yt_dlp/extractor/tver.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     int_or_none,
  10     remove_start,
  11     smuggle_url,
  12     strip_or_none,
  13     try_get,
  14 )
  15
  16
  17 class TVerIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?tver\.jp/(?P<path>(?:corner|episode|feature)/(?P<id>f?\d+))'
  19     # videos are only available for 7 days
  20     _TESTS = [{
  21         'url': 'https://tver.jp/corner/f0062178',
  22         'only_matching': True,
  23     }, {
  24         'url': 'https://tver.jp/feature/f0062413',
  25         'only_matching': True,
  26     }, {
  27         'url': 'https://tver.jp/episode/79622438',
  28         'only_matching': True,
  29     }, {
  30         # subtitle = ' '
  31         'url': 'https://tver.jp/corner/f0068870',
  32         'only_matching': True,
  33     }]
  34     _TOKEN = None
  35     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
  36
  37     def _real_initialize(self):
  38         self._TOKEN = self._download_json(
  39             'https://tver.jp/api/access_token.php', None)['token']
  40
  41     def _real_extract(self, url):
  42         path, video_id = re.match(self._VALID_URL, url).groups()
  43         main = self._download_json(
  44             'https://api.tver.jp/v4/' + path, video_id,
  45             query={'token': self._TOKEN})['main']
  46         p_id = main['publisher_id']
  47         service = remove_start(main['service'], 'ts_')
  48         info = {
  49             '_type': 'url_transparent',
  50             'description': try_get(main, lambda x: x['note'][0]['text'], compat_str),
  51             'episode_number': int_or_none(try_get(main, lambda x: x['ext']['episode_number'])),
  52         }
  53
  54         if service == 'cx':
  55             title = main['title']
  56             subtitle = strip_or_none(main.get('subtitle'))
  57             if subtitle:
  58                 title += ' - ' + subtitle
  59             info.update({
  60                 'title': title,
  61                 'url': 'https://i.fod.fujitv.co.jp/plus7/web/%s/%s.html' % (p_id[:4], p_id),
  62                 'ie_key': 'FujiTVFODPlus7',
  63             })
  64         else:
  65             r_id = main['reference_id']
  66             if service not in ('tx', 'russia2018', 'sebare2018live', 'gorin'):
  67                 r_id = 'ref:' + r_id
  68             bc_url = smuggle_url(
  69                 self.BRIGHTCOVE_URL_TEMPLATE % (p_id, r_id),
  70                 {'geo_countries': ['JP']})
  71             info.update({
  72                 'url': bc_url,
  73                 'ie_key': 'BrightcoveNew',
  74             })
  75
  76         return info