import HTMLParser
#This goes in line 318 of HTMLParser
def parse_endtag(self, i):
rawdata = self.rawdata
assert rawdata[i:i+2] == "
if not match:
return -1
j = match.end()
match = endtagfind.match(rawdata, i) #
if not match:
self.error("bad end tag: %s" % `rawdata[i:j]`)
tag = match.group(1)
#START BUGFIX
if self.interesting == interesting_cdata:
#we're in of of the CDATA_CONTENT_ELEMENTS
if tag == self.lasttag and tag in self.CDATA_CONTENT_ELEMENTS:
#its the end of the CDATA_CONTENT_ELEMENTS tag we are in.
self.handle_endtag(tag.lower())
self.clear_cdata_mode()#backto normal mode
else:
#we're inside the CDATA_CONTENT_ELEMENTS tag still. throw the tag to handle_data instead.
self.handle_data(match.group())
else:
#we're not in a CDATA_CONTENT_ELEMENTS tag. standard ending:
self.handle_endtag(tag.lower())
return j
class MyHandler(HTMLParser.HTMLParser):
tags = []
def handle_starttag(self, tag, attr):
self.tags.append(tag)
def handle_endtag(self, tag):
if tag != self.tags[-1]:
#this should never happen in a well formed document
raise "Not well-formed, endtag '" + tag + "' doesn't match starttag '" + self.lasttag + "'"
self.tags.pop(-1)
s = """
This page is completely well formed
blah blah
"""
m = MyHandler()
m.feed(s)