Add tech-stack fingerprinting (server, powered-by, generator)

WarcRecordFetcher was splitting out and discarding the HTTP response
headers to get at the HTML body — now it keeps and parses them, so
Server/X-Powered-By headers get captured alongside the <meta
name="generator"> tag already sitting in the parsed DOM. No extra
requests: same WARC segment already fetched for --with-metadata.

Site copies these from its homepage capture, same as
title/description/keywords. New badges on the site detail page show
the detected platform (e.g. "Wix.com Website Builder") and server
signature at a glance.

Verified against real .es data: correctly detected Wix
("00padel.es"), nginx/Apache/Cloudflare server headers, and PHP
X-Powered-By headers across the batch.

app/Models/Site.php

@@ -14,6 +14,9 @@ class Site extends Model
         'title',
         'description',
         'keywords',
+        'server',
+        'powered_by',
+        'generator',
     ];
 
     public function pages(): HasMany

app/Models/SitePage.php

@@ -27,6 +27,9 @@ class SitePage extends Model
         'title',
         'description',
         'keywords',
+        'server',
+        'powered_by',
+        'generator',
         'content',
         'raw',
         'record_hash',

app/Services/CommonCrawl/CommonCrawlIndexService.php

@@ -125,6 +125,9 @@ class CommonCrawlIndexService
                     'title' => $content['title'],
                     'description' => $content['description'],
                     'keywords' => $content['keywords'],
+                    'server' => $content['server'],
+                    'powered_by' => $content['powered_by'],
+                    'generator' => $content['generator'],
                 ]);
             }
         }

app/Support/CommonCrawl/WarcRecordFetcher.php

@@ -47,16 +47,19 @@ class WarcRecordFetcher
             return [];
         }
 
-        $html = $this->extractHtmlFromWarcSegment($response->body());
+        $segment = $this->extractHtmlFromWarcSegment($response->body());
 
-        return $html === null ? [] : $this->extractHtmlMeta($html, $attributes['url']);
+        return $segment === null
+            ? []
+            : $this->extractHtmlMeta($segment['html'], $attributes['url'], $segment['headers']);
     }
 
     /**
      * A WARC segment (gzip-compressed) contains WARC headers, then the raw HTTP
-     * response (its own headers followed by the HTML body). Strip both header blocks.
+     * response (its own headers followed by the HTML body). Strip the WARC header
+     * block; the HTTP header block is kept (for Server/X-Powered-By) alongside the HTML.
      */
-    private function extractHtmlFromWarcSegment(string $gzipped): ?string
+    private function extractHtmlFromWarcSegment(string $gzipped): ?array
     {
         $decompressed = @gzdecode($gzipped);
 
@@ -72,12 +75,45 @@ class WarcRecordFetcher
 
         [$httpHeaders, $html] = array_pad(preg_split("/\r?\n\r?\n/", $rest, 2), 2, null);
 
-        return $html;
+        return ['headers' => $httpHeaders ?? '', 'html' => $html];
     }
 
-    private function extractHtmlMeta(string $html, string $pageUrl): array
+    /**
+     * Parses a raw HTTP header block (status line + "Name: value" lines) into a
+     * lowercase-keyed map. First occurrence of a header name wins.
+     */
+    private function parseHttpHeaders(string $raw): array
     {
-        $meta = ['title' => null, 'description' => null, 'keywords' => null, 'content' => null, 'links' => []];
+        $headers = [];
+
+        foreach (preg_split("/\r?\n/", $raw) as $index => $line) {
+            if ($index === 0 || ! str_contains($line, ':')) {
+                continue; // line 0 is the "HTTP/1.1 200 OK" status line, not a header
+            }
+
+            [$name, $value] = explode(':', $line, 2);
+            $key = strtolower(trim($name));
+
+            $headers[$key] ??= trim($value);
+        }
+
+        return $headers;
+    }
+
+    private function extractHtmlMeta(string $html, string $pageUrl, string $rawHttpHeaders): array
+    {
+        $headers = $this->parseHttpHeaders($rawHttpHeaders);
+
+        $meta = [
+            'title' => null,
+            'description' => null,
+            'keywords' => null,
+            'generator' => null,
+            'server' => isset($headers['server']) ? mb_substr($headers['server'], 0, 255) : null,
+            'powered_by' => isset($headers['x-powered-by']) ? mb_substr($headers['x-powered-by'], 0, 255) : null,
+            'content' => null,
+            'links' => [],
+        ];
 
         $document = new DOMDocument;
 
@@ -93,11 +129,13 @@ class WarcRecordFetcher
             $meta['title'] = trim(preg_replace('/\s+/', ' ', $titleNode->textContent)) ?: null;
         }
 
-        foreach (['description', 'keywords'] as $name) {
+        foreach (['description', 'keywords', 'generator'] as $name) {
             $node = $xpath->query("//meta[translate(@name, 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz')='{$name}']")->item(0);
 
             if ($node && $node->getAttribute('content') !== '') {
-                $meta[$name] = trim(preg_replace('/\s+/', ' ', $node->getAttribute('content')));
+                $value = trim(preg_replace('/\s+/', ' ', $node->getAttribute('content')));
+                // generator is stored in a varchar column; description/keywords are text.
+                $meta[$name] = $name === 'generator' ? mb_substr($value, 0, 255) : $value;
             }
         }
 

database/migrations/2026_07_22_221213_add_tech_stack_columns.php

@@ -0,0 +1,42 @@
+<?php
+
+use Illuminate\Database\Migrations\Migration;
+use Illuminate\Database\Schema\Blueprint;
+use Illuminate\Support\Facades\Schema;
+
+return new class extends Migration
+{
+    /**
+     * Server/X-Powered-By (from HTTP response headers, already downloaded alongside the
+     * HTML but previously discarded) and generator (from <meta name="generator">) — cheap
+     * tech-stack signals captured for free during the existing --with-metadata WARC fetch.
+     */
+    public function up(): void
+    {
+        Schema::table('site_pages', function (Blueprint $table) {
+            $table->string('server')->nullable()->after('keywords');
+            $table->string('powered_by')->nullable()->after('server');
+            $table->string('generator')->nullable()->after('powered_by');
+        });
+
+        Schema::table('sites', function (Blueprint $table) {
+            $table->string('server')->nullable()->after('keywords');
+            $table->string('powered_by')->nullable()->after('server');
+            $table->string('generator')->nullable()->after('powered_by');
+        });
+    }
+
+    /**
+     * Reverse the migrations.
+     */
+    public function down(): void
+    {
+        Schema::table('site_pages', function (Blueprint $table) {
+            $table->dropColumn(['server', 'powered_by', 'generator']);
+        });
+
+        Schema::table('sites', function (Blueprint $table) {
+            $table->dropColumn(['server', 'powered_by', 'generator']);
+        });
+    }
+};

resources/views/sites/show.blade.php

@@ -18,6 +18,20 @@
             </p>
         @endif
 
+        @if ($site->server || $site->powered_by || $site->generator)
+            <div class="mt-3 flex flex-wrap gap-2">
+                @if ($site->generator)
+                    <span class="rounded-full bg-blue-50 px-3 py-1 text-xs font-medium text-blue-700 dark:bg-blue-950 dark:text-blue-300">{{ $site->generator }}</span>
+                @endif
+                @if ($site->server)
+                    <span class="rounded-full bg-neutral-100 px-3 py-1 text-xs text-neutral-600 dark:bg-neutral-800 dark:text-neutral-400">Server: {{ $site->server }}</span>
+                @endif
+                @if ($site->powered_by)
+                    <span class="rounded-full bg-neutral-100 px-3 py-1 text-xs text-neutral-600 dark:bg-neutral-800 dark:text-neutral-400">Powered by: {{ $site->powered_by }}</span>
+                @endif
+            </div>
+        @endif
+
         <h2 class="mt-8 text-lg font-medium">Pages ({{ $pages->total() }})</h2>
 
         <div class="mt-4 overflow-hidden rounded-lg border border-neutral-200 dark:border-neutral-800">