利用python爬虫抓取OJ上做题信息（终结版）

import webbrowser
import re
import urllib

#获取hdu网页
def getHtml_hdu(url):
    page = urllib.urlopen(url)
    html = page.read()
    #unicodehtml = html.decode("utf-8")
    #return unicodehtml
    return html

#获取poj网页   
def getHtml_poj(url):
    page = urllib.urlopen(url)
    html = page.read()
    #unicodehtml = html.decode("utf-8")
    #return unicodehtml
    return html

#获取cug网页
def getHtml_cug(url):
    page = urllib.urlopen(url)
    html = page.read()
    unicodehtml = html.decode("utf-8")
    return unicodehtml


#获取hdu中用户信息
def zhenghe_hdu(str1,userid,imgre):
    html=getHtml_hdu( str1+userid )
    return re.findall(imgre,html)

#获取cug中用户信息
def zhenghe_cug(str1,userid,imgre):
    html=getHtml_cug( str1+userid )
    return re.findall(imgre,html)

#获取poj中用户信息
def zhenghe_poj(str1,userid,imgre):
    html =getHtml_poj( str1+ userid)
    return re.findall(imgre,htm