python 爬虫 5i5j房屋信息 获取并存储到数据库

 from lxml import etree
 from selenium import webdriver
 import pymysql

 def Geturl(fullurl):#获取每个招聘网页的链接
     browser.get(fullurl)
     shouye_html_text = browser.page_source
     shouye_ele = etree.HTML(shouye_html_text)
     zf_list = shouye_ele.xpath('/html/body/div[4]/div[1]/div[2]/ul/li/div/h3/a/@href')#链接url
     zf_url_list  = []
     for zf_url_lost in zf_list:
         zf_url  = 'https://bj.5i5j.com'+zf_url_lost
         zf_url_list.append(zf_url)
     return zf_url_list
 def Getinfo(zp_url_list):
     for zp_url in zp_url_list:
         browser.get(zp_url)
         zp_info_html = browser.page_source
         zp_ele = etree.HTML(zp_info_html)
         zp_info_title = str(zp_ele.xpath('//html/body/div[3]/div[1]/div[1]/h1/text()')[0])
         zp_info_num = str(zp_ele.xpath('/html/body/div[3]/div[2]/div[2]/div[1]/div[1]/div/p[1]/text()')[0])+'元/月'#价格
         zp_info_type = str(zp_ele.xpath('/html/body/div[3]/div[2]/div[2]/div[1]/div[2]/div/p[1]/text()')[0])#户型
         zp_info_zone = str(zp_ele.xpath('/html/body/div[3]/div[2]/div[2]/div[1]/div[3]/div/p[1]/text()')[0])+'平米'#房屋大小
         zp_info_need_1 = str(zp_ele.xpath('/html/body/div[3]/div[2]/div[2]/div[2]/ul/li[1]/span/text()')[0])#房屋信息
         zp_info_need_2 = str(zp_ele.xpath('/html/body/div[3]/div[2]/div[2]/div[2]/ul/li[1]/a/text()')[0])#房屋信息
         zp_info_need = zp_info_need_1+zp_info_need_2
         connection = pymysql.connect(host='localhost', user='root', password='', db='5i5j', )
         try:
             with connection.cursor() as cursor:
                 sql = "INSERT INTO `5i5j_info` (`title`,`num`,`type`, `zone`,`need`) VALUES (%s,%s,%s,%s, %s)"
                 cursor.execute(sql, (zp_info_title,zp_info_num,zp_info_type,zp_info_zone,zp_info_need))
             connection.commit()
         finally:
             connection.close()
         print(zp_info_title,zp_info_num,zp_info_type,zp_info_zone,zp_info_need)
 if __name__ == '__main__':
     browser = webdriver.Chrome()
     pags = int(input('需要几页?'))
     for i in range(1,pags+1):
         url = 'https://bj.5i5j.com/zufang/huilongguan/n{}/'
         fullurl = url.format(str(i))
         zf_url_list = Geturl(fullurl)
         print(fullurl)
         # print(zf_url_list)
         Getinfo(zf_url_list)
     browser.close()