Merge 1a68959dc4 into 4b5eec0aaa

Fix bug in 720b3dc453

Closes #11623
Authored by: jkruse

yt_dlp/extractor/chaturbate.py

@@ -59,16 +59,15 @@ def _extract_from_api(self, video_id, tld):
                 'Accept': 'application/json',
             }, fatal=False, impersonate=True) or {}
 
-        status = response.get('room_status')
-        if status != 'public':
-            if error := self._ERROR_MAP.get(status):
-                raise ExtractorError(error, expected=True)
-            self.report_warning('Falling back to webpage extraction')
-            return None
-
         m3u8_url = response.get('url')
         if not m3u8_url:
+            status = response.get('room_status')
+            if error := self._ERROR_MAP.get(status):
+                raise ExtractorError(error, expected=True)
+            if status == 'public':
                 self.raise_geo_restricted()
+            self.report_warning(f'Got status "{status}" from API; falling back to webpage extraction')
+            return None
 
         return {
             'id': video_id,

yt_dlp/extractor/polskieradio.py

@@ -458,7 +458,10 @@ class PolskieRadioPlayerIE(InfoExtractor):
         'info_dict': {
             'id': '3',
             'ext': 'm4a',
-            'title': 'Trójka',
+            'title': r're:Trójka \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+            'thumbnail': 'https://player.polskieradio.pl/images/trojka-color-logo.png',
+            'live_status': 'is_live',
+            'display_id': 'trojka',
         },
         'params': {
             'format': 'bestaudio',
@@ -467,12 +470,20 @@ class PolskieRadioPlayerIE(InfoExtractor):
     }]
 
     def _get_channel_list(self, channel_url='no_channel'):
+        webpage = self._download_webpage(self._BASE_URL, channel_url)
+        player_hash = self._search_regex(r'/main\.bundle\.js\?([a-f0-9]+)', webpage, 'player hash')
+        channel_list = self.cache.load('polskieradio-player-channel-list', player_hash)
+        if channel_list:
+            return channel_list
         player_code = self._download_webpage(
             self._PLAYER_URL, channel_url,
             note='Downloading js player')
-        channel_list = js_to_json(self._search_regex(
+        channel_list = self._search_json(
-            r';var r="anteny",a=(\[.+?\])},', player_code, 'channel list'))
+            r''';\s*var\s[a-zA-Z_]+\s*=\s*["']anteny["']\s*,\s*[a-zA-Z_]+\s*=\s*''',
-        return self._parse_json(channel_list, channel_url)
+            player_code, 'channel list', channel_url, transform_source=js_to_json,
+            contains_pattern=r'\[{(?s:.+)}\]')
+        self.cache.store('polskieradio-player-channel-list', player_hash, channel_list)
+        return channel_list
 
     def _real_extract(self, url):
         channel_url = self._match_id(url)
@@ -495,19 +506,11 @@ def _real_extract(self, url):
         if not station:
             raise ExtractorError('Station not found even though we extracted channel')
 
-        formats = []
+        formats = self._extract_m3u8_formats(
-        for stream_url in station['Streams']:
+            next((
-            stream_url = self._proto_relative_url(stream_url)
+                stream_url.replace('http:', 'https:') for stream_url in station['Streams'] if stream_url.endswith('.m3u8')
-            if stream_url.endswith('/playlist.m3u8'):
+            )),
-                formats.extend(self._extract_m3u8_formats(stream_url, channel_url, live=True))
+            channel_url, live=True)
-            elif stream_url.endswith('/manifest.f4m'):
-                formats.extend(self._extract_mpd_formats(stream_url, channel_url))
-            elif stream_url.endswith('/Manifest'):
-                formats.extend(self._extract_ism_formats(stream_url, channel_url))
-            else:
-                formats.append({
-                    'url': stream_url,
-                })
 
         return {
             'id': str(channel['id']),