02爬虫 爬取百度贴吧帖子

#encoding:utf-8
# -*- coding: utf-8 -*-
# coding:utf-8
import urllib
import urllib2
import re
#处理页面标签类

class Tool:
    #去除img标签,7位长空格
    removeImg = re.compile('<img.*?>| {7}|')
    #删除超链接标签
    removeAddr = re.compile('<a.*?>|</a>')
    #把换行的标签换为\n
    replaceLine = re.compile('<tr>|<div>|</div>|</p>')
    #将表格制表<td>替换为\t
    replaceTD= re.compile('<td>')
    #把段落开头换为\n加空两格
    replacePara = re.compile('<p.*?>')
    #将换行符或双换行符替换为\n
    replaceBR = re.compile('<br><br>|<br>')
    #将其余标签剔除
    removeExtraTag = re.compile('<.*?>')
    def replace(self,x):
        x = re.sub(self.removeImg,"",x)
        x = re.sub(self.removeAddr,"",x)
        x = re.sub(self.replaceLine,"\n",x)
        x = re.sub(self.replaceTD,"\t",x)
        x = re.sub(self.replacePara,"\n    ",x)
        x = re.sub(self.replaceBR,"\n",x)
        x = re.sub(self.removeExtraTag,"",x)
        #strip()将前后多余内容删除
        return x.strip()

class BDTB:

    def __init__(self,baseUrl,seeLZ):
        self.baseURL = baseUrl
        self.seeLZ = '?see_lz='+str(seeLZ)
        self.tool = Tool()

    def getPage(self,pageNum):
        try:
            url = self.baseURL+ self.seeLZ + '&pn=' + str(pageNum)
            request = urllib2.Request(url)
            response = urllib2.urlopen(request)
            #print response.read()
            return response
        except urllib2.URLError, e:
            if hasattr(e,"reason"):
                print u"error",e.reason
                return None
    def getTitle(self):
        page = self.getPage(1)
        pattern = re.compile('<h3 .*?title="(.*?)" style=.*?</h3>', re.S)
        page=page.read().decode('utf-8')
        result = re.search(pattern,page)
        if result:
            print result.group(1)
            return result.group(1).strip()
        else:
            return None
    def getPageNum(self):
        page = self.getPage(1)
        pattern = re.compile('<li .*?max-page="(.*?)".*?/>',re.S)
        page=page.read().decode('utf-8')
        result = re.search(pattern,page)
        if result:
            print result.group(1)  #测试输出
            return result.group(1).strip()
        else:
            return None
    #获取每一层楼的内容,传入页面内容
    def getContent(self,page):
        pattern = re.compile('<div id="post_content_.*?>(.*?)</div>',re.S)
        page=page.read().decode('utf-8')
        items = re.findall(pattern,page)
        floor=1
        for item in items:
            print floor,u'楼---------------------------------------\n'
            print self.tool.replace(item)
            floor+=1
baseURL = 'http://tieba.baidu.com/p/3138733512'
bdtb = BDTB(baseURL, 1)
#bdtb.getPage(1)
bdtb.getContent(bdtb.getPage(1))