ytdl-nightly/youtube_dl/extractor/freesound.py

37 lines
1.5 KiB
Python
Raw Normal View History

2013-07-15 17:16:44 +02:00
import re
from .common import InfoExtractor
2013-07-15 21:33:45 +02:00
from ..utils import determine_ext
2013-07-15 17:16:44 +02:00
2013-07-15 21:33:45 +02:00
class FreesoundIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
2013-07-15 17:17:09 +02:00
_TEST = {
u'url': u'http://www.freesound.org/people/miklovan/sounds/194503/',
u'file': u'194503.mp3',
u'md5': u'12280ceb42c81f19a515c745eae07650',
u'info_dict': {
2013-07-15 21:33:45 +02:00
u"title": u"gulls in the city.wav",
u"uploader" : u"miklovan",
u'description': u'the sounds of seagulls in the city',
2013-07-15 17:17:09 +02:00
}
}
2013-07-15 17:16:44 +02:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2013-07-15 21:33:45 +02:00
music_id = mobj.group('id')
2013-07-15 17:16:44 +02:00
webpage = self._download_webpage(url, music_id)
2013-07-15 21:33:45 +02:00
title = self._html_search_regex(r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
webpage, 'music title', flags=re.DOTALL)
music_url = self._og_search_property('audio', webpage, 'music url')
description = self._html_search_regex(r'<div id="sound_description">(.*?)</div>',
webpage, 'description', fatal=False, flags=re.DOTALL)
2013-07-15 17:16:44 +02:00
return [{
'id': music_id,
'title': title,
'url': music_url,
2013-07-15 21:33:45 +02:00
'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'),
'ext': determine_ext(music_url),
'description': description,
}]