2014-06-25 18:07:23 +02:00
|
|
|
# coding: utf-8
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
import re
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2015-02-23 12:11:19 +01:00
|
|
|
from ..utils import clean_html
|
2014-06-25 18:07:23 +02:00
|
|
|
|
2014-06-25 23:47:38 +02:00
|
|
|
|
2014-06-25 18:07:23 +02:00
|
|
|
class SoundgasmIE(InfoExtractor):
|
|
|
|
_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)
|
2014-06-25 23:47:38 +02:00
|
|
|
display_id = mobj.group('title')
|
2014-06-25 18:07:23 +02:00
|
|
|
audio_title = mobj.group('user') + '_' + mobj.group('title')
|
2014-06-25 23:47:38 +02:00
|
|
|
webpage = self._download_webpage(url, display_id)
|
|
|
|
audio_url = self._html_search_regex(
|
|
|
|
r'(?s)m4a\:\s"([^"]+)"', webpage, 'audio URL')
|
2014-06-25 18:07:23 +02:00
|
|
|
audio_id = re.split('\/|\.', audio_url)[-2]
|
2014-06-25 23:47:38 +02:00
|
|
|
description = self._html_search_regex(
|
|
|
|
r'(?s)<li>Description:\s(.*?)<\/li>', webpage, 'description',
|
|
|
|
fatal=False)
|
2014-06-25 18:07:23 +02:00
|
|
|
|
|
|
|
return {
|
|
|
|
'id': audio_id,
|
2014-06-25 23:47:38 +02:00
|
|
|
'display_id': display_id,
|
2014-06-25 18:07:23 +02:00
|
|
|
'url': audio_url,
|
|
|
|
'title': audio_title,
|
|
|
|
'description': description
|
|
|
|
}
|
2015-02-23 12:11:19 +01:00
|
|
|
|
|
|
|
class SoundgasmProfileIE(InfoExtractor):
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<id>[0-9a-zA-Z_\-]+)/?$'
|
|
|
|
_TEST = {
|
|
|
|
'url': 'http://soundgasm.net/u/ytdl',
|
|
|
|
'playlist_count': 1,
|
|
|
|
'info_dict': {
|
|
|
|
'_type': 'playlist',
|
|
|
|
'id': 'ytdl',
|
|
|
|
'title': 'ytdl'
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
profile_id = self._match_id(url)
|
|
|
|
webpage = self._download_webpage(url, profile_id)
|
|
|
|
|
|
|
|
ids = re.findall(r'''<a\s+href=".+?/u/%s/([^/]+)">''' % re.escape(profile_id), webpage)
|
|
|
|
ids = [clean_html(id) for id in ids]
|
|
|
|
|
|
|
|
entries = []
|
|
|
|
for id in ids:
|
|
|
|
entries.append({
|
|
|
|
'_type': 'url',
|
|
|
|
'url': ('http://soundgasm.net/u/%s/%s' % (profile_id, id))
|
|
|
|
})
|
|
|
|
|
|
|
|
info_dict = {
|
|
|
|
'_type': 'playlist',
|
|
|
|
'id': profile_id,
|
|
|
|
'title': profile_id,
|
|
|
|
'entries': entries
|
|
|
|
}
|
|
|
|
|
|
|
|
return info_dict;
|