yt_dlp/extractor/audioboom.py

   1 from .common import InfoExtractor
   2 from ..utils import clean_html, float_or_none, traverse_obj, unescapeHTML
   3
   4
   5 class AudioBoomIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
   7     _TESTS = [{
   8         'url': 'https://audioboom.com/posts/7398103-asim-chaudhry',
   9         'md5': '4d68be11c9f9daf3dab0778ad1e010c3',
  10         'info_dict': {
  11             'id': '7398103',
  12             'ext': 'mp3',
  13             'title': 'Asim Chaudhry',
  14             'description': 'md5:0ed714ae0e81e5d9119cac2f618ad679',
  15             'duration': 4000.99,
  16             'uploader': 'Sue Perkins: An hour or so with...',
  17             'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins',
  18         },
  19     }, {  # Direct mp3-file link
  20         'url': 'https://audioboom.com/posts/8128496.mp3',
  21         'md5': 'e329edf304d450def95c7f86a9165ee1',
  22         'info_dict': {
  23             'id': '8128496',
  24             'ext': 'mp3',
  25             'title': 'TCRNo8 / DAILY 03 - In Control',
  26             'description': 'md5:44665f142db74858dfa21c5b34787948',
  27             'duration': 1689.7,
  28             'uploader': 'Lost Dot Podcast: The Trans Pyrenees and Transcontinental Race',
  29             'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channels/5003904',
  30         },
  31     }, {
  32         'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
  33         'only_matching': True,
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38         webpage = self._download_webpage(f'https://audioboom.com/posts/{video_id}', video_id)
  39
  40         clip_store = self._search_json(
  41             r'data-react-class="V5DetailPagePlayer"\s*data-react-props=["\']',
  42             webpage, 'clip store', video_id, fatal=False, transform_source=unescapeHTML)
  43         clip = traverse_obj(clip_store, ('clips', 0), expected_type=dict) or {}
  44
  45         return {
  46             'id': video_id,
  47             'url': clip.get('clipURLPriorToLoading') or self._og_search_property('audio', webpage, 'audio url'),
  48             'title': clip.get('title') or self._html_search_meta(['og:title', 'og:audio:title', 'audio_title'], webpage),
  49             'description': (clip.get('description') or clean_html(clip.get('formattedDescription'))
  50                             or self._og_search_description(webpage)),
  51             'duration': float_or_none(clip.get('duration') or self._html_search_meta('weibo:audio:duration', webpage)),
  52             'uploader': clip.get('author') or self._html_search_meta(
  53                 ['og:audio:artist', 'twitter:audio:artist_name', 'audio_artist'], webpage, 'uploader'),
  54             'uploader_url': clip.get('author_url') or self._html_search_regex(
  55                 r'<div class="avatar flex-shrink-0">\s*<a href="(?P<uploader_url>http[^"]+)"',
  56                 webpage, 'uploader url', fatal=False),
  57         }