[TeacherTube] add user + collection, removed classrooms

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

diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py
index b3cb6bd76db9b691135a9a32e2d9ab5cda1f8655..73b4a363460f682b3f9bf8a6a1841b239e8f989f 100644 (file)
--- a/youtube_dl/extractor/teachertube.py
+++ b/youtube_dl/extractor/teachertube.py
@@ -14,7 +14,7 @@ class TeacherTubeIE(InfoExtractor):
     IE_NAME = 'teachertube'
     IE_DESC = 'teachertube.com videos'
 
-    _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=)(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=|video/|audio/)(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997',
@@ -66,6 +66,7 @@ class TeacherTubeIE(InfoExtractor):
 
         media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage)
         media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage))
+        media_urls.extend(re.findall(r'\'file\'\s*:\s*["\']([^"\']+)["\'],', webpage))
 
         formats = [
             {
@@ -79,28 +80,38 @@ class TeacherTubeIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'thumbnail': self._html_search_regex(r'var\s+thumbUrl\s*=\s*"([^"]+)"', webpage, 'thumbnail'),
+            'thumbnail': self._html_search_regex(r'\'image\'\s*:\s*["\']([^"\']+)["\']', webpage, 'thumbnail'),
             'formats': formats,
             'description': description,
         }
 
 
-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)