xpath之28二手房数据爬取

# 需求： 爬取58二手房房源信息
from lxml import etree
import requests

if __name__ == "__main__":
    # 爬取页面源码数据
    headers = {
        ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36‘
    }   # UA伪装
    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
    li_list = tree.xpath(‘//ul[@class="house-list-wrap"]/li‘)
    print(li_list)
    fp = open(‘58二手房.txt‘,‘w‘,encoding=‘utf-8‘)
    for li in li_list:
        # 局部解析
        title = li.xpath(‘./div[2]/h2/a/text()‘)[0]
        print(title)
        fp.write(title+‘\n‘) #todo