爬取学校新闻标题
import requests
from lxml import etree
if __name__ == '__main__':
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36'
' (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'}
url = 'http://www.lzy.edu.cn/index/xxxw/%d.htm'
fp=open('biaoti.txt','w',encoding='utf-8')
for pageNum in range(1,122):
new_url = format(url%pageNum)
page=requests.get(url=new_url,headers=headers)
page.encoding = 'utf-8'
page_text = page.text
tree = etree.HTML(page_text)
li_list = tree.xpath('//ul[@class="mainBlc"]/li')
for li in li_list:
title=li.xpath('./span/a/text()')[0]
fp.write(title+'\n')
print(title)