debian/copyright: Fix lintian's dep5-copyright-license-name-not-unique.

[youtubedl] / youtube_dl / extractor / teachertube.py

diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py
index 2c2113b1404fb3631126636bdb38ba839008a404..82675431f863fded8768241e2ad21c4874f8525d 100644 (file)
--- a/youtube_dl/extractor/teachertube.py
+++ b/youtube_dl/extractor/teachertube.py
@@ -57,12 +57,10 @@ class TeacherTubeIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        title = self._html_search_meta('title', webpage, 'title')
+        title = self._html_search_meta('title', webpage, 'title', fatal=True)
         TITLE_SUFFIX = ' - TeacherTube'
         if title.endswith(TITLE_SUFFIX):
             title = title[:-len(TITLE_SUFFIX)].strip()
@@ -101,7 +99,18 @@ class TeacherTubeUserIE(InfoExtractor):
 
     _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(user/profile|collection)/(?P<user>[0-9a-zA-Z]+)/?'
 
-    _MEDIA_RE = r'(?s)"sidebar_thumb_time">[0-9:]+</div>.+?<a href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)">'
+    _MEDIA_RE = r'''(?sx)
+        class="?sidebar_thumb_time"?>[0-9:]+</div>
+        \s*
+        <a\s+href="(https?://(?:www\.)?teachertube\.com/(?:video|audio)/[^"]+)"
+    '''
+    _TEST = {
+        'url': 'http://www.teachertube.com/user/profile/rbhagwati2',
+        'info_dict': {
+            'id': 'rbhagwati2'
+        },
+        'playlist_mincount': 179,
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -110,15 +119,13 @@ class TeacherTubeUserIE(InfoExtractor):
         urls = []
         webpage = self._download_webpage(url, user_id)
         urls.extend(re.findall(self._MEDIA_RE, webpage))
-        
-        pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[1:-1]
+
+        pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[:-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(self._MEDIA_RE, webpage))
-
-        entries = []
-        for url in urls:
-            entries.append(self.url_result(url, 'TeacherTube'))
+            webpage = self._download_webpage(more, user_id, 'Downloading page %s/%s' % (p, len(pages)))
+            video_urls = re.findall(self._MEDIA_RE, webpage)
+            urls.extend(video_urls)
 
+        entries = [self.url_result(vurl, 'TeacherTube') for vurl in urls]
         return self.playlist_result(entries, user_id)