python beautifulsoup多线程分析抓取网页

#encoding=utf-8
#@description:蜘蛛抓取内容。

import Queue
import threading
import urllib,urllib2
import time
from BeautifulSoup import BeautifulSoup

hosts = [ "http://www.baidu.com", "http://www.163.com"]#要抓取的网页

queue = Queue.Queue()
out_queue = Queue.Queue()

class ThreadUrl(threading.Thread):
     """Threaded Url Grab"""
     def __init__(self, queue, out_queue):
        threading.Thread.__init__(self)
        self.queue = queue
        self.out_queue = out_queue

     def run(self):
         while True:
             #grabs host from queue
            host = self.queue.get()
            proxy_support = urllib2.ProxyHandler({ 'http': 'http://xxx.xxx.xxx.xxxx'}) #代理IP
            opener = urllib2.build_opener(proxy_support, urllib2.HTTPHandler)
            urllib2.install_opener(opener)

             #grabs urls of hosts and then grabs chunk of webpage
            url = urllib.urlopen(host)
            chunk = url.read()

             #place chunk into out queue
            self.out_queue.put(chunk)

             #signals to queue job is done
            self.queue.task_done()

class DatamineThread(threading.Thread):
     """Threaded Url Grab"""
     def __init__(self, out_queue):
        threading.Thread.__init__(self)
        self.out_queue = out_queue

     def run(self):
         while True:
             #grabs host from queue
            chunk = self.out_queue.get()

             #parse the chunk
            soup = BeautifulSoup(chunk)
             print soup.findAll([ 'title']))

             #signals to queue job is done
            self.out_queue.task_done()

start = time.time()
def main():

     #spawn a pool of threads, and pass them queue instance

    t = ThreadUrl(queue, out_queue)
    t.setDaemon(True)
    t.start()

     #populate queue with data
     for host  in hosts:
        queue.put(host)

    dt = DatamineThread(out_queue)
    dt.setDaemon(True)
    dt.start()


     #wait on the queue until everything has been processed
    queue.join()
    out_queue.join()

main()
print  "Elapsed Time:  %s " % (time.time() - start)
 

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值