初级的用php写的采集程序

php  /  管理员 发布于 7年前   120

可以先用这个采集然后在用帝国处理
####################################################################################
#作者：9elong
#网站：个人小站不值一提
#时间：2007-01-01
#声明：仅用于学习php之用。
#功能：采集单页面图片。
#说明：3个示范表单已经写好正则用来示范。没有任何功能说明，一切都在源代码里。附加论坛图片采集正则示范
####################################################################################
//把图片从信息页抓取下来的函数
function  getimg($url,$n,$key,$imgqian,$imgbiao,$titlekey)
{
                //$key图片地址正则
                //$titlekey图片标题正则
                //$imgqian图片地址前缀
                //$imgbiao图片地址特殊标识
                global  $n;
                global  $msg;
                global  $result;
                global  $imgadd;
                global  $title;
                $msg=file_get_contents($url);
                $key=str_replace("{图片地址}","(.+)",$key);
                $key="|".$key."|isU";
                preg_match_all($key,$msg,$result);
                $c=count($result[0]);
                for($i=0;$i<$c;$i++)
                {
                                $img=$result[0][$i]."
";
                                if(ereg("^.*".$imgbiao.".*$",$img))
                                {
                                                $img=str_replace($imgbiao,$imgqian.$imgbiao,$img);
                                                preg_match("|http://(.+)jpg|isU",$img,$img);
                                                $imgadd[$n]=$img[0];
                                                //echo  "
";
                                                $n++;
                                }
                                elseif(ereg("^.*jpg.*$",$img))
                                {
                                                preg_match("|http://(.+)jpg|isU",$img,$img);
                                                $imgadd[$n]=$img[0];
                                                if($img[0]!="")
                                                $n++;
                                }
                                unset($img);
                }                                
                                $titlekey=str_replace("{图片标题}","(.+)",$titlekey);
                                $titlekey="|".$titlekey."|isU";
                                preg_match($titlekey,$msg,$title);
                                //echo  $title[0];
                                return  $title;
                return  $msg;
                return  $result;
                return  $n;
                return  $imgadd;
}
####################################################################################
#不支持file_get_contents()函数可以使用下面的替换
#$i=0;
#$handle=@fopen($url,"rb");
#while  (!@feof($handle))
#{
#                $buffer[$i]=  @fgets($handle,  4096);
#                $i++;
#}
#fclose($handle);
#$msg=join("",$buffer);
####################################################################################
if($_GET['act']=="getimgadd"&&$_POST['url']!="")
{
                $url=$_POST['url'];
        getimg($url,"0",$_POST['key'],$_POST['imgqian'],$_POST['imgbiao'],$_POST['titlekey']);
####################################################################################
        //获取分页
                if($_POST['getpage']=="是")
        {
                                $_POST['page']=str_replace("{分页地址}","(.+)",$_POST['page']);
                $page="|".$_POST['page']."|isU";
                //echo  $page;
        preg_match_all($page,$msg,$presult);
                if($_POST['pc']==""||$_POST['pc']=="全部")
                        $pc=count($presult[0]);
                else
                                $pc=$_POST['pc'];
                if($_POST['pc']>count($presult[0]))
                                $pc=count($presult[0]);
                for($i=1;$i<$pc;$i++)
                {
                                $pageurl=$presult[0][$i];
                                //echo  $pageurl."
";
                                if(ereg("^.*[1-9].*$",$pageurl))
                                {
                                                $pageurl=str_replace("                                                $pagekey=str_replace("{关键地址}","(.+)",$_POST['pagekey']);
                                                $pagekey="|".$pagekey."|isU";
                                                preg_match($pagekey,$pageurl,$N3[$i]);
                                                //echo  ($N3[$i][0])."
";
                                                getimg($N3[$i][0],$n,$_POST['key'],$_POST['imgqian'],$_POST['imgbiao'],$_POST['titlekey']);
                                }
                }
        }
####################################################################################
        echo  "图片集〖".$title[1]."〗".$n."张图片被抓取
返回首页
";

                while(list($num,$var)=each($imgadd))
                {
                                if($_POST['showtype']=="图片")
                                {
                                                echo  "
";
                                }
                                else
                                echo  $var."
";
                }
####################################################################################
                //exit();
}
?>
实例1(信息页有分页，使用了简单的分页正则)：

输入图片地址

图片地址正则

图片地址前缀

图片地址标识

图片标题正则{图片标题}