youtube_dl/extractor/tutv.py

   1 import base64
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_parse_qs,
   7 )
   8
   9 class TutvIE(InfoExtractor):
  10     _VALID_URL=r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)'
  11     _TEST = {
  12         u'url': u'http://tu.tv/videos/noah-en-pabellon-cuahutemoc',
  13         u'file': u'2742556.flv',
  14         u'md5': u'5eb766671f69b82e528dc1e7769c5cb2',
  15         u'info_dict': {
  16             u"title": u"Noah en pabellon cuahutemoc"
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         mobj = re.match(self._VALID_URL, url)
  22         video_id = mobj.group('id')
  23
  24         webpage = self._download_webpage(url, video_id)
  25         internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, u'internal video ID')
  26
  27         data_url = u'http://tu.tv/flvurl.php?codVideo=' + str(internal_id)
  28         data_content = self._download_webpage(data_url, video_id, note=u'Downloading video info')
  29         data = compat_parse_qs(data_content)
  30         video_url = base64.b64decode(data['kpt'][0]).decode('utf-8')
  31         ext = video_url.partition(u'?')[0].rpartition(u'.')[2]
  32
  33         info = {
  34             'id': internal_id,
  35             'url': video_url,
  36             'ext': ext,
  37             'title': self._og_search_title(webpage),
  38         }
  39         return [info]