Python多线程原理与用法实例剖析

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import re
import urllib
import threading
import Queue
import timeit
def getHtml(url):
  html_page = urllib.urlopen(url).read()
  return html_page
# 提取网页中图片的URL
def getUrl(html):
  pattern = r'src="(http://img.*?)"' # 正则表达式
  imgre = re.compile(pattern)
  imglist = re.findall(imgre, html) # re.findall(pattern,string) 在string中寻找所有匹配成功的字符串，以列表形式返回值
  return imglist
class getImg(threading.Thread):
  def __init__(self, queue, thread_name=0): # 线程公用一个队列
    threading.Thread.__init__(self)
    self.queue = queue
    self.thread_name = thread_name
    self.start() # 启动线程
  # 使用队列实现进程间通信
  def run(self):
    global count
    while (True):
      imgurl = self.queue.get() # 调用队列对象的get()方法从队头删除并返回一个项目
      urllib.urlretrieve(imgurl, 'E:\mnt\girls\%s.jpg' % count)
      count += 1
      if self.queue.empty():
        break
      self.queue.task_done() # 当使用者线程调用 task_done() 以表示检索了该项目、并完成了所有的工作时，那么未完成的任务的总数就会减少。
imglist = []
def main():
  global imglist
  url = "http://huaban.com/favorite/beauty/" # 要爬的网页地址
  html = getHtml(url)
  imglist = getUrl(html)
def main_1():
  global count
  threads = []
  count = 0
  queue = Queue.Queue()
  # 将所有任务加入队列
  for img in imglist:
    queue.put(img)
  # 多线程爬去图片
  for i in range(4):
    thread = getImg(queue, i)
    threads.append(thread)
  # 阻塞线程，直到线程执行完成
  for thread in threads:
    thread.join()
if __name__ == '__main__':
  main()
  t = timeit.Timer(main_1)
  print t.timeit(1)

def main_1():
  global count
  threads = []
  count = 0
  queue = Queue.Queue()
  # 将所有任务加入队列
  for img in imglist:
    queue.put(img)
  # 多线程爬去图片
  for i in range(1):
    thread = getImg(queue, i)
    threads.append(thread)
  # 阻塞线程，直到线程执行完成
  for thread in threads:
    thread.join()

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import threading
import timeit
def countdown(n):
  while n > 0:
    n -= 1
def task1():
  COUNT = 100000000
  thread1 = threading.Thread(target=countdown, args=(COUNT,))
  thread1.start()
  thread1.join()
def task2():
  COUNT = 100000000
  thread1 = threading.Thread(target=countdown, args=(COUNT // 2,))
  thread2 = threading.Thread(target=countdown, args=(COUNT // 2,))
  thread1.start()
  thread2.start()
  thread1.join()
  thread2.join()
if __name__ == '__main__':
  t1 = timeit.Timer(task1)
  print "countdown in one thread ", t1.timeit(1)
  t2 = timeit.Timer(task2)
  print "countdown in two thread ", t2.timeit(1)