这两天在看多线程，感觉这两篇文章解决我的问题，新技能get！

https://my.oschina.net/leejun2005/blog/194270

https://www.waitalone.cn/python-thread-map.html

标准使用多队列挖掘网站：

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

hosts = ["https://yahoo.com", "https://google.com", "https://amazon.com",
        "https://ibm.com", "https://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)