youtube_dl/extractor/freesound.py

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