aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/tver.py
blob: a54f49319a41ece1864c132dce53683102b626ea (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
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    int_or_none,
    remove_start,
    smuggle_url,
    strip_or_none,
    try_get,
)


class TVerIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?tver\.jp/(?P<path>(?:corner|episode|feature)/(?P<id>f?\d+))'
    # videos are only available for 7 days
    _TESTS = [{
        'url': 'https://tver.jp/corner/f0062178',
        'only_matching': True,
    }, {
        'url': 'https://tver.jp/feature/f0062413',
        'only_matching': True,
    }, {
        'url': 'https://tver.jp/episode/79622438',
        'only_matching': True,
    }, {
        # subtitle = ' '
        'url': 'https://tver.jp/corner/f0068870',
        'only_matching': True,
    }]
    _TOKEN = None
    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'

    def _real_initialize(self):
        self._TOKEN = self._download_json(
            'https://tver.jp/api/access_token.php', None)['token']

    def _real_extract(self, url):
        path, video_id = re.match(self._VALID_URL, url).groups()
        main = self._download_json(
            'https://api.tver.jp/v4/' + path, video_id,
            query={'token': self._TOKEN})['main']
        p_id = main['publisher_id']
        service = remove_start(main['service'], 'ts_')
        info = {
            '_type': 'url_transparent',
            'description': try_get(main, lambda x: x['note'][0]['text'], compat_str),
            'episode_number': int_or_none(try_get(main, lambda x: x['ext']['episode_number'])),
        }

        if service == 'cx':
            title = main['title']
            subtitle = strip_or_none(main.get('subtitle'))
            if subtitle:
                title += ' - ' + subtitle
            info.update({
                'title': title,
                'url': 'https://i.fod.fujitv.co.jp/plus7/web/%s/%s.html' % (p_id[:4], p_id),
                'ie_key': 'FujiTVFODPlus7',
            })
        else:
            r_id = main['reference_id']
            if service not in ('tx', 'russia2018', 'sebare2018live', 'gorin'):
                r_id = 'ref:' + r_id
            bc_url = smuggle_url(
                self.BRIGHTCOVE_URL_TEMPLATE % (p_id, r_id),
                {'geo_countries': ['JP']})
            info.update({
                'url': bc_url,
                'ie_key': 'BrightcoveNew',
            })

        return info