yt_dlp/extractor/whyp.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     float_or_none,
   4     str_or_none,
   5     traverse_obj,
   6     url_or_none,
   7 )
   8
   9
  10 class WhypIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?whyp\.it/tracks/(?P<id>\d+)'
  12     _TESTS = [{
  13         'url': 'https://www.whyp.it/tracks/18337/home-page-example-track-b4kq7',
  14         'md5': 'c1187b42ebf8605284e3dc92aeb33d16',
  15         'info_dict': {
  16             'url': 'https://cdn.whyp.it/50eb17cc-e9ff-4e18-b89b-dc9206a95cb1.mp3',
  17             'id': '18337',
  18             'title': 'Home Page Example Track',
  19             'description': 'md5:bd758000fb93f3159339c852b5b9133c',
  20             'ext': 'mp3',
  21             'duration': 52.82,
  22             'uploader': 'Brad',
  23             'uploader_id': '1',
  24             'thumbnail': 'https://cdn.whyp.it/a537bb36-3373-4c61-96c8-27fc1b2f427a.jpg',
  25         },
  26     }, {
  27         'url': 'https://www.whyp.it/tracks/18337',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         unique_id = self._match_id(url)
  33         webpage = self._download_webpage(url, unique_id)
  34         data = self._search_nuxt_data(webpage, unique_id)['rawTrack']
  35
  36         return {
  37             'url': data['audio_url'],
  38             'id': unique_id,
  39             **traverse_obj(data, {
  40                 'title': 'title',
  41                 'description': 'description',
  42                 'duration': ('duration', {float_or_none}),
  43                 'uploader': ('user', 'username'),
  44                 'uploader_id': ('user', 'id', {str_or_none}),
  45                 'thumbnail': ('artwork_url', {url_or_none}),
  46             }),
  47             'ext': 'mp3',
  48             'vcodec': 'none',
  49             'http_headers': {'Referer': 'https://whyp.it/'},
  50         }