diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-05 17:37:42 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-05 17:37:42 +0000 |
commit | c7bab7c39fd51c0812f70020172766303191bc01 (patch) | |
tree | 56c05fbdd4fc47409d48ba318a4b621a7b0d299a /yt_dlp/extractor/radiozet.py | |
parent | Initial commit. (diff) | |
download | yt-dlp-c7bab7c39fd51c0812f70020172766303191bc01.tar.xz yt-dlp-c7bab7c39fd51c0812f70020172766303191bc01.zip |
Adding upstream version 2023.03.04.upstream/2023.03.04upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'yt_dlp/extractor/radiozet.py')
-rw-r--r-- | yt_dlp/extractor/radiozet.py | 50 |
1 files changed, 50 insertions, 0 deletions
diff --git a/yt_dlp/extractor/radiozet.py b/yt_dlp/extractor/radiozet.py new file mode 100644 index 0000000..6752017 --- /dev/null +++ b/yt_dlp/extractor/radiozet.py @@ -0,0 +1,50 @@ +from .common import InfoExtractor +from ..utils import ( + traverse_obj, + strip_or_none, +) + + +class RadioZetPodcastIE(InfoExtractor): + _VALID_URL = r'https?://player\.radiozet\.pl\/Podcasty/.*?/(?P<id>.+)' + _TEST = { + 'url': 'https://player.radiozet.pl/Podcasty/Nie-Ma-Za-Co/O-przedmiotach-szkolnych-ktore-przydaja-sie-w-zyciu', + 'md5': 'e03665c316b4fbc5f6a8f232948bbba3', + 'info_dict': { + 'id': '42154', + 'display_id': 'O-przedmiotach-szkolnych-ktore-przydaja-sie-w-zyciu', + 'title': 'O przedmiotach szkolnych, które przydają się w życiu', + 'description': 'md5:fa72bed49da334b09e5b2f79851f185c', + 'release_timestamp': 1592985480, + 'ext': 'mp3', + 'thumbnail': r're:^https?://.*\.png$', + 'duration': 83, + 'series': 'Nie Ma Za Co', + 'creator': 'Katarzyna Pakosińska', + } + } + + def _call_api(self, podcast_id, display_id): + return self._download_json( + f'https://player.radiozet.pl/api/podcasts/getPodcast/(node)/{podcast_id}/(station)/radiozet', + display_id) + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + podcast_id = self._html_search_regex(r'<div.*?\sid="player".*?\sdata-id=[\'"]([^\'"]+)[\'"]', + webpage, 'podcast id') + data = self._call_api(podcast_id, display_id)['data'][0] + + return { + 'id': podcast_id, + 'display_id': display_id, + 'title': strip_or_none(data.get('title')), + 'description': strip_or_none(traverse_obj(data, ('program', 'desc'))), + 'release_timestamp': data.get('published_date'), + 'url': traverse_obj(data, ('player', 'stream')), + 'thumbnail': traverse_obj(data, ('program', 'image', 'original')), + 'duration': traverse_obj(data, ('player', 'duration')), + 'series': strip_or_none(traverse_obj(data, ('program', 'title'))), + 'creator': strip_or_none(traverse_obj(data, ('presenter', 0, 'title'))), + } |