Python模拟分割大文件以及多线程处理的实现方法

#!/usr/bin/env python

#--*-- coding:utf-8 --*--

from random import randint

from time import ctime

from time import sleep

import queue

import threading

class MyTask(object):

  """具体的任务类"""

  def __init__(self, name):

    self.name = name

    self._work_time = randint(1, 5)

  def work(self):

    print("Task %s is start : %s, sleep time= %d" % (self.name, ctime(), self._work_time))

    sleep(self._work_time)

    print("Task %s is end : %s" % (self.name, ctime()))

class MyThread(threading.Thread):

  """多线程的类"""

  def __init__(self, my_queue):

    self.my_queue = my_queue

    super(MyThread, self).__init__()

  def run(self):

    while True:

      if self.my_queue.qsize() > 0:

        self.my_queue.get().work()

      else:

        break

def print_split_line(num=30):

  print("*" * num)

if __name__ == "__main__":

  print_split_line()

  import my_read_file

  # 分割文件

  sf = my_read_file.SplitFiles(r"F:\multiple_thread_read_file.txt", line_count=300)

  file_num = sf.split_file()

  queue_length = file_num

  my_queue = queue.LifoQueue(queue_length)

  threads = []

  for i in range(queue_length):

    file_name = sf.get_part_file_name(i)

    mt = MyTask(file_name)

    my_queue.put_nowait(mt)

  for i in range(queue_length):

    mtd = MyThread(my_queue)

    threads.append(mtd)

  for i in range(queue_length):

    threads[i].start()

  for i in range(queue_length):

    threads[i].join()

  print_split_line()