西刺ip代理python爬虫+mysql储存

import requests 
import re
import pymysql
import struct
import socket
from bs4 import BeautifulSoup
db     = pymysql.connect('localhost','root','oracle','xici_proxy',use_unicode=True, charset="utf8")
cursor = db.cursor()
cursor.execute("DROP TABLE IF EXISTS IPLIST")
sql    = '''create table iplist(
            id INT NOT NULL AUTO_INCREMENT,
            ip long,
            port int,
            address char(40),
            anony char(20),
            protocol char(20),
            speed char(40),
            time char(40),
            PRIMARY KEY ( id )
            );
        '''
cursor.execute(sql)
for page in range(1,3):
    url='http://www.xicidaili.com/nn/{}'.format(page)
    headers={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36'}
    data=requests.get(url=url,headers=headers).text
    #print (url,requests.get(url=url,headers=headers).status_code)
    soup=BeautifulSoup(data,'html.parser')
    trs1 = soup.find('table',id='ip_list')
    #print (trs1)
    trs = trs1.find_all('tr')
    for tr in trs[1:]:
        tds = tr.find_all('td')
        if tds[1].find('img') is None :
            nation = '未知'
            locate = '未知'
        else:
            nation =   tds[1].find('img')['alt'].strip()
            locate  =   tds[4].text.strip()
        ip      =   tds[1].text.strip()
        ip_num=p=socket.ntohl(struct.unpack("I",socket.inet_aton(ip))[0])
        port    =   tds[2].text.strip()
        address =   tds[3].text.strip()
        anony   =   tds[4].text.strip()
        protocol=   tds[5].text.strip()
        speed   =   tds[6].find('div')['title'].strip()
        time    =   tds[9].text.strip()
        sql1    ='''insert into iplist
                    (ip,port,address,anony,protocol,speed,time)
                    values({},{},'{}','{}','{}','{}','{}');'''.format(ip_num,port,address,anony,protocol,speed,time)
        print (sql1)
        try:
            cursor.execute(sql1)
            db.commit()
        except:
            db.rollback()
            print('回滚')
            print ('ip:',ip_num,'port:',port,'address:',address,'anony:',anony,'protocol:',protocol,'speed:',speed,'time:',time)
db.close()

 

posted @ 2017-09-01 16:30  夯大力哥哥  阅读(785)  评论(0)    收藏  举报