youtube_dl/extractor/anitube.py

   1 import re
   2 import xml.etree.ElementTree
   3
   4 from .common import InfoExtractor
   5
   6
   7 class AnitubeIE(InfoExtractor):
   8     IE_NAME = u'anitube.se'
   9     _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
  10
  11     _TEST = {
  12         u'url': u'http://www.anitube.se/video/36621',
  13         u'md5': u'59d0eeae28ea0bc8c05e7af429998d43',
  14         u'file': u'36621.mp4',
  15         u'info_dict': {
  16             u'id': u'36621',
  17             u'ext': u'mp4',
  18             u'title': u'Recorder to Randoseru 01',
  19         },
  20         u'skip': u'Blocked in the US',
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26
  27         webpage = self._download_webpage(url, video_id)
  28         key = self._html_search_regex(r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)',
  29                                       webpage, u'key')
  30
  31         webpage_config = self._download_webpage('http://www.anitube.se/nuevo/econfig.php?key=%s' % key,
  32                                                 key)
  33         config_xml = xml.etree.ElementTree.fromstring(webpage_config.encode('utf-8'))
  34
  35         video_title = config_xml.find('title').text
  36
  37         formats = []
  38         video_url = config_xml.find('file')
  39         if video_url is not None:
  40             formats.append({
  41                 'format_id': 'sd',
  42                 'url': video_url.text,
  43             })
  44         video_url = config_xml.find('filehd')
  45         if video_url is not None:
  46             formats.append({
  47                 'format_id': 'hd',
  48                 'url': video_url.text,
  49             })
  50
  51         return {
  52             'id': video_id,
  53             'title': video_title,
  54             'formats': formats
  55         }