add get_url

ox/api.py

@@ -131,6 +131,12 @@ class API(object):
             form.add_field('data', json.dumps(data))
         return self._json_request(self.url, form)
 
+    def get_url(self, url):
+        request = urllib.request.Request(url, method='GET')
+        f = self._opener.open(request)
+        result = f.read()
+        return result
+
     def save_url(self, url, filename, overwrite=False):
         chunk_size = 16 * 1024
         if not os.path.exists(filename) or overwrite:

ox/web/imdb.py

@@ -193,7 +193,7 @@ class Imdb(SiteParser):
         'language': zebra_list('Language', more=['<a.*?>(.*?)</a>']),
         'originalTitle': {
             'page': 'releaseinfo',
-            're': '<td>\(original title\)</td>\s*<td>(.*?)</td>',
+            're': '<td.*?>\s*?\(original title\)\s*?</td>\s*<td.*?>(.*?)</td>',
             'type': 'string'
         },
         'summary': zebra_table('Plot Summary', more=[