下面的函数foo返回一个字符串'foo'。我如何才能获得从线程的目标返回的值'foo' ?

from threading import Thread

def foo(bar):
    print('hello {}'.format(bar))
    return 'foo'
    
thread = Thread(target=foo, args=('world!',))
thread.start()
return_value = thread.join()

上面所示的“一种明显的方法”不起作用:thread.join()返回None。


当前回答

根据上面提到的,下面是适用于Python3的更通用的解决方案。

import threading

class ThreadWithReturnValue(threading.Thread):
    def __init__(self, *init_args, **init_kwargs):
        threading.Thread.__init__(self, *init_args, **init_kwargs)
        self._return = None
    def run(self):
        self._return = self._target(*self._args, **self._kwargs)
    def join(self):
        threading.Thread.join(self)
        return self._return

使用

        th = ThreadWithReturnValue(target=requests.get, args=('http://www.google.com',))
        th.start()
        response = th.join()
        response.status_code  # => 200

其他回答

一种常见的解决方案是用装饰器来包装函数foo

result = queue.Queue()

def task_wrapper(*args):
    result.put(target(*args))

那么整个代码可能是这样的

result = queue.Queue()

def task_wrapper(*args):
    result.put(target(*args))

threads = [threading.Thread(target=task_wrapper, args=args) for args in args_list]

for t in threads:
    t.start()
    while(True):
        if(len(threading.enumerate()) < max_num):
            break
for t in threads:
    t.join()
return result

Note

一个重要的问题是返回值可能是无序的。 (事实上,返回值不一定保存到队列中,因为您可以选择任意线程安全的数据结构)

你可以使用ThreadPool()的pool.apply_async()来返回test()的值,如下所示:

from multiprocessing.pool import ThreadPool

def test(num1, num2):
    return num1 + num2

pool = ThreadPool(processes=1) # Here
result = pool.apply_async(test, (2, 3)) # Here
print(result.get()) # 5

并且,你也可以使用concurrent.futures.ThreadPoolExecutor()的submit()来返回test()的值,如下所示:

from concurrent.futures import ThreadPoolExecutor

def test(num1, num2):
    return num1 + num2

with ThreadPoolExecutor(max_workers=1) as executor:
    future = executor.submit(test, 2, 3) # Here
print(future.result()) # 5

并且,代替返回,你可以使用数组结果,如下所示:

from threading import Thread

def test(num1, num2, r):
    r[0] = num1 + num2 # Instead of "return"

result = [None] # Here

thread = Thread(target=test, args=(2, 3, result))
thread.start()
thread.join()
print(result[0]) # 5

而不是返回,你也可以使用队列结果,如下所示:

from threading import Thread
import queue

def test(num1, num2, q):
    q.put(num1 + num2) # Instead of "return" 

queue = queue.Queue() # Here

thread = Thread(target=test, args=(2, 3, queue))
thread.start()
thread.join()
print(queue.get()) # '5'

我偷了kindall的答案,稍微整理了一下。

关键部分是为join()添加*args和**kwargs,以便处理超时

class threadWithReturn(Thread):
    def __init__(self, *args, **kwargs):
        super(threadWithReturn, self).__init__(*args, **kwargs)
        
        self._return = None
    
    def run(self):
        if self._Thread__target is not None:
            self._return = self._Thread__target(*self._Thread__args, **self._Thread__kwargs)
    
    def join(self, *args, **kwargs):
        super(threadWithReturn, self).join(*args, **kwargs)
        
        return self._return

更新答案如下

这是我得到最多好评的答案,所以我决定更新可以在py2和py3上运行的代码。

此外,我看到许多对这个问题的回答都显示出对Thread.join()缺乏理解。有些完全不能处理timeout参数。但是当你有(1)一个可以返回None的目标函数并且(2)你也将timeout参数传递给join()时,还有一种极端情况你应该注意。请参阅“TEST 4”以理解这个极端情况。

ThreadWithReturn类,用于py2和py3:

import sys
from threading import Thread
from builtins import super    # https://stackoverflow.com/a/30159479

_thread_target_key, _thread_args_key, _thread_kwargs_key = (
    ('_target', '_args', '_kwargs')
    if sys.version_info >= (3, 0) else
    ('_Thread__target', '_Thread__args', '_Thread__kwargs')
)

class ThreadWithReturn(Thread):
    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        self._return = None
    
    def run(self):
        target = getattr(self, _thread_target_key)
        if target is not None:
            self._return = target(
                *getattr(self, _thread_args_key),
                **getattr(self, _thread_kwargs_key)
            )
    
    def join(self, *args, **kwargs):
        super().join(*args, **kwargs)
        return self._return

一些示例测试如下所示:

import time, random

# TEST TARGET FUNCTION
def giveMe(arg, seconds=None):
    if not seconds is None:
        time.sleep(seconds)
    return arg

# TEST 1
my_thread = ThreadWithReturn(target=giveMe, args=('stringy',))
my_thread.start()
returned = my_thread.join()
# (returned == 'stringy')

# TEST 2
my_thread = ThreadWithReturn(target=giveMe, args=(None,))
my_thread.start()
returned = my_thread.join()
# (returned is None)

# TEST 3
my_thread = ThreadWithReturn(target=giveMe, args=('stringy',), kwargs={'seconds': 5})
my_thread.start()
returned = my_thread.join(timeout=2)
# (returned is None) # because join() timed out before giveMe() finished

# TEST 4
my_thread = ThreadWithReturn(target=giveMe, args=(None,), kwargs={'seconds': 5})
my_thread.start()
returned = my_thread.join(timeout=random.randint(1, 10))

你能确定我们在测试4中可能遇到的极端情况吗?

问题是我们期望giveMe()返回None(参见TEST 2),但我们也期望join()在超时时返回None。

None表示:

(1)这就是giveMe()返回的,或者

(2) join()超时

这个例子很简单,因为我们知道giveMe()总是返回None。但在真实的实例中(目标可能返回None或其他内容),我们希望显式地检查发生了什么。

下面是如何解决这种极端情况:

# TEST 4
my_thread = ThreadWithReturn(target=giveMe, args=(None,), kwargs={'seconds': 5})
my_thread.start()
returned = my_thread.join(timeout=random.randint(1, 10))

if my_thread.isAlive():
    # returned is None because join() timed out
    # this also means that giveMe() is still running in the background
    pass
    # handle this based on your app's logic
else:
    # join() is finished, and so is giveMe()
    # BUT we could also be in a race condition, so we need to update returned, just in case
    returned = my_thread.join()

我发现做到这一点的最短和最简单的方法是利用Python类及其动态属性。您可以使用threading.current_thread()从派生线程的上下文中检索当前线程,并将返回值赋给一个属性。

import threading

def some_target_function():
    # Your code here.
    threading.current_thread().return_value = "Some return value."

your_thread = threading.Thread(target=some_target_function)
your_thread.start()
your_thread.join()

return_value = your_thread.return_value
print(return_value)

我对这个问题的解决方案是将函数和线程包装在一个类中。不需要使用池、队列或c类型变量传递。它也是非阻塞的。而是检查状态。参见代码末尾如何使用它的示例。

import threading

class ThreadWorker():
    '''
    The basic idea is given a function create an object.
    The object can then run the function in a thread.
    It provides a wrapper to start it,check its status,and get data out the function.
    '''
    def __init__(self,func):
        self.thread = None
        self.data = None
        self.func = self.save_data(func)

    def save_data(self,func):
        '''modify function to save its returned data'''
        def new_func(*args, **kwargs):
            self.data=func(*args, **kwargs)

        return new_func

    def start(self,params):
        self.data = None
        if self.thread is not None:
            if self.thread.isAlive():
                return 'running' #could raise exception here

        #unless thread exists and is alive start or restart it
        self.thread = threading.Thread(target=self.func,args=params)
        self.thread.start()
        return 'started'

    def status(self):
        if self.thread is None:
            return 'not_started'
        else:
            if self.thread.isAlive():
                return 'running'
            else:
                return 'finished'

    def get_results(self):
        if self.thread is None:
            return 'not_started' #could return exception
        else:
            if self.thread.isAlive():
                return 'running'
            else:
                return self.data

def add(x,y):
    return x +y

add_worker = ThreadWorker(add)
print add_worker.start((1,2,))
print add_worker.status()
print add_worker.get_results()