PHP判斷來訪是搜尋引擎蜘蛛還是普通使用者的代碼小結_php執行個體

1、推薦的一種方法：php判斷搜尋引擎蜘蛛爬蟲還是人為存取碼,摘自Discuz x3.2

<?phpfunction checkrobot($useragent=''){static $kw_spiders = array('bot', 'crawl', 'spider' ,'slurp', 'sohu-search', 'lycos', 'robozilla');static $kw_browsers = array('msie', 'netscape', 'opera', 'konqueror', 'mozilla');$useragent = strtolower(empty($useragent) ? $_SERVER['HTTP_USER_AGENT'] : $useragent);if(strpos($useragent, 'http://') === false && dstrpos($useragent, $kw_browsers)) return false;if(dstrpos($useragent, $kw_spiders)) return true;return false;}function dstrpos($string, $arr, $returnvalue = false) {if(empty($string)) return false;foreach((array)$arr as $v) {if(strpos($string, $v) !== false) {$return = $returnvalue ? $v : true;return $return;}}return false;}if(checkrobot()){echo '機器人爬蟲';}else{echo '人';}?>

實際應用中可以這樣判斷，直接不是搜尋引擎才執行操作

<?phpif(!checkrobot()){//do something}?>

2、第二種方法：

使用PHP實現蜘蛛訪問日誌統計

$useragent = addslashes(strtolower($_SERVER['HTTP_USER_AGENT'])); if (strpos($useragent, 'googlebot')!== false){$bot = 'Google';} elseif (strpos($useragent,'mediapartners-google') !== false){$bot = 'Google Adsense';} elseif (strpos($useragent,'baiduspider') !== false){$bot = 'Baidu';} elseif (strpos($useragent,'sogou spider') !== false){$bot = 'Sogou';} elseif (strpos($useragent,'sogou web') !== false){$bot = 'Sogou web';} 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-d H:i:s')."\t".$_SERVER["REMOTE_ADDR"]."\t".$bot."\t".'http://'.$_SERVER['SERVER_NAME'].$_SERVER["REQUEST_URI"]."\r\n");   fclose($fp); }

第三種方法：

我們可以通過HTTP_USER_AGENT來判斷是否是蜘蛛，搜尋引擎的蜘蛛都有自己的獨特標誌，下面列取了一部分。

function is_crawler() {   $userAgent = strtolower($_SERVER['HTTP_USER_AGENT']);   $spiders = array(     'Googlebot', // Google 爬蟲     'Baiduspider', // 百度爬蟲     'Yahoo! Slurp', // 雅虎爬蟲     'YodaoBot', // 有道爬蟲     'msnbot' // Bing爬蟲     // 更多爬蟲關鍵字   );   foreach ($spiders as $spider) {     $spider = strtolower($spider);     if (strpos($userAgent, $spider) !== false) {       return true;     }   }   return false; }

下面的php代碼附帶了更多的蜘蛛標識

function isCrawler() {     echo $agent= strtolower($_SERVER['HTTP_USER_AGENT']);     if (!empty($agent)) {         $spiderSite= array(             "TencentTraveler",             "Baiduspider+",             "BaiduGame",             "Googlebot",             "msnbot",             "Sosospider+",             "Sogou web spider",             "ia_archiver",             "Yahoo! Slurp",             "YoudaoBot",             "Yahoo Slurp",             "MSNBot",             "Java (Often spam bot)",             "BaiDuSpider",             "Voila",             "Yandex bot",             "BSpider",             "twiceler",             "Sogou Spider",             "Speedy Spider",             "Google AdSense",             "Heritrix",             "Python-urllib",             "Alexa (IA Archiver)",             "Ask",             "Exabot",             "Custo",             "OutfoxBot/YodaoBot",             "yacy",             "SurveyBot",             "legs",             "lwp-trivial",             "Nutch",             "StackRambler",             "The web archive (IA Archiver)",             "Perl tool",             "MJ12bot",             "Netcraft",             "MSIECrawler",             "WGet tools",             "larbin",             "Fish search",         );         foreach($spiderSite as $val) {             $str = strtolower($val);             if (strpos($agent, $str) !== false) {                 return true;             }         }     } else {         return false;     } } if (isCrawler()){     echo "你好蜘蛛精！"; } else{    echo "你不是蜘蛛精啊！"; } 

第四種方法：

<?php$flag = false;$tmp = $_SERVER['HTTP_USER_AGENT'];if(strpos($tmp, 'Googlebot') !== false){  $flag = true;} else if(strpos($tmp, 'Baiduspider') >0){  $flag = true;} else if(strpos($tmp, 'Yahoo! Slurp') !== false){  $flag = true;} else if(strpos($tmp, 'msnbot') !== false){  $flag = true;} else if(strpos($tmp, 'Sosospider') !== false){  $flag = true;} else if(strpos($tmp, 'YodaoBot') !== false || strpos($tmp, 'OutfoxBot') !== false){  $flag = true;} else if(strpos($tmp, 'Sogou web spider') !== false || strpos($tmp, 'Sogou Orion spider') !== false){  $flag = true;} else if(strpos($tmp, 'fast-webcrawler') !== false){  $flag = true;} else if(strpos($tmp, 'Gaisbot') !== false){  $flag = true;} else if(strpos($tmp, 'ia_archiver') !== false){  $flag = true;} else if(strpos($tmp, 'altavista') !== false){  $flag = true;} else if(strpos($tmp, 'lycos_spider') !== false){  $flag = true;} else if(strpos($tmp, 'Inktomi slurp') !== false){  $flag = true;}if($flag == false){  header("Location: http://www.jb51.net" . $_SERVER['REQUEST_URI']);  // 自動轉到http://www.jb51.net 對應的網頁  // $_SERVER['REQUEST_URI'] 為網域名稱後面的路徑  // 或換成header("Location: http://www.jb51.net/abc/d.php");  exit();}?>