看看我们要达到的目的

E6F758B1-DD5E-40FE-97F4-BD377A3D2570.png

1.下载PYCHARM
PYcharm

#coding=utf-8

import sys
import re
import urllib




def gethtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html


def getmessage(html):

    p = re.compile(r'<div class="content">(.*)</div><script type="text/javascript">')
    message = re.findall(p, html)  # 返回正则匹配的结果

    return message


fp = open('data.txt','w+')


for i in range(1,7000):

    i = str(i)
    web = gethtml('http://ishuo.cn/subject/' + i)
    message = getmessage(web)
    message2 = ''.join(message)  # 将结果转换为字符串类型

    message2=str(message2)

    print message2

    fp.writelines(message2 + '\n')



fp.close()