yt_dlp/extractor/audioboom.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     float_or_none,
   5     unescapeHTML,
   6     traverse_obj,
   7 )
   8
   9
  10 class AudioBoomIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
  12     _TESTS = [{
  13         'url': 'https://audioboom.com/posts/7398103-asim-chaudhry',
  14         'md5': '4d68be11c9f9daf3dab0778ad1e010c3',
  15         'info_dict': {
  16             'id': '7398103',
  17             'ext': 'mp3',
  18             'title': 'Asim Chaudhry',
  19             'description': 'md5:0ed714ae0e81e5d9119cac2f618ad679',
  20             'duration': 4000.99,
  21             'uploader': 'Sue Perkins: An hour or so with...',
  22             'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins',
  23         }
  24     }, {  # Direct mp3-file link
  25         'url': 'https://audioboom.com/posts/8128496.mp3',
  26         'md5': 'e329edf304d450def95c7f86a9165ee1',
  27         'info_dict': {
  28             'id': '8128496',
  29             'ext': 'mp3',
  30             'title': 'TCRNo8 / DAILY 03 - In Control',
  31             'description': 'md5:44665f142db74858dfa21c5b34787948',
  32             'duration': 1689.7,
  33             'uploader': 'Lost Dot Podcast: The Trans Pyrenees and Transcontinental Race',
  34             'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channels/5003904',
  35         }
  36     }, {
  37         'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
  38         'only_matching': True,
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43         webpage = self._download_webpage(f'https://audioboom.com/posts/{video_id}', video_id)
  44
  45         clip_store = self._search_json(
  46             r'data-react-class="V5DetailPagePlayer"\s*data-react-props=["\']',
  47             webpage, 'clip store', video_id, fatal=False, transform_source=unescapeHTML)
  48         clip = traverse_obj(clip_store, ('clips', 0), expected_type=dict) or {}
  49
  50         return {
  51             'id': video_id,
  52             'url': clip.get('clipURLPriorToLoading') or self._og_search_property('audio', webpage, 'audio url'),
  53             'title': clip.get('title') or self._html_search_meta(['og:title', 'og:audio:title', 'audio_title'], webpage),
  54             'description': (clip.get('description') or clean_html(clip.get('formattedDescription'))
  55                             or self._og_search_description(webpage)),
  56             'duration': float_or_none(clip.get('duration') or self._html_search_meta('weibo:audio:duration', webpage)),
  57             'uploader': clip.get('author') or self._html_search_meta(
  58                 ['og:audio:artist', 'twitter:audio:artist_name', 'audio_artist'], webpage, 'uploader'),
  59             'uploader_url': clip.get('author_url') or self._html_search_regex(
  60                 r'<div class="avatar flex-shrink-0">\s*<a href="(?P<uploader_url>http[^"]+)"',
  61                 webpage, 'uploader url', fatal=False),
  62         }