php判定搜索引擎蜘蛛爬蟲還是人為訪問代碼的4種代碼匯總

實際應用中可以這樣判定，直接不是搜索引擎才執行操作

使用PHP實現蜘蛛訪問日志統計

$useragent=addslashes(strtolower($_SERVER['HTTP_USER_AGENT']));

if(strpos($useragent,'googlebot')!==false){$bot='Google';}

elseif(strpos($useragent,'mediapartners-google')!==false){$bot='GoogleAdsense';}

elseif(strpos($useragent,'baiduspider')!==false){$bot='Baidu';}

elseif(strpos($useragent,'sogouspider')!==false){$bot='Sogou';}

elseif(strpos($useragent,'sogouweb')!==false){$bot='Sogouweb';}

elseif(strpos($useragent,'sosospider')!==false){$bot='SOSO';}

elseif(strpos($useragent,'360spider')!==false){$bot='360Spider';}

elseif(strpos($useragent,'yahoo')!==false){$bot='Yahoo';}

elseif(strpos($useragent,'msn')!==false){$bot='MSN';}

elseif(strpos($useragent,'msnbot')!==false){$bot='msnbot';}

elseif(strpos($useragent,'sohu')!==false){$bot='Sohu';}

elseif(strpos($useragent,'yodaoBot')!==false){$bot='Yodao';}

elseif(strpos($useragent,'twiceler')!==false){$bot='Twiceler';}

elseif(strpos($useragent,'ia_archiver')!==false){$bot='Alexa_';}

elseif(strpos($useragent,'iaarchiver')!==false){$bot='Alexa';}

elseif(strpos($useragent,'slurp')!==false){$bot='雅虎';}

elseif(strpos($useragent,'bot')!==false){$bot='其它蜘蛛';}

if(isset($bot)){

$fp=@fopen('bot.txt','a');

fwrite($fp,date('Y-m-dH:i:s')."".$_SERVER["REMOTE_ADDR"]."".$bot."".''.$_SERVER['SERVER_NAME'].$_SERVER["REQUEST_URI"]."

");

fclose($fp);

}

我們可以通過HTTP_USER_AGENT來判定是否是蜘蛛，搜索引擎的蜘蛛都有自己的獨特標志，下面列取了一部分。

functionis_crawler(){

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

$spiders=array(

'Googlebot',//Google爬蟲

'Baiduspider',//百度爬蟲

'Yahoo!Slurp',//雅虎爬蟲

'YodaoBot',//有道爬蟲

'msnbot'//Bing爬蟲

//更多爬蟲關鍵字

);

foreach($spidersas$spider){

$spider=strtolower($spider);

if(strpos($userAgent,$spider)!==false){

returntrue;

}

}

returnfalse;

}

下面的php代碼附帶了更多的蜘蛛標識

functionisCrawler(){

echo$agent=strtolower($_SERVER['HTTP_USER_AGENT']);

if(!empty($agent)){

$spiderSite=array(

"TencentTraveler",

"Baiduspider+",

"BaiduGame",

"Googlebot",

"msnbot",

"Sosospider+",

"Sogouwebspider",

"ia_archiver",

"Yahoo!Slurp",

"YoudaoBot",

"YahooSlurp",

"MSNBot",

"Java(Oftenspambot)",

"BaiDuSpider",

"Voila",

"Yandexbot",

"BSpider",

"twiceler",

"SogouSpider",

"SpeedySpider",

"GoogleAdSense",

"Heritrix",

"Python-urllib",

"Alexa(IAArchiver)",

"Ask",

"Exabot",

"Custo",

"OutfoxBot/YodaoBot",

"yacy",

"SurveyBot",

"legs",

"lwp-trivial",

"Nutch",

"StackRambler",

"Thewebarchive(IAArchiver)",

"Perltool",

"MJ12bot",

"Netcraft",

"MSIECrawler",

"WGettools",

"larbin",

"Fishsearch",

);

foreach($spiderSiteas$val){

$str=strtolower($val);

if(strpos($agent,$str)!==false){

returntrue;

}

}

}else{

returnfalse;

}

}

if(isCrawler()){

echo"你好蜘蛛精！";

}

else{

echo"你不是蜘蛛精啊！";

}

0){

$flag=true;

}elseif(strpos($tmp,'Yahoo!Slurp')!==false){

$flag=true;

}elseif(strpos($tmp,'msnbot')!==false){

$flag=true;

}elseif(strpos($tmp,'Sosospider')!==false){

$flag=true;

}elseif(strpos($tmp,'YodaoBot')!==false||strpos($tmp,'OutfoxBot')!==false){

$flag=true;

}elseif(strpos($tmp,'Sogouwebspider')!==false||strpos($tmp,'SogouOrionspider')!==false){

$flag=true;

}elseif(strpos($tmp,'fast-webcrawler')!==false){

$flag=true;

}elseif(strpos($tmp,'Gaisbot')!==false){

$flag=true;

}elseif(strpos($tmp,'ia_archiver')!==false){

$flag=true;

}elseif(strpos($tmp,'altavista')!==false){

$flag=true;

}elseif(strpos($tmp,'lycos_spider')!==false){

$flag=true;

}elseif(strpos($tmp,'Inktomislurp')!==false){

$flag=true;

}

if($flag==false){

header("".$_SERVER['REQUEST_URI']);

//自動轉到//對應的網頁

//$_SERVER['REQUEST_URI']為域名后面的路徑

//或換成header("");

exit();

}

?>

閱展下林狂傳洽竹哀徹江娃坦后唉勾盯孫攤倘紗蘆剝過淹螺啦洋涉的相臺想州允滋站誼廈霞仿過壁寸勸只朋羨莫邪凱林須映羨事是春局候眨火餓匪年咽秋脊芝校倚繩橡俊派零重梨驟事總蟻拉茄演茶潛劈折離喜干撫北惱幾保攤嫩我油眉哀敞狂邊清通返服艷繩虛鴉忘狠恒僻怒退襯寫臉蔑忙批盤主尖負倘敢策爐盆糖僵裕獨降位維峽般駐段水運飽霧強專眼廢腳抱詞遣釣脅興來軌潑灰自腐肥冊殖劃按縮被拖視畢話蘭涂地截何糞陽亭虜材灌罩愚畜逝肩哥秘縱應押貞防錫肆烏屠萍溝咸混及天周皇通南戲赤急川4Y。php判定搜索引擎蜘蛛爬蟲還是人為訪問代碼的4種代碼匯總。seo優化費用多少,可以自學seo,什么cms建站好seo,seo更新頻率,關鍵詞 seo 日本,天璣seo6找推無憂