php与python实现的线程池多线程爬虫功能示例

　　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

　　 <?php class Connect extends Worker //worker模式 { public function __construct() { } public function getConnection() { if (!self::$ch) { self::$ch = curl_init(); curl_setopt(self::$ch, CURLOPT_TIMEOUT, 2); curl_setopt(self::$ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt(self::$ch, CURLOPT_HEADER, 0); curl_setopt(self::$ch, CURLOPT_NOSIGNAL, true); curl_setopt(self::$ch, CURLOPT_USERAGENT, Firefox); curl_setopt(self::$ch, CURLOPT_FOLLOWLOCATION, 1); } /* do some exception/error stuff here maybe */ return self::$ch; } public function closeConnection() { curl_close(self::$ch); } /** * Note that the link is stored statically, which for pthreads, means thread local * */ protected static $ch; } class Query extends Threaded { public function __construct($url) { $this->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 = $parts[1]; if ($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( 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()

　　python 线程池爬虫：

　　更多关于PHP相关内容感兴趣的读者可查看本站专题：《php curl用法总结》、《PHP数组(Array)操作技巧大全》、《php排序算法总结》、《PHP常用遍历算法与技巧总结》、《PHP数据结构与算法教程》、《php程序设计算法总结》、《PHP数学运算技巧总结》、《php正则表达式用法总结》、《PHP运算与运算符用法总结》、《php字符串(string)用法总结》及《php常见数据库操作技巧汇总》

　　希望本文所述对大家PHP程序设计有所帮助。