代码一:
#!/usr/bin/python
# -*- coding: utf-8 -*-
#encoding=utf-8
import threading
import Queue
import sys
import urllib2
import re
import MySQLdb
#
# 数据库变量设置
#
DB_HOST = '127.0.0.1'
DB_USER = "XXXX"
DB_PASSWD = "XXXXXXXX"
DB_NAME = "xxxx"
#
# 变量设置
#
THREAD_LIMIT = 3
jobs = Queue.Queue(5)
singlelock = threading.Lock()
info = Queue.Queue()
def workerbee(inputlist):
for x in xrange(THREAD_LIMIT):
print 'Thead {0} started.'.format(x)
t = spider()
t.start()
for i in inputlist:
try:
jobs.put(i, block=True, timeout=5)
except:
singlelock.acquire()
print "The queue is full !"
singlelock.release()
# Wait for the threads to finish
singlelock.acquire() # Acquire the lock so we can print
print "Waiting for threads to finish."
singlelock.release() # Release the lock
jobs.join() # This command waits for all threads to finish.
# while not jobs.empty():
# print jobs.get()
def getTitle(url,time=10):
response = urllib2.urlopen(url,timeout=time)
html = response.read()
response.close()
reg = r'<title>(.*"htmlcode">
#!/usr/bin/python
# -*- coding: utf-8 -*-
#encoding=utf-8
#Filename:robot.py
import threading,Queue,sys,urllib2,re
#
# 变量设置
#
THREAD_LIMIT = 3 #设置线程数
jobs = Queue.Queue(5) #设置队列长度
singlelock = threading.Lock() #设置一个线程锁,避免重复调用
urls = ['http://games.sina.com.cn/w/n/2013-04-28/1634703505.shtml','http://games.sina.com.cn/w/n/2013-04-28/1246703487.shtml','http://games.sina.com.cn/w/n/2013-04-28/1028703471.shtml','http://games.sina.com.cn/w/n/2013-04-27/1015703426.shtml','http://games.sina.com.cn/w/n/2013-04-26/1554703373.shtml','http://games.sina.com.cn/w/n/2013-04-26/1512703346.shtml','http://games.sina.com.cn/w/n/2013-04-26/1453703334.shtml','http://games.sina.com.cn/w/n/2013-04-26/1451703333.shtml','http://games.sina.com.cn/w/n/2013-04-26/1445703329.shtml','http://games.sina.com.cn/w/n/2013-04-26/1434703322.shtml','http://games.sina.com.cn/w/n/2013-04-26/1433703321.shtml','http://games.sina.com.cn/w/n/2013-04-26/1433703320.shtml','http://games.sina.com.cn/w/n/2013-04-26/1429703318.shtml','http://games.sina.com.cn/w/n/2013-04-26/1429703317.shtml','http://games.sina.com.cn/w/n/2013-04-26/1409703297.shtml','http://games.sina.com.cn/w/n/2013-04-26/1406703296.shtml','http://games.sina.com.cn/w/n/2013-04-26/1402703292.shtml','http://games.sina.com.cn/w/n/2013-04-26/1353703286.shtml','http://games.sina.com.cn/w/n/2013-04-26/1348703284.shtml','http://games.sina.com.cn/w/n/2013-04-26/1327703275.shtml','http://games.sina.com.cn/w/n/2013-04-26/1239703265.shtml','http://games.sina.com.cn/w/n/2013-04-26/1238703264.shtml','http://games.sina.com.cn/w/n/2013-04-26/1231703262.shtml','http://games.sina.com.cn/w/n/2013-04-26/1229703261.shtml','http://games.sina.com.cn/w/n/2013-04-26/1228703260.shtml','http://games.sina.com.cn/w/n/2013-04-26/1223703259.shtml','http://games.sina.com.cn/w/n/2013-04-26/1218703258.shtml','http://games.sina.com.cn/w/n/2013-04-26/1202703254.shtml','http://games.sina.com.cn/w/n/2013-04-26/1159703251.shtml','http://games.sina.com.cn/w/n/2013-04-26/1139703233.shtml']
def workerbee(inputlist):
for x in xrange(THREAD_LIMIT):
print 'Thead {0} started.'.format(x)
t = spider()
t.start()
for i in inputlist:
try:
jobs.put(i, block=True, timeout=5)
except:
singlelock.acquire()
print "The queue is full !"
singlelock.release()
# Wait for the threads to finish
singlelock.acquire() # Acquire the lock so we can print
print "Waiting for threads to finish."
singlelock.release() # Release the lock
jobs.join() # This command waits for all threads to finish.
# while not jobs.empty():
# print jobs.get()
def getTitle(url,time=10):
response = urllib2.urlopen(url,timeout=time)
html = response.read()
response.close()
reg = r'<title>(.*?)</title>'
title = re.compile(reg).findall(html)
title = title[0].decode('gb2312','replace').encode('utf-8')
return title
class spider(threading.Thread):
def run(self):
while 1:
try:
job = jobs.get(True,1)
singlelock.acquire()
title = getTitle(job)
print 'This {0} is {1}'.format(job,title)
singlelock.release()
jobs.task_done()
except:
break;
if __name__ == '__main__':
workerbee(urls)
标签:
python,多线程采集
免责声明:本站文章均来自网站采集或用户投稿,网站不提供任何软件下载或自行开发的软件!
如有用户或公司发现本站内容信息存在侵权行为,请邮件告知! 858582#qq.com
桃源资源网 Design By www.nqtax.com
暂无“python实现多线程采集的2个代码例子”评论...
稳了!魔兽国服回归的3条重磅消息!官宣时间再确认!
昨天有一位朋友在大神群里分享,自己亚服账号被封号之后居然弹出了国服的封号信息对话框。
这里面让他访问的是一个国服的战网网址,com.cn和后面的zh都非常明白地表明这就是国服战网。
而他在复制这个网址并且进行登录之后,确实是网易的网址,也就是我们熟悉的停服之后国服发布的暴雪游戏产品运营到期开放退款的说明。这是一件比较奇怪的事情,因为以前都没有出现这样的情况,现在突然提示跳转到国服战网的网址,是不是说明了简体中文客户端已经开始进行更新了呢?