xZero707/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 11:31:29 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge 1a68959dc4 into f919729538

Browse Source
This commit is contained in:
LN Liberda 2024-11-18 15:33:37 +05:30 committed by GitHub
commit 0c9247f7a3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 20 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
yt_dlp/extractor/polskieradio.py
View File

@ -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(
r';var r="anteny",a=(\[.+?\])},', player_code, 'channel list'))
return self._parse_json(channel_list, channel_url)
channel_list = 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'\[{(?s:.+)}\]')
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 = []
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': str(channel['id']),