python多线程处理数据

python多线程处理数据

从文件读取数据，多线程处理

#! /usr/bin/env python
#encoding=utf-8

import threading
import time
from Queue import Queue

def readFile():
    file_object = open('/opt/dev/python/list.dat')
    global queue
    for line in file_object:                    
        queue.put(line)

class Consumer(threading.Thread):
    def run(self):
        global queue
        while queue.qsize() > 0:
            msg = self.name + '消费了 '+queue.get()
            print msg
            time.sleep(0.01)

queue = Queue()
def main():
    readFile()
    for i in range(5):
        c = Consumer()
        c.start()

if __name__ == '__main__':
    main()

测试数据

队列1
队列2
队列3
队列4
队列5
队列6
队列7
队列8
队列9
队列10
队列11
队列12
队列13
队列14
队列15
队列16

运行结果：

Thread-2消费了 队列879
Thread-3消费了 队列880
Thread-5消费了 队列881
Thread-4消费了 队列882
Thread-6消费了 队列883
Thread-2消费了 队列884
Thread-2消费了 队列885
Thread-6消费了 队列886
Thread-3消费了 队列88

shell单词计数

grep -io '队列' 1.log|wc -l

附：python的生产者消费者代码

#! /usr/bin/env python
#encoding=utf-8

import threading
import time
from Queue import Queue

class Producer(threading.Thread):
    def run(self):
        global queue
        count = 0
        while True:
            for i in range(100):
                if queue.qsize() > 1000:
                     pass
                else:
                     count = count +1
                     msg = '生成产品'+str(count)
                     queue.put(msg)
                     print msg
            time.sleep(1)

class Consumer(threading.Thread):
    def run(self):
        global queue
        while True:
            for i in range(3):
                if queue.qsize() < 100:
                    pass
                else:
                    msg = self.name + '消费了 '+queue.get()
                    print msg
            time.sleep(1)

queue = Queue()


def test():
    for i in range(500):
        queue.put('初始产品'+str(i))
    for i in range(2):
        p = Producer()
        p.start()
    for i in range(5):
        c = Consumer()
        c.start()
if __name__ == '__main__':
    test()