（三）爬取百度帖子（完善）

# -*- coding:utf-8 -*-
import urllib
import urllib2
import re

#百度贴吧
class BDTB:

    #初始化，传入基地址，是否只看楼主的参数
    def __init__(self,baseUrl,seeLZ):
        self.baseURL = baseUrl
        self.seeLZ = '?see_lz='+str(seeLZ)
        self.tool = Tool()
        self.file = None

    #传入页码，获取该页帖子的代码
    def getPage(self,pageNum):
        try:
            url = self.baseURL+ self.seeLZ + '&pn=' + str(pageNum)
            request = urllib2.Request(url)
            response = urllib2.urlopen(request)  
            return response.read().decode('utf-8')   #此处没写decode('utf-8') 导致result = re.search(pattern,page)处提示错误
        except urllib2.URLError, e:     #当网络连接失败时报错
            if hasattr(e,"reason"):
                print u"连接百度贴吧失败,错误原因",e.reason
                return None
    #获取帖子标题
    def getTitle(self):
        page = self.getPage(1)
        pattern = re.compile('<h3 class="core_title_txt.*?>(.*?)</h3>',re.S)
        result = re.search(pattern,page)
        print type(result)
        if result:
            print result.group(1)  #测试输出
            return result.group(1).strip()
        else:
            return None 
    #获取帖子一共有多少页
    def getPageNum(self):
        page = self.getPage(1)
        pattern = re.compile('<li class="l_reply_num.*?</span>.*?<span.*?>(.*?)</span>',re.S)
        result = re.search(pattern,page)
        if result:
            print result.group(1)  #测试输出
            return result.group(1).strip()
        else:
            return None

    def getContent(self,page):
        #正则表达式极易弄错
        pattern = re.compile('<div id="post_content_.*?>(.*?)</div>',re.S)
        items = re.findall(pattern,page)
        #使显示楼层，更舒服
        contents=[]
        for item in items:
            content = "\n"+self.tool.replace(item)+"\n"
            contents.append(content.encode('utf-8'))
        return contents
    #将数据写入文件中
    def writeTofile(self,contents,file):
        self.file = open("ss.txt","w")
        count = 1
        for content in contents:
            #楼之间的分隔符
            floorLine = "\n" + str(count)+ "floor: " + u"-----------------------------------------------------------------------------------------\n"
            self.file.write(floorLine)
            self.file.write(content)
            count+=1
        self.file.close()

#处理页面标签类，因为直接使用getContent中的正则表达式会匹配到很多没用的标签，为了只匹配文字设计该类！
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()

baseURL = 'http://tieba.baidu.com/p/3138733512'
bdtb = BDTB(baseURL,1)
#bdtb.getPage(1)
#bdtb.getTitle()
#bdtb.getPageNum()
contents = bdtb.getContent(bdtb.getPage(1))
bdtb.writeTofile(contents,"ss.txt")