From c4da5ff971f22bf3c93ac521d6805f7fb561284b Mon Sep 17 00:00:00 2001 From: YuenSzeHong <40477634+YuenSzeHong@users.noreply.github.com> Date: Fri, 28 Jan 2022 20:58:03 +0800 Subject: [PATCH] [Fujitv] Extract metadata and support premium (#2505) Authored by: YuenSzeHong --- yt_dlp/extractor/fujitv.py | 62 ++++++++++++++++++++------------------ 1 file changed, 33 insertions(+), 29 deletions(-) diff --git a/yt_dlp/extractor/fujitv.py b/yt_dlp/extractor/fujitv.py index 1cea62609..f3cb9a6f4 100644 --- a/yt_dlp/extractor/fujitv.py +++ b/yt_dlp/extractor/fujitv.py @@ -1,48 +1,52 @@ # coding: utf-8 from __future__ import unicode_literals - +from ..utils import HEADRequest from .common import InfoExtractor class FujiTVFODPlus7IE(InfoExtractor): - _VALID_URL = r'https?://fod\.fujitv\.co\.jp/title/[0-9a-z]{4}/(?P[0-9a-z]+)' - _BASE_URL = 'http://i.fod.fujitv.co.jp/' - _BITRATE_MAP = { - 300: (320, 180), - 800: (640, 360), - 1200: (1280, 720), - 2000: (1280, 720), - 4000: (1920, 1080), - } + _VALID_URL = r'https?://fod\.fujitv\.co\.jp/title/(?P[0-9a-z]{4})/(?P[0-9a-z]+)' + _BASE_URL = 'https://i.fod.fujitv.co.jp/' _TESTS = [{ - 'url': 'https://fod.fujitv.co.jp/title/5d40/5d40810075', + 'url': 'https://fod.fujitv.co.jp/title/5d40/5d40110076', 'info_dict': { - 'id': '5d40810075', - 'title': '5d40810075', + 'id': '5d40110076', 'ext': 'mp4', - 'format_id': '4000', - 'thumbnail': 'http://i.fod.fujitv.co.jp/pc/image/wbtn/wbtn_5d40810075.jpg' + 'title': '#1318 『まる子、まぼろしの洋館を見る』の巻', + 'series': 'ちびまる子ちゃん', + 'series_id': '5d40', + 'description': 'md5:b3f51dbfdda162ac4f789e0ff4d65750', + 'thumbnail': 'https://i.fod.fujitv.co.jp/img/program/5d40/episode/5d40110076_a.jpg', }, - 'skip': 'Expires after a week' }] def _real_extract(self, url): - video_id = self._match_id(url) - formats = self._extract_m3u8_formats( - self._BASE_URL + 'abr/tv_android/%s.m3u8' % video_id, video_id, 'mp4') - for f in formats: - wh = self._BITRATE_MAP.get(f.get('tbr')) - if wh: - f.update({ - 'width': wh[0], - 'height': wh[1], - }) - self._sort_formats(formats) + series_id, video_id = self._match_valid_url(url).groups() + self._request_webpage(HEADRequest(url), video_id) + json_info = {} + token = self._get_cookies(url).get('CT') + if token: + 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) + else: + self.report_warning(f'The token cookie is needed to extract video metadata. {self._LOGIN_HINTS["cookies"]}') + formats, subtitles = [], {} + src_json = self._download_json(f'{self._BASE_URL}abrjson_v2/tv_android/{video_id}', video_id) + for src in src_json['video_selector']: + if not src.get('url'): + continue + fmt, subs = self._extract_m3u8_formats_and_subtitles(src['url'], video_id, 'mp4') + formats.extend(fmt) + subtitles = self._merge_subtitles(subtitles, subs) + self._sort_formats(formats, ['tbr']) return { 'id': video_id, - 'title': video_id, + 'title': json_info.get('ep_title'), + 'series': json_info.get('lu_title'), + 'series_id': series_id, + 'description': json_info.get('ep_description'), 'formats': formats, - 'thumbnail': self._BASE_URL + 'pc/image/wbtn/wbtn_%s.jpg' % video_id, + 'subtitles': subtitles, + 'thumbnail': f'{self._BASE_URL}img/program/{series_id}/episode/{video_id}_a.jpg', }