yt-dlp/youtube_dl/extractor/soundgasm.py

78 lines
2.4 KiB
Python
Raw Normal View History

2014-06-25 18:07:23 +02:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-06-25 18:07:23 +02:00
class SoundgasmIE(InfoExtractor):
IE_NAME = 'soundgasm'
_VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<user>[0-9a-zA-Z_-]+)/(?P<display_id>[0-9a-zA-Z_-]+)'
2014-06-25 18:07:23 +02:00
_TEST = {
'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
'md5': '010082a2c802c5275bb00030743e75ad',
'info_dict': {
'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
'ext': 'm4a',
'title': 'Piano sample',
'description': 'Royalty Free Sample Music',
'uploader': 'ytdl',
2014-06-25 18:07:23 +02:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
audio_url = self._html_search_regex(
r'(?s)m4a\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'audio URL', group='url')
title = self._search_regex(
r'<div[^>]+\bclass=["\']jp-title[^>]+>([^<]+)',
webpage, 'title', default=display_id)
description = self._html_search_regex(
(r'(?s)<div[^>]+\bclass=["\']jp-description[^>]+>(.+?)</div>',
r'(?s)<li>Description:\s(.*?)<\/li>'),
webpage, 'description', fatal=False)
audio_id = self._search_regex(
r'/([^/]+)\.m4a', audio_url, 'audio id', default=display_id)
2014-06-25 18:07:23 +02:00
return {
'id': audio_id,
'display_id': display_id,
2014-06-25 18:07:23 +02:00
'url': audio_url,
'vcodec': 'none',
'title': title,
'description': description,
'uploader': mobj.group('user'),
2014-06-25 18:07:23 +02:00
}
2015-02-23 12:11:19 +01:00
2015-02-23 16:51:21 +01:00
2015-02-23 12:11:19 +01:00
class SoundgasmProfileIE(InfoExtractor):
IE_NAME = 'soundgasm:profile'
2015-02-23 16:30:30 +01:00
_VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<id>[^/]+)/?(?:\#.*)?$'
2015-02-23 12:11:19 +01:00
_TEST = {
'url': 'http://soundgasm.net/u/ytdl',
'info_dict': {
'id': 'ytdl',
2015-02-23 16:27:24 +01:00
},
'playlist_count': 1,
2015-02-23 12:11:19 +01:00
}
def _real_extract(self, url):
profile_id = self._match_id(url)
2015-02-23 16:27:24 +01:00
webpage = self._download_webpage(url, profile_id)
2015-02-23 12:11:19 +01:00
2015-02-23 16:27:24 +01:00
entries = [
self.url_result(audio_url, 'Soundgasm')
for audio_url in re.findall(r'href="([^"]+/u/%s/[^"]+)' % profile_id, webpage)]
2015-02-23 12:11:19 +01:00
2015-02-23 16:27:24 +01:00
return self.playlist_result(entries, profile_id)