yt_dlp/extractor/azmedien.py

   1 import json
   2
   3 from .common import InfoExtractor
   4 from .kaltura import KalturaIE
   5
   6
   7 class AZMedienIE(InfoExtractor):
   8     IE_DESC = 'AZ Medien videos'
   9     _VALID_URL = r'''(?x)
  10                     https?://
  11                         (?:www\.|tv\.)?
  12                         (?P<host>
  13                             telezueri\.ch|
  14                             telebaern\.tv|
  15                             telem1\.ch|
  16                             tvo-online\.ch
  17                         )/
  18                         [^/]+/
  19                         (?P<id>
  20                             [^/]+-(?P<article_id>\d+)
  21                         )
  22                         (?:
  23                             \#video=
  24                             (?P<kaltura_id>
  25                                 [_0-9a-z]+
  26                             )
  27                         )?
  28                     '''
  29
  30     _TESTS = [{
  31         'url': 'https://tv.telezueri.ch/sonntalk/bundesrats-vakanzen-eu-rahmenabkommen-133214569',
  32         'info_dict': {
  33             'id': '1_anruz3wy',
  34             'ext': 'mp4',
  35             'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen',
  36             'uploader_id': 'TVOnline',
  37             'upload_date': '20180930',
  38             'timestamp': 1538328802,
  39             'view_count': int,
  40             'thumbnail': 'http://cfvod.kaltura.com/p/1719221/sp/171922100/thumbnail/entry_id/1_anruz3wy/version/100031',
  41             'duration': 1930,
  42         },
  43         'params': {
  44             'skip_download': True,
  45         },
  46     }, {
  47         'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
  48         'only_matching': True,
  49     }]
  50     _API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/a4016f65fe62b81dc6664dd9f4910e4ab40383be'
  51     _PARTNER_ID = '1719221'
  52
  53     def _real_extract(self, url):
  54         host, display_id, article_id, entry_id = self._match_valid_url(url).groups()
  55
  56         if not entry_id:
  57             entry_id = self._download_json(
  58                 self._API_TEMPL % (host, host.split('.')[0]), display_id, query={
  59                     'variables': json.dumps({
  60                         'contextId': 'NewsArticle:' + article_id,
  61                     }),
  62                 })['data']['context']['mainAsset']['video']['kaltura']['kalturaId']
  63
  64         return self.url_result(
  65             f'kaltura:{self._PARTNER_ID}:{entry_id}',
  66             ie=KalturaIE.ie_key(), video_id=entry_id)