yt_dlp/extractor/radiozet.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     strip_or_none,
   4     traverse_obj,
   5 )
   6
   7
   8 class RadioZetPodcastIE(InfoExtractor):
   9     _VALID_URL = r'https?://player\.radiozet\.pl\/Podcasty/.*?/(?P<id>.+)'
  10     _TEST = {
  11         'url': 'https://player.radiozet.pl/Podcasty/Nie-Ma-Za-Co/O-przedmiotach-szkolnych-ktore-przydaja-sie-w-zyciu',
  12         'md5': 'e03665c316b4fbc5f6a8f232948bbba3',
  13         'info_dict': {
  14             'id': '42154',
  15             'display_id': 'O-przedmiotach-szkolnych-ktore-przydaja-sie-w-zyciu',
  16             'title': 'O przedmiotach szkolnych, które przydają się w życiu',
  17             'description': 'md5:fa72bed49da334b09e5b2f79851f185c',
  18             'release_timestamp': 1592985480,
  19             'ext': 'mp3',
  20             'thumbnail': r're:^https?://.*\.png$',
  21             'duration': 83,
  22             'series': 'Nie Ma Za Co',
  23             'creator': 'Katarzyna Pakosińska',
  24         },
  25     }
  26
  27     def _call_api(self, podcast_id, display_id):
  28         return self._download_json(
  29             f'https://player.radiozet.pl/api/podcasts/getPodcast/(node)/{podcast_id}/(station)/radiozet',
  30             display_id)
  31
  32     def _real_extract(self, url):
  33         display_id = self._match_id(url)
  34         webpage = self._download_webpage(url, display_id)
  35         podcast_id = self._html_search_regex(r'<div.*?\sid="player".*?\sdata-id=[\'"]([^\'"]+)[\'"]',
  36                                              webpage, 'podcast id')
  37         data = self._call_api(podcast_id, display_id)['data'][0]
  38
  39         return {
  40             'id': podcast_id,
  41             'display_id': display_id,
  42             'title': strip_or_none(data.get('title')),
  43             'description': strip_or_none(traverse_obj(data, ('program', 'desc'))),
  44             'release_timestamp': data.get('published_date'),
  45             'url': traverse_obj(data, ('player', 'stream')),
  46             'thumbnail': traverse_obj(data, ('program', 'image', 'original')),
  47             'duration': traverse_obj(data, ('player', 'duration')),
  48             'series': strip_or_none(traverse_obj(data, ('program', 'title'))),
  49             'creator': strip_or_none(traverse_obj(data, ('presenter', 0, 'title'))),
  50         }