Python爬虫，做了一个爬取百度贴吧中的数据，每次只能获取每一页的前几个数据，后面的都获取不了？

import urllib
import urllib2
from bs4 import BeautifulSoup
import time
baseurl ='http://tieba.baidu.com/p/3138733512?see_lz=1&pn='
def filter(tag):
    return tag.name=="span" and not tag.has_attr('style') and tag.has_attr('class') and tag['class']==['red']
    #return tag.name=="span" and not tag.has_attr("style") and tag.attr("class")=="red"
class BaiDuCraw:
    def __init__(self,baseurl,title=None,soup=None):
        self.baseurl = baseurl
        self.title = title
        self.soup =soup
    def GetPage(self,pnum):
        headers = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}
        totalurl = self.baseurl+str(pnum)
        try:
            req = urllib2.Request(totalurl,headers=headers)
            response = urllib2.urlopen(req)
            content = response.read().decode("utf-8")
            return content
        except urllib2.URLError,e:
            if e.has_attr("code"):
                print e.code
            else:
                print e.reason
            return
    def writetofile(self):
        contentlist = self.soup.find_all(name="div", attrs={"class":"d_post_content j_d_post_content "})
        for content in contentlist:
            f.writelines(content.get_text())
            f.write("\n")
    def start(self):
        content = self.GetPage(1)
        self.soup = BeautifulSoup(content,"lxml")
        self.writetofile()
        
        totalpage = self.soup.find_all(filter)
        totalnum = int(totalpage[0].get_text())
        for i in range(2,totalnum+1):
            content = self.GetPage(i)
            self.soup = BeautifulSoup(content,"lxml")
            self.writetofile()
            time.sleep(2)
f = open("tieba.txt","w+")
mycrawer = BaiDuCraw(baseurl)
mycrawer.start()

---

写成分布式, 主控节点分析url,存储处理结果,爬取分给客户机,然后建个群,每个人运行一下客户端脚本

---

没具体测试过，不过百度限制你是肯定的，这时候你只能找（买）高匿代理IP来做。
之前抓过淘宝的数据，一样也有限制（频率/数量），用高匿IP完美解决，便宜的，10块钱买2万个。