题目

链家网前五页数据
1、名称，2、位置，3、单价，4、总价
https://cs.lianjia.com/ershoufang/

代码

import requests
from lxml import etree

# 爬取前五页的房源信息
for page in range(1, 6):
    url = f"https://cs.lianjia.com/ershoufang/pg{page}"
    # 发送请求并获取网页内容
    response = requests.get(url)
    html = response.text
    # 使用lxml库和xpath解析网页内容
    selector = etree.HTML(html)
    house_list = selector.xpath('//ul[@class="sellListContent"]/li')
    # print(house_list)
    # 解析每个房源的信息
    for house in house_list:
        name = house.xpath('.//div[@class="title"]/a/text()')[0]
        location1 = house.xpath('.//div[@class="flood"]/div/a/text()')[0]
        print(location1)
        location2 = house.xpath('.//div[@class="flood"]/div/a/text()')[1]
        print(location2)
        location = location1 + '-' +location2
        unit_price = house.xpath('.//div[@class="priceInfo"]/div[@class="unitPrice"]/span/text()')[0]
        total_price = house.xpath('.//div[@class="priceInfo"]/div[@class="totalPrice totalPrice2"]/span/text()')[0]+"万"
        print(f'【名称】：{name}, 【位置】：{location}, 【单价】：{unit_price}, 【总价】：{total_price}')

运行结果