1
0
mirror of https://github.com/e107inc/e107.git synced 2025-07-31 20:00:37 +02:00

Updated isBot() method.

This commit is contained in:
Cameron
2021-01-24 10:42:53 -08:00
parent f6290ed533
commit 9487c620e3
3 changed files with 634 additions and 76 deletions

View File

@@ -264,23 +264,206 @@ class e_user_model extends e_admin_model
return (($this->get('user_join') > strtotime($new_user_period." days ago")) ? true : false);
}
final public function isBot()
final public function isBot($userAgent = null)
{
$userAgent = isset($_SERVER['HTTP_USER_AGENT']) ? $_SERVER['HTTP_USER_AGENT'] : '';
if($userAgent === null && isset($_SERVER['HTTP_USER_AGENT']))
{
$userAgent = $_SERVER['HTTP_USER_AGENT'];
}
if(empty($userAgent))
{
return false;
}
$botlist = array( "googlebot", "Bingbot", 'slurp', 'baidu', 'ichiro','nutch','yacy', "Teoma",
"alexa", "froogle", "Gigabot", "inktomi",
$botlist = array(
// old list.
"Teoma", "alexa", "froogle", "Gigabot", "inktomi",
"looksmart", "URL_Spider_SQL", "Firefly", "NationalDirectory",
"Ask Jeeves", "TECNOSEEK", "InfoSeek", "WebFindBot", "girafabot",
"crawler", "www.galaxy.com", "Scooter", "msnbot", "appie", "FAST", "WebBug", "Spade", "ZyBorg", "rabaz",
"crawler", "www.galaxy.com", "Googlebot", "Scooter", "Slurp",
"msnbot", "appie", "FAST", "WebBug", "Spade", "ZyBorg", "rabaz",
"Baiduspider", "Feedfetcher-Google", "TechnoratiSnoop", "Rankivabot",
"Mediapartners-Google", "Sogou web spider", "WebAlta Crawler","TweetmemeBot",
"Butterfly","Twitturls","Me.dium","Twiceler");
"Butterfly","Twitturls","Me.dium","Twiceler",
// new list.
'80legs',
'ABACHOBot',
'Accoona-AI-Agent',
'AddSugarSpiderBot',
'AnyApexBot',
'Arachmo',
'B-l-i-t-z-B-O-T',
'Baiduspider',
'BecomeBot',
'BeslistBot',
'BillyBobBot',
'Bimbot',
'bingbot',
'BlitzBot',
'boitho.com-dc',
'boitho.com-robot',
'btbot',
'CatchBot',
'Cerberian Drtrs',
'Charlotte',
'ConveraCrawler',
'cosmos',
'Covario',
'DataparkSearch',
'DiamondBot',
'Discobot',
'dotnetdot', // DotBot
'EARTHCOM.info',
'EmeraldShield.com WebBot',
'envolk[ITS]spider',
'EsperanzaBot',
'Exabot',
'FAST Enterprise',
'fastsearch', // FAST Enterprise
'FAST-WebCrawler',
'FDSE robot',
'findlinks',
'FurlBot',
'FyberSpider',
'g2crawler',
'Gaisbot',
'GalaxyBot',
'genieBot',
'Gigabot',
'Girafabot',
'Googlebot',
'Googlebot-Image',
'GurujiBot',
'HappyFunBot',
'hl_ftien_spider',
'holmes',
'htdig',
'iaskspider',
'ia_archiver',
'iCCrawler',
'ichiro',
'igdeSpyder',
'IRLbot',
'IssueCrawler',
'Jaxified Bot',
'Jyxobot',
'KoepaBot',
'L.webis',
'LapozzBot',
'larbin',
'LDSpider',
'LexxeBot',
'Linguee Bot',
'LinkWalker',
'lmspider',
'lwp-trivial',
'mabontland',
'magpie-crawler',
'Mediapartners-Google',
'MJ12bot',
'MLBot',
'Mnogosearch',
'mogimogi',
'MojeekBot',
'Moreoverbot',
'Morning Paper',
'msnbot',
'msrbot',
'MVAClient',
'mxbot',
'NetResearchServer',
'NetSeer',
'NewsGator',
'NG-Search',
'nicebot',
'noxtrumbot',
'Nusearch Spider',
'NutchCVS',
'Nymesis',
'obot',
'oegp',
'omgilibot',
'OmniExplorer_Bot',
'OOZBOT',
'Orbiter',
'PageBites',
'Peew',
'polybot',
'Pompos',
'PostPost',
'psbot',
'PycURL',
'Qseero',
'radian',
'RAMPyBot',
'RufusBot',
'SandCrawler',
'SBIder',
'ScoutJet',
'Scrubby',
'SearchSight',
'Seekbot',
'semanticdiscovery',
'Sensis Web Crawler',
'SEOChat::Bot',
'SeznamBot',
'Shim-Crawler',
'ShopWiki',
'Shoula robot',
'Silk',
'silk',
'Sitebot',
'Snappy',
'sogou spider',
'Sosospider',
'Speedy Spider',
'Sqworm',
'StackRambler',
'suggybot',
'SurveyBot',
'SynooBot',
'Teoma',
'TerrawizBot',
'TheSuBot',
'Thumbnail.CZ robot',
'TinEye',
'truwoGPS',
'TurnitinBot',
'TweetedTimes Bot',
'TwengaBot',
'updated',
'Urlfilebot',
'Vagabondo',
'VoilaBot',
'Vortex',
'voyager',
'VYU2',
'webcollage',
'Websquash.com',
'wf84',
'WoFindeIch Robot',
'WomlpeFactory',
'Xaldon_WebSpider',
'yacy',
'Yahoo! Slurp',
'Yahoo! Slurp China',
'YahooSeeker',
'YahooSeeker-Testing',
'YandexBot',
'YandexImages',
'YandexMetrika',
'Yasaklibot',
'Yeti',
'YodaoBot',
'yoogliFetchAgent',
'YoudaoBot',
'Zao',
'Zealbot',
'zspider',
'ZyBorg'
);
foreach($botlist as $bot)
{