]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/vk.py
2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
8 from ..compat
import compat_str
19 from .vimeo
import VimeoIE
20 from .pladform
import PladformIE
23 class VKIE(InfoExtractor
):
30 (?:m\.)?vk\.com/video_|
33 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
35 (?:m\.)?vk\.com/(?:.+?\?.*?z=)?video|
36 (?:www\.)?daxab.com/embed/
38 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
45 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
46 'md5': '0deae91935c54e00003c2a00646315f0',
50 'title': 'ProtivoGunz - Хуёвая песня',
51 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
53 'upload_date': '20120212',
58 'url': 'http://vk.com/video205387401_165548505',
59 'md5': '6c0aeb2e90396ba97035b9cbde548700',
63 'uploader': 'Tom Cruise',
66 'upload_date': '20130721',
71 'note': 'Embedded video',
72 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
73 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
77 'uploader': 'Vladimir Gavrin',
80 'upload_date': '20120730',
83 'skip': 'This video has been removed from public access.',
87 # please update if you find a video whose URL follows the same pattern
88 'url': 'http://vk.com/video-8871596_164049491',
89 'md5': 'a590bcaf3d543576c9bd162812387666',
90 'note': 'Only available for registered users',
94 'uploader': 'Триллеры',
95 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
97 'upload_date': '20121218',
100 'skip': 'Requires vk account credentials',
103 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
104 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
108 'uploader': 'Киномания - лучшее из мира кино',
111 'upload_date': '20140328',
113 'skip': 'Requires vk account credentials',
116 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
117 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
118 'note': 'ivi.ru embed',
122 'title': 'Книга Илая',
124 'upload_date': '20140626',
127 'skip': 'Only works from Russia',
130 # video (removed?) only available with list id
131 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
132 'md5': '091287af5402239a1051c37ec7b92913',
136 'title': 'ТюменцевВВ_09.07.2015',
137 'uploader': 'Anton Ivanov',
139 'upload_date': '20150709',
145 'url': 'https://vk.com/video276849682_170681728',
149 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
150 'description': 'md5:d9903938abdc74c738af77f527ca0596',
152 'upload_date': '20130116',
153 'uploader': "Children's Joy Foundation",
154 'uploader_id': 'thecjf',
159 # video key is extra_data not url\d+
160 'url': 'http://vk.com/video-110305615_171782105',
161 'md5': 'e13fcda136f99764872e739d13fac1d1',
165 'title': 'S-Dance, репетиции к The way show',
166 'uploader': 'THE WAY SHOW | 17 апреля',
167 'upload_date': '20160207',
172 # removed video, just testing that we match the pattern
173 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
174 'only_matching': True,
177 # age restricted video, requires vk account credentials
178 'url': 'https://vk.com/video205387401_164765225',
179 'only_matching': True,
183 'url': 'https://vk.com/video-76116461_171554880',
184 'only_matching': True,
189 (username
, password
) = self
._get
_login
_info
()
193 login_page
= self
._download
_webpage
(
194 'https://vk.com', None, 'Downloading login page')
196 login_form
= self
._hidden
_inputs
(login_page
)
199 'email': username
.encode('cp1251'),
200 'pass': password
.encode('cp1251'),
203 request
= sanitized_Request(
204 'https://login.vk.com/?act=login',
205 urlencode_postdata(login_form
))
206 login_page
= self
._download
_webpage
(
207 request
, None, note
='Logging in as %s' % username
)
209 if re
.search(r
'onLoginFailed', login_page
):
210 raise ExtractorError(
211 'Unable to login, incorrect username and/or password', expected
=True)
213 def _real_initialize(self
):
216 def _real_extract(self
, url
):
217 mobj
= re
.match(self
._VALID
_URL
, url
)
218 video_id
= mobj
.group('videoid')
221 info_url
= 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
222 # Some videos (removed?) can only be downloaded with list id specified
223 list_id
= mobj
.group('list_id')
225 info_url
+= '&list=%s' % list_id
227 info_url
= 'http://vk.com/video_ext.php?' + mobj
.group('embed_query')
228 video_id
= '%s_%s' % (mobj
.group('oid'), mobj
.group('id'))
230 info_page
= self
._download
_webpage
(info_url
, video_id
)
232 error_message
= self
._html
_search
_regex
(
233 [r
'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
234 r
'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
235 info_page
, 'error message', default
=None)
237 raise ExtractorError(error_message
, expected
=True)
239 if re
.search(r
'<!>/login\.php\?.*\bact=security_check', info_page
):
240 raise ExtractorError(
241 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
245 r
'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
246 'Video %s has been removed from public access due to rightholder complaint.',
248 r
'<!>Please log in or <':
249 'Video %s is only available for registered users, '
250 'use --username and --password options to provide account credentials.',
253 'Video %s does not exist.',
255 r
'<!>Видео временно недоступно':
256 'Video %s is temporarily unavailable.',
259 'Access denied to video %s.',
262 for error_re
, error_msg
in ERRORS
.items():
263 if re
.search(error_re
, info_page
):
264 raise ExtractorError(error_msg
% video_id
, expected
=True)
266 youtube_url
= self
._search
_regex
(
267 r
'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
268 info_page
, 'youtube iframe', default
=None)
270 return self
.url_result(youtube_url
, 'Youtube')
272 vimeo_url
= VimeoIE
._extract
_vimeo
_url
(url
, info_page
)
273 if vimeo_url
is not None:
274 return self
.url_result(vimeo_url
)
276 pladform_url
= PladformIE
._extract
_url
(info_page
)
278 return self
.url_result(pladform_url
)
280 m_rutube
= re
.search(
281 r
'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page
)
282 if m_rutube
is not None:
283 rutube_url
= self
._proto
_relative
_url
(
284 m_rutube
.group(1).replace('\\', ''))
285 return self
.url_result(rutube_url
)
287 m_opts
= re
.search(r
'(?s)var\s+opts\s*=\s*({.+?});', info_page
)
289 m_opts_url
= re
.search(r
"url\s*:\s*'((?!/\b)[^']+)", m_opts
.group(1))
291 opts_url
= m_opts_url
.group(1)
292 if opts_url
.startswith('//'):
293 opts_url
= 'http:' + opts_url
294 return self
.url_result(opts_url
)
296 data_json
= self
._search
_regex
(r
'var\s+vars\s*=\s*({.+?});', info_page
, 'vars')
297 data
= json
.loads(data_json
)
299 # Extract upload date
301 mobj
= re
.search(r
'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page
)
303 mobj
.group(1) + ' ' + mobj
.group(2)
304 upload_date
= unified_strdate(mobj
.group(1) + ' ' + mobj
.group(2))
307 views
= self
._html
_search
_regex
(
308 r
'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
309 info_page
, 'view count', default
=None)
311 view_count
= str_to_int(self
._search
_regex
(
312 r
'([\d,.]+)', views
, 'view count', fatal
=False))
315 for k
, v
in data
.items():
316 if not k
.startswith('url') and not k
.startswith('cache') and k
!= 'extra_data' or not v
:
318 height
= int_or_none(self
._search
_regex
(
319 r
'^(?:url|cache)(\d+)', k
, 'height', default
=None))
325 self
._sort
_formats
(formats
)
328 'id': compat_str(data
['vid']),
330 'title': unescapeHTML(data
['md_title']),
331 'thumbnail': data
.get('jpg'),
332 'uploader': data
.get('md_author'),
333 'duration': data
.get('duration'),
334 'upload_date': upload_date
,
335 'view_count': view_count
,
339 class VKUserVideosIE(InfoExtractor
):
340 IE_NAME
= 'vk:uservideos'
341 IE_DESC
= "VK - User's Videos"
342 _VALID_URL
= r
'https?://vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
343 _TEMPLATE_URL
= 'https://vk.com/videos'
345 'url': 'http://vk.com/videos205387401',
348 'title': "Tom Cruise's Videos",
350 'playlist_mincount': 4,
352 'url': 'http://vk.com/videos-77521',
353 'only_matching': True,
355 'url': 'http://vk.com/videos-97664626?section=all',
356 'only_matching': True,
359 def _real_extract(self
, url
):
360 page_id
= self
._match
_id
(url
)
362 webpage
= self
._download
_webpage
(url
, page_id
)
366 'http://vk.com/video' + video_id
, 'VK', video_id
=video_id
)
367 for video_id
in orderedSet(re
.findall(r
'href="/video(-?[0-9_]+)"', webpage
))]
369 title
= unescapeHTML(self
._search
_regex
(
370 r
'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
371 webpage
, 'title', default
=page_id
))
373 return self
.playlist_result(entries
, page_id
, title
)