]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vesti.py
debian/NEWS: Add link to my webpage to give more details.
[youtubedl] / youtube_dl / extractor / vesti.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 ExtractorError,
9 int_or_none
10 )
11
12
13 class VestiIE(InfoExtractor):
14 IE_NAME = 'vesti'
15 IE_DESC = 'Вести.Ru'
16 _VALID_URL = r'http://(?:.+?\.)?vesti\.ru/(?P<id>.+)'
17
18 _TESTS = [
19 {
20 'url': 'http://www.vesti.ru/videos?vid=575582&cid=1',
21 'info_dict': {
22 'id': '765035',
23 'ext': 'mp4',
24 'title': 'Вести.net: биткоины в России не являются законными',
25 'description': 'md5:d4bb3859dc1177b28a94c5014c35a36b',
26 'duration': 302,
27 },
28 'params': {
29 # m3u8 download
30 'skip_download': True,
31 },
32 },
33 {
34 'url': 'http://www.vesti.ru/only_video.html?vid=576180',
35 'info_dict': {
36 'id': '766048',
37 'ext': 'mp4',
38 'title': 'США заморозило, Британию затопило',
39 'description': 'md5:f0ed0695ec05aed27c56a70a58dc4cc1',
40 'duration': 87,
41 },
42 'params': {
43 # m3u8 download
44 'skip_download': True,
45 },
46 },
47 {
48 'url': 'http://sochi2014.vesti.ru/video/index/video_id/766403',
49 'info_dict': {
50 'id': '766403',
51 'ext': 'mp4',
52 'title': 'XXII зимние Олимпийские игры. Российские хоккеисты стартовали на Олимпиаде с победы',
53 'description': 'md5:55805dfd35763a890ff50fa9e35e31b3',
54 'duration': 271,
55 },
56 'params': {
57 # m3u8 download
58 'skip_download': True,
59 },
60 'skip': 'Blocked outside Russia'
61 },
62 {
63 'url': 'http://sochi2014.vesti.ru/live/play/live_id/301',
64 'info_dict': {
65 'id': '51499',
66 'ext': 'flv',
67 'title': 'Сочи-2014. Биатлон. Индивидуальная гонка. Мужчины ',
68 'description': 'md5:9e0ed5c9d2fa1efbfdfed90c9a6d179c',
69 },
70 'params': {
71 # rtmp download
72 'skip_download': True,
73 },
74 'skip': 'Translation has finished'
75 }
76 ]
77
78 def _real_extract(self, url):
79 mobj = re.match(self._VALID_URL, url)
80 video_id = mobj.group('id')
81
82 page = self._download_webpage(url, video_id, 'Downloading page')
83
84 mobj = re.search(r'<meta property="og:video" content=".+?\.swf\?v?id=(?P<id>\d+).*?" />', page)
85 if mobj:
86 video_type = 'video'
87 video_id = mobj.group('id')
88 else:
89 mobj = re.search(
90 r'<iframe.+?src="http://player\.rutv\.ru/iframe/(?P<type>[^/]+)/id/(?P<id>\d+)[^"]*".*?></iframe>', page)
91
92 if not mobj:
93 raise ExtractorError('No media found')
94
95 video_type = mobj.group('type')
96 video_id = mobj.group('id')
97
98 json_data = self._download_json(
99 'http://player.rutv.ru/iframe/%splay/id/%s' % ('live-' if video_type == 'live' else '', video_id),
100 video_id, 'Downloading JSON')
101
102 if json_data['errors']:
103 raise ExtractorError('vesti returned error: %s' % json_data['errors'], expected=True)
104
105 playlist = json_data['data']['playlist']
106 medialist = playlist['medialist']
107 media = medialist[0]
108
109 if media['errors']:
110 raise ExtractorError('vesti returned error: %s' % media['errors'], expected=True)
111
112 view_count = playlist.get('count_views')
113 priority_transport = playlist['priority_transport']
114
115 thumbnail = media['picture']
116 width = media['width']
117 height = media['height']
118 description = media['anons']
119 title = media['title']
120 duration = int_or_none(media.get('duration'))
121
122 formats = []
123
124 for transport, links in media['sources'].items():
125 for quality, url in links.items():
126 if transport == 'rtmp':
127 mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>.+)$', url)
128 if not mobj:
129 continue
130 fmt = {
131 'url': mobj.group('url'),
132 'play_path': mobj.group('playpath'),
133 'app': mobj.group('app'),
134 'page_url': 'http://player.rutv.ru',
135 'player_url': 'http://player.rutv.ru/flash2v/osmf.swf?i=22',
136 'rtmp_live': True,
137 'ext': 'flv',
138 'vbr': int(quality),
139 }
140 elif transport == 'm3u8':
141 fmt = {
142 'url': url,
143 'ext': 'mp4',
144 }
145 else:
146 fmt = {
147 'url': url
148 }
149 fmt.update({
150 'width': width,
151 'height': height,
152 'format_id': '%s-%s' % (transport, quality),
153 'preference': -1 if priority_transport == transport else -2,
154 })
155 formats.append(fmt)
156
157 if not formats:
158 raise ExtractorError('No media links available for %s' % video_id)
159
160 self._sort_formats(formats)
161
162 return {
163 'id': video_id,
164 'title': title,
165 'description': description,
166 'thumbnail': thumbnail,
167 'view_count': view_count,
168 'duration': duration,
169 'formats': formats,
170 }