2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..utils import clean_html
10 class SoundgasmIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<user>[0-9a-zA-Z_\-]+)/(?P<title>[0-9a-zA-Z_\-]+)'
13 'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
14 'md5': '010082a2c802c5275bb00030743e75ad',
16 'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
18 'title': 'ytdl_Piano-sample',
19 'description': 'Royalty Free Sample Music'
23 def _real_extract(self, url):
24 mobj = re.match(self._VALID_URL, url)
25 display_id = mobj.group('title')
26 audio_title = mobj.group('user') + '_' + mobj.group('title')
27 webpage = self._download_webpage(url, display_id)
28 audio_url = self._html_search_regex(
29 r'(?s)m4a\:\s"([^"]+)"', webpage, 'audio URL')
30 audio_id = re.split('\/|\.', audio_url)[-2]
31 description = self._html_search_regex(
32 r'(?s)<li>Description:\s(.*?)<\/li>', webpage, 'description',
37 'display_id': display_id,
40 'description': description
43 class SoundgasmProfileIE(InfoExtractor):
44 _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<id>[0-9a-zA-Z_\-]+)/?$'
46 'url': 'http://soundgasm.net/u/ytdl',
55 def _real_extract(self, url):
56 profile_id = self._match_id(url)
57 webpage = self._download_webpage(url, profile_id)
59 ids = re.findall(r'''<a\s+href=".+?/u/%s/([^/]+)">''' % re.escape(profile_id), webpage)
60 ids = [clean_html(id) for id in ids]
66 'url': ('http://soundgasm.net/u/%s/%s' % (profile_id, id))