youtube-dl

commit 31a196d7f55d7d7676c08553474a5ec122178177
parent 9b27e6c3b49175e1e9b8f809607e7fbdee4cb9ac
Author: Petr Půlpán <Pulpan3@gmail.com>
Date:   Sun, 29 Jun 2014 13:45:10 +0200

[TeacherTube] add user + collection, removed classrooms

Diffstat:
M
test/test_playlists.py
 | 
10
+++++-----
M
youtube_dl/extractor/__init__.py
 | 
2
+-
M
youtube_dl/extractor/teachertube.py
 | 
28
+++++++++++++++++++---------

3 files changed, 25 insertions(+), 15 deletions(-)
diff --git a/test/test_playlists.py b/test/test_playlists.py
@@ -28,7 +28,7 @@ from youtube_dl.extractor import (
     SoundcloudSetIE,
     SoundcloudUserIE,
     SoundcloudPlaylistIE,
-    TeacherTubeClassroomIE,
+    TeacherTubeUserIE,
     LivestreamIE,
     LivestreamOriginalIE,
     NHLVideocenterIE,
@@ -379,13 +379,13 @@ class TestPlaylists(unittest.TestCase):
             result['title'], 'Brace Yourself - Today\'s Weirdest News')
         self.assertTrue(len(result['entries']) >= 10)
 
-    def test_TeacherTubeClassroom(self):
+    def test_TeacherTubeUser(self):
         dl = FakeYDL()
-        ie = TeacherTubeClassroomIE(dl)
-        result = ie.extract('http://www.teachertube.com/view_classroom.php?user=rbhagwati2')
+        ie = TeacherTubeUserIE(dl)
+        result = ie.extract('http://www.teachertube.com/user/profile/rbhagwati2')
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'rbhagwati2')
-        self.assertTrue(len(result['entries']) >= 20)
+        self.assertTrue(len(result['entries']) >= 179)
 
 if __name__ == '__main__':
     unittest.main()
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -282,7 +282,7 @@ from .sztvhu import SztvHuIE
 from .tagesschau import TagesschauIE
 from .teachertube import (
     TeacherTubeIE,
-    TeacherTubeClassroomIE,
+    TeacherTubeUserIE,
 )
 from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
diff --git 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)