]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/vk.py
2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
20 from .vimeo
import VimeoIE
21 from .pladform
import PladformIE
24 class VKIE(InfoExtractor
):
30 (?:m\.)?vk\.com/video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|
32 (?:m\.)?vk\.com/(?:.+?\?.*?z=)?video|
33 (?:www\.)?biqle\.ru/watch/
35 (?P<videoid>[^s].*?)(?:\?(?:.*\blist=(?P<list_id>[\da-f]+))?|%2F|$)
42 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
43 'md5': '0deae91935c54e00003c2a00646315f0',
47 'title': 'ProtivoGunz - Хуёвая песня',
48 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
50 'upload_date': '20120212',
55 'url': 'http://vk.com/video205387401_165548505',
56 'md5': '6c0aeb2e90396ba97035b9cbde548700',
60 'uploader': 'Tom Cruise',
63 'upload_date': '20130721',
68 'note': 'Embedded video',
69 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
70 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
74 'uploader': 'Vladimir Gavrin',
77 'upload_date': '20120730',
83 # please update if you find a video whose URL follows the same pattern
84 'url': 'http://vk.com/video-8871596_164049491',
85 'md5': 'a590bcaf3d543576c9bd162812387666',
86 'note': 'Only available for registered users',
90 'uploader': 'Триллеры',
91 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
93 'upload_date': '20121218',
96 'skip': 'Requires vk account credentials',
99 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
100 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
104 'uploader': 'Киномания - лучшее из мира кино',
107 'upload_date': '20140328',
109 'skip': 'Requires vk account credentials',
112 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
113 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
114 'note': 'ivi.ru embed',
118 'title': 'Книга Илая',
120 'upload_date': '20140626',
123 'skip': 'Only works from Russia',
126 # video (removed?) only available with list id
127 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
128 'md5': '091287af5402239a1051c37ec7b92913',
132 'title': 'ТюменцевВВ_09.07.2015',
133 'uploader': 'Anton Ivanov',
135 'upload_date': '20150709',
141 'url': 'https://vk.com/video276849682_170681728',
145 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
146 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
148 'upload_date': '20130116',
149 'uploader': "Children's Joy Foundation",
150 'uploader_id': 'thecjf',
155 # removed video, just testing that we match the pattern
156 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
157 'only_matching': True,
160 # age restricted video, requires vk account credentials
161 'url': 'https://vk.com/video205387401_164765225',
162 'only_matching': True,
166 'url': 'http://www.biqle.ru/watch/847655_160197695',
167 'only_matching': True,
171 'url': 'https://vk.com/video-76116461_171554880',
172 'only_matching': True,
177 (username
, password
) = self
._get
_login
_info
()
181 login_page
= self
._download
_webpage
(
182 'https://vk.com', None, 'Downloading login page')
184 login_form
= self
._hidden
_inputs
(login_page
)
187 'email': username
.encode('cp1251'),
188 'pass': password
.encode('cp1251'),
191 request
= sanitized_Request(
192 'https://login.vk.com/?act=login',
193 compat_urllib_parse
.urlencode(login_form
).encode('utf-8'))
194 login_page
= self
._download
_webpage
(
195 request
, None, note
='Logging in as %s' % username
)
197 if re
.search(r
'onLoginFailed', login_page
):
198 raise ExtractorError(
199 'Unable to login, incorrect username and/or password', expected
=True)
201 def _real_initialize(self
):
204 def _real_extract(self
, url
):
205 mobj
= re
.match(self
._VALID
_URL
, url
)
206 video_id
= mobj
.group('videoid')
209 video_id
= '%s_%s' % (mobj
.group('oid'), mobj
.group('id'))
211 info_url
= 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
213 # Some videos (removed?) can only be downloaded with list id specified
214 list_id
= mobj
.group('list_id')
216 info_url
+= '&list=%s' % list_id
218 info_page
= self
._download
_webpage
(info_url
, video_id
)
220 error_message
= self
._html
_search
_regex
(
221 r
'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
222 info_page
, 'error message', default
=None)
224 raise ExtractorError(error_message
, expected
=True)
226 if re
.search(r
'<!>/login\.php\?.*\bact=security_check', info_page
):
227 raise ExtractorError(
228 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
232 r
'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
233 'Video %s has been removed from public access due to rightholder complaint.',
235 r
'<!>Please log in or <':
236 'Video %s is only available for registered users, '
237 'use --username and --password options to provide account credentials.',
240 'Video %s does not exist.',
242 r
'<!>Видео временно недоступно':
243 'Video %s is temporarily unavailable.',
246 'Access denied to video %s.',
249 for error_re
, error_msg
in ERRORS
.items():
250 if re
.search(error_re
, info_page
):
251 raise ExtractorError(error_msg
% video_id
, expected
=True)
253 youtube_url
= self
._search
_regex
(
254 r
'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
255 info_page
, 'youtube iframe', default
=None)
257 return self
.url_result(youtube_url
, 'Youtube')
259 vimeo_url
= VimeoIE
._extract
_vimeo
_url
(url
, info_page
)
260 if vimeo_url
is not None:
261 return self
.url_result(vimeo_url
)
263 pladform_url
= PladformIE
._extract
_url
(info_page
)
265 return self
.url_result(pladform_url
)
267 m_rutube
= re
.search(
268 r
'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page
)
269 if m_rutube
is not None:
270 rutube_url
= self
._proto
_relative
_url
(
271 m_rutube
.group(1).replace('\\', ''))
272 return self
.url_result(rutube_url
)
274 m_opts
= re
.search(r
'(?s)var\s+opts\s*=\s*({.+?});', info_page
)
276 m_opts_url
= re
.search(r
"url\s*:\s*'((?!/\b)[^']+)", m_opts
.group(1))
278 opts_url
= m_opts_url
.group(1)
279 if opts_url
.startswith('//'):
280 opts_url
= 'http:' + opts_url
281 return self
.url_result(opts_url
)
283 data_json
= self
._search
_regex
(r
'var\s+vars\s*=\s*({.+?});', info_page
, 'vars')
284 data
= json
.loads(data_json
)
286 # Extract upload date
288 mobj
= re
.search(r
'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page
)
290 mobj
.group(1) + ' ' + mobj
.group(2)
291 upload_date
= unified_strdate(mobj
.group(1) + ' ' + mobj
.group(2))
294 views
= self
._html
_search
_regex
(
295 r
'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
296 info_page
, 'view count', fatal
=False)
298 view_count
= str_to_int(self
._search
_regex
(
299 r
'([\d,.]+)', views
, 'view count', fatal
=False))
304 'width': int(k
[len('url'):]),
305 } for k
, v
in data
.items()
306 if k
.startswith('url')]
307 self
._sort
_formats
(formats
)
310 'id': compat_str(data
['vid']),
312 'title': unescapeHTML(data
['md_title']),
313 'thumbnail': data
.get('jpg'),
314 'uploader': data
.get('md_author'),
315 'duration': data
.get('duration'),
316 'upload_date': upload_date
,
317 'view_count': view_count
,
321 class VKUserVideosIE(InfoExtractor
):
322 IE_NAME
= 'vk:uservideos'
323 IE_DESC
= "VK - User's Videos"
324 _VALID_URL
= r
'https?://vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
325 _TEMPLATE_URL
= 'https://vk.com/videos'
327 'url': 'http://vk.com/videos205387401',
330 'title': "Tom Cruise's Videos",
332 'playlist_mincount': 4,
334 'url': 'http://vk.com/videos-77521',
335 'only_matching': True,
337 'url': 'http://vk.com/videos-97664626?section=all',
338 'only_matching': True,
341 def _real_extract(self
, url
):
342 page_id
= self
._match
_id
(url
)
344 webpage
= self
._download
_webpage
(url
, page_id
)
348 'http://vk.com/video' + video_id
, 'VK', video_id
=video_id
)
349 for video_id
in orderedSet(re
.findall(r
'href="/video(-?[0-9_]+)"', webpage
))]
351 title
= unescapeHTML(self
._search
_regex
(
352 r
'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
353 webpage
, 'title', default
=page_id
))
355 return self
.playlist_result(entries
, page_id
, title
)