yt_dlp/extractor/audioboom.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     float_or_none,
   5 )
   6
   7
   8 class AudioBoomIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
  10     _TESTS = [{
  11         'url': 'https://audioboom.com/posts/7398103-asim-chaudhry',
  12         'md5': '7b00192e593ff227e6a315486979a42d',
  13         'info_dict': {
  14             'id': '7398103',
  15             'ext': 'mp3',
  16             'title': 'Asim Chaudhry',
  17             'description': 'md5:2f3fef17dacc2595b5362e1d7d3602fc',
  18             'duration': 4000.99,
  19             'uploader': 'Sue Perkins: An hour or so with...',
  20             'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins',
  21         }
  22     }, {
  23         'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
  24         'only_matching': True,
  25     }]
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29
  30         webpage = self._download_webpage(url, video_id)
  31
  32         clip = None
  33
  34         clip_store = self._parse_json(
  35             self._html_search_regex(
  36                 r'data-new-clip-store=(["\'])(?P<json>{.+?})\1',
  37                 webpage, 'clip store', default='{}', group='json'),
  38             video_id, fatal=False)
  39         if clip_store:
  40             clips = clip_store.get('clips')
  41             if clips and isinstance(clips, list) and isinstance(clips[0], dict):
  42                 clip = clips[0]
  43
  44         def from_clip(field):
  45             if clip:
  46                 return clip.get(field)
  47
  48         audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property(
  49             'audio', webpage, 'audio url')
  50         title = from_clip('title') or self._html_search_meta(
  51             ['og:title', 'og:audio:title', 'audio_title'], webpage)
  52         description = from_clip('description') or clean_html(from_clip('formattedDescription')) or self._og_search_description(webpage)
  53
  54         duration = float_or_none(from_clip('duration') or self._html_search_meta(
  55             'weibo:audio:duration', webpage))
  56
  57         uploader = from_clip('author') or self._html_search_meta(
  58             ['og:audio:artist', 'twitter:audio:artist_name', 'audio_artist'], webpage, 'uploader')
  59         uploader_url = from_clip('author_url') or self._html_search_meta(
  60             'audioboo:channel', webpage, 'uploader url')
  61
  62         return {
  63             'id': video_id,
  64             'url': audio_url,
  65             'title': title,
  66             'description': description,
  67             'duration': duration,
  68             'uploader': uploader,
  69             'uploader_url': uploader_url,
  70         }