
409 m_rutube = re.search(
410 r'\ssrc
="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
411 if m_rutube is not None:
412 rutube_url = self._proto_relative_url(
413 m_rutube.group(1).replace('\\', ''))
414 return self.url_result(rutube_url)
416 dailymotion_urls = DailymotionIE._extract_urls(info_page)
418 return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key())
420 odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page)
421 if odnoklassniki_url:
422 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
424 sibnet_urls = self._extract_sibnet_urls(info_page)
426 return self.url_result(sibnet_urls[0])
428 m_opts = re.search(r'(?s
)var\s
+opts\s
*=\s
*({.+?}
);', info_page)
430 m_opts_url = re.search(r"url\s*:\s*'((?
!/\b)[^
']+)", m_opts.group(1))
432 opts_url = m_opts_url.group(1)
433 if opts_url.startswith('//'):
434 opts_url = 'http
:' + opts_url
435 return self.url_result(opts_url)
437 data = player['params
'][0]
438 title = unescapeHTML(data['md_title
'])
441 # 3 = post live (finished live)
442 is_live = data.get('live
') == 2
444 timestamp = unified_timestamp(self._html_search_regex(
445 r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,
446 'upload date', default=None)) or int_or_none(data.get('date'))
448 view_count = str_to_int(self._search_regex(
449 r'class=["\']mv_views_count
[^
>]+>\s
*([\d
,.]+)',
450 info_page, 'view count
', default=None))
453 for format_id, format_url in data.items():
454 format_url = url_or_none(format_url)
455 if not format_url or not format_url.startswith(('http
', '//', 'rtmp
')):
457 if (format_id.startswith(('url
', 'cache
'))
458 or format_id in ('extra_data
', 'live_mp4
', 'postlive_mp4
')):
459 height = int_or_none(self._search_regex(
460 r'^
(?
:url|cache
)(\d
+)', format_id, 'height
', default=None))
462 'format_id
': format_id,
466 elif format_id == 'hls
':
467 formats.extend(self._extract_m3u8_formats(
468 format_url, video_id, 'mp4
', 'm3u8_native
',
469 m3u8_id=format_id, fatal=False, live=is_live))
470 elif format_id == 'rtmp
':
472 'format_id
': format_id,
476 self._sort_formats(formats)
479 for sub in data.get('subs
') or {}:
480 subtitles.setdefault(sub.get('lang
', 'en
'), []).append({
481 'ext
': sub.get('title
', '.srt
').split('.')[-1],
482 'url
': url_or_none(sub.get('url
')),
489 'thumbnail
': data.get('jpg
'),
490 'uploader
': data.get('md_author
'),
491 'uploader_id
': str_or_none(data.get('author_id
') or mv_data.get('authorId
')),
492 'duration
': int_or_none(data.get('duration
') or mv_data.get('duration
')),
493 'timestamp
': timestamp,
494 'view_count
': view_count,
495 'like_count
': int_or_none(mv_data.get('likes
')),
496 'comment_count
': int_or_none(mv_data.get('commcount
')),
498 'subtitles
': subtitles,
502 class VKUserVideosIE(VKBaseIE):
503 IE_NAME = 'vk
:uservideos
'
504 IE_DESC = "VK - User's Videos
"
505 _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/video/@(?P<id>[^?$#/&]+)(?!\?.*\bz=video)(?:[/?#&](?:.*?\bsection=(?P<section>\w+))?|$)'
506 _TEMPLATE_URL = 'https://vk.com/videos'
508 'url': 'https://vk.com/video/@mobidevices',
510 'id': '-17892518_all',
512 'playlist_mincount': 1355,
514 'url': 'https://vk.com/video/@mobidevices?section=uploaded',
516 'id': '-17892518_uploaded',
518 'playlist_mincount': 182,
520 _VIDEO = collections.namedtuple('Video', ['owner_id', 'id'])
522 def _entries(self, page_id, section):
523 video_list_json = self._download_payload('al_video', page_id, {
524 'act': 'load_videos_silent',
529 count = video_list_json['count']
530 total = video_list_json['total']
531 video_list = video_list_json['list']
534 for video in video_list:
535 v = self._VIDEO._make(video[:2])
536 video_id = '%d_%d' % (v.owner_id, v.id)
537 yield self.url_result(
538 'http://vk.com/video' + video_id, VKIE.ie_key(), video_id)
541 video_list_json = self._download_payload('al_video', page_id, {
542 'act': 'load_videos_silent',
547 count += video_list_json['count']
548 video_list = video_list_json['list']
550 def _real_extract(self, url):
551 u_id, section = self._match_valid_url(url).groups()
552 webpage = self._download_webpage(url, u_id)
553 page_id = self._search_regex(r'data-owner-id\s?=\s?"([^
"]+)"', webpage, 'page_id
')
557 return self.playlist_result(self._entries(page_id, section), '%s_%s' % (page_id, section))
560 class VKWallPostIE(VKBaseIE):
561 IE_NAME = 'vk
:wallpost
'
562 _VALID_URL = r'https?
://(?
:(?
:(?
:(?
:m|new
)\
.)?vk\
.com
/(?
:[^?
]+\?.*\bw
=)?
wall(?P
<id>-?\d
+_\d
+)))'
564 # public page URL, audio playlist
565 'url
': 'https
://vk
.com
/bs
.official?w
=wall
-23538238_35',
567 'id': '-23538238_35',
568 'title
': 'Black Shadow
- Wall post
-23538238_35',
569 'description
': 'md5
:3f84b9c4f9ef499731cf1ced9998cc0c
',
572 'md5
': '5ba93864ec5b85f7ce19a9af4af080f6
',
574 'id': '135220665_111806521',
576 'title
': 'Black Shadow
- Слепое Верование
',
578 'uploader
': 'Black Shadow
',
579 'artist
': 'Black Shadow
',
580 'track
': 'Слепое Верование
',
583 'md5
': '4cc7e804579122b17ea95af7834c9233
',
585 'id': '135220665_111802303',
587 'title
': 'Black Shadow
- Война
- Негасимое Бездны Пламя
!',
589 'uploader
': 'Black Shadow
',
590 'artist
': 'Black Shadow
',
591 'track
': 'Война
- Негасимое Бездны Пламя
!',
595 'skip_download
': True,
598 'skip
': 'Requires vk account credentials
',
600 # single YouTube embed, no leading -
601 'url
': 'https
://vk
.com
/wall85155021_6319
',
603 'id': '85155021_6319',
604 'title
': 'Сергей Горбунов
- Wall post
85155021_6319',
610 'skip
': 'Requires vk account credentials
',
613 'url
': 'https
://vk
.com
/wall
-23538238_35',
614 'only_matching
': True,
616 # mobile wall page URL
617 'url
': 'https
://m
.vk
.com
/wall
-23538238_35',
618 'only_matching
': True,
620 _BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789
+/='
621 _AUDIO = collections.namedtuple('Audio
', ['id', 'owner_id
', 'url
', 'title
', 'performer
', 'duration
', 'album_id
', 'unk
', 'author_link
', 'lyrics
', 'flags
', 'context
', 'extra
', 'hashes
', 'cover_url
', 'ads
'])
623 def _decode(self, enc):
627 r = self._BASE64_CHARS.index(c)
629 e = 64 * e + r if cond else r
632 dec += chr(255 & e >> (-2 * n & 6))
635 def _unmask_url(self, mask_url, vk_id):
636 if 'audio_api_unavailable
' in mask_url:
637 extra = mask_url.split('?extra
=')[1].split('#')
638 func
, base
= self
._decode
(extra
[1]).split(chr(11))
639 mask_url
= list(self
._decode
(extra
[0]))
640 url_len
= len(mask_url
)
641 indexes
= [None] * url_len
642 index
= int(base
) ^ vk_id
643 for n
in range(url_len
- 1, -1, -1):
644 index
= (url_len
* (n
+ 1) ^ index
+ n
) % url_len
646 for n
in range(1, url_len
):
648 index
= indexes
[url_len
- 1 - n
]
649 mask_url
[n
] = mask_url
[index
]
651 mask_url
= ''.join(mask_url
)
654 def _real_extract(self
, url
):
655 post_id
= self
._match
_id
(url
)
657 webpage
= self
._download
_payload
('wkview', post_id
, {
659 'w': 'wall' + post_id
,
662 description
= clean_html(get_element_by_class('wall_post_text', webpage
))
663 uploader
= clean_html(get_element_by_class('author', webpage
))
667 for audio
in re
.findall(r
'data-audio="([^"]+)', webpage
):
668 audio
= self
._parse
_json
(unescapeHTML(audio
), post_id
)
669 a
= self
._AUDIO
._make
(audio
[:16])
672 title
= unescapeHTML(a
.title
)
673 performer
= unescapeHTML(a
.performer
)
675 'id': '%s_%s' % (a
.owner_id
, a
.id),
676 'url': self
._unmask
_url
(a
.url
, a
.ads
['vk_id']),
677 'title': '%s - %s' % (performer
, title
) if performer
else title
,
678 'thumbnails': [{'url': c_url}
for c_url
in a
.cover_url
.split(',')] if a
.cover_url
else None,
679 'duration': int_or_none(a
.duration
),
680 'uploader': uploader
,
684 'protocol': 'm3u8_native',
687 for video
in re
.finditer(
688 r
'<a[^>]+href=(["\'])(?P
<url
>/video(?
:-?
[\d_
]+).*?
)\
1', webpage):
689 entries.append(self.url_result(
690 compat_urlparse.urljoin(url, video.group('url
')), VKIE.ie_key()))
692 title = 'Wall post
%s' % post_id
694 return self.playlist_result(
695 orderedSet(entries), post_id,
696 '%s - %s' % (uploader, title) if uploader else title,