爬取百度贴吧数据信息，并进行简单处理



import urllib2,random,time,re
class Tool:
    #去除img标签，7位长空格
    removeimg=re.compile('<img.*?>| {7}|')
    #删除超链接标签
    removeA=re.compile('<a.*?>|</a>')
    #把换行的标签换为\n
    removeLine=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.removeA,"",x)
         x = re.sub(self.removeLine,"\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="?seeLZ="+str(seeLZ)
    #传入页码，获取该页码网页的代码
    def get_page(self,pagenum):
        try:
            url=self.baseurl+self.seeLZ+"&pn"+str(pagenum)
            request=urllib2.Request(url)
            content=urllib2.urlopen(request).read()
            return content
        except urllib2.URLErroe,e:
            if hasattr(e,"reason"):
                print "连接百度贴吧失败",e.reason
                return None
    #获取帖子一共多少页
    def get_pagenum(self):
        content=self.get_page(1)
        #print content
        pattern=re.compile('<h1 class="l_reply_num.*?</span>.*?<span.*?>(.*?)</span>',re.S)
        result=re.search(pattern,content)
        if result:
            return result.group(1).strip()
        else:
            return None
    #获取该网页的标题
    def get_title(self):
        pattern=re.compile('<h1 class="core_title_txt.*?>(.*?)</h1>',re.S)
        content=self.get_page(1)
        result=re.search(pattern,content)
        if result:
            #输出
            print result.group(1).strip()
        else:
            return None
    #获取传入网页的内容
    def get_content(self):
        content=self.get_page(1)
        pattern=re.compile('<div id="post_content_.*?>(.*?)</div>')
        items=re.findall(pattern,content)
        for item in items:
            print item
                          
if __name__=="__main__":
    baseurl=" http://tieba.baidu.com/"
    bdtb=BDTB(baseurl,1)
    content=bdtb.get_page(1)
    tool=Tool()
    print tool.replace(content)