<?php
/**
* Check if the given user agent string is one of a crawler, spider, or bot.
*
* @param string $user_agent
* A user agent string (e.g. Googlebot/2.1 (+http://www.google.com/bot.html))
*
* @return bool
* TRUE if the user agent is a bot, FALSE if not.
*/
function smart_ip_detect_crawler($user_agent) {
// User lowercase string for comparison.
$user_agent = strtolower($_SERVER['HTTP_USER_AGENT']);
// A list of some common words used only for bots and crawlers.
$bot_identifiers = array(
'bot',
'slurp',
'crawler',
'spider',
'curl',
'facebook',
'fetch',
);
// See if one of the identifiers is in the UA string.
foreach ($bot_identifiers as $identifier) {
if (strpos($user_agent, $identifier) !== FALSE) {
return TRUE;
}
}
return FALSE;
}
?>

Or

<script>
function botCheck(){
var botPattern = "(googlebot\/|Googlebot-Mobile|Googlebot-Image|Google favicon|Mediapartners-Google|bingbot|slurp|java|wget|curl|Commons-HttpClient|Python-urllib|libwww|httpunit|nutch|phpcrawl|msnbot|jyxobot|FAST-WebCrawler|FAST Enterprise Crawler|biglotron|teoma|convera|seekbot|gigablast|exabot|ngbot|ia_archiver|GingerCrawler|webmon |httrack|webcrawler|grub.org|UsineNouvelleCrawler|antibot|netresearchserver|speedy|fluffy|bibnum.bnf|findlink|msrbot|panscient|yacybot|AISearchBot|IOI|ips-agent|tagoobot|MJ12bot|dotbot|woriobot|yanga|buzzbot|mlbot|yandexbot|purebot|Linguee Bot|Voyager|CyberPatrol|voilabot|baiduspider|citeseerxbot|spbot|twengabot|postrank|turnitinbot|scribdbot|page2rss|sitebot|linkdex|Adidxbot|blekkobot|ezooms|dotbot|Mail.RU_Bot|discobot|heritrix|findthatfile|europarchive.org|NerdByNature.Bot|sistrix crawler|ahrefsbot|Aboundex|domaincrawler|wbsearchbot|summify|ccbot|edisterbot|seznambot|ec2linkfinder|gslfbot|aihitbot|intelium_bot|facebookexternalhit|yeti|RetrevoPageAnalyzer|lb-spider|sogou|lssbot|careerbot|wotbox|wocbot|ichiro|DuckDuckBot|lssrocketcrawler|drupact|webcompanycrawler|acoonbot|openindexspider|gnam gnam spider|web-archive-net.com.bot|backlinkcrawler|coccoc|integromedb|content crawler spider|toplistbot|seokicks-robot|it2media-domain-crawler|ip-web-crawler.com|siteexplorer.info|elisabot|proximic|changedetection|blexbot|arabot|WeSEE:Search|niki-bot|CrystalSemanticsBot|rogerbot|360Spider|psbot|InterfaxScanBot|Lipperhey SEO Service|CC Metadata Scaper|g00g1e.net|GrapeshotCrawler|urlappendbot|brainobot|fr-crawler|binlar|SimpleCrawler|Livelapbot|Twitterbot|cXensebot|smtbot|bnf.fr_bot|A6-Indexer|ADmantX|Facebot|Twitterbot|OrangeBot|memorybot|AdvBot|MegaIndex|SemanticScholarBot|ltx71|nerdybot|xovibot|BUbiNG|Qwantify|archive.org_bot|Applebot|TweetmemeBot|crawler4j|findxbot|SemrushBot|yoozBot|lipperhey|y!j-asr|Domain Re-Animator Bot|AddThis)";
var re = new RegExp(botPattern, 'i');
var userAgent = navigator.userAgent;
if (re.test(userAgent)) {
return true;
}else{
return false;
}
}
</script>

https://www.mkyong.com/java/java-check-if-web-request-is-from-google-crawler/
http://www.cult-f.net/detect-crawlers-with-php/
https://gist.github.com/ScottPhillips/2904459