[ie/S4C] Add series support and extract subs/thumbs (#7776)

Authored by: ifan-t

yt_dlp/extractor/_extractors.py

@@ -1710,7 +1710,10 @@
     RuvIE,
     RuvSpilaIE
 )
-from .s4c import S4CIE
+from .s4c import (
+    S4CIE,
+    S4CSeriesIE
+)
 from .safari import (
     SafariIE,
     SafariApiIE,

yt_dlp/extractor/s4c.py

@@ -1,5 +1,5 @@
 from .common import InfoExtractor
-from ..utils import traverse_obj
+from ..utils import traverse_obj, url_or_none
 
 
 class S4CIE(InfoExtractor):
@@ -11,7 +11,8 @@ 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',
@@ -21,6 +22,7 @@ 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'
         },
     }]
 
@@ -30,7 +32,7 @@ def _real_extract(self, url):
             f'https://www.s4c.cymru/df/full_prog_details?lang=e&programme_id={video_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',
@@ -38,7 +40,13 @@ def _real_extract(self, url):
                 'mode': 'od',
                 'appId': 'clic',
                 'streamName': '',
-            }, note='Downloading player config JSON')['filename']
+            }, note='Downloading player config JSON')
+        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'),
+            })
         m3u8_url = self._download_json(
             'https://player-api.s4c-cdn.co.uk/streaming-urls/prod', video_id, query={
                 'mode': 'od',
@@ -46,17 +54,52 @@ def _real_extract(self, url):
                 'region': 'WW',
                 'extra': 'false',
                 'thirdParty': 'false',
-                'filename': filename,
+                'filename': player_config['filename'],
             }, note='Downloading streaming urls JSON')['hls']
-        formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
 
         return {
             'id': video_id,
-            'formats': formats,
+            'formats': self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls'),
             'subtitles': subtitles,
+            'thumbnail': url_or_none(player_config.get('poster')),
             **traverse_obj(details, ('full_prog_details', 0, {
                 'title': (('programme_title', 'series_title'), {str}),
                 'description': ('full_billing', {str.strip}),
                 'duration': ('duration', {lambda x: int(x) * 60}),
             }), get_all=False),
         }
+
+
+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',
+            'description': 'md5:e878ebf660dce89bd2ef521d7ce06397'
+        },
+    }, {
+        'url': 'https://www.s4c.cymru/clic/series/866852587',
+        'playlist_mincount': 8,
+        'info_dict': {
+            'id': '866852587',
+            'title': 'FFIT Cymru',
+            'description': 'md5:abcb3c129cb68dbb6cd304fd33b07e96'
+        },
+    }]
+
+    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(f'https://www.s4c.cymru/clic/programme/{episode_id}', S4CIE, episode_id)
+             for episode_id in traverse_obj(series_details, ('other_progs_in_series', ..., 'id'))],
+            series_id, traverse_obj(series_details, ('full_prog_details', 0, 'series_title', {str})))