]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vk.py
36cd7e52e7a492207a3b47934d327f4845ab1d62
2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
10 compat_urllib_request
,
17 class VKIE(InfoExtractor
):
19 _VALID_URL
= r
'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))'
24 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
25 'md5': '0deae91935c54e00003c2a00646315f0',
29 'title': 'ProtivoGunz - Хуёвая песня',
30 'uploader': 're:Noize MC.*',
35 'url': 'http://vk.com/video4643923_163339118',
36 'md5': 'f79bccb5cd182b1f43502ca5685b2b36',
40 'uploader': 'Elya Iskhakova',
41 'title': 'Dream Theater - Hollow Years Live at Budokan 720*',
46 'note': 'Embedded video',
47 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
48 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
52 'uploader': 'Vladimir Gavrin',
58 'url': 'http://vk.com/video-8871596_164049491',
59 'md5': 'a590bcaf3d543576c9bd162812387666',
60 'note': 'Only available for registered users',
64 'uploader': 'Триллеры',
65 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
68 'skip': 'Requires vk account credentials',
71 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
72 'md5': 'd82c22e449f036282d1d3f7f4d276869',
76 'uploader': 'Киномания - лучшее из мира кино',
77 'title': 'Запах женщины (1992)',
80 'skip': 'Requires vk account credentials',
83 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
84 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
88 'uploader': 'Киномания - лучшее из мира кино',
92 'skip': 'Requires vk account credentials',
95 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
96 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
97 'note': 'ivi.ru embed',
101 'title': 'Книга Илая',
104 'skip': 'Only works from Russia',
109 (username
, password
) = self
._get
_login
_info
()
121 request
= compat_urllib_request
.Request('https://login.vk.com/?act=login',
122 compat_urllib_parse
.urlencode(login_form
).encode('utf-8'))
123 login_page
= self
._download
_webpage
(request
, None, note
='Logging in as %s' % username
)
125 if re
.search(r
'onLoginFailed', login_page
):
126 raise ExtractorError('Unable to login, incorrect username and/or password', expected
=True)
128 def _real_initialize(self
):
131 def _real_extract(self
, url
):
132 mobj
= re
.match(self
._VALID
_URL
, url
)
133 video_id
= mobj
.group('videoid')
136 video_id
= '%s_%s' % (mobj
.group('oid'), mobj
.group('id'))
138 info_url
= 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id
139 info_page
= self
._download
_webpage
(info_url
, video_id
)
142 r
'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
143 'Video %s has been removed from public access due to rightholder complaint.',
144 r
'<!>Please log in or <':
145 'Video %s is only available for registered users, '
146 'use --username and --password options to provide account credentials.',
148 'Video %s does not exist.'
151 for error_re
, error_msg
in ERRORS
.items():
152 if re
.search(error_re
, info_page
):
153 raise ExtractorError(error_msg
% video_id
, expected
=True)
155 m_yt
= re
.search(r
'src="(http://www.youtube.com/.*?)"', info_page
)
157 self
.to_screen('Youtube video detected')
158 return self
.url_result(m_yt
.group(1), 'Youtube')
160 m_opts
= re
.search(r
'(?s)var\s+opts\s*=\s*({.*?});', info_page
)
162 m_opts_url
= re
.search(r
"url\s*:\s*'([^']+)", m_opts
.group(1))
164 opts_url
= m_opts_url
.group(1)
165 if opts_url
.startswith('//'):
166 opts_url
= 'http:' + opts_url
167 return self
.url_result(opts_url
)
169 data_json
= self
._search
_regex
(r
'var vars = ({.*?});', info_page
, 'vars')
170 data
= json
.loads(data_json
)
175 'width': int(k
[len('url'):]),
176 } for k
, v
in data
.items()
177 if k
.startswith('url')]
178 self
._sort
_formats
(formats
)
181 'id': compat_str(data
['vid']),
183 'title': unescapeHTML(data
['md_title']),
184 'thumbnail': data
.get('jpg'),
185 'uploader': data
.get('md_author'),
186 'duration': data
.get('duration')