yt-dlp/youtube_dl/extractor/newgrounds.py

54 lines
1.6 KiB
Python
Raw Normal View History

2014-01-22 21:41:28 +01:00
from __future__ import unicode_literals
2013-09-18 16:54:45 +02:00
import json
import re
from .common import InfoExtractor
2013-09-18 22:14:43 +02:00
2013-09-18 16:54:45 +02:00
class NewgroundsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
_TESTS = [{
2014-01-22 21:41:28 +01:00
'url': 'http://www.newgrounds.com/audio/listen/549479',
'md5': 'fe6033d297591288fa1c1f780386f07a',
'info_dict': {
2014-02-02 12:03:36 +01:00
'id': '549479',
'ext': 'mp3',
'title': 'B7 - BusMode',
'uploader': 'Burn7',
2013-09-18 16:54:45 +02:00
}
}, {
'url': 'http://www.newgrounds.com/portal/view/673111',
'md5': '3394735822aab2478c31b1004fe5e5bc',
'info_dict': {
'id': '673111',
'ext': 'mp4',
'title': 'Dancin',
'uploader': 'Squirrelman82',
},
}]
2013-09-18 16:54:45 +02:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
music_id = mobj.group('id')
webpage = self._download_webpage(url, music_id)
2014-11-23 20:41:03 +01:00
2014-01-22 21:41:28 +01:00
title = self._html_search_regex(
r'<title>([^>]+)</title>', webpage, 'title')
2014-01-22 21:41:28 +01:00
uploader = self._html_search_regex(
[r',"artist":"([^"]+)",', r'[\'"]owner[\'"]\s*:\s*[\'"]([^\'"]+)[\'"],'],
webpage, 'uploader')
2014-11-23 20:41:03 +01:00
2014-01-22 21:41:28 +01:00
music_url_json_string = self._html_search_regex(
r'({"url":"[^"]+"),', webpage, 'music url') + '}'
2013-09-18 16:54:45 +02:00
music_url_json = json.loads(music_url_json_string)
music_url = music_url_json['url']
2013-09-18 22:14:43 +02:00
return {
2014-01-22 21:41:28 +01:00
'id': music_id,
'title': title,
'url': music_url,
2013-09-18 16:54:45 +02:00
'uploader': uploader,
2013-09-18 22:14:43 +02:00
}