private $pageURL; privat " /> 国产精品18久久久,四季av在线一区二区三区,色综合久久88色综合天天提莫

色尼玛亚洲综合影院,亚洲3atv精品一区二区三区,麻豆freexxxx性91精品,欧美在线91

一個(gè)基于phpQuery的php通用采集類分享

一、采集類源碼
復(fù)制代碼 代碼如下:
<?php
  /**
  *通用列表采集類
  *版本V1.3
  *作者:JAE
  */
    require_once '../phpQuery/phpQuery/phpQuery.php';
    class QueryList{

        private $pageURL;
         private $regArr = array();
         public $jsonArr = array();
         private $regRange;
         private $html;
         /************************************************
         * 參數(shù): 頁(yè)面地址 選擇器數(shù)組 塊選擇器
         * 【選擇器數(shù)組】說(shuō)明:格式array("名稱"=>array("選擇器","類型"),.......)
         * 【類型】說(shuō)明:值 "text" ,"html" ,"屬性"
         *【塊選擇器】:指 先按照規(guī)則 選出 幾個(gè)大塊 ,然后再分別再在塊里面 進(jìn)行相關(guān)的選擇
         *************************************************/
         function QueryList($pageURL,$regArr=array(),$regRange='')
         {
             $this->pageURL = $pageURL;

             //為了能獲取https://
               $ch = curl_init();
                curl_setopt($ch, CURLOPT_URL,$this->pageURL);
                curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
                curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false);
                curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
                $this->html = curl_exec($ch);
               curl_close($ch);

             if(!empty($regArr))
             {

                  $this->regArr = $regArr;
                 $this->regRange = $regRange;
                 $this->getList();
             }

         }
         function setQuery($regArr,$regRange='')
         {
             $this->jsonArr=array();
             $this->regArr = $regArr;
             $this->regRange = $regRange;
             $this->getList();
         }
        private function getList()
         {

             $hobj = phpQuery::newDocumentHTML($this->html);
             if(!empty($this->regRange))
             {
             $robj = pq($hobj)->find($this->regRange);

              $i=0;
             foreach($robj as $item)
             {

                 while(list($key,$reg_value)=each($this->regArr))
                 {
                     $iobj = pq($item)->find($reg_value[0]);

                       switch($reg_value[1])
                       {
                           case 'text':
                                 $this->jsonArr[$i][$key] = trim(pq($iobj)->text());
                                 break;
                           case 'html':
                                 $this->jsonArr[$i][$key] = trim(pq($iobj)->html());
                                 break;
                           default:
                                $this->jsonArr[$i][$key] = pq($iobj)->attr($reg_value[1]);
                                break;

                        }
                 }
                 //重置數(shù)組指針
                 reset($this->regArr);
                 $i++;
              }
             }
             else
             {
            while(list($key,$reg_value)=each($this->regArr))
             {
                $lobj = pq($hobj)->find($reg_value[0]);

                  
                   $i=0;
                   foreach($lobj as $item)
                   {
                       switch($reg_value[1])
                       {
                           case 'text':
                                 $this->jsonArr[$i++][$key] = trim(pq($item)->text());
                                 break;
                           case 'html':
                                 $this->jsonArr[$i++][$key] = trim(pq($item)->html());
                                 break;
                           default:
                                $this->jsonArr[$i++][$key] = pq($item)->attr($reg_value[1]);
                                break;

                        }

                    
                   }

       
             }
           }
         } 
         function getJSON()
         {
             return json_encode($this->jsonArr);
         }

}

二、使用例子

復(fù)制代碼 代碼如下:
<?php
require 'Query/QueryList.class.php';


//采集OSC的代碼分享列表,標(biāo)題 鏈接 作者
$url = "http://www.oschina.NET/code/list";
$reg = array("title"=>array(".code_title a:eq(0)","text"),"url"=>array(".code_title a:eq(0)","href"),"author"=>array("img","title"));
$rang = ".code_list li";
$hj = new QueryList($url,$reg,$rang);
$arr = $hj->jsonArr;
print_r($arr);
//如果還想采當(dāng)前頁(yè)面右邊的 TOP40活躍貢獻(xiàn)者 圖像,得到JSON數(shù)據(jù),可以這樣寫
$reg = array("portrait"=>array(".hot_top img","src"));
$hj->setQuery($reg);
$json = $hj->getJSON();
echo $json . "<hr/>";

//采OSC內(nèi)容頁(yè)內(nèi)容
$url = "http://www.oschina.NET/code/snippet_186288_23816";
$reg = array("title"=>array(".QTitle h1","text"),"con"=>array(".Content","html"));
$hj = new QueryList($url,$reg);
$arr = $hj->jsonArr;
print_r($arr);

//就舉這么多例子吧,是不是用來(lái)做采集很方便

php技術(shù)一個(gè)基于phpQuery的php通用采集類分享,轉(zhuǎn)載需保留來(lái)源!

鄭重聲明:本文版權(quán)歸原作者所有,轉(zhuǎn)載文章僅為傳播更多信息之目的,如作者信息標(biāo)記有誤,請(qǐng)第一時(shí)間聯(lián)系我們修改或刪除,多謝。

主站蜘蛛池模板: 丰都县| 中牟县| 云梦县| 盘锦市| 长海县| 邵阳市| 广丰县| 内江市| 钦州市| 青州市| 保亭| 望谟县| 微山县| 丹阳市| 富源县| 绍兴市| 保山市| 昌平区| 陈巴尔虎旗| 界首市| 綦江县| 府谷县| 静安区| 澜沧| 习水县| 仲巴县| 莆田市| 扬中市| 娱乐| 禹城市| 河津市| 宁远县| 永吉县| 重庆市| 上高县| 青岛市| 贡觉县| 安多县| 共和县| 密云县| 吉木萨尔县|