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     }
  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         webpage_config = self._download_webpage('http://www.anitube.se/nuevo/econfig.php?key=%s' % key,
  31                                                 key)
  32         config_xml = xml.etree.ElementTree.fromstring(webpage_config.encode('utf-8'))
  33
  34         video_title = config_xml.find('title').text
  35
  36         formats = []
  37         video_url = config_xml.find('file')
  38         if video_url is not None:
  39             formats.append({
  40                 'format_id': 'sd',
  41                 'url': video_url.text,
  42             })
  43         video_url = config_xml.find('filehd')
  44         if video_url is not None:
  45             formats.append({
  46                 'format_id': 'hd',
  47                 'url': video_url.text,
  48             })
  49
  50         return {
  51             'id': video_id,
  52             'title': video_title,
  53             'formats': formats
  54         }