Rename utv.py to unistra.py and extract more info
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Thu, 22 Aug 2013 11:19:35 +0000 (13:19 +0200)
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Thu, 22 Aug 2013 11:19:35 +0000 (13:19 +0200)
There are other sites that could be named utv, which would conflict if they are added

youtube_dl/extractor/__init__.py
youtube_dl/extractor/unistra.py [new file with mode: 0644]
youtube_dl/extractor/utv.py [deleted file]

index 5830511695776e0e508a3e889c5455643ee1e96c..b4db8f0bf7933ef111ad682f8bcbeb1fb989515f 100644 (file)
@@ -75,7 +75,7 @@ from .tudou import TudouIE
 from .tumblr import TumblrIE
 from .tutv import TutvIE
 from .ustream import UstreamIE
-from .utv import UTVIE
+from .unistra import UnistraIE
 from .vbox7 import Vbox7IE
 from .veoh import VeohIE
 from .vevo import VevoIE
diff --git a/youtube_dl/extractor/unistra.py b/youtube_dl/extractor/unistra.py
new file mode 100644 (file)
index 0000000..5ba0a90
--- /dev/null
@@ -0,0 +1,32 @@
+import re
+
+from .common import InfoExtractor
+
+class UnistraIE(InfoExtractor):
+    _VALID_URL = r'http://utv.unistra.fr/(?:index|video).php\?id_video\=(\d+)'
+
+    _TEST = {
+        u'url': u'http://utv.unistra.fr/video.php?id_video=154',
+        u'file': u'154.mp4',
+        u'md5': u'736f605cfdc96724d55bb543ab3ced24',
+        u'info_dict': {
+            u'title': u'M!ss Yella',
+            u'description': u'md5:75e8439a3e2981cd5d4b6db232e8fdfc',
+        },
+    }
+
+    def _real_extract(self, url):
+        id = re.match(self._VALID_URL, url).group(1)
+        webpage = self._download_webpage(url, id)
+        file = re.search(r'file: "(.*?)",', webpage).group(1)
+        title = self._html_search_regex(r'<title>UTV - (.*?)</', webpage, u'title')
+
+        video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file
+
+        return {'id': id,
+                'title': title,
+                'ext': 'mp4',
+                'url': video_url,
+                'description': self._html_search_regex(r'<meta name="Description" content="(.*?)"', webpage, u'description', flags=re.DOTALL),
+                'thumbnail': self._search_regex(r'image: "(.*?)"', webpage, u'thumbnail'),
+                }
diff --git a/youtube_dl/extractor/utv.py b/youtube_dl/extractor/utv.py
deleted file mode 100644 (file)
index 013e86a..0000000
+++ /dev/null
@@ -1,22 +0,0 @@
-import re
-
-from .common import InfoExtractor
-
-class UTVIE(InfoExtractor):
-    _VALID_URL = r'http://utv.unistra.fr/index.php\?id_video\=(\d+)'
-
-    def _real_extract(self, url):
-        id = re.match(self._VALID_URL, url).group(1)
-        webpage = self._download_webpage(url, id)
-        url = re.search(r'file: "(.*?)",', webpage).group(1)
-        title = re.search(r'/utv/\d+/.*/(.*?).mp4', url).group(1)
-        
-        video_url = 'http://vod-flash.u-strasbg.fr:8080/' + url
-
-        track_info = {'id':id,
-                      'title' : title,
-                      'ext' :   'mp4',
-                      'url' :   video_url
-                      }
-
-        return [track_info]