#!/usr/bin/env python 
# -*- coding:utf-8 -*-
import requests
from lxml import etree
# 需求：爬取58二手房中的房源信息

if __name__ == "__main__":
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'
    }
    # 爬取到页面源码数据
    url = 'https://bj.58.com/ershoufang/'
    page_text = requests.get(url=url, headers=headers).text

    # 数据解析
    tree = etree.HTML(page_text)
    # 存储的就是li标签对象
    div_list = tree.xpath('//section[@class="list"]//h3/text()')
    print(div_list)
    fp = open('58.txt', 'w', encoding='utf-8')
    for item in div_list:
        fp.write(item + '\n')