_ Git - youtube-dl/blob - youtube_dl/extractor/ign.py

   1 import re
   2 import json
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     determine_ext,
   7 )
   8
   9 class IGNIE(InfoExtractor):
  10     _VALID_URL = r'http://www.ign.com/videos/.+/(?P<name>.+)'
  11     IE_NAME = u'ign.com'
  12
  13     _TEST = {
  14         u'url': u'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
  15         u'file': u'8f862beef863986b2785559b9e1aa599.mp4',
  16         u'md5': u'eac8bdc1890980122c3b66f14bdd02e9',
  17         u'info_dict': {
  18             u'title': u'The Last of Us Review',
  19             u'description': u'md5:c8946d4260a4d43a00d5ae8ed998870c',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         name = mobj.group('name')
  26         config_url = url + '.config'
  27         webpage = self._download_webpage(url, name)
  28         config = json.loads(self._download_webpage(config_url, name, u'Downloading video info'))
  29
  30         self.report_extraction(name)
  31         description = self._html_search_regex(r'<span class="page-object-description">(.+?)</span>',
  32                                               webpage, 'video description', flags=re.DOTALL)
  33         media = config['playlist']['media']
  34         video_url = media['url']
  35
  36         return {'id': media['metadata']['videoId'],
  37                 'url': video_url,
  38                 'ext': determine_ext(video_url),
  39                 'title': media['metadata']['title'],
  40                 'description': description,
  41                 'thumbnail': media['poster'][0]['url'].replace('{size}', 'small'),
  42                 }
  43
  44
  45