这里有一个简单的示例：您需要尝试一些替代URL，并返回第一个URL的内容以进行响应。

import Queue
import threading
import urllib2

# Called by each thread
def get_url(q, url):
    q.put(urllib2.urlopen(url).read())

theurls = ["http://google.com", "http://yahoo.com"]

q = Queue.Queue()

for u in theurls:
    t = threading.Thread(target=get_url, args = (q,u))
    t.daemon = True
    t.start()

s = q.get()
print s

在这种情况下，线程被用作一种简单的优化：每个子线程都在等待URL解析和响应，以将其内容放入队列；每个线程都是一个守护进程（如果主线程结束，则不会保持进程运行——这比不结束更常见）；主线程启动所有子线程，在队列中执行get以等待其中一个线程完成put，然后发出结果并终止（这将删除所有可能仍在运行的子线程，因为它们是守护进程线程）。

Python中线程的正确使用总是与I/O操作相关（因为CPython无论如何都不使用多个内核来运行CPU绑定的任务，线程的唯一原因是在等待一些I/O时不会阻塞进程）。顺便说一句，队列几乎总是将工作分配给线程和/或收集工作结果的最佳方式，而且它们本质上是线程安全的，因此它们使您不用担心锁、条件、事件、信号量和其他线程间协调/通信概念。

我发现这非常有用：创建与内核一样多的线程，并让它们执行（大量）任务（在本例中，调用shell程序）：

import Queue
import threading
import multiprocessing
import subprocess

q = Queue.Queue()
for i in range(30): # Put 30 tasks in the queue
    q.put(i)

def worker():
    while True:
        item = q.get()
        # Execute a task: call a shell program and wait until it completes
        subprocess.call("echo " + str(item), shell=True)
        q.task_done()

cpus = multiprocessing.cpu_count() # Detect number of cores
print("Creating %d threads" % cpus)
for i in range(cpus):
     t = threading.Thread(target=worker)
     t.daemon = True
     t.start()

q.join() # Block until all tasks are done

Alex Martelli的回答对我有所帮助。不过，这里有一个我认为更有用的修改版本（至少对我来说）。

更新：可在Python 2和Python 3中使用

try:
    # For Python 3
    import queue
    from urllib.request import urlopen
except:
    # For Python 2 
    import Queue as queue
    from urllib2 import urlopen

import threading

worker_data = ['http://google.com', 'http://yahoo.com', 'http://bing.com']

# Load up a queue with your data. This will handle locking
q = queue.Queue()
for url in worker_data:
    q.put(url)

# Define a worker function
def worker(url_queue):
    queue_full = True
    while queue_full:
        try:
            # Get your data off the queue, and do some work
            url = url_queue.get(False)
            data = urlopen(url).read()
            print(len(data))

        except queue.Empty:
            queue_full = False

# Create as many threads as you want
thread_count = 5
for i in range(thread_count):
    t = threading.Thread(target=worker, args = (q,))
    t.start()

我在这里看到了很多没有执行实际工作的示例，它们大多是CPU限制的。这里是一个CPU绑定任务的示例，它计算1000万到1005万之间的所有素数。我在这里使用了所有四种方法：

import math
import timeit
import threading
import multiprocessing
from concurrent.futures import ThreadPoolExecutor, ProcessPoolExecutor


def time_stuff(fn):
    """
    Measure time of execution of a function
    """
    def wrapper(*args, **kwargs):
        t0 = timeit.default_timer()
        fn(*args, **kwargs)
        t1 = timeit.default_timer()
        print("{} seconds".format(t1 - t0))
    return wrapper

def find_primes_in(nmin, nmax):
    """
    Compute a list of prime numbers between the given minimum and maximum arguments
    """
    primes = []

    # Loop from minimum to maximum
    for current in range(nmin, nmax + 1):

        # Take the square root of the current number
        sqrt_n = int(math.sqrt(current))
        found = False

        # Check if the any number from 2 to the square root + 1 divides the current numnber under consideration
        for number in range(2, sqrt_n + 1):

            # If divisible we have found a factor, hence this is not a prime number, lets move to the next one
            if current % number == 0:
                found = True
                break

        # If not divisible, add this number to the list of primes that we have found so far
        if not found:
            primes.append(current)

    # I am merely printing the length of the array containing all the primes, but feel free to do what you want
    print(len(primes))

@time_stuff
def sequential_prime_finder(nmin, nmax):
    """
    Use the main process and main thread to compute everything in this case
    """
    find_primes_in(nmin, nmax)

@time_stuff
def threading_prime_finder(nmin, nmax):
    """
    If the minimum is 1000 and the maximum is 2000 and we have four workers,
    1000 - 1250 to worker 1
    1250 - 1500 to worker 2
    1500 - 1750 to worker 3
    1750 - 2000 to worker 4
    so let’s split the minimum and maximum values according to the number of workers
    """
    nrange = nmax - nmin
    threads = []
    for i in range(8):
        start = int(nmin + i * nrange/8)
        end = int(nmin + (i + 1) * nrange/8)

        # Start the thread with the minimum and maximum split up to compute
        # Parallel computation will not work here due to the GIL since this is a CPU-bound task
        t = threading.Thread(target = find_primes_in, args = (start, end))
        threads.append(t)
        t.start()

    # Don’t forget to wait for the threads to finish
    for t in threads:
        t.join()

@time_stuff
def processing_prime_finder(nmin, nmax):
    """
    Split the minimum, maximum interval similar to the threading method above, but use processes this time
    """
    nrange = nmax - nmin
    processes = []
    for i in range(8):
        start = int(nmin + i * nrange/8)
        end = int(nmin + (i + 1) * nrange/8)
        p = multiprocessing.Process(target = find_primes_in, args = (start, end))
        processes.append(p)
        p.start()

    for p in processes:
        p.join()

@time_stuff
def thread_executor_prime_finder(nmin, nmax):
    """
    Split the min max interval similar to the threading method, but use a thread pool executor this time.
    This method is slightly faster than using pure threading as the pools manage threads more efficiently.
    This method is still slow due to the GIL limitations since we are doing a CPU-bound task.
    """
    nrange = nmax - nmin
    with ThreadPoolExecutor(max_workers = 8) as e:
        for i in range(8):
            start = int(nmin + i * nrange/8)
            end = int(nmin + (i + 1) * nrange/8)
            e.submit(find_primes_in, start, end)

@time_stuff
def process_executor_prime_finder(nmin, nmax):
    """
    Split the min max interval similar to the threading method, but use the process pool executor.
    This is the fastest method recorded so far as it manages process efficiently + overcomes GIL limitations.
    RECOMMENDED METHOD FOR CPU-BOUND TASKS
    """
    nrange = nmax - nmin
    with ProcessPoolExecutor(max_workers = 8) as e:
        for i in range(8):
            start = int(nmin + i * nrange/8)
            end = int(nmin + (i + 1) * nrange/8)
            e.submit(find_primes_in, start, end)

def main():
    nmin = int(1e7)
    nmax = int(1.05e7)
    print("Sequential Prime Finder Starting")
    sequential_prime_finder(nmin, nmax)
    print("Threading Prime Finder Starting")
    threading_prime_finder(nmin, nmax)
    print("Processing Prime Finder Starting")
    processing_prime_finder(nmin, nmax)
    print("Thread Executor Prime Finder Starting")
    thread_executor_prime_finder(nmin, nmax)
    print("Process Executor Finder Starting")
    process_executor_prime_finder(nmin, nmax)
if __name__ == "__main__":
    main()

以下是我的Mac OS X四核计算机的结果

Sequential Prime Finder Starting
9.708213827005238 seconds
Threading Prime Finder Starting
9.81836523200036 seconds
Processing Prime Finder Starting
3.2467174359990167 seconds
Thread Executor Prime Finder Starting
10.228896902000997 seconds
Process Executor Finder Starting
2.656402041000547 seconds

作为第二个anwser的python3版本：

import queue as Queue
import threading
import urllib.request

# Called by each thread
def get_url(q, url):
    q.put(urllib.request.urlopen(url).read())

theurls = ["http://google.com", "http://yahoo.com", "http://www.python.org","https://wiki.python.org/moin/"]

q = Queue.Queue()
def thread_func():
    for u in theurls:
        t = threading.Thread(target=get_url, args = (q,u))
        t.daemon = True
        t.start()

    s = q.get()
    
def non_thread_func():
    for u in theurls:
        get_url(q,u)
        

    s = q.get()
   

您可以测试它：

start = time.time()
thread_func()
end = time.time()
print(end - start)

start = time.time()
non_thread_func()
end = time.time()
print(end - start)

non_thread_func（）花费的时间应该是thread_func（）的4倍

以前的解决方案都没有在我的GNU/Linux服务器上使用多个内核（我没有管理员权限）。他们只是在一个核心上跑步。

我使用较低级别的os.fork接口来派生多个进程。这是对我有用的代码：

from os import fork

values = ['different', 'values', 'for', 'threads']

for i in range(len(values)):
    p = fork()
    if p == 0:
        my_function(values[i])
        break