进程详解

1.面向对象 __setitrm__  getitem__

class Foo(object):
    def __init__(self):
        self.info={}
    def __setitem__(self, key, value):
        self.info[key]=value
    def __getitem__(self, item):#item为key
        print(item)
        return self.info[item]
obj=Foo()
obj["c"]=233#这里只是单纯的作为字典
print(obj["c"])

2.面向对象__setattr__,__getattr__

class Foo(object):
    def __init__(self):
        object.__setattr__(self,"info",{})#模块内部本质的方法
    def __setattr__(self, key, value):
        self.info[key]=value
    def __getattr__(self, item):#这里的item 差不多是key
        print(item)
        return self.info[item]
obj=Foo()
obj.name="alex"#这里是引用过来的
print(obj.name)

二 进程

1.进程间不可以传递数据,同时也是有主进程的,默认deamon=flase 主进程完毕可以等待子进程

import multiprocessing
import threading
lst=[]
def func(i):
    # print("验证可不可以数据间")
    lst.append(i)
    print( lst)
def run():
    for i in  range(10):
        t1=multiprocessing.Process(target=func,args=(i,))
        t1.start()
if __name__ == '__main__':
    run()

2.进程也可以分为两种写法 一个是引入模块 multiprocseeing ,另一个是继承父类

class Foo(multiprocessing.Process):
    def run(self):
        a=multiprocessing.current_process()
        print("进程 %s" % a)
def run():
    obj=Foo()
    obj.start()
if __name__ == '__main__':
    run()

3.进程可以通过queue 和 manager 来进行信息共享

queue 在windows  上可能不会运行

import multiprocessing
import threading
import queue
import time
q=multiprocessing.Queue()
def tesk(i,q):
    
    q.put=(i)#队列用来限制
def run:
    for i  in  range(10):
        t1=multiprocessing.Process(target=tesk,args=(i,q,))
        t1.start()
    while 1:
        v1=q.get()#这里有一个循环
        print(v1)    
if __name__ == '__main__':
    run()

Manager

用字典的形式阻止

def tesk(arg,dic):
    time.sleep(5)
    dic[arg]=100
if __name__ == '__main__':
    m = multiprocessing.Manager()
    dic=m.dict()
    lst=[]
    for i in  range(10):
        t1=multiprocessing.Process(target=tesk,args=(i,dic))
        t1.start()
        lst.append(t1)
    while 1:#用来做一个判断 .否则即使程序运行完事也不结束
        con=0
        for i in  lst:#这里的i 是每次循环的进程
            if not i.is_alive():#若果进程不在,说明已经运行完毕,因为子进程还没有结束,
                #若是提前结束会报错
                con+=1
        if con==len(lst):#知道相等才停止
            break
    print(dic)

4.进程锁

lock=multiprocessing.RLock()
def tesk(i):
    print("鬼子来了")
    lock.acquire()
    time.sleep(2)
    print(i)
    lock.release()
if __name__ == '__main__':
    t1=multiprocessing.Process(target=tesk,args=(1,))
    t1.start()
    t2=multiprocessing.Process(target=tesk,args=(1,))
    t2.start()

5.进程池

from  concurrent.futures import  ThreadPoolExecutor,ProcessPoolExecutor
def tesk(i):
    time.sleep(5)
    print("真想%s" % i)
if __name__ == '__main__':
    m=ProcessPoolExecutor(5)
    for i  in range(5):
        m.submit(tesk,i)

 6.爬虫初识

import requests#
from bs4 import BeautifulSoup#提取一类相似的类型
from concurrent.futures import ThreadPoolExecutor,ProcessPoolExecutor#多线程


# 模拟浏览器发送请求
# 内部创建 sk = socket.socket()
# 和抽屉进行socket连接 sk.connect(...)
# sk.sendall('...')
# sk.recv(...)

def task(url):
    print(url)
    r1 = requests.get(
        url=url,
        headers={
            'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0'
        }#模拟谷歌浏览器发送请求
    )
    # 查看下载下来的文本信息
    soup = BeautifulSoup(r1.text,'html.parser')
    print(soup.text)
    content_list = soup.find('div',attrs={'id':'content-list'})
    for item in content_list.find_all('div',attrs={'class':'item'}):
        title = item.find('a').text.strip()
        target_url = item.find('a').get('href')
        print(title,target_url)
def run():
    pool = ThreadPoolExecutor(5)
    for i in range(1,50):
        pool.submit(task,'https://www.cnblogs.com/qq849784670/p/9578990.html')


if __name__ == '__main__':
    run()