X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fnewgrounds.py;h=9bea610c88a4ac48cc1b84ed5c3fae45789d643e;hb=9cafc3fd8b54b9b91a145cddf9e4db0bd59e1b5f;hp=cd117b04edeff88d90842f2ed8e15a8c43bde714;hpb=cf372f0778e82cdc181a6173909589e640ac29fb;p=youtube-dl diff --git a/youtube_dl/extractor/newgrounds.py b/youtube_dl/extractor/newgrounds.py index cd117b04e..9bea610c8 100644 --- a/youtube_dl/extractor/newgrounds.py +++ b/youtube_dl/extractor/newgrounds.py @@ -1,15 +1,12 @@ from __future__ import unicode_literals -import json -import re - from .common import InfoExtractor class NewgroundsIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/audio/listen/(?P[0-9]+)' - _TEST = { - 'url': 'http://www.newgrounds.com/audio/listen/549479', + _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P[0-9]+)' + _TESTS = [{ + 'url': 'https://www.newgrounds.com/audio/listen/549479', 'md5': 'fe6033d297591288fa1c1f780386f07a', 'info_dict': { 'id': '549479', @@ -17,25 +14,32 @@ class NewgroundsIE(InfoExtractor): '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): - mobj = re.match(self._VALID_URL, url) - music_id = mobj.group('id') - webpage = self._download_webpage(url, music_id) + media_id = self._match_id(url) + webpage = self._download_webpage(url, media_id) title = self._html_search_regex( - r',"name":"([^"]+)",', webpage, 'music title') + r'([^>]+)', webpage, 'title') + uploader = self._html_search_regex( - r',"artist":"([^"]+)",', webpage, 'music uploader') + r'Author\s*]+>([^<]+)', webpage, 'uploader', fatal=False) - music_url_json_string = self._html_search_regex( - r'({"url":"[^"]+"),', webpage, 'music url') + '}' - music_url_json = json.loads(music_url_json_string) - music_url = music_url_json['url'] + music_url = self._parse_json(self._search_regex( + r'"url":("[^"]+"),', webpage, ''), media_id) return { - 'id': music_id, + 'id': media_id, 'title': title, 'url': music_url, 'uploader': uploader,