]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vk.py
2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
20 from .vimeo
import VimeoIE
23 class VKIE(InfoExtractor
):
29 (?:m\.)?vk\.com/video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|
31 (?:m\.)?vk\.com/(?:.+?\?.*?z=)?video|
32 (?:www\.)?biqle\.ru/watch/
34 (?P<videoid>[^s].*?)(?:\?(?:.*\blist=(?P<list_id>[\da-f]+))?|%2F|$)
41 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
42 'md5': '0deae91935c54e00003c2a00646315f0',
46 'title': 'ProtivoGunz - Хуёвая песня',
47 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
49 'upload_date': '20120212',
54 'url': 'http://vk.com/video205387401_165548505',
55 'md5': '6c0aeb2e90396ba97035b9cbde548700',
59 'uploader': 'Tom Cruise',
62 'upload_date': '20130721',
67 'note': 'Embedded video',
68 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
69 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
73 'uploader': 'Vladimir Gavrin',
76 'upload_date': '20120730',
82 # please update if you find a video whose URL follows the same pattern
83 'url': 'http://vk.com/video-8871596_164049491',
84 'md5': 'a590bcaf3d543576c9bd162812387666',
85 'note': 'Only available for registered users',
89 'uploader': 'Триллеры',
90 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
92 'upload_date': '20121218',
95 'skip': 'Requires vk account credentials',
98 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
99 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
103 'uploader': 'Киномания - лучшее из мира кино',
106 'upload_date': '20140328',
108 'skip': 'Requires vk account credentials',
111 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
112 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
113 'note': 'ivi.ru embed',
117 'title': 'Книга Илая',
119 'upload_date': '20140626',
122 'skip': 'Only works from Russia',
125 # video (removed?) only available with list id
126 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
127 'md5': '091287af5402239a1051c37ec7b92913',
131 'title': 'ТюменцевВВ_09.07.2015',
132 'uploader': 'Anton Ivanov',
134 'upload_date': '20150709',
140 'url': 'https://vk.com/video276849682_170681728',
144 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
145 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
147 'upload_date': '20130116',
148 'uploader': "Children's Joy Foundation",
149 'uploader_id': 'thecjf',
154 # removed video, just testing that we match the pattern
155 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
156 'only_matching': True,
159 # age restricted video, requires vk account credentials
160 'url': 'https://vk.com/video205387401_164765225',
161 'only_matching': True,
165 'url': 'http://www.biqle.ru/watch/847655_160197695',
166 'only_matching': True,
171 (username
, password
) = self
._get
_login
_info
()
175 login_page
= self
._download
_webpage
(
176 'https://vk.com', None, 'Downloading login page')
178 login_form
= self
._hidden
_inputs
(login_page
)
181 'email': username
.encode('cp1251'),
182 'pass': password
.encode('cp1251'),
185 request
= sanitized_Request(
186 'https://login.vk.com/?act=login',
187 compat_urllib_parse
.urlencode(login_form
).encode('utf-8'))
188 login_page
= self
._download
_webpage
(
189 request
, None, note
='Logging in as %s' % username
)
191 if re
.search(r
'onLoginFailed', login_page
):
192 raise ExtractorError(
193 'Unable to login, incorrect username and/or password', expected
=True)
195 def _real_initialize(self
):
198 def _real_extract(self
, url
):
199 mobj
= re
.match(self
._VALID
_URL
, url
)
200 video_id
= mobj
.group('videoid')
203 video_id
= '%s_%s' % (mobj
.group('oid'), mobj
.group('id'))
205 info_url
= 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
207 # Some videos (removed?) can only be downloaded with list id specified
208 list_id
= mobj
.group('list_id')
210 info_url
+= '&list=%s' % list_id
212 info_page
= self
._download
_webpage
(info_url
, video_id
)
214 error_message
= self
._html
_search
_regex
(
215 r
'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
216 info_page
, 'error message', default
=None)
218 raise ExtractorError(error_message
, expected
=True)
220 if re
.search(r
'<!>/login\.php\?.*\bact=security_check', info_page
):
221 raise ExtractorError(
222 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
226 r
'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
227 'Video %s has been removed from public access due to rightholder complaint.',
229 r
'<!>Please log in or <':
230 'Video %s is only available for registered users, '
231 'use --username and --password options to provide account credentials.',
234 'Video %s does not exist.',
236 r
'<!>Видео временно недоступно':
237 'Video %s is temporarily unavailable.',
240 'Access denied to video %s.',
243 for error_re
, error_msg
in ERRORS
.items():
244 if re
.search(error_re
, info_page
):
245 raise ExtractorError(error_msg
% video_id
, expected
=True)
247 youtube_url
= self
._search
_regex
(
248 r
'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
249 info_page
, 'youtube iframe', default
=None)
251 return self
.url_result(youtube_url
, 'Youtube')
253 vimeo_url
= VimeoIE
._extract
_vimeo
_url
(url
, info_page
)
254 if vimeo_url
is not None:
255 return self
.url_result(vimeo_url
)
257 m_rutube
= re
.search(
258 r
'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page
)
259 if m_rutube
is not None:
260 self
.to_screen('rutube video detected')
261 rutube_url
= self
._proto
_relative
_url
(
262 m_rutube
.group(1).replace('\\', ''))
263 return self
.url_result(rutube_url
)
265 m_opts
= re
.search(r
'(?s)var\s+opts\s*=\s*({.+?});', info_page
)
267 m_opts_url
= re
.search(r
"url\s*:\s*'((?!/\b)[^']+)", m_opts
.group(1))
269 opts_url
= m_opts_url
.group(1)
270 if opts_url
.startswith('//'):
271 opts_url
= 'http:' + opts_url
272 return self
.url_result(opts_url
)
274 data_json
= self
._search
_regex
(r
'var\s+vars\s*=\s*({.+?});', info_page
, 'vars')
275 data
= json
.loads(data_json
)
277 # Extract upload date
279 mobj
= re
.search(r
'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page
)
281 mobj
.group(1) + ' ' + mobj
.group(2)
282 upload_date
= unified_strdate(mobj
.group(1) + ' ' + mobj
.group(2))
285 views
= self
._html
_search
_regex
(
286 r
'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
287 info_page
, 'view count', fatal
=False)
289 view_count
= str_to_int(self
._search
_regex
(
290 r
'([\d,.]+)', views
, 'view count', fatal
=False))
295 'width': int(k
[len('url'):]),
296 } for k
, v
in data
.items()
297 if k
.startswith('url')]
298 self
._sort
_formats
(formats
)
301 'id': compat_str(data
['vid']),
303 'title': unescapeHTML(data
['md_title']),
304 'thumbnail': data
.get('jpg'),
305 'uploader': data
.get('md_author'),
306 'duration': data
.get('duration'),
307 'upload_date': upload_date
,
308 'view_count': view_count
,
312 class VKUserVideosIE(InfoExtractor
):
313 IE_NAME
= 'vk:uservideos'
314 IE_DESC
= "VK - User's Videos"
315 _VALID_URL
= r
'https?://vk\.com/videos(?P<id>-?[0-9]+)$'
316 _TEMPLATE_URL
= 'https://vk.com/videos'
318 'url': 'http://vk.com/videos205387401',
321 'title': "Tom Cruise's Videos",
323 'playlist_mincount': 4,
325 'url': 'http://vk.com/videos-77521',
326 'only_matching': True,
329 def _real_extract(self
, url
):
330 page_id
= self
._match
_id
(url
)
332 webpage
= self
._download
_webpage
(url
, page_id
)
336 'http://vk.com/video' + video_id
, 'VK', video_id
=video_id
)
337 for video_id
in orderedSet(re
.findall(r
'href="/video(-?[0-9_]+)"', webpage
))]
339 title
= unescapeHTML(self
._search
_regex
(
340 r
'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
341 webpage
, 'title', default
=page_id
))
343 return self
.playlist_result(entries
, page_id
, title
)