ecshop 蜘蛛爬行记录的实现

最新推荐文章于 2020-12-03 19:31:30 发布

LKK

最新推荐文章于 2020-12-03 19:31:30 发布

阅读量681

点赞数

分类专栏： PHP类文章标签： server yahoo url string query sql

PHP类专栏收录该内容

3 篇文章 0 订阅

订阅专栏

效果
http://www.hongyun2000.com/bot.php

实现步骤：
1.添加数据库表

Sql代码

-- --------------------------------------------------------
--
-- 蜘蛛表的结构 `ecs_bot`
--
CREATE TABLE IF NOT EXISTS `ecs_bot` (
`id` int (11) NOT NULL AUTO_INCREMENT,
`url` varchar (255) DEFAULT NULL ,
`bot` varchar (20) DEFAULT NULL ,
`time ` varchar (30) DEFAULT NULL ,
`ip` varchar (50) DEFAULT NULL ,
PRIMARY KEY (`id`)
) ENGINE=MyISAM DEFAULT CHARSET=utf8 AUTO_INCREMENT=1 ;

-- --------------------------------------------------------





--


-- 蜘蛛表的结构 `ecs_bot`


--





CREATE TABLE IF NOT EXISTS `ecs_bot` (


  `id` int(11) NOT NULL AUTO_INCREMENT,


  `url` varchar(255) DEFAULT NULL,


  `bot` varchar(20) DEFAULT NULL,


  `time` varchar(30) DEFAULT NULL,


  `ip` varchar(50) DEFAULT NULL,


  PRIMARY KEY (`id`)


) ENGINE=MyISAM DEFAULT CHARSET=utf8 AUTO_INCREMENT=1 ;

2.修改lib_main.php里的is_spider()

Php代码

/**
* 判断是否为搜索引擎蜘蛛
*
* @access public
* @return string
*/
function is_spider( $record = true)
{
static $spider = NULL;
if ( $spider !== NULL)
{
return $spider ;
}
if ( empty empty ( $_SERVER [ 'HTTP_USER_AGENT' ]))
{
$spider = '' ;
return '' ;
}
$searchengine_bot = array (
'googlebot' ,
'mediapartners-google' ,
'baiduspider+' ,
'msnbot' ,
'yodaobot' ,
'yahoo! slurp;' ,
'yahoo! slurp china;' ,
'iaskspider' ,
'sogou web spider' ,
'sogou push spider'
);
$searchengine_name = array (
'GOOGLE' ,
'GOOGLE ADSENSE' ,
'BAIDU' ,
'MSN' ,
'YODAO' ,
'YAHOO' ,
'Yahoo China' ,
'IASK' ,
'SOGOU' ,
'SOGOU'
);
$spider = strtolower ( $_SERVER [ 'HTTP_USER_AGENT' ]);
foreach ( $searchengine_bot AS $key => $value )
{
if ( strpos ( $spider , $value ) !== false)
{
$spider = $searchengine_name [ $key ];
if ( $record === true)
{
$GLOBALS [ 'db' ]->autoReplace( $GLOBALS [ 'ecs' ]->table( 'searchengine' ), array ( 'date' => local_date( 'Y-m-d' ), 'searchengine' => $spider , 'count' => 1), array ( 'count' => 1));
//蜘蛛爬行记录 author heui
$record_count = $GLOBALS [ 'db' ]->getOne( 'SELECT COUNT(*) FROM ' . $GLOBALS [ 'ecs' ]->table( 'bot' ));
if ( $record_count >10000)
{
//超过10000开始删除
$GLOBALS [ 'db' ]->query( "DELETE FROM " . $GLOBALS [ 'ecs' ]->table( 'bot' ). " LIMIT 1" );
}
$server_name = $_SERVER [ "SERVER_NAME" ];
$server_port = $_SERVER [ "SERVER_PORT" ];
$script_name = $_SERVER [ "SCRIPT_NAME" ];
$query_string = $_SERVER [ "QUERY_STRING" ];
$server_ip = $_SERVER [ "REMOTE_ADDR" ];
$url = "http://" . $server_name ;
if ( $server_port != "80" )
{
$url = $url . ":" . $server_port ;
}
$url = $url . $script_name ;
if ( $query_string != "" )
{
$url = $url . "?" . $query_string ;
}
$sql = "INSERT INTO " . $GLOBALS [ 'ecs' ]->table( 'bot' ) . "(" .
"id, url, bot, time, ip) " .
"VALUES('', '" . $url . "', '" . $spider . "','" .gmtime(). "','" . $server_ip . "')" ;
$GLOBALS [ 'db' ]->query( $sql );
}
return $spider ;
}
}
$spider = '' ;
return '' ;
}

/**


 * 判断是否为搜索引擎蜘蛛


 *


 * @access  public


 * @return  string


 */


function is_spider($record = true)


{


    static $spider = NULL;





    if ($spider !== NULL)


    {


        return $spider;


    }





    if (empty($_SERVER['HTTP_USER_AGENT']))


    {


        $spider = '';





        return '';


    }





    $searchengine_bot = array(


        'googlebot',


        'mediapartners-google',


        'baiduspider+',


        'msnbot',


        'yodaobot',


        'yahoo! slurp;',


        'yahoo! slurp china;',


        'iaskspider',


        'sogou web spider',


        'sogou push spider'


    );





    $searchengine_name = array(


        'GOOGLE',


        'GOOGLE ADSENSE',


        'BAIDU',


        'MSN',


        'YODAO',


        'YAHOO',


        'Yahoo China',


        'IASK',


        'SOGOU',


        'SOGOU'


    );





    $spider = strtolower($_SERVER['HTTP_USER_AGENT']);





    foreach ($searchengine_bot AS $key => $value)


    {


        if (strpos($spider, $value) !== false)


        {


            $spider = $searchengine_name[$key];





            if ($record === true)


            {


            	


                $GLOBALS['db']->autoReplace($GLOBALS['ecs']->table('searchengine'), array('date' => local_date('Y-m-d'), 'searchengine' => $spider, 'count' => 1), array('count' => 1));


                


                //蜘蛛爬行记录 author heui


                $record_count = $GLOBALS['db']->getOne('SELECT COUNT(*) FROM ' . $GLOBALS['ecs']->table('bot'));


                if($record_count>10000)


                {


                	//超过10000开始删除


                	$GLOBALS['db']->query("DELETE FROM ".$GLOBALS['ecs']->table('bot')." LIMIT 1");


                }


                


                $server_name  = $_SERVER["SERVER_NAME"];


                $server_port  = $_SERVER["SERVER_PORT"];


                $script_name  = $_SERVER["SCRIPT_NAME"];


                $query_string = $_SERVER["QUERY_STRING"];


                $server_ip    = $_SERVER["REMOTE_ADDR"];





                $url="http://".$server_name;


                if ($server_port != "80")


                {


                	$url = $url.":".$server_port;


                }                          


                   $url=$url.$script_name;

                  if ($query_string !="")

                {


                	$url=$url."?".$query_string;


                }


                


                $sql="INSERT INTO " . $GLOBALS['ecs']->table('bot') . "(" .


                                "id, url, bot, time, ip) ".


                            "VALUES('', '" . $url . "', '".$spider."','".gmtime()."','".$server_ip. "')";





                $GLOBALS['db']->query($sql);


	 


            }





            return $spider;


        }


    }





    $spider = '';





    return '';


}

3.增加查看蜘蛛爬行列表页面bot.php

Php代码

<?php
/**
* 蜘蛛爬行记录列表
* bot.php
* ============================================================================
* @author heui
*/
define('IN_ECS' , true);
require (dirname( __FILE__ ) . '/includes/init.php' );
if ((DEBUG_MODE & 2) != 2)
{
$smarty ->caching = true;
}
/* 初始化分页信息 */
$page = isset( $_REQUEST [ 'page' ]) && intval ( $_REQUEST [ 'page' ]) > 0 ? intval ( $_REQUEST [ 'page' ]) : 1;
$size = 100;
$cache_id = sprintf( '%X' , crc32( $page . '_' . $size ));
if (! $smarty ->is_cached( 'bot.dwt' , $cache_id ))
{
$smarty ->assign( 'bot_list' , get_bot_list( $page , $size ));
$record_count = $GLOBALS [ 'db' ]->getOne( 'SELECT COUNT(*) FROM ' . $GLOBALS [ 'ecs' ]->table( 'bot' ));
$page_count = $record_count > 0 ? intval ( ceil ( $record_count / $size )) : 1;
$smarty ->assign( 'pager' , get_pager( 'bot.php' , array (), $record_count , $page , $size ));
}
$smarty ->display( 'bot.dwt' , $cache_id );
/**
* 获取蜘蛛爬行记录列表
* @author heui
* @return array
*/
function get_bot_list( $page , $size )
{
$sql = "SELECT id, url, bot, time, ip FROM " . $GLOBALS [ 'ecs' ]->table( 'bot' ). "ORDER BY time DESC" ;
$res = $GLOBALS [ 'db' ]->selectLimit( $sql , $size , ( $page - 1) * $size );
$arr = array ();
while ( $row = $GLOBALS [ 'db' ]->fetchRow( $res ))
{
$arr [ $row [ 'id' ]][ 'id' ] = $row [ 'id' ];
$arr [ $row [ 'id' ]][ 'url' ] = $row [ 'url' ];
$arr [ $row [ 'id' ]][ 'bot' ] = $row [ 'bot' ];
$arr [ $row [ 'id' ]][ 'time' ] = date ( "Y-m-j H:i:s" , $row [ 'time' ]);
$arr [ $row [ 'id' ]][ 'ip' ] = $row [ 'ip' ];
}
return $arr ;
}

<?php


/**


 * 蜘蛛爬行记录列表 


 * bot.php


 * ============================================================================


 * @author heui


 */


define('IN_ECS', true);


require(dirname(__FILE__) . '/includes/init.php');





if ((DEBUG_MODE & 2) != 2)


{


	$smarty->caching = true;


}


/* 初始化分页信息 */


$page = isset($_REQUEST['page'])   && intval($_REQUEST['page'])  > 0 ? intval($_REQUEST['page'])  : 1;


$size = 100;





$cache_id = sprintf('%X', crc32($page.'_'.$size));





if (!$smarty->is_cached('bot.dwt', $cache_id))


{


	$smarty->assign('bot_list',     get_bot_list($page, $size));	


	$record_count = $GLOBALS['db']->getOne('SELECT COUNT(*) FROM ' . $GLOBALS['ecs']->table('bot'));


	$page_count = $record_count > 0 ? intval(ceil($record_count / $size)) : 1;	


	$smarty->assign('pager',       get_pager('bot.php', array(), $record_count, $page, $size));	   


}


$smarty->display('bot.dwt', $cache_id);


/**


 * 获取蜘蛛爬行记录列表


 * @author heui


 * @return  array


 */


function get_bot_list($page, $size)


{


	$sql = "SELECT id, url, bot, time, ip FROM " . $GLOBALS['ecs']->table('bot'). "ORDER BY time DESC";


	$res = $GLOBALS['db']->selectLimit($sql, $size, ($page - 1) * $size);


	


	$arr = array();


	while ($row = $GLOBALS['db']->fetchRow($res))	


	{


		$arr[$row['id']]['id']    = $row['id'];


		$arr[$row['id']]['url']   = $row['url'];


		$arr[$row['id']]['bot']   = $row['bot'];


		$arr[$row['id']]['time']  = date("Y-m-j H:i:s",$row['time']);


		$arr[$row['id']]['ip']    = $row['ip'];


	}





	return $arr;


}

4.增加蜘蛛爬行列表的模板 bot.dwt

Html代码

<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd" >
< html xmlns = "http://www.w3.org/1999/xhtml" >
< head >
< meta http-equiv = "Content-Type" content = "text/html; charset=utf-8" />
< title > 蜘蛛爬行记录 </ title >
< style >
ul, li{
float:left;
list-style: none;
}
ul{
width:900px;
}
</ style >
</ head >
< body >
< ul style = "background-color:#FF0000;" >
< li style = "width: 50px;" > id </ li >
< li style = "width: 300px;" > url </ li >
< li style = "width: 100px;" > bot </ li >
< li style = "width: 200px;" > time </ li >
< li style = "width: 200px;" > ip </ li >
</ ul >
< ul >
< li style = "width: 50px;" > {$bot.id} </ li >
< li style = "width: 300px;" > < a href = "{$bot.url}" target = "_blank" > {$bot.url|truncate:30} </ a > </ li >
< li style = "width: 100px;" > {$bot.bot} </ li >
< li style = "width: 200px;" > {$bot.time} </ li >
< li style = "width: 200px;" > {$bot.ip} </ li >
</ ul >
< ul > < li >
< span style = "margin-right:10px;" > {$lang.pager_1} < b > {$pager.record_count} </ b > {$lang.pager_2} </ span >
< a href = "{$pager.page_first}" > {$lang.page_first} ... </ a >
< a class = "prev" href = "{$pager.page_prev}" > {$lang.page_prev} </ a >
< span > {$key} </ span >
< a href = "{$item}" > [{$key}] </ a >
< a href = "{$pager.page_next}" > {$lang.page_next} </ a >
< a href = "{$pager.page_last}" > ...{$lang.page_last} </ a >
</ li > </ ul >
</ body >
</ html >

LKK

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
ecshop 蜘蛛爬行记录的实现

效果http://www.hongyun2000.com/bot.php实现步骤：1.添加数据库表Sql代码 -- -------------------------------------------------------- --
复制链接

扫一扫

专栏目录