# robots.txt - heldermesquita.pt
# SEO + IA (llms.txt) - Otimizado para LLMs, GEO e indexação sem açúcar
# version: 5.0
# last-update: 2026-03-23

User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# Low-value / duplicate URLs
Disallow: /wp-login.php
Disallow: /search/
Disallow: /feed/
Disallow: /comments/feed/

# Query-parameter duplicates
Disallow: /*?s=*
Disallow: /*?replytocom=*
Disallow: /*?add-to-cart=*
Disallow: /*?orderby=*
Disallow: /*?filter=*
Disallow: /*?rating=*
Disallow: /*?min_price=*
Disallow: /*?max_price=*
Disallow: /*?srsltid=*

# LLM hints
Allow: /llms.txt

# ai.json:
Allow: /ai.json

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Google SGE / Gemini
User-agent: Google-Extended
Allow: /

# Apple Spotlight / Apple Intelligence
User-agent: Applebot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /
User-agent: anthropic-ai
Allow: /

# Bing / Copilot
User-agent: bingbot
Allow: /
User-agent: msnbot
Allow: /

# ================================
# AI Crawlers adicionais (treino + resposta)
# ================================

# Common Crawl (datasets usados por múltiplas IAs)
User-agent: CCBot
Allow: /

# Perplexity (motor de resposta)
User-agent: PerplexityBot
Allow: /

# ChatGPT (requests via utilizador)
User-agent: ChatGPT-User
Allow: /

# xAI (Grok)
User-agent: xAI-Bot
Allow: /

# ByteDance / TikTok IA (opcional estratégico)
User-agent: Bytespider
Allow: /

# Amazon IA (Alexa / LLMs)
User-agent: Amazonbot
Allow: /

# ================================

Sitemap: https://heldermesquita.pt/sitemap_index.xml