youtube_dl/extractor/tutv.py

   1 from __future__ import unicode_literals
   2
   3 import base64
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import compat_parse_qs
   8
   9
  10 class TutvIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)'
  12     _TEST = {
  13         'url': 'http://tu.tv/videos/robots-futbolistas',
  14         'md5': '627c7c124ac2a9b5ab6addb94e0e65f7',
  15         'info_dict': {
  16             'id': '2973058',
  17             'ext': 'flv',
  18             'title': 'Robots futbolistas',
  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         internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID')
  28
  29         data_content = self._download_webpage(
  30             'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info')
  31         video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8')
  32
  33         return {
  34             'id': internal_id,
  35             'url': video_url,
  36             'title': self._og_search_title(webpage),
  37         }