Detect link in posts better

Credit goes to Josef Kokeš

models/__init__.py

@@ -69,6 +69,8 @@
 from askbot import mail
 
 from django import VERSION
+import HTMLParser
+
 
 #stores the 1.X version not the security release numbers
 DJANGO_VERSION = VERSION[:2]
@@ -758,7 +760,8 @@ def user_assert_can_post_text(self, text):
     """Raises exceptions.PermissionDenied, if user does not have
     privilege to post given text, depending on the contents
     """
-    if re.search(URL_RE, text):
+    html_parser = HTMLParser.HTMLParser()
+    if re.search(URL_RE, html_parser.unescape(text).lower()):
         min_rep = askbot_settings.MIN_REP_TO_SUGGEST_LINK
         if self.is_authenticated() and self.reputation < min_rep:
             message = _(

utils/markup.py

@@ -12,8 +12,8 @@
 from askbot.utils.html import urlize_html
 from django.utils.html import urlize
 from markdown2 import Markdown
-#url taken from http://regexlib.com/REDetails.aspx?regexp_id=501
-URL_RE = re.compile("((?<!(href|.src|data)=['\"])((http|https|ftp)\://([a-zA-Z0-9\.\-]+(\:[a-zA-Z0-9\.&amp;%\$\-]+)*@)*((25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[0-9])|localhost|([a-zA-Z0-9\-]+\.)*[a-zA-Z0-9\-]+\.(com|edu|gov|int|mil|net|org|biz|arpa|info|name|pro|aero|coop|museum|[a-zA-Z]{2}))(\:[0-9]+)*(/($|[a-zA-Z0-9\.\,\?\'\\\+&amp;%\$#\=~_\-]+))*))")
+#url taken from https://askfit.cz/question/1076/testovaci-spam-2/?answer=1077#post-id-1077
+URL_RE = re.compile('(https?|ftp)://')
 
 def get_parser():
     """returns an instance of configured ``markdown2`` parser