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
|
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
from ..utils import (
unified_strdate,
int_or_none,
qualities,
unescapeHTML,
)
class OdnoklassnikiIE(InfoExtractor):
_VALID_URL = r'https?://(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
_TESTS = [{
# metadata in JSON
'url': 'http://ok.ru/video/20079905452',
'md5': '8e24ad2da6f387948e7a7d44eb8668fe',
'info_dict': {
'id': '20079905452',
'ext': 'mp4',
'title': 'Культура меняет нас (прекрасный ролик!))',
'duration': 100,
'uploader_id': '330537914540',
'uploader': 'Виталий Добровольский',
'like_count': int,
'age_limit': 0,
},
}, {
# metadataUrl
'url': 'http://ok.ru/video/63567059965189-0',
'md5': '9676cf86eff5391d35dea675d224e131',
'info_dict': {
'id': '63567059965189-0',
'ext': 'mp4',
'title': 'Девушка без комплексов ...',
'duration': 191,
'uploader_id': '534380003155',
'uploader': 'Андрей Мещанинов',
'like_count': int,
'age_limit': 0,
},
}, {
'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://ok.ru/video/%s' % video_id, video_id)
player = self._parse_json(
unescapeHTML(self._search_regex(
r'data-attributes="([^"]+)"', webpage, 'player')),
video_id)
flashvars = player['flashvars']
metadata = flashvars.get('metadata')
if metadata:
metadata = self._parse_json(metadata, video_id)
else:
metadata = self._download_json(
compat_urllib_parse_unquote(flashvars['metadataUrl']),
video_id, 'Downloading metadata JSON')
movie = metadata['movie']
title = movie['title']
thumbnail = movie.get('poster')
duration = int_or_none(movie.get('duration'))
author = metadata.get('author', {})
uploader_id = author.get('id')
uploader = author.get('name')
upload_date = unified_strdate(self._html_search_meta(
'ya:ovs:upload_date', webpage, 'upload date', default=None))
age_limit = None
adult = self._html_search_meta(
'ya:ovs:adult', webpage, 'age limit', default=None)
if adult:
age_limit = 18 if adult == 'true' else 0
like_count = int_or_none(metadata.get('likeCount'))
quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
formats = [{
'url': f['url'],
'ext': 'mp4',
'format_id': f['name'],
'quality': quality(f['name']),
} for f in metadata['videos']]
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'upload_date': upload_date,
'uploader': uploader,
'uploader_id': uploader_id,
'like_count': like_count,
'age_limit': age_limit,
'formats': formats,
}
|
