Allowing URLs for 13.cl without the /programas prefix
authorJuan C. Olivares <cristobal@cxsoftware.com>
Mon, 3 Mar 2014 02:41:13 +0000 (23:41 -0300)
committerJuan C. Olivares <cristobal@cxsoftware.com>
Mon, 3 Mar 2014 02:41:13 +0000 (23:41 -0300)
youtube_dl/extractor/canal13cl.py

index 3b4c7cdb77bafa1502390f237dd2adf11ed94ba0..781c1b50375d50d37d8041c8138ea76ca34196d7 100644 (file)
@@ -5,22 +5,26 @@ from .common import InfoExtractor
 
 
 class Canal13clIE(InfoExtractor):
-    _VALID_URL = r'^http://(?:www\.)?13\.cl/programa/'
+    _VALID_URL = r'^http://(?:www\.)?13\.cl/'
     IE_NAME = 'Canal13cl'
 
     def _real_extract(self, url):
-        webpage = self._download_webpage(url)
+        webpage = self._download_webpage(url, url)
+        video_id = self._html_search_regex(
+            r'http://streaming.13.cl/(.*)\.mp4',
+            webpage, u'video_id')
         title = self._html_search_regex(
-            r'articuloTitulo = \'(.*?)\'',
+            r'(articuloTitulo = \"(.*?)\"|(.*?)\|)',
             webpage, u'title')
         url = self._html_search_regex(
-            r'articuloVideo = \'(.*?)\'',
+            r'articuloVideo = \"(.*?)\"',
             webpage, u'url')
         thumbnail = self._html_search_regex (
-            r'articuloImagen = \'(.*?)\'',
+            r'articuloImagen = \"(.*?)\"',
             webpage, u'thumbnail')
 
         return {
+            'video_id': video_id,
             'url': url,
             'title': title,
             'ext': 'mp4',