Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/jeuxvideo.py

   1 # coding: utf-8
   2
   3 import json
   4 import re
   5 import xml.etree.ElementTree
   6
   7 from .common import InfoExtractor
   8
   9 class JeuxVideoIE(InfoExtractor):
  10     _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
  11
  12     _TEST = {
  13         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',
  14         u'file': u'5182.mp4',
  15         u'md5': u'e0fdb0cd3ce98713ef9c1e1e025779d0',
  16         u'info_dict': {
  17             u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
  18             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',
  19         },
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         title = re.match(self._VALID_URL, url).group(1)
  25         webpage = self._download_webpage(url, title)
  26         m_download = re.search(r'<param name="flashvars" value="config=(.*?)" />', webpage)
  27
  28         xml_link = m_download.group(1)
  29
  30         id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1)
  31
  32         xml_config = self._download_webpage(xml_link, title,
  33                                                   'Downloading XML config')
  34         config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
  35         info = re.search(r'<format\.json>(.*?)</format\.json>',
  36                          xml_config, re.MULTILINE|re.DOTALL).group(1)
  37         info = json.loads(info)['versions'][0]
  38
  39         video_url = 'http://video720.jeuxvideo.com/' + info['file']
  40
  41         return {'id': id,
  42                 'title' : config.find('titre_video').text,
  43                 'ext' : 'mp4',
  44                 'url' : video_url,
  45                 'description': self._og_search_description(webpage),
  46                 'thumbnail': config.find('image').text,
  47                 }