1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-05 10:42:37 +01:00
yt-dlp/youtube_dl/extractor/newgrounds.py
Yen Chi Hsuan 6c3affcb18
[newgrounds] Fix uploader extraction
Closes #10584

Also change test URLs to HTTPS, as proposed by
@stepshal in #10593.

Closes #10593
2016-09-10 20:09:09 +08:00

47 lines
1.4 KiB
Python

from __future__ import unicode_literals
from .common import InfoExtractor
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',
'md5': 'fe6033d297591288fa1c1f780386f07a',
'info_dict': {
'id': '549479',
'ext': 'mp3',
'title': 'B7 - BusMode',
'uploader': 'Burn7',
}
}, {
'url': 'https://www.newgrounds.com/portal/view/673111',
'md5': '3394735822aab2478c31b1004fe5e5bc',
'info_dict': {
'id': '673111',
'ext': 'mp4',
'title': 'Dancin',
'uploader': 'Squirrelman82',
},
}]
def _real_extract(self, url):
media_id = self._match_id(url)
webpage = self._download_webpage(url, media_id)
title = self._html_search_regex(
r'<title>([^>]+)</title>', webpage, 'title')
uploader = self._html_search_regex(
r'Author\s*<a[^>]+>([^<]+)', webpage, 'uploader', fatal=False)
music_url = self._parse_json(self._search_regex(
r'"url":("[^"]+"),', webpage, ''), media_id)
return {
'id': media_id,
'title': title,
'url': music_url,
'uploader': uploader,
}