欧美bbbwbbbw肥妇,免费乱码人妻系列日韩,一级黄片

一個(gè)基于phpQuery的php通用采集類(lèi)分享

 更新時(shí)間:2014年04月09日 09:04:01   作者:  
這是自己以前寫(xiě)的一個(gè)php的采集類(lèi),自己一直在用,自我感覺(jué)很簡(jiǎn)單很強(qiáng)大,只要懂一點(diǎn)點(diǎn)選擇器的知識(shí)就可以采集任何頁(yè)面了,也支持https頁(yè)面,做簡(jiǎn)單的采集足夠用了

一、采集類(lèi)源碼

復(fù)制代碼 代碼如下:

<?php
  /**
  *通用列表采集類(lèi)
  *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 $html;
         /************************************************
         * 參數(shù): 頁(yè)面地址 選擇器數(shù)組 塊選擇器
         * 【選擇器數(shù)組】說(shuō)明:格式array("名稱(chēng)"=>array("選擇器","類(lèi)型"),.......)
         * 【類(lèi)型】說(shuō)明:值 "text" ,"html" ,"屬性"
         *【塊選擇器】:指 先按照規(guī)則 選出 幾個(gè)大塊 ,然后再分別再在塊里面 進(jìn)行相關(guān)的選擇
         *************************************************/
         function QueryList($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(xiě)
$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

相關(guān)文章

最新評(píng)論