题目9 爬取某学校官网通告前三页爬虫代码

import requests
from lxml import etree
for i in range(1,4):
    resp=requests.get(f'http://www.jscvc.cn/242/list{i}.htm')
    resp.encoding="utf-8"
    page_text=etree.HTML(resp.text)
    li_list=page_text.xpath('//*[@id="wp_news_w9"]/a')
    for li in li_list:
        title=li.xpath("./span[1]/text()")
        data=li.xpath("./span[2]/text()")
        with open("notice9.txt","a",encoding="utf-8") as file:
            file.write(f"{title[0]},{data[0]}\n")