xpath 练习 爬取链家网

from  lxml import etree
import requests
#网页地址
url = 'https://nc.lianjia.com/ershoufang/'
#请求头
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36'
}
#添加请求头
r= requests.get(url,headers=headers)
#print(r.text)
html = etree.HTML(r.text)
res = html.xpath("//div[@class='info clear']")
for i in res:
    # 房屋名称
    name = i.xpath("div[1]/a/text()")
    print(name)
    #地址
    adders = i.xpath("div[2]/div/a[1]/text()")
    print(adders)
    #家
    home = i.xpath("div[3]/div/text()")
    print(home)
    #关注信息
    all = i.xpath("div[4]/text()")
    print(all)

#print(res)

!](https://img-blog.csdnimg.cn/8cfb4508b96442a1b4b9de1b4f5b579c.png?x-oss-process=image/watermark,type_ZHJvaWRzYW5zZmFsbGJhY2s,shadow_50,text_Q1NETiBA5aKo5riK7pST,size_20,color_FFFFFF,t_70,g_se,x_16)

#房屋

#地址

#家

#关注信息

总结xpath还是很好用就是不太习惯 bs4用习惯了