php 使用simple_html_dom抓取oschina的新闻资讯

感觉网站太空洞了,就找了找平时自己浏览的IT资讯网站,将内容抓取过来,这样就不能每个网站都浏览了.

[PHP]代码

  //标题+预览 
   public function to_oschina(){
        $datas=$this->_comm_oschina();
        $this->mylib->My_show_list(mymsg::PZ_OSCHINA, 'pc/oschina',$datas,null,'no desc',5,$this->pagesize);    
    }  
   //仅标题
     public function to_oschina_title(){
        $datas=$this->_comm_oschina();
        $this->mylib->My_show_list(mymsg::PZ_OSCHINA, 'pc/oschina_title',$datas,null,'no desc',5,$this->pagemax);    
    } 
   //在页面停留指定秒后开始抓取数据
    function _comm_oschina(){
        $datas=$this->mytool->getInfo();
        $datas["url"]="http://www.oschina.net";
        $datas["ajaxMethod"]="get_oschina";
        $datas["funMethod"]="to_oschina";
        return $datas;     
    } 

   //前台用ajax进行调用 
    function get_oschina(){  
      $this->_insert_oschina();
    }

  function _insert_oschina(){

         $url="http://www.oschina.net/news/list";
          $html = file_get_html($url);
          $result = $html->find('.ArticleList ul li');

          for($j=0;$j<20;$j++){
            $obj=$result[$j];
            $detail=$obj->find("td");
            for($i=0;$i<count($detail);$i++){
             $h=$detail[$i]->find("h3 a",$i);
             if(!empty($h)){
                $data["title"]=$h->innertext;   //标题
                $url=$h->href;
                $data["uri"]= str_replace("http://www.oschina.net","",$url);;          //URI地址
             }

             $p=$detail[$i]->find(".date",$i);
             if(!empty($p)){
                $data["author_url"]=$p->find('a',$i)->href; //作者地址
                $data["author_nm"]=$p->find('a',$i)->innertext; //作者名称
                $data["time_detail"]=$p->innertext();     //作者发布信息
                $data["no"]= substr($data["time_detail"],strrpos($data["time_detail"],"(")+1,16);
             }
             $d=$detail[$i]->find(".detail",$i);
              if(!empty($p)){
                $data["info"]=$d->innertext;    //简介
              }
            }
           $bool=$this->mcom_model->checkIsExit(mymsg::PZ_OSCHINA,array("title"=>$data["title"]));
            if(!$bool){
               $this->mcom_model->insert_data(mymsg::PZ_OSCHINA,$data);
            }
        }  
    }

这样就能抓取oschina的资讯保存进数据库,刷新后可查看

查看实例:http://www.xiuxiandou.com/xitong/pachong/to_oschina