python多线程问题

Sha*_*kan 0 python multithreading

任何人都可以告诉我为什么这个代码在启动线程后生成队列?基本上,队列是在for循环之后生成的,但在ThreadUrl类中它已经使用了queue.get()方法.这是如何运作的?如何从尚未生成的队列中获取值?

for i in range(5):
    t = ThreadUrl(queue, out_queue)
    t.setDaemon(True)
    t.start()

# This is what confuses me! Shouldn't it be above the for loop??
for host in hosts:
    queue.put(host)

for i in range(5):
    dt = DatamineThread(out_queue)
    dt.setDaemon(True)
    dt.start()

#wait on the queue until everything has been processed
queue.join()
out_queue.join()
Run Code Online (Sandbox Code Playgroud)

这是完整的来源

import Queue
import threading
import urllib2
import time
from BeautifulSoup import BeautifulSoup

hosts = ["http://yahoo.com", "http://google.com", "http://amazon.com",
        "http://ibm.com", "http://apple.com"]

queue = Queue.Queue()
out_queue = Queue.Queue()

class ThreadUrl(threading.Thread):
    """Threaded Url Grab"""
    def __init__(self, queue, out_queue):
        threading.Thread.__init__(self)
        self.queue = queue
        self.out_queue = out_queue

    def run(self):
        while True:
            #grabs host from queue
            host = self.queue.get()

            #grabs urls of hosts and then grabs chunk of webpage
            url = urllib2.urlopen(host)
            chunk = url.read()

            #place chunk into out queue
            self.out_queue.put(chunk)

            #signals to queue job is done
            self.queue.task_done()

class DatamineThread(threading.Thread):
    """Threaded Url Grab"""
    def __init__(self, out_queue):
        threading.Thread.__init__(self)
        self.out_queue = out_queue

    def run(self):
        while True:
            #grabs host from queue
            chunk = self.out_queue.get()

            #parse the chunk
            soup = BeautifulSoup(chunk)
            print soup.findAll(['title'])

            #signals to queue job is done
            self.out_queue.task_done()

start = time.time()
def main():

    #spawn a pool of threads, and pass them queue instance
    for i in range(5):
        t = ThreadUrl(queue, out_queue)
        t.setDaemon(True)
        t.start()

    #populate queue with data
    for host in hosts:
        queue.put(host)

    for i in range(5):
        dt = DatamineThread(out_queue)
        dt.setDaemon(True)
        dt.start()


    #wait on the queue until everything has been processed
    queue.join()
    out_queue.join()

main()
print "Elapsed Time: %s" % (time.time() - start)
Run Code Online (Sandbox Code Playgroud)

Rom*_*huk 6

host = self.queue.get()块执行线程,直到某个元素出现在queue.

所以

#spawn a pool of threads, and pass them queue instance
for i in range(5):
    t = ThreadUrl(queue, out_queue)
    t.setDaemon(True)
    t.start()
Run Code Online (Sandbox Code Playgroud)

创建5个正在等待队列中任何元素的线程.

#populate queue with data
for host in hosts:
    queue.put(host)
Run Code Online (Sandbox Code Playgroud)

填充队列.在此线程开始处理之后.