多线程代码分享

import requests

from lxml import etree

u0='https://www.qjnu.edu.cn/channels/9260.html'

n=eval(input("请输入需要爬取的页数:"))

def PaChong(u,ii):

a=requests.get(u)

b=a.content c=etree.HTML(b) title=c.xpath('//h4[@class="media-heading"]/a/text()')

title.append('\n') title.insert(0,'第'+str(ii)+'页:') t='前'+str(n)+'页新闻标题--多线程.txt'

with open(t,'a')as f:

f.writelines(title)

return title#创建一个地址队列

from queue import Queue

url_queue=Queue()url_queue.put(u0)

for i in range(2,n+1): u_i=u0[:-5]+'_'+str(i)+u0[-5:]

url_queue.put(u_i)