aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2016-04-16 17:36:30 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2016-04-16 17:41:56 +0800
commit0de968b58408a5584c9ad51f646f07e0fe161def (patch)
tree1e1d6d1474eab9fd144bb0fb8426ca2d071e9e13 /youtube_dl/extractor
parent0841d5013c21457932b34af6a121f26619ba5aca (diff)
[newgrounds] Support videos (closes #9138)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/newgrounds.py21
1 files changed, 16 insertions, 5 deletions
diff --git a/youtube_dl/extractor/newgrounds.py b/youtube_dl/extractor/newgrounds.py
index cd117b04e..705940323 100644
--- a/youtube_dl/extractor/newgrounds.py
+++ b/youtube_dl/extractor/newgrounds.py
@@ -7,8 +7,8 @@ from .common import InfoExtractor
class NewgroundsIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/audio/listen/(?P<id>[0-9]+)'
- _TEST = {
+ _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
+ _TESTS = [{
'url': 'http://www.newgrounds.com/audio/listen/549479',
'md5': 'fe6033d297591288fa1c1f780386f07a',
'info_dict': {
@@ -17,7 +17,16 @@ class NewgroundsIE(InfoExtractor):
'title': 'B7 - BusMode',
'uploader': 'Burn7',
}
- }
+ }, {
+ 'url': 'http://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)
@@ -25,9 +34,11 @@ class NewgroundsIE(InfoExtractor):
webpage = self._download_webpage(url, music_id)
title = self._html_search_regex(
- r',"name":"([^"]+)",', webpage, 'music title')
+ r'<title>([^>]+)</title>', webpage, 'title')
+
uploader = self._html_search_regex(
- r',"artist":"([^"]+)",', webpage, 'music uploader')
+ [r',"artist":"([^"]+)",', r'[\'"]owner[\'"]\s*:\s*[\'"]([^\'"]+)[\'"],'],
+ webpage, 'uploader')
music_url_json_string = self._html_search_regex(
r'({"url":"[^"]+"),', webpage, 'music url') + '}'