并发编程（六）

from concurrent.futures import ProcessPoolExecutor,ThreadPoolExecutor
from threading import current_thread
import requests
import os
import time
import random

def get(url):
    print(‘%s GET %s‘ %(current_thread().name,url))
    response=requests.get(url)
    time.sleep(random.randint(1,3))

    if response.status_code == 200:
        # 干解析的活
        return response.text

def pasrse(obj):
    res=obj.result()
    print(‘%s 解析结果为：%s‘ %(current_thread().name,len(res)))

if __name__ == ‘__main__‘:
    urls=[
        ‘https://www.baidu.com‘,
        ‘https://www.baidu.com‘,
        ‘https://www.baidu.com‘,
        ‘https://www.baidu.com‘,
        ‘https://www.baidu.com‘,
        ‘https://www.baidu.com‘,
        ‘https://www.baidu.com‘,
        ‘https://www.baidu.com‘,
        ‘https://www.python.org‘,
    ]

    pool=ThreadPoolExecutor(4)
    for url in urls:
        obj=pool.submit(get,url)
        obj.add_done_callback(pasrse)
     print(‘主线程‘,current_thread().name)

    

import queue

q=queue.Queue()
q.put(‘first‘)
q.put(‘second‘)
q.put(‘third‘)

print(q.get())
print(q.get())
print(q.get())
‘‘‘
结果(先进先出):
first
second
third
‘‘‘

import queue

q=queue.LifoQueue()
q.put(‘first‘)
q.put(‘second‘)
q.put(‘third‘)

print(q.get())
print(q.get())
print(q.get())
‘‘‘
结果(后进先出):
third
second
first
‘‘‘

import queue

q=queue.PriorityQueue()
#put进入一个元组,元组的第一个元素是优先级(通常是数字,也可以是非数字之间的比较),数字越小优先级越高
q.put((20,‘a‘))
q.put((10,‘b‘))
q.put((30,‘c‘))

print(q.get())
print(q.get())
print(q.get())
‘‘‘
结果(数字越小优先级越高,优先级高的优先出队):
(10, ‘b‘)
(20, ‘a‘)
(30, ‘c‘)
‘‘‘

Constructor for a priority queue. maxsize is an integer that sets the upperbound limit on the number of items that can be placed in the queue. Insertion will block once this size has been reached, until queue items are consumed. If maxsize is less than or equal to zero, the queue size is infinite.

The lowest valued entries are retrieved first (the lowest valued entry is the one returned by sorted(list(entries))[0]). A typical pattern for entries is a tuple in the form: (priority_number, data).

exception queue.Empty
Exception raised when non-blocking get() (or get_nowait()) is called on a Queue object which is empty.

exception queue.Full
Exception raised when non-blocking put() (or put_nowait()) is called on a Queue object which is full.

Queue.qsize()
Queue.empty() #return True if empty  
Queue.full() # return True if full 
Queue.put(item, block=True, timeout=None)
Put item into the queue. If optional args block is true and timeout is None (the default), block if necessary until a free slot is available. If timeout is a positive number, it blocks at most timeout seconds and raises the Full exception if no free slot was available within that time. Otherwise (block is false), put an item on the queue if a free slot is immediately available, else raise the Full exception (timeout is ignored in that case).

Queue.put_nowait(item)
Equivalent to put(item, False).

Queue.get(block=True, timeout=None)
Remove and return an item from the queue. If optional args block is true and timeout is None (the default), block if necessary until an item is available. If timeout is a positive number, it blocks at most timeout seconds and raises the Empty exception if no item was available within that time. Otherwise (block is false), return an item if one is immediately available, else raise the Empty exception (timeout is ignored in that case).

Queue.get_nowait()
Equivalent to get(False).

Two methods are offered to support tracking whether enqueued tasks have been fully processed by daemon consumer threads.

Queue.task_done()
Indicate that a formerly enqueued task is complete. Used by queue consumer threads. For each get() used to fetch a task, a subsequent call to task_done() tells the queue that the processing on the task is complete.

If a join() is currently blocking, it will resume when all items have been processed (meaning that a task_done() call was received for every item that had been put() into the queue).

Raises a ValueError if called more times than there were items placed in the queue.

Queue.join() block直到queue被消费完毕

from threading import Thread,Event
import threading
import time,random
def conn_mysql():
    count=1
    while not event.is_set():
        if count > 3:
            raise TimeoutError(‘链接超时‘)
        print(‘<%s>第%s次尝试链接‘ % (threading.current_thread().getName(), count))
        event.wait(0.5)
        count+=1
    print(‘<%s>链接成功‘ %threading.current_thread().getName())


def check_mysql():
    print(‘\033[45m[%s]正在检查mysql\033[0m‘ % threading.current_thread().getName())
    time.sleep(random.randint(2,4))
    event.set()
if __name__ == ‘__main__‘:
    event=Event()
    conn1=Thread(target=conn_mysql)
    conn2=Thread(target=conn_mysql)
    check=Thread(target=check_mysql)

    conn1.start()
    conn2.start()
    check.start()

#串行执行
import time
def consumer(res):
    ‘‘‘任务1:接收数据,处理数据‘‘‘
    pass

def producer():
    ‘‘‘任务2:生产数据‘‘‘
    res=[]
    for i in range(10000000):
        res.append(i)
    return res

start=time.time()
#串行执行
res=producer()
consumer(res) #写成consumer(producer())会降低执行效率
stop=time.time()
print(stop-start) #1.5536692142486572



#基于yield并发执行
import time
def consumer():
    ‘‘‘任务1:接收数据,处理数据‘‘‘
    while True:
        x=yield

def producer():
    ‘‘‘任务2:生产数据‘‘‘
    g=consumer()
    next(g)
    for i in range(10000000):
        g.send(i)

start=time.time()
#基于yield保存状态,实现两个任务直接来回切换,即并发的效果
#PS:如果每个任务中都加上打印,那么明显地看到两个任务的打印是你一次我一次,即并发执行的.
producer()

stop=time.time()
print(stop-start) #2.0272178649902344

import time
def consumer():
    ‘‘‘任务1:接收数据,处理数据‘‘‘
    while True:
        x=yield

def producer():
    ‘‘‘任务2:生产数据‘‘‘
    g=consumer()
    next(g)
    for i in range(10000000):
        g.send(i)
        time.sleep(2)

start=time.time()
producer() #并发执行,但是任务producer遇到io就会阻塞住,并不会切到该线程内的其他任务去执行

stop=time.time()
print(stop-start)

yield并不能实现遇到io切换

from gevent import monkey;monkey.patch_all()
from threading import current_thread
import gevent
import time

def eat():
    print(‘%s eat 1‘ %current_thread().name)
    time.sleep(5)
    print(‘%s eat 2‘ %current_thread().name)
def play():
    print(‘%s play 1‘ %current_thread().name)
    time.sleep(3)
    print(‘%s play 2‘ %current_thread().name)

g1=gevent.spawn(eat)
g2=gevent.spawn(play)

# gevent.sleep(100)
# g1.join()
# g2.join()
print(current_thread().name)
gevent.joinall([g1,g2])