scripts

commit: 8e1f4c215db0cf82aa57c9bc3f21615183e69379
parent: 18b2ff82942f3bb7b57540ab67e6c8c757144e7e
Author: lanodan <lanodan.delta@free.fr>
Date:   Wed, 12 Mar 2014 21:11:45 +0100

URL Parser

Diffstat:
D
IRCBot/.IRCBot.py.swo
0

M
IRCBot/.IRCBot.py.swp
0

D
IRCBot/.config.ini.swp
0

M
IRCBot/IRCBot.py
9
++++-----

4 files changed, 4 insertions(+), 5 deletions(-)
diff --git a/IRCBot/.IRCBot.py.swo b/IRCBot/.IRCBot.py.swo
Binary files differ.
diff --git a/IRCBot/.IRCBot.py.swp b/IRCBot/.IRCBot.py.swp
Binary files differ.
diff --git a/IRCBot/.config.ini.swp b/IRCBot/.config.ini.swp
Binary files differ.
diff --git a/IRCBot/IRCBot.py b/IRCBot/IRCBot.py
@@ -67,11 +67,9 @@ while 1:    #puts it in a loop
     t = text.split(':!say') #you can change t and to :)
     to = t[1].strip() #this code is for getting the first word after !hi
     irc.send('PRIVMSG '+channel+' :'+str(to)+'\n')
-  if text.find('http://') != -1:
-    t = text.split('http://')
-    line = t[1].strip()
-    t = line.split()
-    url = 'http://'+t[0].strip()
+  if text.find('http') != -1:
+    parse = re.findall('https?://[^\"\'\(\)\[\]\{\}\<\>]+', text)
+    url = str(parse[0]).rstrip() #took the first link and remove newline and whitespaces
     if check_url(url):
       get = urllib.urlopen(url)
       wget = get.read()
@@ -79,6 +77,7 @@ while 1:    #puts it in a loop
       if wget.find('<title>') != -1:
         title = get_title(wget)
         irc.send('PRIVMSG '+channel+' :('+url+')Title: '+title+' \n')
+        print '('+url+')Title: '+title
   if text.find(':!stop in the name of sey') != -1:
     irc.send('QUIT : '+quitMsg+'\n')
     sys.exit(0)