home · contact · privacy
Assume default charset utf-8 when no charset found in URL interpreter.
authorChristian Heller <c.heller@plomlompom.de>
Sun, 17 Jan 2016 20:21:17 +0000 (21:21 +0100)
committerChristian Heller <c.heller@plomlompom.de>
Sun, 17 Jan 2016 20:21:17 +0000 (21:21 +0100)
plomlombot.py

index 36228f3..e4a5be3 100644 (file)
@@ -78,8 +78,11 @@ def url_check(msg):
         webpage = urllib.request.urlopen(url, timeout=15)
         content_type = webpage.info().get_content_type()
         charset = webpage.info().get_content_charset()
-        if not charset or not content_type in ('text/html', 'text/xml',
+        if not charset:
+            charset="utf-8"
+        if not content_type in ('text/html', 'text/xml',
                 'application/xhtml+xml'):
+            print("TROUBLE INTERPRETING URL: bad content_type " + content_type)
             continue
         content = webpage.read().decode(charset)
         title = str(content).split('<title>')[1].split('</title>')[0]