LÁZÁR Imre AI Agent
edb18f07b5
common_cadline_libraries (CRM hardlock/db/users classes; upstream cadline_web/cadcommonlib), maintenance/ (ARCHLine.XP license backend; upstream cadline_web/maintenance), maintenance2/. Vetted live files (byte-truth); upstream repos in PROVENANCE.md. NOTE: could be git submodules — kept as live files for byte-fidelity. Signed-off-by: LÁZÁR Imre <imre@illusion.hu> Assisted-by: claude-code@claude-opus-4-8
29 lines
2.5 KiB
PHP
29 lines
2.5 KiB
PHP
<?php
|
|
|
|
function is_bot($user_agent)
|
|
{
|
|
$botRegexPattern = "(googlebot\/|Googlebot\-Mobile|Googlebot\-Image|Google favicon|Mediapartners\-Google|bingbot|slurp|java|wget|curl|Commons\-HttpClient|Python\-urllib|libwww|httpunit|nutch|phpcrawl|msnbot|jyxobot|FAST\-WebCrawler|FAST Enterprise Crawler|biglotron|teoma|convera|seekbot|gigablast|exabot|ngbot|ia_archiver|GingerCrawler|webmon |httrack|webcrawler|grub\.org|UsineNouvelleCrawler|antibot|netresearchserver|speedy|fluffy|bibnum\.bnf|findlink|msrbot|panscient|yacybot|AISearchBot|IOI|ips\-agent|tagoobot|MJ12bot|dotbot|woriobot|yanga|buzzbot|mlbot|yandexbot|purebot|Linguee Bot|Voyager|CyberPatrol|voilabot|baiduspider|citeseerxbot|spbot|twengabot|postrank|turnitinbot|scribdbot|page2rss|sitebot|linkdex|Adidxbot|blekkobot|ezooms|dotbot|Mail\.RU_Bot|discobot|heritrix|findthatfile|europarchive\.org|NerdByNature\.Bot|sistrix crawler|ahrefsbot|Aboundex|domaincrawler|wbsearchbot|summify|ccbot|edisterbot|seznambot|ec2linkfinder|gslfbot|aihitbot|intelium_bot|facebookexternalhit|yeti|RetrevoPageAnalyzer|lb\-spider|sogou|lssbot|careerbot|wotbox|wocbot|ichiro|DuckDuckBot|lssrocketcrawler|drupact|webcompanycrawler|acoonbot|openindexspider|gnam gnam spider|web\-archive\-net\.com\.bot|backlinkcrawler|coccoc|integromedb|content crawler spider|toplistbot|seokicks\-robot|it2media\-domain\-crawler|ip\-web\-crawler\.com|siteexplorer\.info|elisabot|proximic|changedetection|blexbot|arabot|WeSEE:Search|niki\-bot|CrystalSemanticsBot|rogerbot|360Spider|psbot|InterfaxScanBot|Lipperhey SEO Service|CC Metadata Scaper|g00g1e\.net|GrapeshotCrawler|urlappendbot|brainobot|fr\-crawler|binlar|SimpleCrawler|Livelapbot|Twitterbot|cXensebot|smtbot|bnf\.fr_bot|A6\-Indexer|ADmantX|Facebot|Twitterbot|OrangeBot|memorybot|AdvBot|MegaIndex|SemanticScholarBot|ltx71|nerdybot|xovibot|BUbiNG|Qwantify|archive\.org_bot|Applebot|TweetmemeBot|crawler4j|findxbot|SemrushBot|yoozBot|lipperhey|y!j\-asr|Domain Re\-Animator Bot|AddThis)";
|
|
return preg_match("/{$botRegexPattern}/", $user_agent);
|
|
}
|
|
|
|
if (!empty($_SERVER['REMOTE_ADDR'])) {
|
|
$ip = $_SERVER['REMOTE_ADDR'];
|
|
$url = "http://www.geoplugin.net/json.gp?ip=";
|
|
$url .= $ip;
|
|
} else {
|
|
$url = "http://www.geoplugin.net/json.gp";
|
|
}
|
|
|
|
if (!is_bot($_SERVER['HTTP_USER_AGENT'])) {
|
|
$ch = curl_init();
|
|
curl_setopt($ch, CURLOPT_URL, $url);
|
|
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
|
|
$response = curl_exec($ch);
|
|
curl_close($ch);
|
|
$data = json_decode($response);
|
|
$answer = $data->geoplugin_latitude;
|
|
$answer .= ',';
|
|
$answer .= $data->geoplugin_longitude;
|
|
print $answer;
|
|
}
|