进程中的锁以及进程池

1. 进程
2. 数据共享
3. 锁
4. 进程池
5. 模块(爬虫)
- requests
- bs4(beautifulsoup)
6. 协程

# 1.类的特殊方法的补充
#   (1)对象名.xxx       执行类中的__getattr__方法
#   (2)对象名.xxx=xxx   执行类中的__setattr__方法

# class Foo(object):
#     info={}
#     def __init__(self,name):
#         self.name=name   #初始化方法的本质是执行的object类中的__steattr__方法
#     def __setattr__(self, key, value):
#         self.info[key]=value
#     def __getattr__(self, item):
#         return self.info[item]
# obj=Foo('lisa')
# obj.age=18
# print(obj.info)
# print(obj.age)
# 一.进程
#   1.进程间数据不共享
# import multiprocessing
# data_list=[]
# def task(arg):
#     data_list.append(arg)
#     print(data_list)
# def run():
#     for i in range(1,11):
#         p=multiprocessing.Process(target=task,args=(i,))
#         p.start()
# if __name__ == '__main__':
#     run()

#   2.常用功能:
#       主进程默认等子进程执行完毕
# import time
# import multiprocessing
# data_list=[]
# def task(arg):
#
#     data_list.append(arg)
#     time.sleep(2)
#     print(data_list)
# def run():
#     for i in range(1,11):
#         p=multiprocessing.Process(target=task,args=(i,))
#         p.start()
#         p.join()
# if __name__ == '__main__':
#     run()
#         (1)daemon,主进程不再等子进程执行结束
# import time
# import multiprocessing
# data_list = []
# def task(arg):
#     data_list.append(arg)
#     time.sleep(2)
#     print(data_list)
# def run():
#     for i in range(1,11):
#         p = multiprocessing.Process(target=task, args=(i,))
#         p.daemon=True  #此处进程与线程的写法不再相同,不是括号中写布尔值了
#         p.start()
# if __name__ == '__main__':
#     run()
#       (2)join没有参数,主进程默认等子进程执行完毕再往下走
# import time
# import multiprocessing
# data_list = []
# def task(arg):
#     data_list.append(arg)
#     time.sleep(2)
#     print(data_list)
# def run():
#     for i in range(1,11):
#         p = multiprocessing.Process(target=task, args=(i,))
#         p.start()
#         p.join()
#         print('执行完了')
# if __name__ == '__main__':
#     run()
# 运行结果:
#[1]
# 执行完了
# [2]
# 执行完了
# [3]
# 执行完了
# [4]
# 执行完了
# [5]
# 执行完了
# [6]
# 执行完了
# [7]
# 执行完了
# [8]
# 执行完了
# [9]
# 执行完了
# [10]
# 执行完了
#
#       (3)join有参数,让主进程在这里最多等待几秒,无论是否执行完都会继续往下走
# import time
# import multiprocessing
# data_list = []
# def task(arg):
#     data_list.append(arg)
#     time.sleep(2)
#     print(data_list)
# def run():
#     for i in range(1,11):
#         p = multiprocessing.Process(target=task, args=(i,))
#         p.start()
#         p.join(1)
#         print('执行完了')
# if __name__ == '__main__':
#     run()
# 运行结果:
# 执行完了
# 执行完了
# [1]
# 执行完了
# [2]
# 执行完了
# [3]
# 执行完了
# [4]
# 执行完了
# [5]
# 执行完了
# [6]
# 执行完了
# [7]
# 执行完了
# [8]
# 执行完了
# [9]
# [10]

#       (4)进程名称:与线程不同的是不再是setname,getname,直接name
# import time
# import multiprocessing
# data_list = []
# def task(arg):
#     data_list.append(arg)
#     p=multiprocessing.current_process()
#     name=p.name
#     time.sleep(2)
#     print(name,data_list)
# def run():
#     p = multiprocessing.Process(target=task, args=(1,))
#     p.name='去玩儿'
#     p.start()
#     print('执行完了')
# if __name__ == '__main__':
#     run()

#   3.与线程相同的是除了正常import multiprocessing写线程,还可以用类继承的方法创建进程
# import multiprocessing
# class MyProcess(multiprocessing.Process):
#     def run(self):
#         print('当前线程名称%s' % multiprocessing.current_process())
# def task():
#     p1=MyProcess()
#     p1.start()
#     p2 = MyProcess()
#     p2.start()
# if __name__ == '__main__':
#     task()
#二.进程间数据共享
# Queue

#   linux:

# import multiprocessing
# q=multiprocessing.Queue()
# def task(arg):
#     q.put(arg)
# def run():
#     for i in range(10):
#         p=multiprocessing.Process(target=task,args=(i,))
#         p.start()
#     while 1:
#         print(q.get())
# run()

#   windows:

# import multiprocessing
# def task(arg,q):
#     q.put(arg)
# if __name__ == '__main__':
#     q = multiprocessing.Queue()
#     for i in range(10):
#         p=multiprocessing.Process(target=task,args=(i,q))
#         p.start()
#     while 1:
#         print(q.get())


#1.Manager

#       Linux

# import multiprocessing
# m=multiprocessing.Manager()
# dic=m.dict()  #一个特殊的字典,是所有进程共享的
# def task(arg):
#     dic[arg]=100
# def run():
#     for i in range(10):
#         p=multiprocessing.Process(target=task,args=(i,))
#         p.start()
#     while 1:
#         print(dic.items())
# run()

#       Windows

# import time
# import multiprocessing
# def task(arg,dic):
#     dic[arg]=arg
# if __name__ == '__main__':
#     m = multiprocessing.Manager()
#     dic = m.dict()#会写到一个文件中
#     def run():
#         for i in range(10):
#             p=multiprocessing.Process(target=task,args=(i,dic))
#             p.start()
#     run()
#     time.sleep(10) #如果不加这句,有可能主进程结束了,子进程还没有结束,主进程结束了,文件就删除了,子进程就无法找到文件,所以会报错
#     print(dic)
#
#三,进程锁(进程间存在数据共享的时候才有必要加锁)

# import time
# def task(arg,lock):
#     lock.acquire()
#     time.sleep(1)
#     print(arg)
#     lock.release()
# if __name__ == '__main__':
#     import multiprocessing
#     lock = multiprocessing.RLock()
#     def run():
#         for i in range(1, 11):
#             p = multiprocessing.Process(target=task, args=(i,lock,))
#             p.start()
#     run()

#四.进程池

# import time
# from concurrent.futures import ThreadPoolExecutor,ProcessPoolExecutor
# def task(arg):
#     time.sleep(1)
#     print(arg)
# if __name__ == '__main__':
#     pool=ProcessPoolExecutor(5)
#     for i in range(16):
#         pool.submit(task,i)


#五.
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
#
# #