python爬虫爬取ip记录网站信息并存入数据库

时间：2021-10-17 19:48:43
 import requests

 import re

 import pymysql

 #10页 仔细观察路由

 db = pymysql.connect("localhost","root","root","testdb" )

 cursor = db.cursor()

 for i in range(1,10):

     url = 'http://*******8****'

     url=url+'index_'+str(i)+'.html'

     response = requests.get(url)

     HTML = response.text

     pattern= re.compile(r'(((2(5[0-5]|[0-4]\d))|[0-1]?\d{1,2})(\.((2(5[0-5]|[0-4]\d))|[0-1]?\d{1,2})){3})')

     compile_1 = re.compile(r'\s+(\d{3,6})\s')

     compile_2 = re.compile(r'\s+([\u4e00-\u9fa5]{1,9})\s?(?:省|*|内蒙古|市|县|区])')

     # compile_4 = re.compile(r's+(\d{4}/\d{2}/\d{2}\s+\d{2}:\d{2}:\d{2})\s')

     res2 = compile_2.findall(HTML)

     res1 = compile_1.findall(HTML)

     result = pattern.findall(HTML)

     # res3 = compile_4.findall(HTML)

     # print(res3,len(result))

     for ip_ in result:

         print(ip_[0])

         sql = "INSERT INTO test (ip,port,place) VALUES ('%s','%s','%s')" %(ip_[0],res1[0],res2[0])

         print(sql)

         cursor.execute(sql)

 db.close()

 # 使用cursor()方法获取操作游标

相关文章