Python 爬虫多线程详解及实例代码

# -*-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">

 # 一般方式
 n_start = time.time()
 for each in urlList:
  open_url(each)
 n_end = time.time()
 print 'the normal way take %s s' % (n_end-n_start)






# 多线程
 t_start = time.time()
 threadList = [MyThread(open_url, (url,)) for url in urlList]
 for t in threadList:
  t.setDaemon(True)
  t.start()
 for i in threadList:
  i.join()
 t_end = time.time()
 print 'the thread way take %s s' % (t_end-t_start)



分别用两种方式获取10个访问速度比较慢的网页，一般方式耗时50s，多线程耗时10s。

多线程代码解读:


# 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。