# 进程:启动多个进程,进程之间是由操作系统负责调用
# 线程:启动多个线程,真正由被cpu执行的最小单位实际是线程
# 开启一个线程,创建一个线程,寄存器、堆栈
# 关闭一个线程
# 协程
# 本质上是一个线程
# 能够在多个任务之间来切换来节省一些IO时间
# 协程中任务之间的切换也消耗时间,但是开销要远远小于进程和线程之间的切换
# 实现并发的手段
def consumer(): while True: x = yield print('处理了数据:',x) def producer(): c = consumer() next(c) for i in range(10): print('生成了数据:',i) c.send(i) producer()
# 真正的协程模块就是使用greenlet完成的切换 from greenlet import greenlet def eat(): print('eating start') g2.switch() print('eating end') g2.switch() def play(): print('playing start') g1.switch() print('playing end') g1 = greenlet(eat) g2 = greenlet(play) g1.switch()
from gevent import monkey;monkey.patch_all() import time import gevent def eat(): print('eating start') time.sleep(1) print('eating end') def play(): print('playing start') time.sleep(1) print('playing end') g1 = gevent.spawn(eat) g2 = gevent.spawn(play) g1.join() g2.join()
# 同步和异步的列子 from gevent import monkey;monkey.patch_all() import time import gevent def task(): time.sleep(1) print(12345) def sync(): for i in range(10): task() def async(): g_lst = [] for i in range(10): g = gevent.spawn(task) g_lst.append(g) gevent.joinall(g_lst) sync() async()
# 协程:能够在一个线程中实现并发效果的概念
# 依赖于能够规避一些在任务中的IO操作
# 在任务的执行过程中检测到io就切换到其他任务
# 爬虫的例子
# 请求过程中的IO等待
from gevent import monkey;monkey.patch_all() import gevent from urllib.request import urlopen def get_url(url): response = urlopen(url) content = response.read().decode('utf-8') return len(content) g1 = gevent.spawn(get_url,'http://www.baidu.com') g2 = gevent.spawn(get_url,'http://www.taobao.com') g3 = gevent.spawn(get_url,'http://www.sougou.com') g4 = gevent.spawn(get_url,'http://www.hao123.com') g5 = gevent.spawn(get_url,'http://www.cisco.com') g6 = gevent.spawn(get_url,'http://www.cnblogs.com') gevent.joinall([g1,g2,g3,g4,g5,g6]) print(g1.value) print(g2.value) print(g3.value) print(g4.value) print(g5.value) print(g6.value)
socket-协程
#server
from gevent import monkey;monkey.patch_all() import socket import gevent def talk(conn): conn.send(b'hello') print(conn.recv(1024).decode('utf-8')) conn.close() sk = socket.socket() sk.bind(('127.0.0.1',8080)) sk.listen() while True: conn,addr = sk.accept() gevent.spawn(talk,conn) sk.close()
#client
import socket sk = socket.socket() sk.connect(('127.0.0.1',8080)) print(sk.recv(1024)) msg = input('>>>>').encode('utf-8') sk.send(msg) sk.close()
协程 在一个线程上,提高cpu的利用率
# 协程相比多线程的优势。切换效率提高了
# 同步:提交一个任务之后要等待这个任务执行完毕;
# 异步:只管提交任务;不等待这个任务执行完毕就可以做其他事情
# 阻塞:recv recvfrom accept
# 非阻塞
# 阻塞 运行状态---阻塞状态---就绪状态
非阻塞IO方式实现socke#server
#server
import socket
sk = socket.socket()
sk.bind(('127.0.0.1',8080))
sk.setblocking(False)
sk.listen()
conn_l = []
del_conn = []
while True:
try:
conn,addr = sk.accept() #不阻塞,但是没有连我会报错
print('建立连接!',addr)
conn_l.append(conn)
except BlockingIOError:
for con in conn_l:
try:
msg = con.recv(1024) #非阻塞,如果没有数据就报错
if msg == b'':
del_conn.append(con)
continue
print(msg)
conn.send(b'byebye')
except BlockingIOError:pass
for con in del_conn:
conn.close()
conn_l.remove(con)
del_conn.clear()
#client import time import socket import threading def func(): sk = socket.socket() sk.connect(('127.0.0.1',8080)) sk.send(b'hello') time.sleep(1) print(sk.recv(1024)) sk.close() for i in range(20): threading.Thread(target=func).start()
IO多路复用-socket
#server import socket import select sk = socket.socket() sk.bind(('127.0.0.1',8080)) sk.setblocking(False) sk.listen() read_lst = [sk] while True: r_lst,w_lst,x_lst = select.select(read_lst,[],[]) for i in r_lst: if i is sk: conn,addr = i.accept() read_lst.append(conn) else: ret = i.recv(1024) if ret == b'': i.close() read_lst.remove(i) continue print(ret) i.send(b'bybybybyby')
#client import time import socket import threading def func(): sk = socket.socket() sk.connect(('127.0.0.1',8080)) sk.send(b'gogogog') time.sleep(3) print(sk.recv(1024)) sk.close() for i in range(20): threading.Thread(target=func).start()