一、异步爬网页
'''
协程并发爬网页
'''
from urllib import request
import gevent,time
from gevent import monkey # 让gevent知道urllib里的哪些操作属于IO操作monkey.patch_all() # 标记当前程序所有的IO操作def f(url):
print("GET:{0}".format(url))
resp = request.urlopen(url)
data = resp.read()
print('{0} bytes received from {1}'.format(len(data), url))time_start = time.time()
f("https://www.python.org")
f("https://www.yahoo.com")
f("https://github.com")
print("同步耗时:{0}".format(time.time()-time_start))async_time_start = time.time()
gevent.joinall([gevent.spawn(f,"https://www.python.org"),
gevent.spawn(f, "https://www.yahoo.com"),
gevent.spawn(f, "https://github.com")])
print("异步耗时:{0}".format(time.time()-async_time_start))'''
GET:https://www.python.org
49060 bytes received from https://www.python.org
GET:https://www.yahoo.com
498196 bytes received from https://www.yahoo.com
GET:https://github.com
64978 bytes received from https://github.com
同步耗时:10.61960744857788
GET:https://www.python.org
GET:https://www.yahoo.com
GET:https://github.com
86167 bytes received from https://github.com
49060 bytes received from https://www.python.org
503102 bytes received from https://www.yahoo.com
异步耗时:3.7582149505615234
'''
二、异步处理socket请求
服务端:
import socket
import gevent
from gevent import monkeymonkey.patch_all()def server(port):
s = socket.socket()
s.bind(('0.0.0.0', port))
s.listen(500)
while True:
cli, addr = s.accept() # 之前多并发是启动一个线程
gevent.spawn(handle_request, cli)def handle_request(conn):
try:
while True:
data = conn.recv(1024)
print("recv:", data)
conn.send(data)
if not data:
conn.shutdown(socket.SHUT_WR)
except Exception as ex:
print(ex)
finally:
conn.close()if __name__ == '__main__':
server(8001)
客户端:
import socketHOST = 'localhost'
PORT = 8001s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.connect((HOST, PORT))
while True:
msg = bytes(input(">>").strip(), encoding="utf-8")
s.sendall(msg)
data = s.recv(1024)
print("Received:", repr(data))
s.close()