python爬虫之xpath实战

python爬虫之xpath实战

代码：

import requests
from lxml import etree
if __name__ == '__main__':
    url = "https://wx.58.com/ershoufang/"
    headers = {"user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"}
    page_text = requests.get(url=url,headers=headers).text
    #数据解析
    tree = etree.HTML(page_text)
    li_list = tree.xpath('//ul[@class="house-list-wrap"]/li')
    fp = open('58.txt','w',encoding="utf-8")
    for li in li_list:
        title = li.xpath('./div[2]/h2/a/text()')[0]
        print(title)
        fp.write(title+'\n')

运行结果：