PHP屏蔽蜘蛛访问代码并实现蜘蛛访问日志统计

首页 » 未分类 » 2019年09月10日晚上 11:33:16 » 本文：4126字

选择打赏方式

屏蔽蜘蛛相信每一位站长都不希望这样做吧，因为蜘蛛的访问就没有用户的浏览，直接会给我们带来一定损失，不过也有例外，某些网站就不希望被蜘蛛爬行，接下来为你介绍屏蔽蜘蛛的php代码

主要原理就是判断蜘蛛的HTTP_USER_AGENT

// 屏蔽蜘蛛访问
function banspider($ban_str){
  if(preg_match("/{$ban_str}/i",$_SERVER['HTTP_USER_AGENT'])){
    exit;
  }
}

下面我就给大家一步步得3完善这个demo

function is_crawler(){
  $userAgent = strtolower($_SERVER['HTTP_USER_AGENT']);
  $spiders = array(
    'Googlebot', // Google 爬虫
    'Baiduspider', // 百度爬虫
    '360Spider', // 360爬虫
    'Yahoo! Slurp', // 雅虎爬虫
    'YodaoBot', // 有道爬虫
    'msnbot' // Bing爬虫
    // 更多爬虫关键字
  );
  foreach ($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)) {
        $spiderSite= array(
            "TencentTraveler",
            "Baiduspider",
            "360Spider",
            "BaiduGame",
            "Googlebot",
            "msnbot",
            "Sosospider+",
            "Sogou web spider",
            "ia_archiver",
            "Yahoo! Slurp",
            "YoudaoBot",
            "Yahoo Slurp",
            "MSNBot",
            "Java (Often spam bot)",
            "BaiDuSpider",
            "Voila",
            "Yandex bot",
            "BSpider",
            "twiceler",
            "Sogou Spider",
            "Speedy Spider",
            "Google AdSense",
            "Heritrix",
            "Python-urllib",
            "Alexa (IA Archiver)",
            "Ask",
            "Exabot",
            "Custo",
            "OutfoxBot/YodaoBot",
            "yacy",
            "SurveyBot",
            "legs",
            "lwp-trivial",
            "Nutch",
            "StackRambler",
            "The web archive (IA Archiver)",
            "Perl tool",
            "MJ12bot",
            "Netcraft",
            "MSIECrawler",
            "WGet tools",
            "larbin",
            "Fish search",
        );
        foreach($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！";
}

拓展：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);
}

本文标签：PHP