1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-16 20:07:19 +01:00
youtube-dl/youtube_dl/extractor/freesound.py

40 lines
1.4 KiB
Python
Raw Normal View History

2014-02-10 21:03:14 +01:00
from __future__ import unicode_literals
2013-07-15 17:16:44 +02:00
import re
from .common import InfoExtractor
2014-02-10 21:03:14 +01:00
2013-07-15 17:16:44 +02:00
2013-07-15 21:33:45 +02:00
class FreesoundIE(InfoExtractor):
2014-02-10 21:03:14 +01:00
_VALID_URL = r'https?://(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
2013-07-15 17:17:09 +02:00
_TEST = {
2014-02-10 21:03:14 +01:00
'url': 'http://www.freesound.org/people/miklovan/sounds/194503/',
'md5': '12280ceb42c81f19a515c745eae07650',
'info_dict': {
'id': '194503',
'ext': 'mp3',
'title': 'gulls in the city.wav',
'uploader': 'miklovan',
'description': '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)
2014-02-10 21:03:14 +01:00
title = self._html_search_regex(
r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
webpage, 'music title', flags=re.DOTALL)
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
2014-02-10 21:03:14 +01:00
return {
'id': music_id,
'title': title,
'url': self._og_search_property('audio', webpage, 'music url'),
2013-07-15 21:33:45 +02:00
'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'),
'description': description,
2014-02-10 21:03:14 +01:00
}