Python爬虫（五）

源码：

import requests
from lxml import etree
from my_mysql import MysqlConnect


mc = MysqlConnect('127.0.0.1','root','123456','homework')
sql = 'insert into lianjia(title,addr,shape,area,dire,price) values(%s,%s,%s,%s,%s,%s)'
for page in range(3):
    url = 'https://bj.lianjia.com/zufang/pg{}rp2rp1/'.format(page)
    response = requests.get(url)
    html = etree.HTML(response.text)
    li_list = html.xpath('//ul[@id="house-lst"]/li')
    # print(li_list)
    for li_ele in li_list:
        title = li_ele.xpath('./div[2]/h2/a')[0].text
        addr = li_ele.xpath('./div[2]/div[1]/div[1]/a/span')[0].text
        shape = li_ele.xpath('./div[2]/div[1]/div[1]/span[1]/span')[0].text
        area = li_ele.xpath('./div[2]/div[1]/div[1]/span[2]')[0].text
        dire = li_ele.xpath('./div[2]/div[1]/div[1]/span[3]')[0].text
        price = li_ele.xpath('./div[2]/div[2]/div[1]/span')[0].text
        # print(title,addr,shape,area,price)
        data = (title,addr,shape,area,dire,price)
        print(data)
        mc.exec_data(sql,data)
        # break