"""
HTML Parser
- Written by BroytMann. Copyright (C) 1997-2008 PhiloSoft Design
+ Written by Broytman. Copyright (C) 1997-2008 PhiloSoft Design
"""
from HTMLParser import HTMLParseError
_HTMLParser.__init__(self)
self.charset = charset
self.meta_charset = 0
- self.title = ''
- self.refresh = ''
+ self.title = None
+ self.refresh = None
self.icon = None
def end_head(self):
if (not self.charset) and (http_equiv == "content-type"):
try:
- # extract charset from "text/html; foo; charset=UTF-8; bar;"
- self.charset = content.lower().split('charset=')[1].split(';')[0]
+ # extract charset from "text/html; foo; charset=UTF-8, bar; baz;"
+ self.charset = content.lower().split('charset=')[1].split(';')[0].split(',')[0]
self.meta_charset = 1 # Remember that the charset was retrieved from
# META tag, not from the Content-Type header
except IndexError: