python爬虫豆瓣租房

import urllib.request
import urllib.error
import urllib.response
import urllib.parse
import time
import re

pagenum = []

def GetInfo(page):
    url = 'https://www.douban.com/group/topic/' + str(page)
    user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
    headers = {'User-Agent':user_agent}
    try:
        response = urllib.request.urlopen(url)
        content = response.read().decode('utf-8')
        pattern = re.compile('.*?
(.*?)
',re.S)
        items = re.findall(pattern,content)
        for item in items:
            replacePP = re.compile('
')
            info = re.sub(replacePP,"\n",item)
            print ("----------------------------------------------------------")
            print (info)
            print ("----------------------------------------------------------")
    except urllib.error.URLError as e :
        if hasattr(e, "code"):
            print (e.code)
        if hasattr(e, "reason"):
            print (e.reason)


def GetPageNum(start):
    url = 'https://www.douban.com/group/beijingzufang/discussion?start='  + str(start)
    try:
        response = urllib.request.urlopen(url)
        content = response.read().decode('utf-8')
        pattern = re.compile('.*?.*?',re.S)
        items = re.findall(pattern,content)
        for item in items:
            #print (item)
            #print (item[36:-3])
            pagenum.append(item[36:-3])
    except urllib.error.URLError as e :
        if hasattr(e, "code"):
            print (e.code)
        if hasattr(e, "reason"):
            print (e.reason)

if __name__ == '__main__':
    print("请输入最新需要条数： ")
    AllTitles = int(input())
    StartPage =  int( AllTitles / 25 )
    for i in range(1, StartPage+1):
        GetPageNum(i * 25)
    for num in pagenum:
        GetInfo(num)