python 并发 进程 数据共享 锁 进程池

面向对象补充:对象中设置值

class Foo(object):

    def __init__(self):
        object.__setattr__(self, 'info', {}) # 在对象中设置值的本质

    def __setattr__(self, key, value):
        self.info[key] = value

    def __getattr__(self, item):
        print(item)
        return self.info[item]

obj = Foo()
obj.name = 'alex'
print(obj.name)
v = []
for i in range(10000):
    v.append(i)

print(v)

1. 进程

　　进程间数据不共享

data_list = []

def task(arg):
    data_list.append(arg)
    print(data_list)


def run():
    for i in range(10):
        p = multiprocessing.Process(target=task,args=(i,))
        # p = threading.Thread(target=task,args=(i,))
        p.start()

if __name__ == '__main__':
    run()

常用功能:

import time
def task(arg):
    time.sleep(2)
    print(arg)


def run():
    print('111111111')
    p1 = multiprocessing.Process(target=task,args=(1,))
    p1.name = 'pp1'
    p1.start()
    print('222222222')

    p2 = multiprocessing.Process(target=task, args=(2,))
    p2.name = 'pp2'
    p2.start()
    print('333333333')

if __name__ == '__main__':
    run()

类继承方式创建进程:

class MyProcess(multiprocessing.Process):

    def run(self):
        print('当前进程',multiprocessing.current_process())


def run():
    p1 = MyProcess()
    p1.start()

    p2 = MyProcess()
    p2.start()

if __name__ == '__main__':
    run()

2.进程间数据共享:   (multiprocessing.Queue    ,      Manager)

 

import multiprocessing
import threading　　　　　　#第一种
import queue
import time
 q = multiprocessing.Queue()

 def task(arg,q):
     q.put(arg)


 def run():
     for i in range(10):
         p = multiprocessing.Process(target=task, args=(i, q,))
         p.start()

     while True:
         v = q.get()
            print(v)
 if __name__ == '__main__':
     run()




def task(arg,dic):
    time.sleep(2)
    dic[arg] = 100

if __name__ == '__main__':
    m = multiprocessing.Manager()　　　　#第二种
    dic = {}
    process_list = []
    for i in range(10):
        p = multiprocessing.Process(target=task, args=(i,dic,))
        p.start()

        process_list.append(p)

    while True:
        count = 0
        for p in process_list:
            if not p.is_alive():
                count += 1
        if count == len(process_list):
            break
    print(dic)

进程间的数据其他电脑:

lock = multiprocessing.RLock()
def task(arg,):
    print("鬼子扛枪")
    lock.acquire()
    time.sleep(2)
    print(arg)
    lock.release()
if __name__ == '__main__':
    while True:
    ........

3.进程锁:

import time
import threading
import multiprocessing


lock = multiprocessing.RLock()

def task(arg):
    print('鬼子来了')
    lock.acquire()
    time.sleep(2)
    print(arg)
    lock.release()


if __name__ == '__main__':
    p1 = multiprocessing.Process(target=task,args=(1,))
    p1.start()

    p2 = multiprocessing.Process(target=task, args=(2,))
    p2.start()

4.进程池

import time
from concurrent.futures import ThreadPoolExecutor,ProcessPoolExecutor

def task(arg):
    time.sleep(2)
    print(arg)

if __name__ == '__main__':

    pool = ProcessPoolExecutor(5)
    for i in range(10):
        pool.submit(task,i)

5.初始爬虫.

　　安装 :  pip3  install  requests

　　　　　 pip3  install  beautifulsoup4

　　问题 : 找不到内部指令?

　　　　    方式一 : C:\Users\SF\AppData\Local\Programs\Python\Python36\Scripts\pip3 install  requests

　　　　　 方式二 :  C:\Users\SF\AppData\Local\Programs\Python\Python36\Scripts

　　　　　 pip3  install  requests

简单爬虫示例:

import requests
from bs4 import BeautifulSoup
from concurrent.futures import ThreadPoolExecutor,ProcessPoolExecutor


# 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; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.92 Safari/537.36'
        }
    )

    # 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://dig.chouti.com/all/hot/recent/%s' %i)


if __name__ == '__main__':
    run()

进程和线程那个好?

回答是:  线程好

进程池/  线程池的应用   与爬虫有关