yt_dlp/extractor/ilpost.py

   1
   2 from .common import InfoExtractor
   3 from ..utils import (
   4     ExtractorError,
   5     float_or_none,
   6     int_or_none,
   7     url_or_none,
   8     urlencode_postdata,
   9 )
  10 from ..utils.traversal import traverse_obj
  11
  12
  13 class IlPostIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?ilpost\.it/episodes/(?P<id>[^/?#]+)'
  15     _TESTS = [{
  16         'url': 'https://www.ilpost.it/episodes/1-avis-akvasas-ka/',
  17         'md5': '43649f002d85e1c2f319bb478d479c40',
  18         'info_dict': {
  19             'id': '2972047',
  20             'ext': 'mp3',
  21             'display_id': '1-avis-akvasas-ka',
  22             'title': '1. Avis akvasas ka',
  23             'url': 'https://www.ilpost.it/wp-content/uploads/2023/12/28/1703781217-l-invasione-pt1-v6.mp3',
  24             'timestamp': 1703835014,
  25             'upload_date': '20231229',
  26             'duration': 2495.0,
  27             'availability': 'public',
  28             'series_id': '235598',
  29             'description': '',
  30         },
  31     }]
  32
  33     def _real_extract(self, url):
  34         display_id = self._match_id(url)
  35         webpage = self._download_webpage(url, display_id)
  36
  37         endpoint_metadata = self._search_json(
  38             r'var\s+ilpostpodcast\s*=', webpage, 'metadata', display_id)
  39         episode_id = endpoint_metadata['post_id']
  40         podcast_id = endpoint_metadata['podcast_id']
  41         podcast_metadata = self._download_json(
  42             endpoint_metadata['ajax_url'], display_id, data=urlencode_postdata({
  43                 'action': 'checkpodcast',
  44                 'cookie': endpoint_metadata['cookie'],
  45                 'post_id': episode_id,
  46                 'podcast_id': podcast_id,
  47             }))
  48
  49         episode = traverse_obj(podcast_metadata, (
  50             'data', 'postcastList', lambda _, v: str(v['id']) == episode_id, {dict}), get_all=False)
  51         if not episode:
  52             raise ExtractorError('Episode could not be extracted')
  53
  54         return {
  55             'id': episode_id,
  56             'display_id': display_id,
  57             'series_id': podcast_id,
  58             'vcodec': 'none',
  59             **traverse_obj(episode, {
  60                 'title': ('title', {str}),
  61                 'description': ('description', {str}),
  62                 'url': ('podcast_raw_url', {url_or_none}),
  63                 'thumbnail': ('image', {url_or_none}),
  64                 'timestamp': ('timestamp', {int_or_none}),
  65                 'duration': ('milliseconds', {float_or_none(scale=1000)}),
  66                 'availability': ('free', {lambda v: 'public' if v else 'subscriber_only'}),
  67             }),
  68         }