youtube_dl/extractor/freesound.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class FreesoundIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
  10     _TEST = {
  11         'url': 'http://www.freesound.org/people/miklovan/sounds/194503/',
  12         'md5': '12280ceb42c81f19a515c745eae07650',
  13         'info_dict': {
  14             'id': '194503',
  15             'ext': 'mp3',
  16             'title': 'gulls in the city.wav',
  17             'uploader': 'miklovan',
  18             'description': 'the sounds of seagulls in the city',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         music_id = mobj.group('id')
  25         webpage = self._download_webpage(url, music_id)
  26         title = self._html_search_regex(
  27             r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
  28             webpage, 'music title', flags=re.DOTALL)
  29         description = self._html_search_regex(
  30             r'<div id="sound_description">(.*?)</div>', webpage, 'description',
  31             fatal=False, flags=re.DOTALL)
  32
  33         return {
  34             'id': music_id,
  35             'title': title,
  36             'url': self._og_search_property('audio', webpage, 'music url'),
  37             'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'),
  38             'description': description,
  39         }