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
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
|
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none
)
class VestiIE(InfoExtractor):
IE_NAME = 'vesti'
IE_DESC = 'Вести.Ru'
_VALID_URL = r'http://(?:.+?\.)?vesti\.ru/(?P<id>.+)'
_TESTS = [
{
'url': 'http://www.vesti.ru/videos?vid=575582&cid=1',
'info_dict': {
'id': '765035',
'ext': 'mp4',
'title': 'Вести.net: биткоины в России не являются законными',
'description': 'md5:d4bb3859dc1177b28a94c5014c35a36b',
'duration': 302,
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://www.vesti.ru/only_video.html?vid=576180',
'info_dict': {
'id': '766048',
'ext': 'mp4',
'title': 'США заморозило, Британию затопило',
'description': 'md5:f0ed0695ec05aed27c56a70a58dc4cc1',
'duration': 87,
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://sochi2014.vesti.ru/video/index/video_id/766403',
'info_dict': {
'id': '766403',
'ext': 'mp4',
'title': 'XXII зимние Олимпийские игры. Российские хоккеисты стартовали на Олимпиаде с победы',
'description': 'md5:55805dfd35763a890ff50fa9e35e31b3',
'duration': 271,
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://sochi2014.vesti.ru/live/play/live_id/301',
'info_dict': {
'id': '51499',
'ext': 'flv',
'title': 'Сочи-2014. Биатлон. Индивидуальная гонка. Мужчины ',
'description': 'md5:9e0ed5c9d2fa1efbfdfed90c9a6d179c',
},
'params': {
# rtmp download
'skip_download': True,
},
'skip': 'Translation has finished'
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
page = self._download_webpage(url, video_id, 'Downloading page')
mobj = re.search(r'<meta property="og:video" content=".+?\.swf\?v?id=(?P<id>\d+).*?" />', page)
if mobj:
video_type = 'video'
video_id = mobj.group('id')
else:
mobj = re.search(
r'<div.+?id="current-video-holder".*?>\s*<iframe src="http://player\.rutv\.ru/iframe/(?P<type>[^/]+)/id/(?P<id>\d+)[^"]*"',
page)
if not mobj:
raise ExtractorError('No media found')
video_type = mobj.group('type')
video_id = mobj.group('id')
json_data = self._download_json(
'http://player.rutv.ru/iframe/%splay/id/%s' % ('live-' if video_type == 'live' else '', video_id),
video_id, 'Downloading JSON')
if json_data['errors']:
raise ExtractorError('vesti returned error: %s' % json_data['errors'], expected=True)
playlist = json_data['data']['playlist']
medialist = playlist['medialist']
media = medialist[0]
if media['errors']:
raise ExtractorError('vesti returned error: %s' % media['errors'], expected=True)
view_count = playlist.get('count_views')
priority_transport = playlist['priority_transport']
thumbnail = media['picture']
width = media['width']
height = media['height']
description = media['anons']
title = media['title']
duration = int_or_none(media.get('duration'))
formats = []
for transport, links in media['sources'].items():
for quality, url in links.items():
if transport == 'rtmp':
mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>.+)$', url)
if not mobj:
continue
fmt = {
'url': mobj.group('url'),
'play_path': mobj.group('playpath'),
'app': mobj.group('app'),
'page_url': 'http://player.rutv.ru',
'player_url': 'http://player.rutv.ru/flash2v/osmf.swf?i=22',
'rtmp_live': True,
'ext': 'flv',
'vbr': int(quality),
}
elif transport == 'm3u8':
fmt = {
'url': url,
'ext': 'mp4',
}
else:
fmt = {
'url': url
}
fmt.update({
'width': width,
'height': height,
'format_id': '%s-%s' % (transport, quality),
'preference': -1 if priority_transport == transport else -2,
})
formats.append(fmt)
if not formats:
raise ExtractorError('No media links available for %s' % video_id)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'view_count': view_count,
'duration': duration,
'formats': formats,
}
|
