]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/soundgasm.py
[soundgasm:profile] Simplify
[yt-dlp.git] / youtube_dl / extractor / soundgasm.py
CommitLineData
1044f8af 1# coding: utf-8
2from __future__ import unicode_literals
3
4import re
5
6from .common import InfoExtractor
93b5071f 7from ..utils import clean_html
1044f8af 8
ba7aa464 9
1044f8af 10class SoundgasmIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<user>[0-9a-zA-Z_\-]+)/(?P<title>[0-9a-zA-Z_\-]+)'
12 _TEST = {
13 'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
14 'md5': '010082a2c802c5275bb00030743e75ad',
15 'info_dict': {
16 'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
17 'ext': 'm4a',
18 'title': 'ytdl_Piano-sample',
19 'description': 'Royalty Free Sample Music'
20 }
21 }
22
23 def _real_extract(self, url):
24 mobj = re.match(self._VALID_URL, url)
ba7aa464 25 display_id = mobj.group('title')
1044f8af 26 audio_title = mobj.group('user') + '_' + mobj.group('title')
ba7aa464
PH
27 webpage = self._download_webpage(url, display_id)
28 audio_url = self._html_search_regex(
29 r'(?s)m4a\:\s"([^"]+)"', webpage, 'audio URL')
1044f8af 30 audio_id = re.split('\/|\.', audio_url)[-2]
ba7aa464
PH
31 description = self._html_search_regex(
32 r'(?s)<li>Description:\s(.*?)<\/li>', webpage, 'description',
33 fatal=False)
1044f8af 34
35 return {
36 'id': audio_id,
ba7aa464 37 'display_id': display_id,
1044f8af 38 'url': audio_url,
39 'title': audio_title,
40 'description': description
41 }
93b5071f
LP
42
43class SoundgasmProfileIE(InfoExtractor):
3cc57f96 44 _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<id>[^/]+)'
93b5071f
LP
45 _TEST = {
46 'url': 'http://soundgasm.net/u/ytdl',
93b5071f 47 'info_dict': {
93b5071f 48 'id': 'ytdl',
3cc57f96
S
49 },
50 'playlist_count': 1,
93b5071f
LP
51 }
52
53 def _real_extract(self, url):
54 profile_id = self._match_id(url)
93b5071f 55
3cc57f96 56 webpage = self._download_webpage(url, profile_id)
93b5071f 57
3cc57f96
S
58 entries = [
59 self.url_result(audio_url, 'Soundgasm')
60 for audio_url in re.findall(r'href="([^"]+/u/%s/[^"]+)' % profile_id, webpage)]
93b5071f 61
3cc57f96 62 return self.playlist_result(entries, profile_id)