[airmozilla] Add new extractor
[youtube-dl] / youtube_dl / extractor / soundgasm.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7
8
9 class SoundgasmIE(InfoExtractor):
10     _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<user>[0-9a-zA-Z_\-]+)/(?P<title>[0-9a-zA-Z_\-]+)'
11     _TEST = {
12         'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
13         'md5': '010082a2c802c5275bb00030743e75ad',
14         'info_dict': {
15             'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
16             'ext': 'm4a',
17             'title': 'ytdl_Piano-sample',
18             'description': 'Royalty Free Sample Music'
19         }
20     }
21
22     def _real_extract(self, url):
23         mobj = re.match(self._VALID_URL, url)
24         display_id = mobj.group('title')
25         audio_title = mobj.group('user') + '_' + mobj.group('title')
26         webpage = self._download_webpage(url, display_id)
27         audio_url = self._html_search_regex(
28             r'(?s)m4a\:\s"([^"]+)"', webpage, 'audio URL')
29         audio_id = re.split('\/|\.', audio_url)[-2]
30         description = self._html_search_regex(
31             r'(?s)<li>Description:\s(.*?)<\/li>', webpage, 'description',
32             fatal=False)
33
34         return {
35             'id': audio_id,
36             'display_id': display_id,
37             'url': audio_url,
38             'title': audio_title,
39             'description': description
40         }