Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tele5.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from .nexx import NexxIE
   6 from ..compat import compat_urlparse
   7
   8
   9 class Tele5IE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:mediathek|tv)/(?P<id>[^?#&]+)'
  11     _TESTS = [{
  12         'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416',
  13         'info_dict': {
  14             'id': '1549416',
  15             'ext': 'mp4',
  16             'upload_date': '20180814',
  17             'timestamp': 1534290623,
  18             'title': 'Pandorum',
  19         },
  20         'params': {
  21             'skip_download': True,
  22         },
  23     }, {
  24         'url': 'https://www.tele5.de/tv/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
  25         'only_matching': True,
  26     }, {
  27         'url': 'https://www.tele5.de/tv/dark-matter/videos',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
  33         video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0]
  34
  35         if not video_id:
  36             display_id = self._match_id(url)
  37             webpage = self._download_webpage(url, display_id)
  38             video_id = self._html_search_regex(
  39                 r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)',
  40                 webpage, 'video id')
  41
  42         return self.url_result(
  43             'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id,
  44             ie=NexxIE.ie_key(), video_id=video_id)