爬内涵段子，开心一刻

使用py2爬取笑话，~~

# coding=utf-8

import urllib2
import re




class Pacong(object):
    def __init__(self,begin=1):
        self.begin = begin
        self.confirm = True
        self.filename = 1
    def get_html(self):
        """获得html网页文件"""
        url = "http://xiaohua.zol.com.cn/aiqing/"+str(self.begin)+".html"
        headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}
        resquest = urllib2.Request(url,headers=headers)
        date = urllib2.urlopen(resquest)
        html = date.read().decode("gbk").encode("utf-8")
        self.clear(html)
        # print html


    def clear(self,html):
        """使用正则整理html获取想要的文件"""
        pattern = re.compile('<div\sclass="summary-text">(.*?)</div>',re.S)
        content_list = pattern.findall(html)
        content_list = content_list
        # print content_list


        #每一次写入都使用不同的文件
        filenames = "第" + str(self.filename) + "页.txt"
        for i in content_list:
            i = i.replace("<p>"," ").replace("</p>......"," ").replace("</p>"," ").replace("&nbsp","")
            self.writePage(i,filenames)
            # print i
        self.filename += 1


    def writePage(self,i,filenames):
        """将整理好的内容写入到本地文件"""


        with open(filenames,"a+") as f:
            f.write(i)


    def command(self):
        """控制程序的运行"""
        while self.confirm:
            duanzi.get_html()
            com = raw_input("是否继续爬去网页：(是按任意键,退出输入exit)")
            if com == "exit":

                break

            self.begin += 1
if __name__ == '__main__':
    duanzi = Pacong()
    duanzi.command()