[Fujitv] Extract metadata and support premium (#2505)

Authored by: YuenSzeHong

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<id>[0-9a-z]+)'
+    _VALID_URL = r'https?://fod\.fujitv\.co\.jp/title/(?P<sid>[0-9a-z]{4})/(?P<id>[0-9a-z]+)'
-    _BASE_URL = 'http://i.fod.fujitv.co.jp/'
+    _BASE_URL = 'https://i.fod.fujitv.co.jp/'
-    _BITRATE_MAP = {
-        300: (320, 180),
-        800: (640, 360),
-        1200: (1280, 720),
-        2000: (1280, 720),
-        4000: (1920, 1080),
-    }
 
     _TESTS = [{
-        'url': 'https://fod.fujitv.co.jp/title/5d40/5d40810075',
+        'url': 'https://fod.fujitv.co.jp/title/5d40/5d40110076',
         'info_dict': {
-            'id': '5d40810075',
+            'id': '5d40110076',
-            'title': '5d40810075',
             'ext': 'mp4',
-            'format_id': '4000',
+            'title': '#1318 『まる子、まぼろしの洋館を見る』の巻',
-            'thumbnail': 'http://i.fod.fujitv.co.jp/pc/image/wbtn/wbtn_5d40810075.jpg'
+            '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)
+        series_id, video_id = self._match_valid_url(url).groups()
-        formats = self._extract_m3u8_formats(
+        self._request_webpage(HEADRequest(url), video_id)
-            self._BASE_URL + 'abr/tv_android/%s.m3u8' % video_id, video_id, 'mp4')
+        json_info = {}
-        for f in formats:
+        token = self._get_cookies(url).get('CT')
-            wh = self._BITRATE_MAP.get(f.get('tbr'))
+        if token:
-            if wh:
+            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)
-                f.update({
+        else:
-                    'width': wh[0],
+            self.report_warning(f'The token cookie is needed to extract video metadata. {self._LOGIN_HINTS["cookies"]}')
-                    'height': wh[1],
+        formats, subtitles = [], {}
-                })
+        src_json = self._download_json(f'{self._BASE_URL}abrjson_v2/tv_android/{video_id}', video_id)
-        self._sort_formats(formats)
+        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',
         }