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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6
   7 from .common import InfoExtractor
   8 from .kaltura import KalturaIE
   9
  10
  11 class AZMedienIE(InfoExtractor):
  12     IE_DESC = 'AZ Medien videos'
  13     _VALID_URL = r'''(?x)
  14                     https?://
  15                         (?:www\.)?
  16                         (?P<host>
  17                             telezueri\.ch|
  18                             telebaern\.tv|
  19                             telem1\.ch
  20                         )/
  21                         [^/]+/
  22                         (?P<id>
  23                             [^/]+-(?P<article_id>\d+)
  24                         )
  25                         (?:
  26                             \#video=
  27                             (?P<kaltura_id>
  28                                 [_0-9a-z]+
  29                             )
  30                         )?
  31                     '''
  32
  33     _TESTS = [{
  34         'url': 'https://www.telezueri.ch/sonntalk/bundesrats-vakanzen-eu-rahmenabkommen-133214569',
  35         'info_dict': {
  36             'id': '1_anruz3wy',
  37             'ext': 'mp4',
  38             'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen',
  39             'description': 'md5:dd9f96751ec9c35e409a698a328402f3',
  40             'uploader_id': 'TVOnline',
  41             'upload_date': '20180930',
  42             'timestamp': 1538328802,
  43         },
  44         'params': {
  45             'skip_download': True,
  46         },
  47     }, {
  48         'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
  49         'only_matching': True
  50     }]
  51
  52     _PARTNER_ID = '1719221'
  53
  54     def _real_extract(self, url):
  55         mobj = re.match(self._VALID_URL, url)
  56         video_id = mobj.group('id')
  57         entry_id = mobj.group('kaltura_id')
  58
  59         if not entry_id:
  60             webpage = self._download_webpage(url, video_id)
  61             api_path = self._search_regex(
  62                 r'["\']apiPath["\']\s*:\s*["\']([^"^\']+)["\']',
  63                 webpage, 'api path')
  64             api_url = 'https://www.%s%s' % (mobj.group('host'), api_path)
  65             payload = {
  66                 'query': '''query VideoContext($articleId: ID!) {
  67                     article: node(id: $articleId) {
  68                       ... on Article {
  69                         mainAssetRelation {
  70                           asset {
  71                             ... on VideoAsset {
  72                               kalturaId
  73                             }
  74                           }
  75                         }
  76                       }
  77                     }
  78                   }''',
  79                 'variables': {'articleId': 'Article:%s' % mobj.group('article_id')},
  80             }
  81             json_data = self._download_json(
  82                 api_url, video_id, headers={
  83                     'Content-Type': 'application/json',
  84                 },
  85                 data=json.dumps(payload).encode())
  86             entry_id = json_data['data']['article']['mainAssetRelation']['asset']['kalturaId']
  87
  88         return self.url_result(
  89             'kaltura:%s:%s' % (self._PARTNER_ID, entry_id),
  90             ie=KalturaIE.ie_key(), video_id=entry_id)