1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/youtube_dl/extractor/newgrounds.py

47 lines
1.4 KiB
Python
Raw Normal View History

2014-01-22 20:41:28 +00:00
from __future__ import unicode_literals
2013-09-18 14:54:45 +00:00
from .common import InfoExtractor
2013-09-18 20:14:43 +00:00
2013-09-18 14:54:45 +00:00
class NewgroundsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.newgrounds.com/audio/listen/549479',
2014-01-22 20:41:28 +00:00
'md5': 'fe6033d297591288fa1c1f780386f07a',
'info_dict': {
2014-02-02 11:03:36 +00:00
'id': '549479',
'ext': 'mp3',
'title': 'B7 - BusMode',
'uploader': 'Burn7',
2013-09-18 14:54:45 +00:00
}
}, {
'url': 'https://www.newgrounds.com/portal/view/673111',
'md5': '3394735822aab2478c31b1004fe5e5bc',
'info_dict': {
'id': '673111',
'ext': 'mp4',
'title': 'Dancin',
'uploader': 'Squirrelman82',
},
}]
2013-09-18 14:54:45 +00:00
def _real_extract(self, url):
media_id = self._match_id(url)
webpage = self._download_webpage(url, media_id)
2014-11-23 19:41:03 +00:00
2014-01-22 20:41:28 +00:00
title = self._html_search_regex(
r'<title>([^>]+)</title>', webpage, 'title')
2014-01-22 20:41:28 +00:00
uploader = self._html_search_regex(
r'Author\s*<a[^>]+>([^<]+)', webpage, 'uploader', fatal=False)
2014-11-23 19:41:03 +00:00
music_url = self._parse_json(self._search_regex(
r'"url":("[^"]+"),', webpage, ''), media_id)
2013-09-18 14:54:45 +00:00
2013-09-18 20:14:43 +00:00
return {
'id': media_id,
2014-01-22 20:41:28 +00:00
'title': title,
'url': music_url,
2013-09-18 14:54:45 +00:00
'uploader': uploader,
2013-09-18 20:14:43 +00:00
}