xpath爬虫二手房案例代码

import requests
from lxml import etree

if name == ‘main’:
# ua 伪装 =》 模拟浏览器上网
headers = {
“User-Agent”: ‘Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36’
}

url = "https://dl.58.com/ershoufang"

#1.通用爬虫
page_info = requests.get(url,headers=headers)

#2.数据解析
root = etree.HTML(page_info.text)

#3.标签定位
div_list = root.xpath('//section[@class="list"]/div')

fp = open("D:\sxwang\project\pycharm\python-sk\data\二手房.txt","w",encoding="jbk")
for div in div_list:
    #标签定位
    title = div.xpath('./a/div[@class="property-content"]/div[@class="property-content-detail"]'
                      '/div[@class="property-content-title"]/h3/text()')[0]
    fp.write(title+"\n")
    print(title,"=>爬虫ok")