python替换html中空标签的例子

#!/bin/python
# site: www.jb200.com
#
__author__ = 'yukaizhao post @ http://jb200.com/'

import re

def remove_empty_tag(input):
    pattern = re.compile(r'<([a-z]+d?)b[^>]*>(&nbsp;|[s　])*</1>',re.IGNORECASE)

    maxLoopTimes = 10
    i = 0
    while i < maxLoopTimes:
        tem = pattern.sub('',input)
        if tem == input:
            input = tem
            break
        else:
            input = tem
        i += 1

    return input

if __name__ == '__main__':
    output = remove_empty_tag('<div>nt&nbsp;&nbsp; </div>hello')
    print output

    output = remove_empty_tag('<div><span> &nbsp;　 </span></div>hello world')
    print output