]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/vk.py
2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
11 compat_urllib_request
,
21 class VKIE(InfoExtractor
):
23 _VALID_URL
= r
'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>[^s].*?)(?:\?|%2F|$))'
28 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
29 'md5': '0deae91935c54e00003c2a00646315f0',
33 'title': 'ProtivoGunz - Хуёвая песня',
34 'uploader': 're:Noize MC.*',
36 'upload_date': '20120212',
40 'url': 'http://vk.com/video205387401_165548505',
41 'md5': '6c0aeb2e90396ba97035b9cbde548700',
45 'uploader': 'Tom Cruise',
48 'upload_date': '20130721'
52 'note': 'Embedded video',
53 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
54 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
58 'uploader': 'Vladimir Gavrin',
61 'upload_date': '20120730',
66 # please update if you find a video whose URL follows the same pattern
67 'url': 'http://vk.com/video-8871596_164049491',
68 'md5': 'a590bcaf3d543576c9bd162812387666',
69 'note': 'Only available for registered users',
73 'uploader': 'Триллеры',
74 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
76 'upload_date': '20121218'
78 'skip': 'Requires vk account credentials',
81 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
82 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
86 'uploader': 'Киномания - лучшее из мира кино',
89 'upload_date': '20140328',
91 'skip': 'Requires vk account credentials',
94 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
95 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
96 'note': 'ivi.ru embed',
100 'title': 'Книга Илая',
102 'upload_date': '20140626',
104 'skip': 'Only works from Russia',
107 # removed video, just testing that we match the pattern
108 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
109 'only_matching': True,
114 (username
, password
) = self
._get
_login
_info
()
126 request
= compat_urllib_request
.Request('https://login.vk.com/?act=login',
127 compat_urllib_parse
.urlencode(login_form
).encode('utf-8'))
128 login_page
= self
._download
_webpage
(request
, None, note
='Logging in as %s' % username
)
130 if re
.search(r
'onLoginFailed', login_page
):
131 raise ExtractorError('Unable to login, incorrect username and/or password', expected
=True)
133 def _real_initialize(self
):
136 def _real_extract(self
, url
):
137 mobj
= re
.match(self
._VALID
_URL
, url
)
138 video_id
= mobj
.group('videoid')
141 video_id
= '%s_%s' % (mobj
.group('oid'), mobj
.group('id'))
143 info_url
= 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id
144 info_page
= self
._download
_webpage
(info_url
, video_id
)
147 r
'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
148 'Video %s has been removed from public access due to rightholder complaint.',
150 r
'<!>Please log in or <':
151 'Video %s is only available for registered users, '
152 'use --username and --password options to provide account credentials.',
155 'Video %s does not exist.'
158 for error_re
, error_msg
in ERRORS
.items():
159 if re
.search(error_re
, info_page
):
160 raise ExtractorError(error_msg
% video_id
, expected
=True)
162 m_yt
= re
.search(r
'src="(http://www.youtube.com/.*?)"', info_page
)
164 self
.to_screen('Youtube video detected')
165 return self
.url_result(m_yt
.group(1), 'Youtube')
167 m_rutube
= re
.search(
168 r
'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page
)
169 if m_rutube
is not None:
170 self
.to_screen('rutube video detected')
171 rutube_url
= self
._proto
_relative
_url
(
172 m_rutube
.group(1).replace('\\', ''))
173 return self
.url_result(rutube_url
)
175 m_opts
= re
.search(r
'(?s)var\s+opts\s*=\s*({.*?});', info_page
)
177 m_opts_url
= re
.search(r
"url\s*:\s*'([^']+)", m_opts
.group(1))
179 opts_url
= m_opts_url
.group(1)
180 if opts_url
.startswith('//'):
181 opts_url
= 'http:' + opts_url
182 return self
.url_result(opts_url
)
184 data_json
= self
._search
_regex
(r
'var vars = ({.*?});', info_page
, 'vars')
185 data
= json
.loads(data_json
)
187 # Extract upload date
189 mobj
= re
.search(r
'id="mv_date_wrap".*?Added ([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page
)
191 mobj
.group(1) + ' ' + mobj
.group(2)
192 upload_date
= unified_strdate(mobj
.group(1) + ' ' + mobj
.group(2))
197 'width': int(k
[len('url'):]),
198 } for k
, v
in data
.items()
199 if k
.startswith('url')]
200 self
._sort
_formats
(formats
)
203 'id': compat_str(data
['vid']),
205 'title': unescapeHTML(data
['md_title']),
206 'thumbnail': data
.get('jpg'),
207 'uploader': data
.get('md_author'),
208 'duration': data
.get('duration'),
209 'upload_date': upload_date
,
213 class VKUserVideosIE(InfoExtractor
):
214 IE_NAME
= 'vk.com:user-videos'
215 IE_DESC
= 'vk.com:All of a user\'s videos'
216 _VALID_URL
= r
'https?://vk\.com/videos(?P<id>[0-9]+)(?:m\?.*)?'
217 _TEMPLATE_URL
= 'https://vk.com/videos'
219 'url': 'http://vk.com/videos205387401',
220 'playlist_mincount': 4,
223 def _real_extract(self
, url
):
224 page_id
= self
._match
_id
(url
)
225 page
= self
._download
_webpage
(url
, page_id
)
226 video_ids
= orderedSet(
227 m
.group(1) for m
in re
.finditer(r
'href="/video([0-9_]+)"', page
))
230 'http://vk.com/video' + video_id
, 'VK', video_id
=video_id
)
231 for video_id
in video_ids
]
232 return self
.playlist_result(url_entries
, page_id
)