PHP代码-数据爬取(a标签和a标签所对应的内容)

public function export(){
        set_time_limit(1000);
// header("Content-type: text/html; charset=utf-8");
        $a = file_get_contents('http://chuangye.yjbys.com/zhengce/');
        $reg = '/</span><a href="(.*)" (.*)>(.*)</isU';
        $result = preg_match_all($reg,$a,$match_result);
        $arr = array();
        foreach($match_result[1] as $k=>$v){
            $tnum = strlen($match_result[3][$k]);
            if(substr($v,0,1) == 'h' && $tnum>21){
                $arr[$k]['art_url'] = $v;
                $arr[$k]['art_title'] = mb_convert_encoding($match_result[3][$k], "UTF-8",'gbk');
//                    $match_result[3][$k];
                    mb_convert_encoding($match_result[3][$k], "UTF-8",'gbk');
                $b = file_get_contents($v);
                preg_match('/<div class="content">(.*)</div>/s',$b,$match);
                $match[0] = iconv("gbk", "utf-8", $match[0]);
                $num =  strpos($match[0],'<script type="text/javascript">a("content_body");</script>');
                $cont = substr($match[0],0,$num)."</div>";
                $cony = str_replace('<div class="ad_top_left"><script type="text/javascript">a("content_1");</script></div>',"",$cont);
                $cont = str_replace('<div class="ad_top_left2"><script type="text/javascript">a("content_2");</script></div>',"",$cony);
//                $cont = str_replace('“','“',$cont);
//                $cont = str_replace('”','”',$cont);
//                $cont = str_replace('…','~',$cont);
//                $cont = str_replace('—','-',$cont);
//                $cont = str_replace('"','“',$cont);
//                $cont = str_replace('•','•',$cont);
                $arr[$k]['art_content'] = html_entity_decode($cont);
                $arr[$k]['state'] = 0;
                $arr[$k]['type'] = 4;
                $arr[$k]['userid'] = 4;
            }
        }
        $arr = array_values($arr);
//        print_r($arr);die;
//        $arr2=array_iconv("gbk","utf-8",$arr);
//        print_r($arr);die;
        $article = M('cxpt_user_article');
        var_dump($article->addAll($arr));echo $article->getLastSql();die;
//        foreach($arr as &$v){
//            $b = file_get_contents($v['url']);
//            preg_match('/<div class="content">(.*)</div>/s',$b,$match);
//            $num =  strpos($match[0],'<script type="text/javascript">a("content_body");</script>');
//            $v['content'] = substr($match[0],0,$num); 
//        }
//        foreach($arr as $v){
//            $info['art_title'] = $v['title'];
//            $info['art_content'] = $v['content'];
//        }
//        print_r($arr);die;
        
    }

  

原文地址:https://www.cnblogs.com/renshi/p/6491418.html