# ============================================================= # robots.txt — grabois.org.br # ============================================================= # --- Todos os bots: 60s entre requests (máx 1 req/min) --- # Nota: Googlebot ignora Crawl-delay. Use Google Search Console para controlar Google. User-agent: * Crawl-delay: 60 # Áreas administrativas — nunca indexar Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /wp-register.php Disallow: /xmlrpc.php # Resultados de busca — SEO poisoning, thin content Disallow: /?s= Disallow: /*/?s= Disallow: /search/ Disallow: /busca/ # API REST — não é conteúdo público Disallow: /wp-json/ # Arquivos de sistema — não são conteúdo Disallow: /wp-content/plugins/ Disallow: /wp-content/themes/ Disallow: /wp-content/cache/ Disallow: /wp-content/uploads/*.php Disallow: /wp-includes/ # Arquivos sensíveis Disallow: /*/trackback/$ Disallow: /*/feed/$ Disallow: /comments/feed/$ Disallow: /*/attachment/ Disallow: /author/ Disallow: /tag/ # Paginação profunda — desperdício de crawl budget Disallow: /page/100/ # URLs antigas do portal (migradas, geram 404) Disallow: /portal/noticia.php Disallow: /portal/noticias/ # Sitemap Sitemap: https://grabois.org.br/sitemap_index.xml