zoukankan      html  css  js  c++  java
  • 通过PHP判断搜索引擎蜘蛛是否访问你的网站

    < DOCTYPE html PUBLIC -WCDTD XHTML StrictEN httpwwwworgTRxhtmlDTDxhtml-strictdtd>



    搜索引擎的蜘蛛访问网站是通过远程抓取页面来进行的,我们不能使用JS代码来取得蜘蛛的Agent信息,但是我们可以通过image标签,这样我们就可以得到蜘蛛的agent资料了,通过对agent资料的分析,就可以确定蜘蛛的种类、性别等因素,我们在通过数据库或者文本来记录就可以进行统计了。
    数据库结构:

    #
    # 表的结构 `naps_stats_bot`
    #

    Create TABLE `naps_stats_bot` (
    `botid` int(10) unsigned NOT NULL auto_increment,
    `botname` varchar(100) NOT NULL default ‘’,
    `botagent` varchar(200) NOT NULL default ‘’,
    `bottag` varchar(100) NOT NULL default ‘’,
    `botcount` int(11) NOT NULL default ‘0&prime;,
    `botlast` datetime NOT NULL default ‘0000-00-00 00:00:00&prime;,
    `botlasturl` varchar(250) NOT NULL default ‘’,
    UNIQUE KEY `botid` (`botid`),
    KEY `botname` (`botname`)
    ) TYPE=MyISAM AUTO_INCREMENT=9 ;

    #
    # 导出表中的数据 `naps_stats_bot`
    #

    Insert INTO `naps_stats_bot` VALUES (1, ‘Googlebot’, ‘Googlebot/2.X (+http://www.googlebot.com/bot.html)’, ‘googlebot’, 0, ‘0000-00-00 00:00:00&prime;, ‘’);
    Insert INTO `naps_stats_bot` VALUES (2, ‘MSNbot’, ‘MSNBOT/0.1 (http://search.msn.com/msnbot.htm)’, ‘msnbot’, 0, ‘0000-00-00 00:00:00&prime;, ‘’);
    Insert INTO `naps_stats_bot` VALUES (3, ‘Inktomi Slurp’, ‘Slurp/2.0&prime;, ’slurp’, 0, ‘0000-00-00 00:00:00&prime;, ‘’);
    Insert INTO `naps_stats_bot` VALUES (4, ‘Baiduspider’, ‘Baiduspider+(+http://www.baidu.com/search/spider.htm)’, ‘baiduspider’, 0, ‘0000-00-00 00:00:00&prime;, ‘’);
    Insert INTO `naps_stats_bot` VALUES (5, ‘Yahoobot’, ‘Mozilla/5.0+(compatible;+Yahoo!+Slurp;+http://help.yahoo.com/help/us/ysearch/slurp)’, ’slurp’, 0, ‘0000-00-00 00:00:00&prime;, ‘’);
    Insert INTO `naps_stats_bot` VALUES (6, ‘Sohubot’, ’sohu-search’, ’sohu-search’, 0, ‘0000-00-00 00:00:00&prime;, ‘’);
    Insert INTO `naps_stats_bot` VALUES (7, ‘Lycos’, ‘Lycos/x.x’, ‘lycos’, 0, ‘0000-00-00 00:00:00&prime;, ‘’);
    Insert INTO `naps_stats_bot` VALUES (8, ‘Robozilla’, ‘Robozilla/1.0&prime;, ‘robozilla’, 0, ‘0000-00-00 00:00:00&prime;, ‘’);

    PHP程序:

    <?php

      

      

      
    error_reporting(E_ALL & ~E_NOTICE);
      
    function get_naps_bot()
    {
             $useragent = strtolower($_SERVER['HTTP_USER_AGENT']);
                            
             if (strpos($useragent, 'googlebot') !== false){
                     return 'Googlebot';
             }
            
             if (strpos($useragent, 'msnbot') !== false){
                     return 'MSNbot';
             }
            
             if (strpos($useragent, 'slurp') !== false){
                     return 'Yahoobot';
             }
            
             if (strpos($useragent, 'baiduspider') !== false){
                     return 'Baiduspider';
             }
            
             if (strpos($useragent, 'sohu-search') !== false){
                     return 'Sohubot';
             }
            
             if (strpos($useragent, 'lycos') !== false){
                     return 'Lycos';
             }
            
             if (strpos($useragent, 'robozilla') !== false){
                     return 'Robozilla';
             }        
             return false;
    }
      
    $tlc_thispage = addslashes($_SERVER['HTTP_USER_AGENT']);
    //添加蜘蛛的抓取记录
    $searchbot = get_naps_bot();
    if ($searchbot) {
             $DB_naps->query("Update naps_stats_bot SET botcount=botcount+1, botlast=NOW(), botlasturl='$tlc_thispage' Where botname='$searchbot'");
    }
      
    ?>

  • 相关阅读:
    css单位及颜色值
    web表单作业
    打卡第一天
    IIS的应用池-网站
    Sublime 提示 The package specified, DocBlockr, is not available
    Git/GitHub 初用体验与总结
    自定义置顶TOP按钮
    Firebug 学习使用教程
    ASP.NET导出文件FileResult的使用
    DataGrid获取当前行某列值
  • 原文地址:https://www.cnblogs.com/netcorner/p/2912321.html
Copyright © 2011-2022 走看看