爬取崔庆才大神的爬虫教程，最后存储到mysql

# -*- coding: utf-8 -*-#coding:utf8import requests,time，unittestfrom lxml import etreeimport pymysqlurl =‘http://cuiqingcai.com/1052.html‘

head = {"User-Agent":"Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.86 Safari/537.36",        "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",        "Accept-Encoding":"gzip, deflate",        "Accept-Language":"zh-CN,zh;q=0.8"

}html = requests.get(url)

selector = etree.HTML(str(html.text))

r = selector.xpath("/html/body/section/div[3]/div/article/p/a/text()")t = selector.xpath("/html/body/section/div[3]/div/article/p/a/@href")#print(r)#print(t)

now = str(time.strftime(‘%Y-%m-%d-%H-%M‘,time.localtime(time.time())))

class datas(object):

def Data_storage(self,dt):

for each in dt:            self.uid=",".join(each).split(‘,‘)[0]            self.uname=",".join(each).split(‘,‘)[1]            self.ulink=",".join(each).split(‘,‘)[2]            uid="\‘"+str(self.uid)+"\‘"            uname="\‘"+str(self.uname)+"\‘"            ulink="\‘"+str(self.ulink)+"\‘"            time="\‘"+str(now)+"\‘"            r="\‘"+str(‘ggg‘)+"\‘"

#print(uid,uname,ulink,r,time)

conn=pymysql.connect(host=‘192.168.191.1‘,user=‘root‘,passwd=‘123456789‘,db=‘data‘,port=3306,charset=‘utf8‘)            cur=conn.cursor()#获取一个游标            sql =‘‘‘INSERT INTO xxb(id,name,remark,link,time)VALUES(%s,%s,%s,%s,%s)‘‘‘%(uid,uname,r,ulink,time)

cur.execute(sql)            cur.execute(‘select * from xxb‘)#执行查询sql语句+            data=cur.fetchall()#执行查询后获取的数据赋值给data变量，每次查到的数据是上一个sql语句的结果，如果要重新查询别的数据，则要在上面重新写个sql查询语句

cur.close()#关闭游标            conn.commit()#事务提交            conn.close()#释放数据库资源

def Data_processing(self):        a=[]        for i in  range(1,31):            a.append(str(i))        dt = list(zip(a,r,t))        self.Data_storage(dt)

if __name__=="__main__":    gg = datas()    gg.Data_processing()