1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
|
# encoding: utf-8
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
compat_urllib_request,
compat_urllib_parse,
compat_str,
unescapeHTML,
)
class VKIE(InfoExtractor):
IE_NAME = 'vk.com'
_VALID_URL = r'https?://vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))'
_NETRC_MACHINE = 'vk'
_TESTS = [
{
'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
'md5': '0deae91935c54e00003c2a00646315f0',
'info_dict': {
'id': '162222515',
'ext': 'flv',
'title': 'ProtivoGunz - Хуёвая песня',
'uploader': 're:Noize MC.*',
'duration': 195,
},
},
{
'url': 'http://vk.com/video4643923_163339118',
'md5': 'f79bccb5cd182b1f43502ca5685b2b36',
'info_dict': {
'id': '163339118',
'ext': 'mp4',
'uploader': 'Elya Iskhakova',
'title': 'Dream Theater - Hollow Years Live at Budokan 720*',
'duration': 558,
}
},
{
'note': 'Embedded video',
'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
'info_dict': {
'id': '162925554',
'ext': 'mp4',
'uploader': 'Vladimir Gavrin',
'title': 'Lin Dan',
'duration': 101,
}
},
{
'url': 'http://vk.com/video-8871596_164049491',
'md5': 'a590bcaf3d543576c9bd162812387666',
'note': 'Only available for registered users',
'info_dict': {
'id': '164049491',
'ext': 'mp4',
'uploader': 'Триллеры',
'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
'duration': 8352,
},
'skip': 'Requires vk account credentials',
},
{
'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
'md5': 'd82c22e449f036282d1d3f7f4d276869',
'info_dict': {
'id': '166094326',
'ext': 'mp4',
'uploader': 'Киномания - лучшее из мира кино',
'title': 'Запах женщины (1992)',
'duration': 9392,
},
'skip': 'Requires vk account credentials',
},
{
'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
'md5': '4d7a5ef8cf114dfa09577e57b2993202',
'info_dict': {
'id': '168067957',
'ext': 'mp4',
'uploader': 'Киномания - лучшее из мира кино',
'title': ' ',
'duration': 7291,
},
'skip': 'Requires vk account credentials',
},
]
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
login_form = {
'act': 'login',
'role': 'al_frame',
'expire': '1',
'email': username,
'pass': password,
}
request = compat_urllib_request.Request('https://login.vk.com/?act=login',
compat_urllib_parse.urlencode(login_form).encode('utf-8'))
login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
if re.search(r'onLoginFailed', login_page):
raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)
def _real_initialize(self):
self._login()
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
if not video_id:
video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
info_url = 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id
info_page = self._download_webpage(info_url, video_id)
if re.search(r'<!>Please log in or <', info_page):
raise ExtractorError('This video is only available for registered users, '
'use --username and --password options to provide account credentials.', expected=True)
m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
if m_yt is not None:
self.to_screen('Youtube video detected')
return self.url_result(m_yt.group(1), 'Youtube')
data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars')
data = json.loads(data_json)
formats = [{
'format_id': k,
'url': v,
'width': int(k[len('url'):]),
} for k, v in data.items()
if k.startswith('url')]
self._sort_formats(formats)
return {
'id': compat_str(data['vid']),
'formats': formats,
'title': unescapeHTML(data['md_title']),
'thumbnail': data.get('jpg'),
'uploader': data.get('md_author'),
'duration': data.get('duration')
}
|
