aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/azmedien.py
blob: fcbdc71b98d98076852e0f88559f4a2ed428d7af (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
# coding: utf-8
from __future__ import unicode_literals

import json
import re

from .common import InfoExtractor
from .kaltura import KalturaIE


class AZMedienIE(InfoExtractor):
    IE_DESC = 'AZ Medien videos'
    _VALID_URL = r'''(?x)
                    https?://
                        (?:www\.)?
                        (?P<host>
                            telezueri\.ch|
                            telebaern\.tv|
                            telem1\.ch
                        )/
                        [^/]+/
                        (?P<id>
                            [^/]+-(?P<article_id>\d+)
                        )
                        (?:
                            \#video=
                            (?P<kaltura_id>
                                [_0-9a-z]+
                            )
                        )?
                    '''

    _TESTS = [{
        'url': 'https://www.telezueri.ch/sonntalk/bundesrats-vakanzen-eu-rahmenabkommen-133214569',
        'info_dict': {
            'id': '1_anruz3wy',
            'ext': 'mp4',
            'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen',
            'uploader_id': 'TVOnline',
            'upload_date': '20180930',
            'timestamp': 1538328802,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
        'only_matching': True
    }]

    _PARTNER_ID = '1719221'

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        host = mobj.group('host')
        video_id = mobj.group('id')
        entry_id = mobj.group('kaltura_id')

        if not entry_id:
            api_url = 'https://www.%s/api/pub/gql/%s' % (host, host.split('.')[0])
            payload = {
                'query': '''query VideoContext($articleId: ID!) {
                    article: node(id: $articleId) {
                      ... on Article {
                        mainAssetRelation {
                          asset {
                            ... on VideoAsset {
                              kalturaId
                            }
                          }
                        }
                      }
                    }
                  }''',
                'variables': {'articleId': 'Article:%s' % mobj.group('article_id')},
            }
            json_data = self._download_json(
                api_url, video_id, headers={
                    'Content-Type': 'application/json',
                },
                data=json.dumps(payload).encode())
            entry_id = json_data['data']['article']['mainAssetRelation']['asset']['kalturaId']

        return self.url_result(
            'kaltura:%s:%s' % (self._PARTNER_ID, entry_id),
            ie=KalturaIE.ie_key(), video_id=entry_id)