administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-18 23:19:40 +00:00
Code Issues Projects Releases Wiki Activity

[radiozet] Add extractor (#1593)

Browse Source 
Authored by: 0xA7404A (Aurora)
This commit is contained in:
Aurora 2021-11-24 10:47:53 +00:00 committed by GitHub
parent da27aeea5c
commit 17b4540662
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 52 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
yt_dlp/extractor/extractors.py
View File

@ -1168,6 +1168,7 @@ from .radiode import RadioDeIE
from .radiojavan import RadioJavanIE
from .radiobremen import RadioBremenIE
from .radiofrance import RadioFranceIE
from .radiozet import RadioZetPodcastIE
from .radiokapital import (
RadioKapitalIE,
RadioKapitalShowIE,

51
yt_dlp/extractor/radiozet.py Normal file
View File

@ -0,0 +1,51 @@
# coding: utf-8
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'))),
}