Add some more checks against evil URLs.

[plomlombot-irc.git] / plomlombot.py

diff --git a/plomlombot.py b/plomlombot.py
index 179bc2a2221d90da84580f57898aa3b704fca0f5..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:
 


@@ -103,7 +103,11 @@ while 1:
             for i in range(len(matches)):
                 url = matches[i]
                 webpage = urllib.request.urlopen(url)
             for i in range(len(matches)):
                 url = matches[i]
                 webpage = urllib.request.urlopen(url)

+                content_type = webpage.info().get_content_type()

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

+                if not charset or not content_type in ('text/html', 'text/xml',
+                    'application/xhtml+xml'):
+                    continue

                 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)