本文实例讲述了php与python实现的线程池多线程爬虫功能。分享给大家供大家参考，具体如下：
多线程爬虫可以用于抓取内容了这个可以提升性能了，这里我们来看php与python 线程池多线程爬虫的例子，代码如下：
php例子
url = $url;
}
public function run()
{
$ch = $this->worker->getConnection();
curl_setopt($ch, CURLOPT_URL, $this->url);
$page = curl_exec($ch);
$info = curl_getinfo($ch);
$error = curl_error($ch);
$this->deal_data($this->url, $page, $info, $error);
$this->result = $page;
}
function deal_data($url, $page, $info, $error)
{
$parts = explode(".", $url);
$id = $parts;
if ($info['http_code'] != 200)
{
$this->show_msg($id, $error);
} else
{
$this->show_msg($id, "OK");
}
}
function show_msg($id, $msg)
{
echo $id."\t$msg\n";
}
public function getResult()
{
return $this->result;
}
protected $url;
protected $result;
}
function check_urls_multi_pthreads()
{
global $check_urls; //定义抓取的连接
$check_urls = array( 'http://xxx.com' => "xx网",);
$pool = new Pool(10, "Connect", array()); //建立10个线程池
foreach ($check_urls as $url => $name)
{
$pool->submit(new Query($url));
}
$pool->shutdown();
}
check_urls_multi_pthreads();
python 多线程
def handle(sid)://这个方法内执行爬虫数据处理
pass
class MyThread(Thread):
"""docstring for ClassName"""
def __init__(self, sid):
Thread.__init__(self)
self.sid = sid
def run():
handle(self.sid)
threads = []
for i in xrange(1,11):
t = MyThread(i)
threads.append(t)
t.start()
for t in threads:
t.join()
页:
[1]