python解析HTML文件的二个例子

#!/usr/bin/python
#
# site: WWW.jb200.com

import re
filename = "index.html"

newContent = "Hello Python World"

filehandle = open(filename, "r")

data = filehandle.read()    
filehandle.close()

matching = re.subn("test", newContent, data)

if matching[1] == 0:
    raise "Error while parsing HTML template"
print "Content-Type: text/htmlnn"
print matching[0]

#!/usr/bin/python
#
#site: www.jb200.com
import htmllib, urllib, formatter, sys

def parse(url, formatter):
    f = urllib.urlopen(url)
    data = f.read()
    f.close()
    p = htmllib.HTMLParser(formatter)
    p.feed(data)
    p.close()

fmt = formatter.AbstractFormatter(formatter.DumbWriter(sys.stdout))
parse("index.htm", fmt)