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。
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',
botlast
datetime NOT NULL default '0000-00-00 00:00:00',
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','0000-00-00 00:00:00','');
INSERT INTO naps_stats_bot
VALUES (2,'MSNbot','MSNBOT/0.1 (http://search.msn.com/msnbot.htm)','msnbot','');
INSERT INTO naps_stats_bot
VALUES (3,'Inktomi Slurp','Slurp/2.0','slurp','');
INSERT INTO naps_stats_bot
VALUES (4,'Baiduspider','Baiduspider+(+http://www.baidu.com/search/spider.htm)','baiduspider','');
INSERT INTO naps_stats_bot
VALUES (5,'Yahoobot','Mozilla/5.0+(compatible;+Yahoo!+Slurp;+http://help.yahoo.com/help/us/ysearch/slurp)','');
INSERT INTO naps_stats_bot
VALUES (6,'Sohubot','sohu-search','');
INSERT INTO naps_stats_bot
VALUES (7,'Lycos','Lycos/x.x','lycos','');
INSERT INTO naps_stats_bot
VALUES (8,'Robozilla','Robozilla/1.0','robozilla','');
query("UPDATE naps_stats_bot SET botcount=botcount+1,botlast=NOW(),botlasturl='$tlc_thispage' WHERE botname='$searchbot'");
}
?>