PHP采用curl多线程抓取网页功能实现

青旅半醒 2022-06-10 08:44 188阅读 0赞

**CURL 支持多线程的抓取网页的功能，代码例子如下**

class HttpMulti {
    
        //curl选项
        private static $options = array(
            CURLOPT_SSL_VERIFYPEER => 0,   //不开启HTTPS请求
            CURLOPT_RETURNTRANSFER => 1,  //请求信息以文件流方式返回
            CURLOPT_CONNECTTIMEOUT => 10,  //连接超时时间 默认为10s
            CURLOPT_TIMEOUT => 20,   //设置curl执行最大时间
            CURLOPT_ENCODING => "gzip", //HTTP请求头中"Accept-Encoding"的值，为空发送所有支持的编码类型
            CURLOPT_HEADER => 0, //设置为true,请求返回的文件流中就会包含response header
            CURLOPT_USERAGENT => 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36',
    		CURLOPT_POST => FALSE,   //默认选择GET的方式发送
    	);
    
    
    	public static function multiRun($urlData=array()){
            if(empty($urlData)) return;
            $data = $curls = array();
            $mh = curl_multi_init();
            foreach($urlData as $k=>$val){
    			$ch = curl_init($val);
                curl_setopt_array($ch, self::$options);
                curl_multi_add_handle($mh, $ch);
    			$curls[$k] = $ch;
    		}
    		// 执行批处理句柄
            self::execMultiHandle($mh);
            if($curls){
                foreach($curls as $_k=>$v){
    				//获得返回信息
                    $data[$_k] = curl_multi_getcontent($v);
                    curl_close($v);
                    curl_multi_remove_handle($mh, $v);
                    curl_multi_close($mh);
                }
            }
    
            return $data;
    
        }
    
    	static private function execMultiHandle($mh){
            if(empty($mh)) return false;
            do{
                $mrc = curl_multi_exec($mh, $active);
            }while($mrc == CURLM_CALL_MULTI_PERFORM);
            while($active && $mrc == CURLM_OK){
                if(curl_multi_select($mh) != -1){
                    do{
                        $mrc = curl_multi_exec($mh, $active);
                    }while($mrc == CURLM_CALL_MULTI_PERFORM);
    			}
            }
        }
    
    }
    
    //测试代码
    $urlData = [
    'https://www.baidu.com/',
    'https://www.taobao.com/',
    'http://weibo.com/',
    'http://www.qq.com/'
    ];
    $res = HttpMulti::multiRun($urlData);