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

   1 # coding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 import re
   6
   7 from .common import InfoExtractor
   8
   9
  10 class JeuxVideoIE(InfoExtractor):
  11     _VALID_URL = r'https?://.*?\.jeuxvideo\.com/.*/(.*?)\.htm'
  12
  13     _TESTS = [{
  14         'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
  15         'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
  16         'info_dict': {
  17             'id': '114765',
  18             'ext': 'mp4',
  19             'title': 'Tearaway : GC 2013 : Tearaway nous présente ses papiers d\'identité',
  20             'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.',
  21         },
  22     }, {
  23         'url': 'http://www.jeuxvideo.com/videos/chroniques/434220/l-histoire-du-jeu-video-la-saturn.htm',
  24         'only_matching': True,
  25     }]
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         title = mobj.group(1)
  30         webpage = self._download_webpage(url, title)
  31         title = self._html_search_meta('name', webpage) or self._og_search_title(webpage)
  32         config_url = self._html_search_regex(
  33             r'data-src(?:set-video)?="(/contenu/medias/video\.php.*?)"',
  34             webpage, 'config URL')
  35         config_url = 'http://www.jeuxvideo.com' + config_url
  36
  37         video_id = self._search_regex(
  38             r'id=(\d+)',
  39             config_url, 'video ID')
  40
  41         config = self._download_json(
  42             config_url, title, 'Downloading JSON config')
  43
  44         formats = [{
  45             'url': source['file'],
  46             'format_id': source['label'],
  47             'resolution': source['label'],
  48         } for source in reversed(config['sources'])]
  49
  50         return {
  51             'id': video_id,
  52             'title': title,
  53             'formats': formats,
  54             'description': self._og_search_description(webpage),
  55             'thumbnail': config.get('image'),
  56         }