# Tax.Network Indexation Configuration # Last updated: 2024-12-18 # Global Tax Information Powerhouse - 251 locations × 60 languages # =========================================== # SEARCH ENGINE CRAWLERS # =========================================== # All standard crawlers - full access User-agent: * Allow: / # Protected areas Disallow: /admin Disallow: /admin/ Disallow: /account Disallow: /account/ Disallow: /auth Disallow: /auth/ Disallow: /api/ Disallow: /functions/ # User applications (require authentication) Disallow: /chat Disallow: /chat/ Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites # Registration and verification flows Disallow: /expert/register Disallow: /verify-opportunity # OAuth callback - technical only Disallow: /auth/oauth-callback # Legacy routes - removed from app Disallow: /articles Disallow: /resources # Prevent duplicate content from query parameters Disallow: /*?preview= Disallow: /*?tab= Disallow: /*?page= Disallow: /*?sort= Disallow: /*?filter= Disallow: /*?locale= Disallow: /*?utm_* # Googlebot - prioritized crawling User-agent: Googlebot Allow: / Crawl-delay: 0 # Bingbot User-agent: Bingbot Allow: / Crawl-delay: 1 # Yahoo Slurp User-agent: Slurp Allow: / Crawl-delay: 1 # DuckDuckBot User-agent: DuckDuckBot Allow: / Crawl-delay: 1 # Yandex User-agent: Yandex Allow: / Crawl-delay: 2 # Baidu Spider User-agent: Baiduspider Allow: / Crawl-delay: 2 # =========================================== # AI/LLM CRAWLERS - Strategic Access for AIO # =========================================== # OpenAI GPTBot - Allow for AI visibility User-agent: GPTBot Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # Anthropic Claude User-agent: anthropic-ai Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources User-agent: Claude-Web Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # Google AI (Bard/Gemini training) User-agent: Google-Extended Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # Perplexity AI User-agent: PerplexityBot Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # Common Crawl (used by many AI systems) User-agent: CCBot Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # Meta/Facebook AI User-agent: FacebookBot Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # ByteDance/TikTok User-agent: Bytespider Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # Apple Intelligence User-agent: Applebot Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # Cohere AI User-agent: cohere-ai Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # You.com AI Search User-agent: YouBot Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # Meta External Agent (Llama models) User-agent: Meta-ExternalAgent Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # Amazon Alexa/AI User-agent: Amazonbot Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # Microsoft Copilot User-agent: Copilot Allow: / Disallow: /admin Disallow: /account Disallow: /auth Disallow: /chat Disallow: /submit-content Disallow: /editor-dashboard Disallow: /favorites Disallow: /expert/register Disallow: /verify-opportunity Disallow: /articles Disallow: /resources # =========================================== # STATIC ASSETS # =========================================== Allow: /logo-tax-network.svg Allow: /robots.txt Allow: /favicon.ico Allow: /llms.txt Allow: /locales/ # =========================================== # SITEMAPS # =========================================== # Primary sitemap index - Tax.Network (global) Sitemap: https://tax.network/sitemap.xml # Primary sitemap index - Tributário (Brazil) Sitemap: https://tributario.com.br/sitemap.xml # Direct sitemap endpoints (backup — uses canonical domain) Sitemap: https://tax.network/sitemap-index # =========================================== # AI/LLM GUIDANCE # =========================================== # See: https://tax.network/llms.txt # Contains structured content guidance for AI crawlers # Follows llmstxt.org specification