5 from .common
import InfoExtractor
6 from .dailymotion
import DailymotionIE
7 from .odnoklassniki
import OdnoklassnikiIE
8 from .pladform
import PladformIE
9 from .sibnet
import SibnetEmbedIE
10 from .vimeo
import VimeoIE
11 from .youtube
import YoutubeIE
16 get_element_html_by_id
,
31 class VKBaseIE(InfoExtractor
):
34 def _download_webpage_handle(self
, url_or_request
, video_id
, *args
, fatal
=True, **kwargs
):
35 response
= super()._download
_webpage
_handle
(url_or_request
, video_id
, *args
, fatal
=fatal
, **kwargs
)
36 challenge_url
, cookie
= response
[1].geturl() if response
else '', None
37 if challenge_url
.startswith('https://vk.com/429.html?'):
38 cookie
= self
._get
_cookies
(challenge_url
).get('hash429')
42 hash429
= hashlib
.md5(cookie
.value
.encode('ascii')).hexdigest()
43 self
._request
_webpage
(
44 update_url_query(challenge_url
, {'key': hash429}
), video_id
, fatal
=fatal
,
45 note
='Resolving WAF challenge', errnote
='Failed to bypass WAF challenge')
46 return super()._download
_webpage
_handle
(url_or_request
, video_id
, *args
, fatal
=True, **kwargs
)
48 def _perform_login(self
, username
, password
):
49 login_page
, url_handle
= self
._download
_webpage
_handle
(
50 'https://vk.com', None, 'Downloading login page')
52 login_form
= self
._hidden
_inputs
(login_page
)
55 'email': username
.encode('cp1251'),
56 'pass': password
.encode('cp1251'),
59 # vk serves two same remixlhk cookies in Set-Cookie header and expects
60 # first one to be actually set
61 self
._apply
_first
_set
_cookie
_header
(url_handle
, 'remixlhk')
63 login_page
= self
._download
_webpage
(
64 'https://vk.com/login', None,
66 data
=urlencode_postdata(login_form
))
68 if re
.search(r
'onLoginFailed', login_page
):
70 'Unable to login, incorrect username and/or password', expected
=True)
72 def _download_payload(self
, path
, video_id
, data
, fatal
=True):
73 endpoint
= f
'https://vk.com/{path}.php'
75 code
, payload
= self
._download
_json
(
76 endpoint
, video_id
, data
=urlencode_postdata(data
), fatal
=fatal
,
79 'X-Requested-With': 'XMLHttpRequest',
82 self
.raise_login_required()
84 raise ExtractorError(clean_html(payload
[0][1:-1]), expected
=True)
91 _EMBED_REGEX
= [r
'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://vk\
.com
/video_ext\
.php
.+?
)\
1']
96 (?:(?:m|new)\.)?vk\.com/video_|
99 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
101 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?(?:video|clip)|
102 (?:www\.)?daxab.com/embed/
104 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>([\da-f]+)|(ln-[\da-zA-Z]+)))?
110 'url
': 'http
://vk
.com
/videos
-77521?z
=video
-77521_162222515%2Fclub77521
',
112 'id': '-77521_162222515',
114 'title
': 'ProtivoGunz
- Хуёвая песня
',
115 'uploader
': 're
:(?
:Noize MC|Alexander Ilyashenko
).*',
116 'uploader_id
': '39545378',
118 'timestamp
': 1329049880,
119 'upload_date
': '20120212',
120 'comment_count
': int,
122 'thumbnail
': r're
:https?
://.+(?
:\
.jpg|getVideoPreview
.*)$
',
124 'params
': {'skip_download': 'm3u8'},
127 'url
': 'http
://vk
.com
/video205387401_165548505
',
129 'id': '205387401_165548505',
132 'uploader
': 'Tom Cruise
',
133 'uploader_id
': '205387401',
135 'timestamp
': 1374364108,
136 'upload_date
': '20130720',
137 'comment_count
': int,
139 'thumbnail
': r're
:https?
://.+(?
:\
.jpg|getVideoPreview
.*)$
',
143 'note
': 'Embedded video
',
144 'url
': 'https
://vk
.com
/video_ext
.php?oid
=-77521&id=162222515&hash=87b046504ccd8bfa
',
146 'id': '-77521_162222515',
148 'uploader
': 're
:(?
:Noize MC|Alexander Ilyashenko
).*',
149 'title
': 'ProtivoGunz
- Хуёвая песня
',
151 'upload_date
': '20120212',
152 'timestamp
': 1329049880,
153 'uploader_id
': '39545378',
154 'thumbnail
': r're
:https?
://.+(?
:\
.jpg|getVideoPreview
.*)$
',
156 'params
': {'skip_download': 'm3u8'},
159 'url
': 'https
://vk
.com
/video
-93049196_456239755?
list=ln
-cBjJ7S4jYYx3ADnmDT
',
161 'id': '-93049196_456239755',
163 'title
': '8 серия
(озвучка
)',
165 'comment_count
': int,
166 'uploader
': 'Dizi2021
',
168 'timestamp
': 1640162189,
169 'upload_date
': '20211222',
170 'uploader_id
': '-93049196',
171 'thumbnail
': r're
:https?
://.+(?
:\
.jpg|getVideoPreview
.*)$
',
175 'note
': 'youtube embed
',
176 'url
': 'https
://vk
.com
/video276849682_170681728
',
180 'title
': "DSWD Awards 'Children
's Joy Foundation, Inc.' Certificate of Registration
and License to Operate
",
181 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
183 'upload_date': '20130117',
184 'uploader': "Children
's Joy Foundation Inc.",
185 'uploader_id
': 'thecjf
',
187 'channel_id
': 'UCgzCNQ11TmR9V97ECnhi3gw
',
188 'availability
': 'public
',
190 'live_status
': 'not_live
',
191 'playable_in_embed
': True,
192 'channel
': 'Children
\'s Joy Foundation Inc
.',
193 'uploader_url
': 'http
://www
.youtube
.com
/user
/thecjf
',
194 'thumbnail
': r're
:https?
://.+\
.jpg$
',
197 'categories
': ['Nonprofits
& Activism
'],
198 'channel_url
': 'https
://www
.youtube
.com
/channel
/UCgzCNQ11TmR9V97ECnhi3gw
',
199 'channel_follower_count
': int,
204 'note
': 'dailymotion embed
',
205 'url
': 'https
://vk
.com
/video
-95168827_456239103?
list=cca524a0f0d5557e16
',
209 'title
': 'md5
:45410f60ccd4b2760da98cb5fc777d70
',
210 'description
': 'md5
:2e71c5c9413735cfa06cf1a166f16c84
',
211 'uploader
': 'Movies
and cinema
.',
212 'upload_date
': '20221218',
213 'uploader_id
': 'x1jdavv
',
214 'timestamp
': 1671387617,
219 'thumbnail
': r're
:https?
://.+x1080$
',
224 'url
': 'https
://vk
.com
/clips
-74006511?z
=clip
-74006511_456247211',
226 'id': '-74006511_456247211',
228 'comment_count
': int,
231 'thumbnail
': r're
:https?
://.+(?
:\
.jpg|getVideoPreview
.*)$
',
232 'timestamp
': 1664995597,
233 'title
': 'Clip by
@madempress',
234 'upload_date
': '20221005',
235 'uploader
': 'Шальная императрица
',
236 'uploader_id
': '-74006511',
240 # video key is extra_data not url\d+
241 'url
': 'http
://vk
.com
/video
-110305615_171782105',
242 'md5
': 'e13fcda136f99764872e739d13fac1d1
',
244 'id': '-110305615_171782105',
246 'title
': 'S
-Dance
, репетиции к The way show
',
247 'uploader
': 'THE WAY SHOW |
17 апреля
',
248 'uploader_id
': '-110305615',
249 'timestamp
': 1454859345,
250 'upload_date
': '20160207',
255 'note
': 'finished live stream
, postlive_mp4
',
256 'url
': 'https
://vk
.com
/videos
-387766?z
=video
-387766_456242764%2Fpl_
-387766_-2',
258 'id': '-387766_456242764',
260 'title
': 'ИгроМир
2016 День
1 — Игромания Утром
',
261 'uploader
': 'Игромания
',
263 'upload_date
': '20160929',
264 'uploader_id
': '-387766',
265 'timestamp
': 1475137527,
266 'thumbnail
': r're
:https?
://.+\
.jpg$
',
267 'comment_count
': int,
271 'skip_download
': True,
275 # live stream, hls and rtmp links, most likely already finished live
276 # stream by the time you are reading this comment
277 'url
': 'https
://vk
.com
/video
-140332_456239111',
278 'only_matching
': True,
281 # removed video, just testing that we match the pattern
282 'url
': 'http
://vk
.com
/feed?z
=video
-43215063_166094326%2Fbb50cacd3177146d7a
',
283 'only_matching
': True,
286 # age restricted video, requires vk account credentials
287 'url
': 'https
://vk
.com
/video205387401_164765225
',
288 'only_matching
': True,
292 'url
': 'https
://vk
.com
/video
-76116461_171554880',
293 'only_matching
': True,
296 'url
': 'http
://new
.vk
.com
/video205387401_165548505
',
297 'only_matching
': True,
300 # This video is no longer available, because its author has been blocked.
301 'url
': 'https
://vk
.com
/video
-10639516_456240611',
302 'only_matching
': True,
305 # The video is not available in your region.
306 'url
': 'https
://vk
.com
/video
-51812607_171445436',
307 'only_matching
': True,
310 'url
': 'https
://vk
.com
/clip30014565_456240946
',
311 'only_matching
': True,
314 def _real_extract(self, url):
315 mobj = self._match_valid_url(url)
316 video_id = mobj.group('videoid
')
324 # Some videos (removed?) can only be downloaded with list id specified
325 list_id = mobj.group('list_id
')
327 data['list'] = list_id
329 payload = self._download_payload('al_video
', video_id, data)
330 info_page = payload[1]
332 mv_data = opts.get('mvData
') or {}
333 player = opts.get('player
') or {}
335 video_id = '%s_%s' % (mobj.group('oid
'), mobj.group('id'))
337 info_page = self._download_webpage(
338 'http
://vk
.com
/video_ext
.php?
' + mobj.group('embed_query
'), video_id)
340 error_message = self._html_search_regex(
341 [r'(?s
)<!><div
[^
>]+class="video_layer_message"[^
>]*>(.+?
)</div
>',
342 r'(?s
)<div
[^
>]+id="video_ext_msg"[^
>]*>(.+?
)</div
>'],
343 info_page, 'error message
', default=None)
345 raise ExtractorError(error_message, expected=True)
347 if re.search(r'<!>/login\
.php
\?.*\bact
=security_check
', info_page):
348 raise ExtractorError(
349 'You are trying to log
in from an unusual location
. You should confirm ownership at vk
.com to log
in with this IP
.',
352 ERROR_COPYRIGHT = 'Video
%s has been removed
from public access due to rightholder complaint
.'
355 r'>Видеозапись
.*? была изъята из публичного доступа в связи с обращением правообладателя
.<':
358 r'>The video
.*? was removed
from public access by request of the copyright holder
.<':
361 r'<!>Please log
in or <':
362 'Video
%s is only available
for registered users
, '
363 'use
--username
and --password options to provide account credentials
.',
366 'Video
%s does
not exist
.',
368 r'<!>Видео временно недоступно
':
369 'Video
%s is temporarily unavailable
.',
372 'Access denied to video
%s.',
374 r'<!>Видеозапись недоступна
, так как её автор был заблокирован
.':
375 'Video
%s is no longer available
, because its author has been blocked
.',
377 r'<!>This video
is no longer available
, because its author has been blocked
.':
378 'Video
%s is no longer available
, because its author has been blocked
.',
380 r'<!>This video
is no longer available
, because it has been deleted
.':
381 'Video
%s is no longer available
, because it has been deleted
.',
383 r'<!>The video
.+?
is not available
in your region
.':
384 'Video
%s is not available
in your region
.',
387 for error_re, error_msg in ERRORS.items():
388 if re.search(error_re, info_page):
389 raise ExtractorError(error_msg % video_id, expected=True)
391 player = self._parse_json(self._search_regex(
392 r'var\s
+playerParams\s
*=\s
*({.+?}
)\s
*;\s
*\n',
393 info_page, 'player params
'), video_id)
395 youtube_url = YoutubeIE._extract_url(info_page)
397 return self.url_result(youtube_url, YoutubeIE.ie_key())
399 vimeo_url = VimeoIE._extract_url(url, info_page)
400 if vimeo_url is not None:
401 return self.url_result(vimeo_url, VimeoIE.ie_key())
403 pladform_url = PladformIE._extract_url(info_page)
405 return self.url_result(pladform_url, PladformIE.ie_key())
407 m_rutube = re.search(
408 r'\ssrc
="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
409 if m_rutube is not None:
410 rutube_url = self._proto_relative_url(
411 m_rutube.group(1).replace('\\', ''))
412 return self.url_result(rutube_url)
414 dailymotion_url = next(DailymotionIE._extract_embed_urls(url, info_page), None)
416 return self.url_result(dailymotion_url, DailymotionIE.ie_key())
418 odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page)
419 if odnoklassniki_url:
420 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
422 sibnet_url = next(SibnetEmbedIE._extract_embed_urls(url, info_page), None)
424 return self.url_result(sibnet_url)
426 m_opts = re.search(r'(?s
)var\s
+opts\s
*=\s
*({.+?}
);', info_page)
428 m_opts_url = re.search(r"url\s*:\s*'((?
!/\b)[^
']+)", m_opts.group(1))
430 opts_url = m_opts_url.group(1)
431 if opts_url.startswith('//'):
432 opts_url = 'http
:' + opts_url
433 return self.url_result(opts_url)
435 data = player['params
'][0]
436 title = unescapeHTML(data['md_title
'])
439 # 3 = post live (finished live)
440 is_live = data.get('live
') == 2
442 timestamp = unified_timestamp(self._html_search_regex(
443 r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,
444 'upload date', default=None)) or int_or_none(data.get('date'))
446 view_count = str_to_int(self._search_regex(
447 r'class=["\']mv_views_count
[^
>]+>\s
*([\d
,.]+)',
448 info_page, 'view count
', default=None))
451 for format_id, format_url in data.items():
452 format_url = url_or_none(format_url)
453 if not format_url or not format_url.startswith(('http
', '//', 'rtmp
')):
455 if (format_id.startswith(('url
', 'cache
'))
456 or format_id in ('extra_data
', 'live_mp4
', 'postlive_mp4
')):
457 height = int_or_none(self._search_regex(
458 r'^
(?
:url|cache
)(\d
+)', format_id, 'height
', default=None))
460 'format_id
': format_id,
464 elif format_id == 'hls
':
465 formats.extend(self._extract_m3u8_formats(
466 format_url, video_id, 'mp4
', 'm3u8_native
',
467 m3u8_id=format_id, fatal=False, live=is_live))
468 elif format_id == 'rtmp
':
470 'format_id
': format_id,
476 for sub in data.get('subs
') or {}:
477 subtitles.setdefault(sub.get('lang
', 'en
'), []).append({
478 'ext
': sub.get('title
', '.srt
').split('.')[-1],
479 'url
': url_or_none(sub.get('url
')),
486 'thumbnail
': data.get('jpg
'),
487 'uploader
': data.get('md_author
'),
488 'uploader_id
': str_or_none(data.get('author_id
') or mv_data.get('authorId
')),
489 'duration
': int_or_none(data.get('duration
') or mv_data.get('duration
')),
490 'timestamp
': timestamp,
491 'view_count
': view_count,
492 'like_count
': int_or_none(mv_data.get('likes
')),
493 'comment_count
': int_or_none(mv_data.get('commcount
')),
495 'subtitles
': subtitles,
499 class VKUserVideosIE(VKBaseIE):
500 IE_NAME = 'vk
:uservideos
'
501 IE_DESC = "VK - User's Videos
"
502 _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/video/(?:playlist/)?(?P<id>[^?$#/&]+)(?!\?.*\bz=video)(?:[/?#&](?:.*?\bsection=(?P<section>\w+))?|$)'
503 _TEMPLATE_URL = 'https://vk.com/videos'
505 'url': 'https://vk.com/video/@mobidevices',
507 'id': '-17892518_all',
509 'playlist_mincount': 1355,
511 'url': 'https://vk.com/video/@mobidevices?section=uploaded',
513 'id': '-17892518_uploaded',
515 'playlist_mincount': 182,
517 'url': 'https://vk.com/video/playlist/-174476437_2',
519 'id': '-174476437_playlist_2',
522 'playlist_mincount': 108,
524 _VIDEO = collections.namedtuple('Video', ['owner_id', 'id'])
526 def _entries(self, page_id, section):
527 video_list_json = self._download_payload('al_video', page_id, {
528 'act': 'load_videos_silent',
533 count = video_list_json['count']
534 total = video_list_json['total']
535 video_list = video_list_json['list']
538 for video in video_list:
539 v = self._VIDEO._make(video[:2])
540 video_id = '%d_%d' % (v.owner_id, v.id)
541 yield self.url_result(
542 'http://vk.com/video' + video_id, VKIE.ie_key(), video_id)
545 video_list_json = self._download_payload('al_video', page_id, {
546 'act': 'load_videos_silent',
551 count += video_list_json['count']
552 video_list = video_list_json['list']
554 def _real_extract(self, url):
555 u_id, section = self._match_valid_url(url).groups()
556 webpage = self._download_webpage(url, u_id)
558 if u_id.startswith('@'):
559 page_id = self._search_regex(r'data-owner-id\s?=\s?"([^
"]+)"', webpage, 'page_id
')
561 page_id, section = u_id.split('_
', 1)
562 section = f'playlist_{section}
'
564 raise ExtractorError('Invalid URL
', expected=True)
569 playlist_title = clean_html(get_element_by_class('VideoInfoPanel__title
', webpage))
570 return self.playlist_result(self._entries(page_id, section), '%s_%s' % (page_id, section), playlist_title)
573 class VKWallPostIE(VKBaseIE):
574 IE_NAME = 'vk
:wallpost
'
575 _VALID_URL = r'https?
://(?
:(?
:(?
:(?
:m|new
)\
.)?vk\
.com
/(?
:[^?
]+\?.*\bw
=)?
wall(?P
<id>-?\d
+_\d
+)))'
577 # public page URL, audio playlist
578 'url
': 'https
://vk
.com
/bs
.official?w
=wall
-23538238_35',
580 'id': '-23538238_35',
581 'title
': 'Black Shadow
- Wall post
-23538238_35',
582 'description
': 'md5
:190c78f905a53e0de793d83933c6e67f
',
585 'md5
': '5ba93864ec5b85f7ce19a9af4af080f6
',
587 'id': '135220665_111806521',
589 'title
': 'Black Shadow
- Слепое Верование
',
591 'uploader
': 'Black Shadow
',
592 'artist
': 'Black Shadow
',
593 'track
': 'Слепое Верование
',
596 'md5
': '4cc7e804579122b17ea95af7834c9233
',
598 'id': '135220665_111802303',
600 'title
': 'Black Shadow
- Война
- Негасимое Бездны Пламя
!',
602 'uploader
': 'Black Shadow
',
603 'artist
': 'Black Shadow
',
604 'track
': 'Война
- Негасимое Бездны Пламя
!',
608 'skip_download
': True,
611 # single YouTube embed with irrelevant reaction videos
612 'url
': 'https
://vk
.com
/wall
-32370614_7173954',
614 'id': '-32370614_7173954',
615 'title
': 'md5
:9f93c405bbc00061d34007d78c75e3bc
',
616 'description
': 'md5
:953b811f26fa9f21ee5856e2ea8e68fc
',
621 'url
': 'https
://vk
.com
/wall
-23538238_35',
622 'only_matching
': True,
624 # mobile wall page URL
625 'url
': 'https
://m
.vk
.com
/wall
-23538238_35',
626 'only_matching
': True,
628 _BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789
+/='
629 _AUDIO = collections.namedtuple('Audio
', ['id', 'owner_id
', 'url
', 'title
', 'performer
', 'duration
', 'album_id
', 'unk
', 'author_link
', 'lyrics
', 'flags
', 'context
', 'extra
', 'hashes
', 'cover_url
', 'ads
'])
631 def _decode(self, enc):
635 r = self._BASE64_CHARS.index(c)
637 e = 64 * e + r if cond else r
640 dec += chr(255 & e >> (-2 * n & 6))
643 def _unmask_url(self, mask_url, vk_id):
644 if 'audio_api_unavailable
' in mask_url:
645 extra = mask_url.split('?extra
=')[1].split('#')
646 func
, base
= self
._decode
(extra
[1]).split(chr(11))
647 mask_url
= list(self
._decode
(extra
[0]))
648 url_len
= len(mask_url
)
649 indexes
= [None] * url_len
650 index
= int(base
) ^ vk_id
651 for n
in range(url_len
- 1, -1, -1):
652 index
= (url_len
* (n
+ 1) ^ index
+ n
) % url_len
654 for n
in range(1, url_len
):
656 index
= indexes
[url_len
- 1 - n
]
657 mask_url
[n
] = mask_url
[index
]
659 mask_url
= ''.join(mask_url
)
662 def _real_extract(self
, url
):
663 post_id
= self
._match
_id
(url
)
665 webpage
= self
._download
_payload
('wkview', post_id
, {
667 'w': 'wall' + post_id
,
670 uploader
= clean_html(get_element_by_class('PostHeaderTitle__authorName', webpage
))
674 for audio
in re
.findall(r
'data-audio="([^"]+)', webpage
):
675 audio
= self
._parse
_json
(unescapeHTML(audio
), post_id
)
678 title
= unescapeHTML(audio
.get('title'))
679 artist
= unescapeHTML(audio
.get('artist'))
681 'id': f
'{audio["owner_id"]}_{audio["id"]}',
682 'title': join_nonempty(artist
, title
, delim
=' - '),
683 'thumbnails': try_call(lambda: [{'url': u}
for u
in audio
['coverUrl'].split(',')]),
684 'duration': int_or_none(audio
.get('duration')),
685 'uploader': uploader
,
693 'container': 'm4a_dash',
697 entries
.extend(self
.url_result(urljoin(url
, entry
), VKIE
) for entry
in set(re
.findall(
698 r
'<a[^>]+href=(?:["\'])(/video(?
:-?
[\d_
]+)[^
"\']*)',
699 get_element_html_by_id('wl_post_body', webpage))))
701 return self.playlist_result(
702 entries, post_id, join_nonempty(uploader, f'Wall post {post_id}', delim=' - '),
703 clean_html(get_element_by_class('wall_post_text', webpage)))