X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fteachertube.py;fp=youtube_dl%2Fextractor%2Fteachertube.py;h=73b4a363460f682b3f9bf8a6a1841b239e8f989f;hb=31a196d7f55d7d7676c08553474a5ec122178177;hp=d9868d569daa346bf7a1659b7bed6073b824b668;hpb=9b27e6c3b49175e1e9b8f809607e7fbdee4cb9ac;p=youtube-dl

diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py
index d9868d569..73b4a3634 100644
--- a/youtube_dl/extractor/teachertube.py
+++ b/youtube_dl/extractor/teachertube.py
@@ -86,22 +86,32 @@ class TeacherTubeIE(InfoExtractor):
         }
 
 
-class TeacherTubeClassroomIE(InfoExtractor):
-    IE_NAME = 'teachertube:classroom'
-    IE_DESC = 'teachertube.com online classrooms'
+class TeacherTubeUserIE(InfoExtractor):
+    IE_NAME = 'teachertube:user:collection'
+    IE_DESC = 'teachertube.com user and collection videos'
 
-    _VALID_URL = r'https?://(?:www\.)?teachertube\.com/view_classroom\.php\?user=(?P<user>[0-9a-zA-Z]+)'
+    _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?'
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user_id = mobj.group('user')
 
-        rss = self._download_xml(
-            'http://www.teachertube.com/rssclassroom.php?mode=user&username=%s' % user_id,
-            user_id, 'Downloading classroom RSS')
+        urls = []
+        webpage = self._download_webpage(url, user_id)
+        urls.extend(re.findall(
+            r'"sidebar_thumb_time">[0-9:]+</div>\s+<a href="(https?://(?:www\.)?teachertube\.com/(video|audio)/[^"]+)">',
+            webpage))
+        
+        pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[1:-1]
+        for p in pages:
+            more = 'http://www.teachertube.com/ajax-user/user-videos/%s?page=%s' % (user_id, p)
+            webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages) + 1))
+            urls.extend(re.findall(
+                r'"sidebar_thumb_time">[0-9:]+</div>\s+<a href="(https?://(?:www\.)?teachertube\.com/(video|audio)/[^"]+)">',
+                webpage))
 
         entries = []
-        for url in rss.findall('.//{http://search.yahoo.com/mrss/}player'):
-            entries.append(self.url_result(url.attrib['url'], 'TeacherTube'))
+        for url in urls:
+            entries.append(self.url_result(url, 'TeacherTube'))
 
         return self.playlist_result(entries, user_id)