python模拟翻页+提取相关信息

代码不全

# coding=utf-8
import urllib,urllib2
import re

class QSBK:
    #初始化函数
    def _init_(self):
        self.pageIndex = 1
        self.user_agent = ''
        self.headers = {'User-Agent':self.user_agent
        self.stories = []

    #获取网页代码
    def getpage(self,pageIndex):
        try:
            url='http://www.qiushibaike.com/hot/page/'+str(pageIndex)
            request = urllib2.Request(url,headers=self.headers)
            respons = urllib2.urlopen(request)
            return respons.read()
        except Exception,e:
            print e

    def getpageItems(self,pageIndex):
        pagecode = self.getpage(pageIndex)
        if not pagecode:
            print '页面加载失败'
            return None
        pattern = re.compile(,re.S)
        items = re.findall(pattern, pagecode)
        pageStories = []
        for item in items:
            pageStories.append(item[0],item[1],item[2],item[3])
            print '作者：',item[0]
            print '内容：',item[1]
            print '阅读：',item[2]
            print '评论：',item[3]
        return pageStories


    def loadpage(self):
        if



spider = QSBK()
spider.getpage(1)