# robots.txt for tratamentes.pt
# Updated: 2026-01-31

# ===========================================
# Facebook/Meta - Allow ads pages for sharing
# ===========================================
User-agent: facebookexternalhit
Allow: /ads/
Allow: /*/ads/
Allow: /

User-agent: Facebot
Allow: /ads/
Allow: /*/ads/
Allow: /

# ===========================================
# AI crawlers — explicit Allow for AI search visibility
# ===========================================
# GPTBot (ChatGPT Search / OpenAI)
User-agent: GPTBot
Allow: /

# ClaudeBot (Anthropic)
User-agent: ClaudeBot
Allow: /

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

# PerplexityBot
User-agent: PerplexityBot
Allow: /

# Applebot (Siri / Apple Intelligence)
User-agent: Applebot
Allow: /

# ===========================================
# All other bots
# ===========================================
User-agent: *

# Allow all pages
Allow: /

# Block technical files and feeds
Disallow: /index.json
Disallow: /index.xml
Disallow: /*/index.json
Disallow: /*/index.xml

# NOTE: /ads/ pages NOT blocked here - Facebook needs access for sharing
# They have noindex meta tag so won't appear in search results anyway

# Block pagination
Disallow: /*/page/

# Block tag and category archives (not needed for SEO, causing 404s)
Disallow: /tags/
Disallow: /*/tags/
Disallow: /categories/
Disallow: /*/categories/

# Block old URL patterns that no longer exist
Disallow: /posts/
Disallow: /services/
Disallow: /legal/

# Note: dev.tratamentes.pt is blocked via .htaccess (403 Forbidden)
# Note: www.tratamentes.pt redirects to tratamentes.pt via .htaccess (301)

# Sitemaps
Sitemap: https://tratamentes.pt/sitemap.xml
Sitemap: https://tratamentes.pt/pt/sitemap.xml
Sitemap: https://tratamentes.pt/en/sitemap.xml

# LLM-friendly content index (https://llmstxt.org)
# llms.txt: https://tratamentes.pt/llms.txt