sosfiw
sosfiw
发布于 3个月前

PHP判断来访是搜索引擎蜘蛛还是普通用户

推荐的一种方法:php判断搜索引擎蜘蛛爬虫还是人为访问代码,摘自Discuz

<?php
function 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 '机器人爬虫';
}else{
    echo '人';
}
?>

注:Discuz 中应将该方法定义成常量 IS_ROBOT,直接使用即可

第二种方法: 使用PHP实现蜘蛛访问日志统计

$useragent = addslashes(strtolower($_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);
 }

第三种方法: 我们可以通过HTTP_USER_AGENT来判断是否是蜘蛛,搜索引擎的蜘蛛都有自己的独特标志,下面列取了一部分。

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

下面的php代码附带了更多的蜘蛛标识

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!"; 
}

第四种方法:

<?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: //www.jb51.net" . $_SERVER['REQUEST_URI']);
  // 自动转到//www.jb51.net 对应的网页
  // $_SERVER['REQUEST_URI'] 为域名后面的路径
  // 或换成header("Location: //www.jb51.net/abc/d.php");
  exit();
}
?>