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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_b64decode,
   6     compat_parse_qs,
   7 )
   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': '0cd9e28ad270488911b0d2a72323395d',
  15         'info_dict': {
  16             'id': '2973058',
  17             'ext': 'mp4',
  18             'title': 'Robots futbolistas',
  19         },
  20     }
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24         webpage = self._download_webpage(url, video_id)
  25
  26         internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID')
  27
  28         data_content = self._download_webpage(
  29             'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info')
  30         video_url = compat_b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8')
  31
  32         return {
  33             'id': internal_id,
  34             'url': video_url,
  35             'title': self._og_search_title(webpage),
  36         }