yt_dlp/extractor/azmedien.py

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