Python多线程爬虫简单示例

# -*-coding:utf-8 -*-
import urllib2, time
import threading
 
 
class MyThread(threading.Thread):
  def __init__(self, func, args):
    threading.Thread.__init__(self)
    self.args = args
    self.func = func
 
  def run(self):
    apply(self.func, self.args)
 
 
def open_url(url):
  request = urllib2.Request(url)
  html = urllib2.urlopen(request).read()
  print len(html)
  return html
 
if __name__ == '__main__':
  # 构造url列表
  urlList = []
  for p in range(1, 10):
    urlList.append('http://s.wanfangdata.com.cn/Paper.aspx"htmlcode">

# 创建线程类，继承Thread类
class MyThread(threading.Thread):
  def __init__(self, func, args):
    threading.Thread.__init__(self) # 调用父类的构造函数
    self.args = args
    self.func = func
 
  def run(self): # 线程活动方法
    apply(self.func, self.args)
  





threadList = [MyThread(open_url, (url,)) for url in urlList] # 调用线程类创建新线程，返回线程列表
  for t in threadList:
    t.setDaemon(True) # 设置守护线程，父线程会等待子线程执行完后再退出
    t.start() # 线程开启
  for i in threadList:
    i.join() # 等待线程终止，等子线程执行完后再执行父线程



以上就是本文的全部内容，希望对大家的学习有所帮助。