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

   1 from __future__ import unicode_literals
   2
   3 import base64
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_parse_qs
   7
   8
   9 class TutvIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)'
  11     _TEST = {
  12         'url': 'http://tu.tv/videos/robots-futbolistas',
  13         'md5': '0cd9e28ad270488911b0d2a72323395d',
  14         'info_dict': {
  15             'id': '2973058',
  16             'ext': 'mp4',
  17             'title': 'Robots futbolistas',
  18         },
  19     }
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23         webpage = self._download_webpage(url, video_id)
  24
  25         internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID')
  26
  27         data_content = self._download_webpage(
  28             'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info')
  29         video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0].encode('utf-8')).decode('utf-8')
  30
  31         return {
  32             'id': internal_id,
  33             'url': video_url,
  34             'title': self._og_search_title(webpage),
  35         }