diff --git a/yt_dlp/extractor/polskieradio.py b/yt_dlp/extractor/polskieradio.py index e0b22fffdf..4ec7dba541 100644 --- a/yt_dlp/extractor/polskieradio.py +++ b/yt_dlp/extractor/polskieradio.py @@ -459,7 +459,10 @@ 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', @@ -471,9 +474,10 @@ def _get_channel_list(self, channel_url='no_channel'): player_code = self._download_webpage( self._PLAYER_URL, channel_url, note='Downloading js player') - channel_list = js_to_json(self._search_regex( - r';var r="anteny",a=(\[.+?\])},', player_code, 'channel list')) - return self._parse_json(channel_list, channel_url) + return self._search_json( + r''';\s*var\s[a-zA-Z_]+\s*=\s*["']anteny["']\s*,\s*[a-zA-Z_]+\s*=\s*''', + player_code, 'channel list', channel_url, transform_source=js_to_json, + contains_pattern=r'\[{(?s:.+)}\]') def _real_extract(self, url): channel_url = self._match_id(url) @@ -496,19 +500,11 @@ def _real_extract(self, url): if not station: raise ExtractorError('Station not found even though we extracted channel') - formats = [] - for stream_url in station['Streams']: - stream_url = self._proto_relative_url(stream_url) - if stream_url.endswith('/playlist.m3u8'): - formats.extend(self._extract_m3u8_formats(stream_url, 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, - }) + formats = self._extract_m3u8_formats( + next(( + stream_url.replace('http:', 'https:') for stream_url in station['Streams'] if stream_url.endswith('.m3u8') + )), + channel_url, live=True) return { 'id': compat_str(channel['id']),