aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/soundgasm.py
blob: e004e2c5ab12705c8d9ff5e12b25f53579539c72 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor


class SoundgasmIE(InfoExtractor):
    IE_NAME = 'soundgasm'
    _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<user>[0-9a-zA-Z_\-]+)/(?P<title>[0-9a-zA-Z_\-]+)'
    _TEST = {
        'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
        'md5': '010082a2c802c5275bb00030743e75ad',
        'info_dict': {
            'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
            'ext': 'm4a',
            'title': 'ytdl_Piano-sample',
            'description': 'Royalty Free Sample Music'
        }
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        display_id = mobj.group('title')
        audio_title = mobj.group('user') + '_' + mobj.group('title')
        webpage = self._download_webpage(url, display_id)
        audio_url = self._html_search_regex(
            r'(?s)m4a\:\s"([^"]+)"', webpage, 'audio URL')
        audio_id = re.split(r'\/|\.', audio_url)[-2]
        description = self._html_search_regex(
            r'(?s)<li>Description:\s(.*?)<\/li>', webpage, 'description',
            fatal=False)

        return {
            'id': audio_id,
            'display_id': display_id,
            'url': audio_url,
            'title': audio_title,
            'description': description
        }


class SoundgasmProfileIE(InfoExtractor):
    IE_NAME = 'soundgasm:profile'
    _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<id>[^/]+)/?(?:\#.*)?$'
    _TEST = {
        'url': 'http://soundgasm.net/u/ytdl',
        'info_dict': {
            'id': 'ytdl',
        },
        'playlist_count': 1,
    }

    def _real_extract(self, url):
        profile_id = self._match_id(url)

        webpage = self._download_webpage(url, profile_id)

        entries = [
            self.url_result(audio_url, 'Soundgasm')
            for audio_url in re.findall(r'href="([^"]+/u/%s/[^"]+)' % profile_id, webpage)]

        return self.playlist_result(entries, profile_id)