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
  10 class JeuxVideoIE(InfoExtractor):
  11     _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
  12
  13     _TEST = {
  14         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',
  15         u'file': u'5182.mp4',
  16         u'md5': u'046e491afb32a8aaac1f44dd4ddd54ee',
  17         u'info_dict': {
  18             u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
  19             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',
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         title = re.match(self._VALID_URL, url).group(1)
  26         webpage = self._download_webpage(url, title)
  27         xml_link = self._html_search_regex(
  28             r'<param name="flashvars" value="config=(.*?)" />',
  29             webpage, u'config URL')
  30
  31         video_id = self._search_regex(
  32             r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',
  33             xml_link, u'video ID')
  34
  35         xml_config = self._download_webpage(
  36             xml_link, title, u'Downloading XML config')
  37         config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
  38         info_json = self._search_regex(
  39             r'(?sm)<format\.json>(.*?)</format\.json>',
  40             xml_config, u'JSON information')
  41         info = json.loads(info_json)['versions'][0]
  42
  43         video_url = 'http://video720.jeuxvideo.com/' + info['file']
  44
  45         return {
  46             'id': video_id,
  47             'title': config.find('titre_video').text,
  48             'ext': 'mp4',
  49             'url': video_url,
  50             'description': self._og_search_description(webpage),
  51             'thumbnail': config.find('image').text,
  52         }