python解析html的库_python解析HTML文件的二个例子

本节内容：

python解析Html文件

1，解析HTML文件 代码示例:

#!/usr/bin/python

#

# site: WWW.JBXUE.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/html\n\n"

print matching[0]

2，解析HTML Web页面 代码示例:

#!/usr/bin/python

#

#site: www.#

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)