#!/usr/bin/python
import urllib
import re

def getss(id):
    urlbase = 'http://acm.pku.edu.cn/JudgeOnline/userstatus?user_id='
    url = urlbase + id
    html = urllib.urlopen(url)
    rs = re.search(r'<td align=center width=25%><a href=status\?result=0&user_id=.*>(\d+)</a></td>', html.read())
    if rs:
        print id + " : " + rs.group(1)
    else:
        print "查无此人!"
    html.close()

if __name__ == '__main__':
    ids = ['test', 'linux', 'abc']
    for id in ids:
        getss(id)

一开始的想法是去解析html文件,看来简单的用RegExp就能解决了,但是若是服务器有一点的改变(比喻在<td align=center width=25%><a href=status\?result=0&user_id=.*>(\d+)</a></td>中加入一个空格)就会匹配失败.