CodePress CMS v1.8.0: BotGuard security engine, HAProxy docs & ARIA fix
- Implement BotGuard security engine (Bot, AI, Scraper & Empty UA blocking) - Add Admin Security page (/admin/security) with toggles, rate limiter & block/allowlists - Add per-IP RateLimiter handoff in index.php with HTTP 429 response - Add dynamic /robots.txt generation and noai/noimageai meta tags - Add RequestLogger status column and blocked badges in admin request logs - Fix ARIAComponents.php syntax errors on lines 67, 137, 262 - Add HAProxy / PFSense bot blocking & IP forwarding guide (docs/haproxy-bot-blocking.md) - Update version to 1.8.0 with release notes in version.php and guides
This commit is contained in:
@@ -9,7 +9,7 @@ class RequestLogger
|
||||
$this->logFile = $logFile;
|
||||
}
|
||||
|
||||
public function log(string $page, string $ip, string $userAgent, string $referrer, string $host, string $acceptLanguage): void
|
||||
public function log(string $page, string $ip, string $userAgent, string $referrer, string $host, string $acceptLanguage, string $status = 'ok'): void
|
||||
{
|
||||
$dir = dirname($this->logFile);
|
||||
if (!is_dir($dir)) {
|
||||
@@ -19,7 +19,7 @@ class RequestLogger
|
||||
$timestamp = date('Y-m-d H:i:s');
|
||||
$ua = substr(preg_replace('/[[:cntrl:]]/', '', $userAgent), 0, 500);
|
||||
$ref = substr(preg_replace('/[[:cntrl:]]/', '', $referrer), 0, 500);
|
||||
$line = "[{$timestamp}] [{$ip}] [{$host}] [{$acceptLanguage}] [{$page}] [{$ua}] [{$ref}]\n";
|
||||
$line = "[{$timestamp}] [{$ip}] [{$host}] [{$acceptLanguage}] [{$page}] [{$ua}] [{$ref}] [{$status}]\n";
|
||||
@file_put_contents($this->logFile, $line, FILE_APPEND | LOCK_EX);
|
||||
}
|
||||
|
||||
@@ -73,116 +73,50 @@ class RequestLogger
|
||||
|
||||
public static function detectVisitorInfo(string $ua, string $user = ''): array
|
||||
{
|
||||
if (empty($ua)) {
|
||||
$userLabel = ($user && $user !== 'Gast') ? $user : 'Onbekend';
|
||||
return ['type' => 'unknown', 'label' => $userLabel, 'badge' => 'secondary', 'icon' => 'bi-question-circle'];
|
||||
}
|
||||
if (class_exists('BotGuard')) {
|
||||
$id = BotGuard::identify($ua);
|
||||
$cat = $id['category'];
|
||||
$label = $id['label'];
|
||||
|
||||
$bots = [
|
||||
'AI' => [
|
||||
'GPTBot' => 'AI (GPTBot)',
|
||||
'ChatGPT-User' => 'AI (ChatGPT)',
|
||||
'Claude-Web' => 'AI (Claude)',
|
||||
'ClaudeBot' => 'AI (ClaudeBot)',
|
||||
'anthropic-ai' => 'AI (Anthropic)',
|
||||
'Google-Extended' => 'AI (Gemini/Google)',
|
||||
'CCBot' => 'AI (CommonCrawl)',
|
||||
'PerplexityBot' => 'AI (Perplexity)',
|
||||
'Amazonbot' => 'AI (Amazon)',
|
||||
'cohere-ai' => 'AI (Cohere)',
|
||||
'OAI-SearchBot' => 'AI (OpenAI)',
|
||||
'Bytespider' => 'AI (ByteDance)',
|
||||
'FacebookBot' => 'AI (Meta/FB)',
|
||||
'Applebot-Extended' => 'AI (Apple)',
|
||||
],
|
||||
'Search' => [
|
||||
'Googlebot' => 'Zoekmachine (Google)',
|
||||
'Bingbot' => 'Zoekmachine (Bing)',
|
||||
'BingPreview' => 'Zoekmachine (Bing)',
|
||||
'Slurp' => 'Zoekmachine (Yahoo)',
|
||||
'DuckDuckBot' => 'Zoekmachine (DuckDuckGo)',
|
||||
'Baiduspider' => 'Zoekmachine (Baidu)',
|
||||
'YandexBot' => 'Zoekmachine (Yandex)',
|
||||
'Sogou' => 'Zoekmachine (Sogou)',
|
||||
'Exabot' => 'Zoekmachine (Exabot)',
|
||||
'facebot' => 'Zoekmachine (Facebook)',
|
||||
],
|
||||
'Scraper' => [
|
||||
'HTTrack' => 'Scraper (HTTrack)',
|
||||
'Scrapy' => 'Scraper (Scrapy)',
|
||||
'PhantomJS' => 'Scraper (PhantomJS)',
|
||||
'HeadlessChrome' => 'Scraper (Headless)',
|
||||
'curl' => 'Scraper (cURL)',
|
||||
'wget' => 'Scraper (Wget)',
|
||||
'python' => 'Scraper (Python)',
|
||||
'Postman' => 'Scraper (Postman)',
|
||||
],
|
||||
];
|
||||
|
||||
foreach ($bots['AI'] as $pattern => $label) {
|
||||
if (stripos($ua, $pattern) !== false) {
|
||||
if ($cat === 'ai') {
|
||||
return ['type' => 'ai', 'label' => $label, 'badge' => 'danger', 'icon' => 'bi-robot'];
|
||||
}
|
||||
}
|
||||
|
||||
foreach ($bots['Search'] as $pattern => $label) {
|
||||
if (stripos($ua, $pattern) !== false) {
|
||||
if ($cat === 'search') {
|
||||
return ['type' => 'search', 'label' => $label, 'badge' => 'primary', 'icon' => 'bi-search'];
|
||||
}
|
||||
}
|
||||
|
||||
foreach ($bots['Scraper'] as $pattern => $label) {
|
||||
if (stripos($ua, $pattern) !== false) {
|
||||
if ($cat === 'scraper') {
|
||||
return ['type' => 'scraper', 'label' => $label, 'badge' => 'warning text-dark', 'icon' => 'bi-bug'];
|
||||
}
|
||||
if ($cat === 'generic') {
|
||||
return ['type' => 'bot', 'label' => 'Bot', 'badge' => 'secondary', 'icon' => 'bi-robot'];
|
||||
}
|
||||
if ($cat === 'empty') {
|
||||
return ['type' => 'empty', 'label' => 'Lege UA', 'badge' => 'secondary', 'icon' => 'bi-slash-circle'];
|
||||
}
|
||||
|
||||
$userPrefix = ($user && $user !== 'Gast') ? htmlspecialchars($user) . ' (' : '';
|
||||
$userSuffix = ($user && $user !== 'Gast') ? ')' : '';
|
||||
|
||||
return [
|
||||
'type' => 'human',
|
||||
'label' => $userPrefix . 'Mens' . $userSuffix,
|
||||
'badge' => 'success',
|
||||
'icon' => 'bi-person-check',
|
||||
];
|
||||
}
|
||||
|
||||
if (preg_match('/(bot|crawler|spider|slurp)/i', $ua)) {
|
||||
return ['type' => 'bot', 'label' => 'Bot', 'badge' => 'secondary', 'icon' => 'bi-robot'];
|
||||
}
|
||||
|
||||
$userPrefix = ($user && $user !== 'Gast') ? htmlspecialchars($user) . ' (' : '';
|
||||
$userSuffix = ($user && $user !== 'Gast') ? ')' : '';
|
||||
|
||||
return [
|
||||
'type' => 'human',
|
||||
'label' => $userPrefix . 'Mens' . $userSuffix,
|
||||
'badge' => 'success',
|
||||
'icon' => 'bi-person-check',
|
||||
];
|
||||
return ['type' => 'unknown', 'label' => 'Bezoeker', 'badge' => 'secondary', 'icon' => 'bi-person'];
|
||||
}
|
||||
|
||||
public static function detectBot(): ?string
|
||||
{
|
||||
$ua = $_SERVER['HTTP_USER_AGENT'] ?? '';
|
||||
if (empty($ua)) return null;
|
||||
|
||||
$bots = [
|
||||
'AI' => [
|
||||
'GPTBot', 'ChatGPT-User', 'Claude-Web', 'ClaudeBot',
|
||||
'anthropic-ai', 'Google-Extended', 'CCBot',
|
||||
'PerplexityBot', 'Amazonbot', 'cohere-ai',
|
||||
'OAI-SearchBot', 'Bytespider', 'FacebookBot',
|
||||
'Applebot-Extended',
|
||||
],
|
||||
'Search' => [
|
||||
'Googlebot', 'Bingbot', 'BingPreview', 'Slurp',
|
||||
'DuckDuckBot', 'Baiduspider', 'YandexBot',
|
||||
'Sogou', 'Exabot', 'facebot',
|
||||
],
|
||||
'Scraper' => [
|
||||
'HTTrack', 'Scrapy', 'PhantomJS', 'HeadlessChrome',
|
||||
],
|
||||
];
|
||||
|
||||
foreach ($bots as $category => $patterns) {
|
||||
foreach ($patterns as $pattern) {
|
||||
if (stripos($ua, $pattern) !== false) {
|
||||
return $category;
|
||||
}
|
||||
if (class_exists('BotGuard')) {
|
||||
$id = BotGuard::identify($ua);
|
||||
if (in_array($id['category'], ['ai', 'search', 'scraper'], true)) {
|
||||
return strtoupper($id['category']);
|
||||
}
|
||||
}
|
||||
|
||||
return null;
|
||||
}
|
||||
|
||||
@@ -197,12 +131,15 @@ class RequestLogger
|
||||
$logs = [];
|
||||
|
||||
foreach ($content as $line) {
|
||||
if (preg_match('/^\[([^\]]+)\] \[([^\]]+)\] \[([^\]]+)\] \[([^\]]*)\] \[([^\]]+)\] \[([^\]]*)\] \[([^\]]*)\]$/', trim($line), $m)) {
|
||||
$trimmed = trim($line);
|
||||
if (preg_match('/^\[([^\]]+)\] \[([^\]]+)\] \[([^\]]+)\] \[([^\]]*)\] \[([^\]]+)\] \[([^\]]*)\] \[([^\]]*)\](?: \[([^\]]*)\])?$/', $trimmed, $m)) {
|
||||
$user = $m[3];
|
||||
// Handle backwards compatibility where host (e.g. localhost:8080 or domain.com) was logged
|
||||
if (str_contains($user, '.') || str_contains($user, ':') || $user === 'cli') {
|
||||
$user = 'Gast';
|
||||
}
|
||||
$status = $m[8] ?? 'ok';
|
||||
if ($status === '') $status = 'ok';
|
||||
|
||||
$visitorInfo = self::detectVisitorInfo($m[6], $user);
|
||||
$logs[] = [
|
||||
'time' => $m[1],
|
||||
@@ -213,6 +150,7 @@ class RequestLogger
|
||||
'page' => $m[5],
|
||||
'ua' => $m[6],
|
||||
'referrer' => $m[7],
|
||||
'status' => $status,
|
||||
];
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user