practice之Python爬取链家网页面（xpath）

导包及数据库

import requests

from lxml import etree

import mysqlhelper

根据需求寻找链家网页（添加%s占位）

base_url = 'https://bj.lianjia.com/zufang/pg%srp1/'

实例化定义好的连接数据库的文件,并编写sql语句

myhelper = mysqlhelper.MysqlHelper()

sql = 'INSERT INTO lianjiaxinxi (title, region, zone, meters, location, price) VALUES' \
      ' (%s, %s, %s, %s, %s, %s)'

循环页码数，爬取多页数据

for i in range(1,4):

    将循环出来的页码数加到上面定义好的路由网址里
    url = base_url % i

    requests的get方法获取路由网址的页面
    response = requests.get(url)
    
    使用etree的HTML方法将请求的网址页面存入一个对象里
    html_ele = etree.HTML(response.text)

使用xpath获取定位需要的数据

    li_list = html_ele.xpath('//ul[@id="house-lst"]/li')

    for li_ele in li_list:
        title = li_ele.xpath('./div[2]/h2/a')[0].text
        print(title)
        region = li_ele.xpath('./div[2]/div[1]/div[1]/a/span')[0].text
        print(region)
        # ./div[2]/div[1]/div[1]/span[1]/span
        zone = li_ele.xpath('./div[2]/div[1]/div[1]/span[1]/span')[0].text
        print(zone)
        meters = li_ele.xpath('./div[2]/div[1]/div[1]/span[2]')[0].text
        print(meters)
        location = li_ele.xpath('./div[2]/div[1]/div[1]/span[3]')[0].text
        print(location)
        price = li_ele.xpath('.//div[@class="price"]/span')[0].text
        print(price)

将数据存储到mysql数据库

        data = (title, region, zone, meters, location, price)
        myhelper.execute_modify_sql(sql, data)