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

   1 from __future__ import unicode_literals
   2 import base64
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_parse_qs,
   8 )
   9
  10
  11 class TutvIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)'
  13     _TEST = {
  14         'url': 'http://tu.tv/videos/noah-en-pabellon-cuahutemoc',
  15         'file': '2742556.flv',
  16         'md5': '5eb766671f69b82e528dc1e7769c5cb2',
  17         'info_dict': {
  18             'title': 'Noah en pabellon cuahutemoc',
  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_url = 'http://tu.tv/flvurl.php?codVideo=' + str(internal_id)
  30         data_content = self._download_webpage(data_url, video_id, note='Downloading video info')
  31         data = compat_parse_qs(data_content)
  32         video_url = base64.b64decode(data['kpt'][0]).decode('utf-8')
  33
  34         return {
  35             'id': internal_id,
  36             'url': video_url,
  37             'title': self._og_search_title(webpage),
  38         }