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
|
# coding: utf-8
import json
import re
import xml.etree.ElementTree
from .common import InfoExtractor
class JeuxVideoIE(InfoExtractor):
_VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
_TEST = {
u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
u'file': u'5182.mp4',
u'md5': u'046e491afb32a8aaac1f44dd4ddd54ee',
u'info_dict': {
u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = re.match(self._VALID_URL, url).group(1)
webpage = self._download_webpage(url, title)
m_download = re.search(r'<param name="flashvars" value="config=(.*?)" />', webpage)
xml_link = m_download.group(1)
id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1)
xml_config = self._download_webpage(xml_link, title,
'Downloading XML config')
config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
info = re.search(r'<format\.json>(.*?)</format\.json>',
xml_config, re.MULTILINE|re.DOTALL).group(1)
info = json.loads(info)['versions'][0]
video_url = 'http://video720.jeuxvideo.com/' + info['file']
return {'id': id,
'title' : config.find('titre_video').text,
'ext' : 'mp4',
'url' : video_url,
'description': self._og_search_description(webpage),
'thumbnail': config.find('image').text,
}
|
