协程_爬虫

爬虫简单实例
from urllib import request
def f(url):
    print('GET: %s' % url)
    resp = request.urlopen(url)
    data = resp.read()
    f=open("url.html",'wb')
    f.write(data)
    f.close()
    print('%d bytes received from %s.' % (len(data), url))

f("https://www.cnblogs.com/alex3714/articles/5248247.html")

爬虫实例
from urllib import request
import gevent,time
from gevent import monkey
 monkey.patch_all() #把当前程序所有的IO操作给我单独的做上标记 相当于打上sleep，识别IO阻塞

def f(url):
     print('GET: %s' % url)
     resp = request.urlopen(url)
     data = resp.read()
     print('%d bytes received from %s.' % (len(data), url))

 urls=['https://www.python.org/',
       'https://www.qq.com/',
       'https://github.com/']

#同步 串行 进程执行
start_time=time.time()
for url in urls:
     f(url)
print("同步cost:",time.time()-start_time)

#异步 协程
async_time_start=time.time()

#开启3个协程，执行f,传f的参数
gevent.joinall([
         gevent.spawn(f, 'https://www.python.org/'),
         gevent.spawn(f, 'https://www.qq.com/'),
         gevent.spawn(f, 'https://github.com/'),
 ])

print("异步cost:",time.time()-async_time_start)