aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/expressen.py
blob: f61178012feb4db017e3c96f18ec4959ac3f4f42 (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
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    int_or_none,
    unescapeHTML,
    unified_timestamp,
)


class ExpressenIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?expressen\.se/tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
    _TESTS = [{
        'url': 'https://www.expressen.se/tv/ledare/ledarsnack/ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden/',
        'md5': '2fbbe3ca14392a6b1b36941858d33a45',
        'info_dict': {
            'id': '8690962',
            'ext': 'mp4',
            'title': 'Ledarsnack: Om arbetslösheten bland kvinnor i speciellt utsatta områden',
            'description': 'md5:f38c81ff69f3de4d269bbda012fcbbba',
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 788,
            'timestamp': 1526639109,
            'upload_date': '20180518',
        },
    }, {
        'url': 'https://www.expressen.se/tv/kultur/kulturdebatt-med-expressens-karin-olsson/',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        display_id = self._match_id(url)

        webpage = self._download_webpage(url, display_id)

        def extract_data(name):
            return self._parse_json(
                self._search_regex(
                    r'data-%s=(["\'])(?P<value>(?:(?!\1).)+)\1' % name,
                    webpage, 'info', group='value'),
                display_id, transform_source=unescapeHTML)

        info = extract_data('video-tracking-info')
        video_id = info['videoId']

        data = extract_data('article-data')
        stream = data['stream']

        if determine_ext(stream) == 'm3u8':
            formats = self._extract_m3u8_formats(
                stream, display_id, 'mp4', entry_protocol='m3u8_native',
                m3u8_id='hls')
        else:
            formats = [{
                'url': stream,
            }]
        self._sort_formats(formats)

        title = info.get('titleRaw') or data['title']
        description = info.get('descriptionRaw')
        thumbnail = info.get('socialMediaImage') or data.get('image')
        duration = int_or_none(info.get('videoTotalSecondsDuration') or
                               data.get('totalSecondsDuration'))
        timestamp = unified_timestamp(info.get('publishDate'))

        return {
            'id': video_id,
            'display_id': display_id,
            'title': title,
            'description': description,
            'thumbnail': thumbnail,
            'duration': duration,
            'timestamp': timestamp,
            'formats': formats,
        }