day10_多线程把六个网站写到文件里

多线程把六个网站写到文件里(串行)

import requests,time,threading

def write_html(url,name):

     r = requests.get(url)

     with open(name,'w',encoding = 'utf8') as f:

          f.write(r.text)

urls =['www.nnzhp.cn','www.besttest.cn','www.imdsx.cn','sb.nnzhp.cn','bbs.besttest.cn','video.besttest.cn']

start_time = time.time()

for url in urls: # 循环每个url

    new_url = 'http://' + url #六个网站

    file_name = url + '.html' # 写入的六个html文件

    write_html(new_url,file_name) # 串行

end_time = time.time()

print('程序总共运行了', end_time - start_time)

 

多线程把六个网站写到文件里(并行)

import requests
import time
import threading


def write_html(url, name):
    r = requests.get(url)
    with open(name, 'w', encoding='utf8') as f:
        f.write(r.text)


urls = ['www.nnzhp.cn', 'www.besttest.cn', 'www.imdsx.cn', 'sb.nnzhp.cn', 'bbs.besttest.cn', 'video.besttest.cn']
lis = []  # 存放每个线程
start_time = time.time()
for url in urls:  # 循环每个url
    new_url = 'http://' + url
    file_name = url + '.html'
    t = threading.Thread(target=write_html, args=(new_url, file_name))  # 实例化一个线程
    lis.append(t)
    t.start()  # 启动一个线程

# 启动六个线程，让他们跑着，主线程等他们，join就是主线程在等待每个子线程执行完成，主线程等待的意思是让子线程把所有的页面都爬完，然后主线程发送邮件

for obj in lis:
    obj.join()  # join必须放在启动的六个线程外面 

end_time = time.time()
print('程序总共运行了', end_time - start_time)