[vgtv] Add new extractor

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

diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py
index 73b4a363460f682b3f9bf8a6a1841b239e8f989f..2c2113b1404fb3631126636bdb38ba839008a404 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=|video/|audio/)(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?teachertube\.com/(viewVideo\.php\?video_id=|music\.php\?music_id=|video/(?:[\da-z-]+-)?|audio/)(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.teachertube.com/viewVideo.php?video_id=339997',
@@ -45,6 +45,15 @@ class TeacherTubeIE(InfoExtractor):
             'title': 'PER ASPERA AD ASTRA',
             'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNI?KE ?KOLE P',
         },
+    }, {
+        'url': 'http://www.teachertube.com/video/intro-video-schleicher-297790',
+        'md5': '9c79fbb2dd7154823996fc28d4a26998',
+        'info_dict': {
+            'id': '297790',
+            'ext': 'mp4',
+            'title': 'Intro Video - Schleicher',
+            'description': 'Intro Video - Why to flip, how flipping will',
+        },
     }]
 
     def _real_extract(self, url):
@@ -92,23 +101,21 @@ 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)/[^"]+)">'
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user_id = mobj.group('user')
 
         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))
+        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]
         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))
+            urls.extend(re.findall(self._MEDIA_RE, webpage))
 
         entries = []
         for url in urls: