summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/eitb.py
blob: 18b802eb1550eee158c51f827328ea4c6adc2b2b (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
from .common import InfoExtractor
from ..networking import Request
from ..utils import (
    float_or_none,
    int_or_none,
    join_nonempty,
    parse_iso8601,
)


class EitbIE(InfoExtractor):
    IE_NAME = 'eitb.tv'
    _VALID_URL = r'https?://(?:www\.)?eitb\.tv/(?:eu/bideoa|es/video)/[^/]+/\d+/(?P<id>\d+)'

    _TEST = {
        'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/4104995148001/4090227752001/lasa-y-zabala-30-anos/',
        'md5': 'edf4436247185adee3ea18ce64c47998',
        'info_dict': {
            'id': '4090227752001',
            'ext': 'mp4',
            'title': '60 minutos (Lasa y Zabala, 30 años)',
            'description': 'Programa de reportajes de actualidad.',
            'duration': 3996.76,
            'timestamp': 1381789200,
            'upload_date': '20131014',
            'tags': list,
        },
    }

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

        video = self._download_json(
            f'http://mam.eitb.eus/mam/REST/ServiceMultiweb/Video/MULTIWEBTV/{video_id}/',
            video_id, 'Downloading video JSON')

        media = video['web_media'][0]

        formats = []
        for rendition in media['RENDITIONS']:
            video_url = rendition.get('PMD_URL')
            if not video_url:
                continue
            tbr = float_or_none(rendition.get('ENCODING_RATE'), 1000)
            formats.append({
                'url': rendition['PMD_URL'],
                'format_id': join_nonempty('http', int_or_none(tbr)),
                'width': int_or_none(rendition.get('FRAME_WIDTH')),
                'height': int_or_none(rendition.get('FRAME_HEIGHT')),
                'tbr': tbr,
            })

        hls_url = media.get('HLS_SURL')
        if hls_url:
            request = Request(
                'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/',
                headers={'Referer': url})
            token_data = self._download_json(
                request, video_id, 'Downloading auth token', fatal=False)
            if token_data:
                token = token_data.get('token')
                if token:
                    formats.extend(self._extract_m3u8_formats(
                        f'{hls_url}?hdnts={token}', video_id, m3u8_id='hls', fatal=False))

        hds_url = media.get('HDS_SURL')
        if hds_url:
            formats.extend(self._extract_f4m_formats(
                '{}?hdcore=3.7.0'.format(hds_url.replace('euskalsvod', 'euskalvod')),
                video_id, f4m_id='hds', fatal=False))

        return {
            'id': video_id,
            'title': media.get('NAME_ES') or media.get('name') or media['NAME_EU'],
            'description': media.get('SHORT_DESC_ES') or video.get('desc_group') or media.get('SHORT_DESC_EU'),
            'thumbnail': media.get('STILL_URL') or media.get('THUMBNAIL_URL'),
            'duration': float_or_none(media.get('LENGTH'), 1000),
            'timestamp': parse_iso8601(media.get('BROADCST_DATE'), ' '),
            'tags': media.get('TAGS'),
            'formats': formats,
        }