feat(brandbook): anadir ingesta automatica de fuentes desde URL web en seccion Fuentes

src/app/api/brandbook/upload/route.ts

@@ -55,15 +55,17 @@ export async function POST(req: NextRequest) {
 
   let filename = 'pegado.txt';
   let text = '';
+  let url = '';
   const ctype = req.headers.get('content-type') || '';
   if (ctype.includes('multipart/form-data')) {
     const form = await req.formData();
     const file = form.get('file');
     const pasted = form.get('text');
-    if (typeof pasted === 'string' && pasted.trim()) {
+    url = String(form.get('url') || '').trim();
+    if (!url && typeof pasted === 'string' && pasted.trim()) {
       text = pasted;
       filename = String(form.get('filename') || 'pegado.txt');
-    } else if (file && typeof file === 'object' && 'arrayBuffer' in file) {
+    } else if (!url && file && typeof file === 'object' && 'arrayBuffer' in file) {
       const f = file as File;
       filename = f.name || 'upload.txt';
       const lower = filename.toLowerCase();
@@ -87,11 +89,80 @@ export async function POST(req: NextRequest) {
     const body = (await req.json().catch(() => ({}))) as {
       text?: string;
       filename?: string;
+      url?: string;
     };
+    url = String(body.url || '').trim();
     text = String(body.text || '');
     filename = String(body.filename || 'pegado.txt');
   }
 
+  if (url) {
+    if (!url.startsWith('http://') && !url.startsWith('https://')) {
+      return NextResponse.json(
+        { error: 'La URL debe empezar por http:// o https://' },
+        { status: 400 }
+      );
+    }
+    try {
+      const resp = await fetch(url, {
+        headers: {
+          'User-Agent':
+            'Mozilla/5.0 (compatible; 4VenturesBrandbot/1.0; +https://4ventures.es)',
+          Accept: 'text/html,application/xhtml+xml,text/plain;q=0.9,*/*;q=0.8',
+        },
+        signal: AbortSignal.timeout(15000),
+      });
+      if (!resp.ok) {
+        return NextResponse.json(
+          { error: `Error al acceder a la URL: HTTP ${resp.status}` },
+          { status: 400 }
+        );
+      }
+      const raw = await resp.text();
+      const clean = raw
+        .replace(/<script[\s\S]*?<\/script>/gi, '')
+        .replace(/<style[\s\S]*?<\/style>/gi, '')
+        .replace(/<noscript[\s\S]*?<\/noscript>/gi, '')
+        .replace(/<svg[\s\S]*?<\/svg>/gi, '')
+        .replace(/<\/(p|div|h[1-6]|li|tr)>/gi, '\n\n')
+        .replace(/<br\s*[\/]?>/gi, '\n');
+
+      text = clean
+        .replace(/&amp;/g, '&')
+        .replace(/&lt;/g, '<')
+        .replace(/&gt;/g, '>')
+        .replace(/&quot;/g, '"')
+        .replace(/&#039;/g, "'")
+        .replace(/&nbsp;/g, ' ')
+        .replace(/<[^>]+>/g, ' ')
+        .replace(/[ \t]+/g, ' ')
+        .replace(/\n\s*\n\s*\n+/g, '\n\n')
+        .trim();
+
+      try {
+        const parsed = new URL(url);
+        const pathSegments = parsed.pathname.split('/').filter(Boolean);
+        const lastSeg = pathSegments[pathSegments.length - 1];
+        filename = lastSeg
+          ? lastSeg.endsWith('.html')
+            ? lastSeg
+            : `${lastSeg}.txt`
+          : `${parsed.hostname}.txt`;
+      } catch {
+        filename = 'fuente-url.txt';
+      }
+    } catch (err) {
+      return NextResponse.json(
+        {
+          error: `No se pudo conectar a la URL: ${
+            err instanceof Error ? err.message : String(err)
+          }`,
+        },
+        { status: 400 }
+      );
+    }
+  }
+
   if (!text.trim()) {
     return NextResponse.json({ error: 'Sin texto' }, { status: 400 });
   }