yt-dlc/youtube_dl/extractor/newgrounds.py

39 lines
1.3 KiB
Python
Raw Normal View History

2013-09-18 16:54:45 +02:00
import json
import re
from .common import InfoExtractor
from ..utils import determine_ext
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/(?P<id>\d+)'
_TEST = {
u'url': u'http://www.newgrounds.com/audio/listen/549479',
u'file': u'549479.mp3',
2013-09-18 18:17:12 +02:00
u'md5': u'fe6033d297591288fa1c1f780386f07a',
2013-09-18 16:54:45 +02:00
u'info_dict': {
u"title": u"B7 - BusMode",
2013-09-18 22:14:43 +02:00
u"uploader": u"Burn7",
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)
2013-09-18 22:14:43 +02:00
title = self._html_search_regex(r',"name":"([^"]+)",', webpage, u'music title')
uploader = self._html_search_regex(r',"artist":"([^"]+)",', webpage, u'music uploader')
2013-09-18 16:54:45 +02:00
2013-09-18 22:14:43 +02:00
music_url_json_string = self._html_search_regex(r'({"url":"[^"]+"),', webpage, u'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 {
2013-09-18 16:54:45 +02:00
'id': music_id,
2013-09-18 22:14:43 +02:00
'title': title,
2013-09-18 16:54:45 +02:00
'url': music_url,
'uploader': uploader,
'ext': determine_ext(music_url),
2013-09-18 22:14:43 +02:00
}