# robots.txt para www.42.netmeios.com # Última atualização: 2025-07-30 # Política para motores de busca, LLMs e agentes automatizados # Regras gerais para todos os agentes User-agent: * Allow: / # Crawl-delay: 2 # removido para evitar aviso no Google # Diretórios e ficheiros sensíveis Disallow: /admin/ Disallow: /includes/ Disallow: /*.bak Disallow: /*.old Disallow: /*.sql # Bots de IA e LLMs User-agent: ChatGPT-User Allow: / Crawl-delay: 5 User-agent: GPTBot Allow: / Crawl-delay: 5 User-agent: Claude-Web Allow: / Crawl-delay: 5 User-agent: DeepSeek Allow: / Crawl-delay: 5 User-agent: Google-Extended Allow: / Crawl-delay: 5 User-agent: anthropic-ai Allow: / Crawl-delay: 5 User-agent: Meta-GPTBot Allow: / Crawl-delay: 5 User-agent: Firecrawler Allow: / Crawl-delay: 5 User-agent: OmigillBot Allow: / Crawl-delay: 5 User-agent: Cohere-ai Allow: / Crawl-delay: 5 # Bots de redes sociais User-agent: facebot Allow: / Crawl-delay: 4 User-agent: twitterbot Allow: / Crawl-delay: 4 User-agent: LinkedInBot Allow: / Crawl-delay: 4 User-agent: Applebot Allow: / Crawl-delay: 4 User-agent: TikTokBot Allow: / Crawl-delay: 4 User-agent: WhatsAppBot Allow: / Crawl-delay: 4 User-agent: TelegramBot Allow: / Crawl-delay: 4 User-agent: Discordbot Allow: / Crawl-delay: 4 User-agent: Slackbot Allow: / Crawl-delay: 4 # Motores de busca clássicos User-agent: Googlebot Allow: / # Crawl-delay: 3 # removido, Google não suporta User-agent: Bingbot Allow: / Crawl-delay: 3 User-agent: YandexBot Allow: / Crawl-delay: 3 User-agent: Baiduspider Allow: / Crawl-delay: 3 # ️ Bots de arquivo e indexação histórica User-agent: CCBot Allow: / Crawl-delay: 10 User-agent: ia_archiver Allow: / Crawl-delay: 10 # ️FICHEIROS DE POLÍTICAS E TRANSPARÊNCIA # Documentos primários Allow: /ai.txt Allow: /ai.php # Versão alternativa do ai.txt Allow: /politica-ia.php Allow: /politica-ia.md # Configurações técnicas Allow: /llms.txt Allow: /llms.yaml Allow: /llms.json Allow: /data.json Allow: /data.yaml # Ferramentas de transparência Allow: /humans.txt Allow: /humans.en.txt Allow: /content-origin.md Allow: /content-origin.en.md # Segurança e padrões web Allow: /.well-known/security.txt Allow: /.well-known/ai-policy.json # Sistema de conteúdo Allow: /sitemap-llms.xml Allow: /remocao-ia.html Allow: /processar-correcao.php # ️ Sitemaps Sitemap: https://www.42.netmeios.com/sitemap.xml Sitemap: https://www.42.netmeios.com/sitemap-news.xml Sitemap: https://www.42.netmeios.com/sitemap-images.xml Sitemap: https://www.42.netmeios.com/sitemap-llms.xml # Política de IA relacionada # Policy-link: https://www.42.netmeios.com/ai.html