ecshop 蜘蛛爬行记录的实现

实现步骤：
1.添加数据库表

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

-- 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()

/**
 * 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 (emptyempty($_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

                $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"];

            //获得当前的脚本网址
$url="http://".$server_name;
                if ($server_port != "80")
                {
                    $url = $url.":".$server_port;
                }
    if(!emptyempty($_SERVER["REQUEST_URI"]))
    {
        $scriptName = $_SERVER["REQUEST_URI"];
        $url .= $scriptName;
    }
    else
    {
        $scriptName = $_SERVER["PHP_SELF"];
        if(emptyempty($_SERVER["QUERY_STRING"]))
        {
            $url .= $scriptName;
        }
        else
        {
            $url .= $scriptName."?".$_SERVER["QUERY_STRING"];
        }
    }


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

                if($record_count>=10000)
                {
                    //超过10000开始替换
                    $mintime = $GLOBALS['db']->getOne("SELECT min(time) FROM ".$GLOBALS['ecs']->table('bot'));
                    $minid = $GLOBALS['db']->getOne("SELECT min(id) FROM ".$GLOBALS['ecs']->table('bot'). " WHERE time= $mintime");
                    if($minid > 5000)
                    {
                        //删除记录
                        $sql = "DELETE FROM ".$GLOBALS['ecs']->table('bot')." WHERE id < 5000 or id > 10000";
                        $GLOBALS['db']->query($sql);
                    }
                    $sql="UPDATE " . $GLOBALS['ecs']->table('bot') . "SET " .
                                "url = '$url', bot = '$spider', time = ".gmtime().",ip = '$server_ip' WHERE id= $minid";
                    $GLOBALS['db']->query($sql);

                }
                else
                {
                    $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
/**
 * 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);

    $arr = array();
    date_default_timezone_set('Asia/Shanghai');
    while ($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

 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www./TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www./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>
<!--{foreach from=$bot_list item=bot}-->
<ul>
<li style="width: 50px;">{$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>
<!--{/foreach}-->

<!--翻页 start-->
<ul><li>
  <span style="margin-right:10px;">{$lang.pager_1}<b>{$pager.record_count}</b> {$lang.pager_2}</span>
  <!-- {if $pager.page_first} --><a href="{$pager.page_first}">{$lang.page_first} ...</a><!-- {/if} -->
  <!-- {if $pager.page_prev} --><a class="prev" href="{$pager.page_prev}">{$lang.page_prev}</a><!-- {/if} -->
  <!-- {if $pager.page_count neq 1} -->
    <!--{foreach from=$pager.page_number key=key item=item}-->
      <!-- {if $pager.page eq $key} -->
      <span>{$key}</span>
      <!-- {else} -->
      <a href="{$item}">[{$key}]</a>
      <!-- {/if} -->
    <!--{/foreach}-->
  <!-- {/if} -->

  <!-- {if $pager.page_next} --><a href="{$pager.page_next}">{$lang.page_next}</a><!-- {/if} -->
  <!-- {if $pager.page_last} --><a href="{$pager.page_last}">...{$lang.page_last}</a><!-- {/if} -->
</li></ul>
<!--翻页 END-->
</body>
</html>