Merge branch 'master' of https://github.com/DarkstaIkers/youtube-dl into DarkstaIkers...

[youtube-dl] / youtube_dl / extractor / newgrounds.py

diff --git a/youtube_dl/extractor/newgrounds.py b/youtube_dl/extractor/newgrounds.py
index 2ef80bce02a8ec95e1a748cbcd27ee1631aeca59..9bea610c88a4ac48cc1b84ed5c3fae45789d643e 100644 (file)
--- a/youtube_dl/extractor/newgrounds.py
+++ b/youtube_dl/extractor/newgrounds.py
@@ -1,38 +1,46 @@
-import json
-import re
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import determine_ext
 
 
 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',
-        u'md5': u'fe6033d297591288fa1c1f780386f07a',
-        u'info_dict': {
-            u"title": u"B7 - BusMode",
-            u"uploader": u"Burn7",
+    _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):
-        mobj = re.match(self._VALID_URL, url)
-        music_id = mobj.group('id')
-        webpage = self._download_webpage(url, music_id)
-        
-        title = self._html_search_regex(r',"name":"([^"]+)",', webpage, u'music title')
-        uploader = self._html_search_regex(r',"artist":"([^"]+)",', webpage, u'music uploader')
-        
-        music_url_json_string = self._html_search_regex(r'({"url":"[^"]+"),', webpage, u'music url') + '}'
-        music_url_json = json.loads(music_url_json_string)
-        music_url = music_url_json['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':       music_id,
-            'title':    title,
-            'url':      music_url,
+            'id': media_id,
+            'title': title,
+            'url': music_url,
             'uploader': uploader,
-            'ext':      determine_ext(music_url),
         }