Fix newest homepage detection, file creation dates, real IP, and request log visitor type

- Fix detectNewestPage() to search subdirectories recursively and handle language prefixes - Fix getFileInfo() to preserve frontmatter created date or ctime instead of overwriting with mtime - Automatically store created date in frontmatter when creating/editing files - Add RequestLogger::getClientIp() with proxy and Cloudflare header support - Replace domain column in request log with visitor/bot type badges (Human, AI, Search, Scraper) - Update 'Activiteitenlog' to 'Activiteiten log' in UI and guide
2026-07-28 16:56:51 +02:00
parent b8d4a4e6d5
commit f81be9e047
9 changed files with 256 additions and 44 deletions
@@ -23,6 +23,114 @@ class RequestLogger
        @file_put_contents($this->logFile, $line, FILE_APPEND | LOCK_EX);
    }

+    public static function getClientIp(): string
+    {
+        $headers = [
+            'HTTP_CF_CONNECTING_IP',
+            'HTTP_X_REAL_IP',
+            'HTTP_CLIENT_IP',
+            'HTTP_X_FORWARDED_FOR',
+            'REMOTE_ADDR',
+        ];
+
+        foreach ($headers as $header) {
+            if (!empty($_SERVER[$header])) {
+                $rawIp = $_SERVER[$header];
+                if (str_contains($rawIp, ',')) {
+                    $ips = explode(',', $rawIp);
+                    $rawIp = trim($ips[0]);
+                }
+                $rawIp = trim($rawIp);
+                if (filter_var($rawIp, FILTER_VALIDATE_IP) !== false) {
+                    return $rawIp;
+                }
+            }
+        }
+
+        return $_SERVER['REMOTE_ADDR'] ?? 'cli';
+    }
+
+    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'];
+        }
+
+        $bots = [
+            'AI' => [
+                'GPTBot' => 'AI (GPTBot)',
+                'ChatGPT-User' => 'AI (ChatGPT)',
+                'Claude-Web' => 'AI (Claude)',
+                'ClaudeBot' => 'AI (ClaudeBot)',
+                'anthropic-ai' => 'AI (Anthropic)',
+                'Google-Extended' => 'AI (Gemini/Google)',
+                'CCBot' => 'AI (CommonCrawl)',
+                'PerplexityBot' => 'AI (Perplexity)',
+                'Amazonbot' => 'AI (Amazon)',
+                'cohere-ai' => 'AI (Cohere)',
+                'OAI-SearchBot' => 'AI (OpenAI)',
+                'Bytespider' => 'AI (ByteDance)',
+                'FacebookBot' => 'AI (Meta/FB)',
+                'Applebot-Extended' => 'AI (Apple)',
+            ],
+            'Search' => [
+                'Googlebot' => 'Zoekmachine (Google)',
+                'Bingbot' => 'Zoekmachine (Bing)',
+                'BingPreview' => 'Zoekmachine (Bing)',
+                'Slurp' => 'Zoekmachine (Yahoo)',
+                'DuckDuckBot' => 'Zoekmachine (DuckDuckGo)',
+                'Baiduspider' => 'Zoekmachine (Baidu)',
+                'YandexBot' => 'Zoekmachine (Yandex)',
+                'Sogou' => 'Zoekmachine (Sogou)',
+                'Exabot' => 'Zoekmachine (Exabot)',
+                'facebot' => 'Zoekmachine (Facebook)',
+            ],
+            'Scraper' => [
+                'HTTrack' => 'Scraper (HTTrack)',
+                'Scrapy' => 'Scraper (Scrapy)',
+                'PhantomJS' => 'Scraper (PhantomJS)',
+                'HeadlessChrome' => 'Scraper (Headless)',
+                'curl' => 'Scraper (cURL)',
+                'wget' => 'Scraper (Wget)',
+                'python' => 'Scraper (Python)',
+                'Postman' => 'Scraper (Postman)',
+            ],
+        ];
+
+        foreach ($bots['AI'] as $pattern => $label) {
+            if (stripos($ua, $pattern) !== false) {
+                return ['type' => 'ai', 'label' => $label, 'badge' => 'danger', 'icon' => 'bi-robot'];
+            }
+        }
+
+        foreach ($bots['Search'] as $pattern => $label) {
+            if (stripos($ua, $pattern) !== false) {
+                return ['type' => 'search', 'label' => $label, 'badge' => 'primary', 'icon' => 'bi-search'];
+            }
+        }
+
+        foreach ($bots['Scraper'] as $pattern => $label) {
+            if (stripos($ua, $pattern) !== false) {
+                return ['type' => 'scraper', 'label' => $label, 'badge' => 'warning text-dark', 'icon' => 'bi-bug'];
+            }
+        }
+
+        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',
+        ];
+    }
+
    public static function detectBot(): ?string
    {
        $ua = $_SERVER['HTTP_USER_AGENT'] ?? '';
@@ -69,10 +177,17 @@ class RequestLogger

        foreach ($content as $line) {
            if (preg_match('/^\[([^\]]+)\] \[([^\]]+)\] \[([^\]]+)\] \[([^\]]*)\] \[([^\]]+)\] \[([^\]]*)\] \[([^\]]*)\]$/', trim($line), $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';
+                }
+                $visitorInfo = self::detectVisitorInfo($m[6], $user);
                $logs[] = [
                    'time' => $m[1],
                    'ip' => $m[2],
-                    'host' => $m[3],
+                    'user' => $user,
+                    'visitor_info' => $visitorInfo,
                    'lang' => $m[4],
                    'page' => $m[5],
                    'ua' => $m[6],