]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tonline.py
New upstream version 2020.03.24
[youtubedl] / youtube_dl / extractor / tonline.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import int_or_none
6
7
8 class TOnlineIE(InfoExtractor):
9 IE_NAME = 't-online.de'
10 _VALID_URL = r'https?://(?:www\.)?t-online\.de/tv/(?:[^/]+/)*id_(?P<id>\d+)'
11 _TEST = {
12 'url': 'http://www.t-online.de/tv/sport/fussball/id_79166266/drittes-remis-zidane-es-muss-etwas-passieren-.html',
13 'md5': '7d94dbdde5f9d77c5accc73c39632c29',
14 'info_dict': {
15 'id': '79166266',
16 'ext': 'mp4',
17 'title': 'Drittes Remis! Zidane: "Es muss etwas passieren"',
18 'description': 'Es läuft nicht rund bei Real Madrid. Das 1:1 gegen den SD Eibar war das dritte Unentschieden in Folge in der Liga.',
19 }
20 }
21
22 def _real_extract(self, url):
23 video_id = self._match_id(url)
24 video_data = self._download_json(
25 'http://www.t-online.de/tv/id_%s/tid_json_video' % video_id, video_id)
26 title = video_data['subtitle']
27
28 formats = []
29 for asset in video_data.get('assets', []):
30 asset_source = asset.get('source') or asset.get('source2')
31 if not asset_source:
32 continue
33 formats_id = []
34 for field_key in ('type', 'profile'):
35 field_value = asset.get(field_key)
36 if field_value:
37 formats_id.append(field_value)
38 formats.append({
39 'format_id': '-'.join(formats_id),
40 'url': asset_source,
41 })
42
43 thumbnails = []
44 for image in video_data.get('images', []):
45 image_source = image.get('source')
46 if not image_source:
47 continue
48 thumbnails.append({
49 'url': image_source,
50 })
51
52 return {
53 'id': video_id,
54 'title': title,
55 'description': video_data.get('description'),
56 'duration': int_or_none(video_data.get('duration')),
57 'thumbnails': thumbnails,
58 'formats': formats,
59 }