[S4C] Add thumbnail extraction, extract series as playlist
authordirkf <fieldhouse@gmx.net>
Sun, 27 Aug 2023 18:08:28 +0000 (19:08 +0100)
committerdirkf <fieldhouse@gmx.net>
Thu, 31 Aug 2023 22:16:50 +0000 (23:16 +0100)
Based on https://github.com/yt-dlp/yt-dlp/pull/7776: thx ifan-t, bashonly

youtube_dl/extractor/extractors.py
youtube_dl/extractor/s4c.py

index cb39876c2798388ddd8fe48eb1c60716e39a4a99..d9289e5bf1a1c7cbeaeb8088aee1ee2590847f39 100644 (file)
@@ -1087,7 +1087,10 @@ from .rutube import (
 from .rutv import RUTVIE
 from .ruutu import RuutuIE
 from .ruv import RuvIE
-from .s4c import S4CIE
+from .s4c import (
+    S4CIE,
+    S4CSeriesIE,
+)
 from .safari import (
     SafariIE,
     SafariApiIE,
index 21d40c2d38aa58f86b078e4158f7094910f1e81f..b152e668005c1f783c187297e7417a0b40f5e97e 100644 (file)
@@ -2,6 +2,8 @@
 
 from __future__ import unicode_literals
 
+from functools import partial as partial_f
+
 from .common import InfoExtractor
 from ..utils import (
     float_or_none,
@@ -9,6 +11,7 @@ from ..utils import (
     T,
     traverse_obj,
     txt_or_none,
+    url_or_none,
 )
 
 
@@ -21,7 +24,8 @@ class S4CIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Y Swn',
             'description': 'md5:f7681a30e4955b250b3224aa9fe70cf0',
-            'duration': 5340
+            'duration': 5340,
+            'thumbnail': 'https://www.s4c.cymru/amg/1920x1080/Y_Swn_2023S4C_099_ii.jpg',
         },
     }, {
         'url': 'https://www.s4c.cymru/clic/programme/856636948',
@@ -31,6 +35,7 @@ class S4CIE(InfoExtractor):
             'title': 'Am Dro',
             'duration': 2880,
             'description': 'md5:100d8686fc9a632a0cb2db52a3433ffe',
+            'thumbnail': 'https://www.s4c.cymru/amg/1920x1080/Am_Dro_2022-23S4C_P6_4005.jpg',
         },
     }]
 
@@ -43,7 +48,7 @@ class S4CIE(InfoExtractor):
                 'programme_id': video_id,
             }, fatal=False)
 
-        filename = self._download_json(
+        player_config = self._download_json(
             'https://player-api.s4c-cdn.co.uk/player-configuration/prod', video_id, query={
                 'programme_id': video_id,
                 'signed': '0',
@@ -51,7 +56,8 @@ class S4CIE(InfoExtractor):
                 'mode': 'od',
                 'appId': 'clic',
                 'streamName': '',
-            }, note='Downloading player config JSON')['filename']
+            }, note='Downloading player config JSON')
+
         m3u8_url = self._download_json(
             'https://player-api.s4c-cdn.co.uk/streaming-urls/prod', video_id, query={
                 'mode': 'od',
@@ -59,18 +65,60 @@ class S4CIE(InfoExtractor):
                 'region': 'WW',
                 'extra': 'false',
                 'thirdParty': 'false',
-                'filename': filename,
+                'filename': player_config['filename'],
             }, note='Downloading streaming urls JSON')['hls']
-        # ... self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
-        formats, subtitles = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', entry_protocol='m3u8_native'), {}
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', entry_protocol='m3u8_native')
+        self._sort_formats(formats)
+
+        subtitles = {}
+        for sub in traverse_obj(player_config, ('subtitles', lambda _, v: url_or_none(v['0']))):
+            subtitles.setdefault(sub.get('3', 'en'), []).append({
+                'url': sub['0'],
+                'name': sub.get('1'),
+            })
 
         return merge_dicts({
             'id': video_id,
             'formats': formats,
             'subtitles': subtitles,
+            'thumbnail': url_or_none(player_config.get('poster')),
         }, traverse_obj(details, ('full_prog_details', 0, {
             'title': (('programme_title', 'series_title'), T(txt_or_none)),
             'description': ('full_billing', T(txt_or_none)),
-            'duration': ('duration', T(lambda x: float_or_none(x, invscale=60))),
+            'duration': ('duration', T(partial_f(float_or_none, invscale=60))),
         }), get_all=False),
             rev=True)
+
+
+class S4CSeriesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?s4c\.cymru/clic/series/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.s4c.cymru/clic/series/864982911',
+        'playlist_mincount': 6,
+        'info_dict': {
+            'id': '864982911',
+            'title': 'Iaith ar Daith',
+        },
+    }, {
+        'url': 'https://www.s4c.cymru/clic/series/866852587',
+        'playlist_mincount': 8,
+        'info_dict': {
+            'id': '866852587',
+            'title': 'FFIT Cymru',
+        },
+    }]
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+        series_details = self._download_json(
+            'https://www.s4c.cymru/df/series_details', series_id, query={
+                'lang': 'e',
+                'series_id': series_id,
+                'show_prog_in_series': 'Y'
+            }, note='Downloading series details JSON')
+
+        return self.playlist_result(
+            (self.url_result('https://www.s4c.cymru/clic/programme/' + episode_id, S4CIE, episode_id)
+             for episode_id in traverse_obj(series_details, ('other_progs_in_series', Ellipsis, 'id'))),
+            playlist_id=series_id, playlist_title=traverse_obj(
+                series_details, ('full_prog_details', 0, 'series_title', T(txt_or_none))))