yt_dlp/extractor/ilpost.py

   1 import functools
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     float_or_none,
   7     int_or_none,
   8     url_or_none,
   9     urlencode_postdata,
  10 )
  11 from ..utils.traversal import traverse_obj
  12
  13
  14 class IlPostIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?ilpost\.it/episodes/(?P<id>[^/?#]+)'
  16     _TESTS = [{
  17         'url': 'https://www.ilpost.it/episodes/1-avis-akvasas-ka/',
  18         'md5': '43649f002d85e1c2f319bb478d479c40',
  19         'info_dict': {
  20             'id': '2972047',
  21             'ext': 'mp3',
  22             'display_id': '1-avis-akvasas-ka',
  23             'title': '1. Avis akvasas ka',
  24             'url': 'https://www.ilpost.it/wp-content/uploads/2023/12/28/1703781217-l-invasione-pt1-v6.mp3',
  25             'timestamp': 1703835014,
  26             'upload_date': '20231229',
  27             'duration': 2495.0,
  28             'availability': 'public',
  29             'series_id': '235598',
  30             'description': '',
  31         }
  32     }]
  33
  34     def _real_extract(self, url):
  35         display_id = self._match_id(url)
  36         webpage = self._download_webpage(url, display_id)
  37
  38         endpoint_metadata = self._search_json(
  39             r'var\s+ilpostpodcast\s*=', webpage, 'metadata', display_id)
  40         episode_id = endpoint_metadata['post_id']
  41         podcast_id = endpoint_metadata['podcast_id']
  42         podcast_metadata = self._download_json(
  43             endpoint_metadata['ajax_url'], display_id, data=urlencode_postdata({
  44                 'action': 'checkpodcast',
  45                 'cookie': endpoint_metadata['cookie'],
  46                 'post_id': episode_id,
  47                 'podcast_id': podcast_id,
  48             }))
  49
  50         episode = traverse_obj(podcast_metadata, (
  51             'data', 'postcastList', lambda _, v: str(v['id']) == episode_id, {dict}), get_all=False)
  52         if not episode:
  53             raise ExtractorError('Episode could not be extracted')
  54
  55         return {
  56             'id': episode_id,
  57             'display_id': display_id,
  58             'series_id': podcast_id,
  59             'vcodec': 'none',
  60             **traverse_obj(episode, {
  61                 'title': ('title', {str}),
  62                 'description': ('description', {str}),
  63                 'url': ('podcast_raw_url', {url_or_none}),
  64                 'thumbnail': ('image', {url_or_none}),
  65                 'timestamp': ('timestamp', {int_or_none}),
  66                 'duration': ('milliseconds', {functools.partial(float_or_none, scale=1000)}),
  67                 'availability': ('free', {lambda v: 'public' if v else 'subscriber_only'}),
  68             }),
  69         }