_ Git - youtube-dl/blob - youtube_dl/extractor/tele5.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from .nexx import NexxIE
   8
   9
  10 class Tele5IE(InfoExtractor):
  11     _VALID_URL = r'https://www\.tele5\.de/(?:mediathek/filme-online/videos\?vid=|tv/)(?P<display_id>[\w-]+)'
  12
  13     _TESTS = [{
  14         'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1550589',
  15         'info_dict': {
  16             'id': '1550589',
  17             'ext': 'mp4',
  18             'upload_date': '20180822',
  19             'timestamp': 1534927316,
  20             'title': 'SchleFaZ: Atomic Shark',
  21         }
  22     }, {
  23         'url': 'https://www.tele5.de/tv/dark-matter/videos',
  24         'only_matching': True,
  25     }]
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         display_id = mobj.group('display_id')
  30
  31         webpage = self._download_webpage(url, display_id)
  32
  33         video_id = self._html_search_regex(
  34             r'id\s*=\s*["\']video-player["\']\s*data-id\s*=\s*["\']([0-9]+)["\']',
  35             webpage, 'video_id')
  36
  37         return self.url_result(
  38             'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id,
  39             ie=NexxIE.ie_key(), video_id=video_id)