From 1044f8afd2156e16e2a0e8d6e656e6aab1f1306b Mon Sep 17 00:00:00 2001 From: pachacamac Date: Wed, 25 Jun 2014 18:07:23 +0200 Subject: [Soundgasm] Add new extractor --- youtube_dl/extractor/soundgasm.py | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) create mode 100644 youtube_dl/extractor/soundgasm.py (limited to 'youtube_dl/extractor/soundgasm.py') diff --git a/youtube_dl/extractor/soundgasm.py b/youtube_dl/extractor/soundgasm.py new file mode 100644 index 000000000..b9d4c6a56 --- /dev/null +++ b/youtube_dl/extractor/soundgasm.py @@ -0,0 +1,34 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + +class SoundgasmIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P[0-9a-zA-Z_\-]+)/(?P[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) + audio_title = mobj.group('user') + '_' + mobj.group('title') + webpage = self._download_webpage(url, '') + audio_url = self._html_search_regex(r'(?s)m4a\:\s"([^"]+)"', webpage, 'audio URL') + audio_id = re.split('\/|\.', audio_url)[-2] + description = self._html_search_regex(r'(?s)<li>Description:\s(.*?)<\/li>', webpage, 'description', fatal=False, flags=re.DOTALL) + + return { + 'id': audio_id, + 'url': audio_url, + 'title': audio_title, + 'description': description + } -- cgit v1.2.3