yt_dlp/extractor/fujitv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3 from ..utils import HEADRequest
   4 from .common import InfoExtractor
   5
   6
   7 class FujiTVFODPlus7IE(InfoExtractor):
   8     _VALID_URL = r'https?://fod\.fujitv\.co\.jp/title/(?P<sid>[0-9a-z]{4})/(?P<id>[0-9a-z]+)'
   9     _BASE_URL = 'https://i.fod.fujitv.co.jp/'
  10
  11     _TESTS = [{
  12         'url': 'https://fod.fujitv.co.jp/title/5d40/5d40110076',
  13         'info_dict': {
  14             'id': '5d40110076',
  15             'ext': 'mp4',
  16             'title': '#1318 『まる子、まぼろしの洋館を見る』の巻',
  17             'series': 'ちびまる子ちゃん',
  18             'series_id': '5d40',
  19             'description': 'md5:b3f51dbfdda162ac4f789e0ff4d65750',
  20             'thumbnail': 'https://i.fod.fujitv.co.jp/img/program/5d40/episode/5d40110076_a.jpg',
  21         },
  22     }]
  23
  24     def _real_extract(self, url):
  25         series_id, video_id = self._match_valid_url(url).groups()
  26         self._request_webpage(HEADRequest(url), video_id)
  27         json_info = {}
  28         token = self._get_cookies(url).get('CT')
  29         if token:
  30             json_info = self._download_json('https://fod-sp.fujitv.co.jp/apps/api/episode/detail/?ep_id=%s&is_premium=false' % video_id, video_id, headers={'x-authorization': f'Bearer {token.value}'}, fatal=False)
  31         else:
  32             self.report_warning(f'The token cookie is needed to extract video metadata. {self._LOGIN_HINTS["cookies"]}')
  33         formats, subtitles = [], {}
  34         src_json = self._download_json(f'{self._BASE_URL}abrjson_v2/tv_android/{video_id}', video_id)
  35         for src in src_json['video_selector']:
  36             if not src.get('url'):
  37                 continue
  38             fmt, subs = self._extract_m3u8_formats_and_subtitles(src['url'], video_id, 'mp4')
  39             formats.extend(fmt)
  40             subtitles = self._merge_subtitles(subtitles, subs)
  41         self._sort_formats(formats, ['tbr'])
  42
  43         return {
  44             'id': video_id,
  45             'title': json_info.get('ep_title'),
  46             'series': json_info.get('lu_title'),
  47             'series_id': series_id,
  48             'description': json_info.get('ep_description'),
  49             'formats': formats,
  50             'subtitles': subtitles,
  51             'thumbnail': f'{self._BASE_URL}img/program/{series_id}/episode/{video_id}_a.jpg',
  52         }