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     _BITRATE_MAP = {
  11         300: (320, 180),
  12         800: (640, 360),
  13         1200: (1280, 720),
  14         2000: (1280, 720),
  15         4000: (1920, 1080),
  16     }
  17
  18     _TESTS = [{
  19         'url': 'https://fod.fujitv.co.jp/title/5d40/5d40110076',
  20         'info_dict': {
  21             'id': '5d40110076',
  22             'ext': 'mp4',
  23             'title': '#1318 『まる子、まぼろしの洋館を見る』の巻',
  24             'series': 'ちびまる子ちゃん',
  25             'series_id': '5d40',
  26             'description': 'md5:b3f51dbfdda162ac4f789e0ff4d65750',
  27             'thumbnail': 'https://i.fod.fujitv.co.jp/img/program/5d40/episode/5d40110076_a.jpg',
  28         },
  29     }, {
  30         'url': 'https://fod.fujitv.co.jp/title/5d40/5d40810083',
  31         'info_dict': {
  32             'id': '5d40810083',
  33             'ext': 'mp4',
  34             'title': '#1324 『まる子とオニの子』の巻／『結成！2月をムダにしない会』の巻',
  35             'description': 'md5:3972d900b896adc8ab1849e310507efa',
  36             'series': 'ちびまる子ちゃん',
  37             'series_id': '5d40',
  38             'thumbnail': 'https://i.fod.fujitv.co.jp/img/program/5d40/episode/5d40810083_a.jpg'},
  39         'skip': 'Video available only in one week'
  40     }]
  41
  42     def _real_extract(self, url):
  43         series_id, video_id = self._match_valid_url(url).groups()
  44         self._request_webpage(HEADRequest(url), video_id)
  45         json_info = {}
  46         token = self._get_cookies(url).get('CT')
  47         if token:
  48             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)
  49         else:
  50             self.report_warning(f'The token cookie is needed to extract video metadata. {self._LOGIN_HINTS["cookies"]}')
  51         formats, subtitles = [], {}
  52         src_json = self._download_json(f'{self._BASE_URL}abrjson_v2/tv_android/{video_id}', video_id)
  53         for src in src_json['video_selector']:
  54             if not src.get('url'):
  55                 continue
  56             fmt, subs = self._extract_m3u8_formats_and_subtitles(src['url'], video_id, 'mp4')
  57             for f in fmt:
  58                 f.update(dict(zip(('height', 'width'),
  59                                   self._BITRATE_MAP.get(f.get('tbr'), ()))))
  60             formats.extend(fmt)
  61             subtitles = self._merge_subtitles(subtitles, subs)
  62         self._sort_formats(formats, ['tbr'])
  63
  64         return {
  65             'id': video_id,
  66             'title': json_info.get('ep_title'),
  67             'series': json_info.get('lu_title'),
  68             'series_id': series_id,
  69             'description': json_info.get('ep_description'),
  70             'formats': formats,
  71             'subtitles': subtitles,
  72             'thumbnail': f'{self._BASE_URL}img/program/{series_id}/episode/{video_id}_a.jpg',
  73         }