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

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class AnitubeIE(InfoExtractor):
   7     IE_NAME = u'anitube.se'
   8     _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
   9
  10     _TEST = {
  11         u'url': u'http://www.anitube.se/video/36621',
  12         u'md5': u'59d0eeae28ea0bc8c05e7af429998d43',
  13         u'file': u'36621.mp4',
  14         u'info_dict': {
  15             u'id': u'36621',
  16             u'ext': u'mp4',
  17             u'title': u'Recorder to Randoseru 01',
  18         },
  19         u'skip': u'Blocked in the US',
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group('id')
  25
  26         webpage = self._download_webpage(url, video_id)
  27         key = self._html_search_regex(r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)',
  28                                       webpage, u'key')
  29
  30         config_xml = self._download_xml('http://www.anitube.se/nuevo/econfig.php?key=%s' % key,
  31                                                 key)
  32
  33         video_title = config_xml.find('title').text
  34
  35         formats = []
  36         video_url = config_xml.find('file')
  37         if video_url is not None:
  38             formats.append({
  39                 'format_id': 'sd',
  40                 'url': video_url.text,
  41             })
  42         video_url = config_xml.find('filehd')
  43         if video_url is not None:
  44             formats.append({
  45                 'format_id': 'hd',
  46                 'url': video_url.text,
  47             })
  48
  49         return {
  50             'id': video_id,
  51             'title': video_title,
  52             'formats': formats
  53         }