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
|
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class MailRuIE(InfoExtractor):
IE_NAME = 'mailru'
IE_DESC = 'Видео@Mail.Ru'
_VALID_URL = r'http://(?:www\.)?my\.mail\.ru/video/.*#video=/?(?P<id>[^/]+/[^/]+/[^/]+/\d+)'
_TEST = {
'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
'md5': 'dea205f03120046894db4ebb6159879a',
'info_dict': {
'id': '46301138',
'ext': 'mp4',
'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
'timestamp': 1393232740,
'upload_date': '20140224',
'uploader': 'sonypicturesrus',
'uploader_id': 'sonypicturesrus@mail.ru',
'duration': 184,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_data = self._download_json(
'http://videoapi.my.mail.ru/videos/%s.json?new=1' % video_id, video_id, 'Downloading video JSON')
author = video_data['author']
uploader = author['name']
uploader_id = author['id']
movie = video_data['movie']
content_id = str(movie['contentId'])
title = movie['title']
thumbnail = movie['poster']
duration = movie['duration']
view_count = video_data['views_count']
formats = [
{
'url': video['url'],
'format_id': video['name'],
} for video in video_data['videos']
]
return {
'id': content_id,
'title': title,
'thumbnail': thumbnail,
'timestamp': video_data['timestamp'],
'uploader': uploader,
'uploader_id': uploader_id,
'duration': duration,
'view_count': view_count,
'formats': formats,
}
|