yt_dlp/extractor/radiozet.py

   1 # coding: utf-8
   2 from .common import InfoExtractor
   3 from ..utils import (
   4     traverse_obj,
   5     strip_or_none,
   6 )
   7
   8
   9 class RadioZetPodcastIE(InfoExtractor):
  10     _VALID_URL = r'https?://player\.radiozet\.pl\/Podcasty/.*?/(?P<id>.+)'
  11     _TEST = {
  12         'url': 'https://player.radiozet.pl/Podcasty/Nie-Ma-Za-Co/O-przedmiotach-szkolnych-ktore-przydaja-sie-w-zyciu',
  13         'md5': 'e03665c316b4fbc5f6a8f232948bbba3',
  14         'info_dict': {
  15             'id': '42154',
  16             'display_id': 'O-przedmiotach-szkolnych-ktore-przydaja-sie-w-zyciu',
  17             'title': 'O przedmiotach szkolnych, które przydają się w życiu',
  18             'description': 'md5:fa72bed49da334b09e5b2f79851f185c',
  19             'release_timestamp': 1592985480,
  20             'ext': 'mp3',
  21             'thumbnail': r're:^https?://.*\.png$',
  22             'duration': 83,
  23             'series': 'Nie Ma Za Co',
  24             'creator': 'Katarzyna Pakosińska',
  25         }
  26     }
  27
  28     def _call_api(self, podcast_id, display_id):
  29         return self._download_json(
  30             f'https://player.radiozet.pl/api/podcasts/getPodcast/(node)/{podcast_id}/(station)/radiozet',
  31             display_id)
  32
  33     def _real_extract(self, url):
  34         display_id = self._match_id(url)
  35         webpage = self._download_webpage(url, display_id)
  36         podcast_id = self._html_search_regex(r'<div.*?\sid="player".*?\sdata-id=[\'"]([^\'"]+)[\'"]',
  37                                              webpage, 'podcast id')
  38         data = self._call_api(podcast_id, display_id)['data'][0]
  39
  40         return {
  41             'id': podcast_id,
  42             'display_id': display_id,
  43             'title': strip_or_none(data.get('title')),
  44             'description': strip_or_none(traverse_obj(data, ('program', 'desc'))),
  45             'release_timestamp': data.get('published_date'),
  46             'url': traverse_obj(data, ('player', 'stream')),
  47             'thumbnail': traverse_obj(data, ('program', 'image', 'original')),
  48             'duration': traverse_obj(data, ('player', 'duration')),
  49             'series': strip_or_none(traverse_obj(data, ('program', 'title'))),
  50             'creator': strip_or_none(traverse_obj(data, ('presenter', 0, 'title'))),
  51         }