Add some more checks against evil URLs.

[plomlombot-irc.git] / plomlombot.py

diff --git a/plomlombot.py b/plomlombot.py
index 7d915dc2f80c79157119089aa2e0dd6e9566d16a..7fa9194af8236e27fd7d547843fc1a1e3577dc8b 100644 (file)
--- a/plomlombot.py
+++ b/plomlombot.py
@@ -9,10 +9,10 @@ import html
 servernet = "irc.freenode.net"
 port = 6667
 servername = ""
 servernet = "irc.freenode.net"
 port = 6667
 servername = ""

-timeout = 480
+timeout = 240

 username = "plomlombot"
 nickname = username
 username = "plomlombot"
 nickname = username

-channel = "#zrolaps"
+channel = "#zrolaps-test"

 
 class IO:
 
 
 class IO:
 


@@ -104,10 +104,10 @@ while 1:
                 url = matches[i]
                 webpage = urllib.request.urlopen(url)
                 content_type = webpage.info().get_content_type()
                 url = matches[i]
                 webpage = urllib.request.urlopen(url)
                 content_type = webpage.info().get_content_type()

-                if not content_type in ('text/html', 'text/xml',
+                charset = webpage.info().get_content_charset()
+                if not charset or not content_type in ('text/html', 'text/xml',

                     'application/xhtml+xml'):
                     continue
                     'application/xhtml+xml'):
                     continue

-                charset = webpage.info().get_content_charset()

                 content = webpage.read().decode(charset)
                 title = str(content).split('<title>')[1].split('</title>')[0]
                 title = html.unescape(title)
                 content = webpage.read().decode(charset)
                 title = str(content).split('<title>')[1].split('</title>')[0]
                 title = html.unescape(title)