python 多协程异步IO爬取网页加速3倍。

 from urllib import request
 import gevent,time
 from gevent import monkey#该模块让当前程序所有io操作单独标记，进行异步操作。

 monkey.patch_all()#对当前程序的io操作打上补丁。没有该monkey方法，异步IO无效。
 def  f(url):
     print('GET:%s'%url)
     resp = request.urlopen(url)#获取网页
     data = resp.read()#读取网页
     print('%d bytes received from  %s'%(len(data),url))#打印长度
 url = ['https://www.yahoo.com/','https://www.python.org/',
  'https://github.com/']
 start = time.time()
 for i in url:
     f(i)#循环运行列表中的网页
 print('串行执行时间：',time.time() - start)#串行执行时间
 async_time = time.time()
 gevent.joinall([
     gevent.spawn(f,'https://www.yahoo.com/')#异步执行启动协程
 ,   gevent.spawn(f,'https://www.python.org/'),
     gevent.spawn(f,'https://github.com/'),
 ])
 print('异步执行时间async time:',time.time() - async_time)#多协程异步IO执行时间

以下为运行结果，明显多协程的牛逼之处。。。。。。。如果不执行monkey方法，则异步IO就会按串行执行。

C:\Users\hushuning\Anaconda3\python.exe C:/Users/hushuning/PycharmProjects/untitled/njx/把当前程序的所有的io操作单独标记，进行异步操作.py
GET:https://www.yahoo.com/
510125 bytes received from  https://www.yahoo.com/
GET:https://www.python.org/
48857 bytes received from  https://www.python.org/
GET:https://github.com/
51373 bytes received from  https://github.com/
串行执行时间： 4.710935354232788
GET:https://www.yahoo.com/
GET:https://www.python.org/
GET:https://github.com/
48857 bytes received from  https://www.python.org/
512422 bytes received from  https://www.yahoo.com/
51373 bytes received from  https://github.com/
异步执行时间async time: 1.6521050930023193

Process finished with exit code 0