# ====================================
# robots.txt - La Petite Fontaine
# ====================================
# Last updated: June 24, 2026
# Purpose: Allow major AI/LLM crawlers for indexing and non-commercial use
# while strictly protecting sensitive Drupal core areas and administrative paths.
# Training and content usage remain governed by https://petitefontaine.be/llms.txt

Sitemap: https://petitefontaine.be/sitemap.xml

# ====================================
# General access to llms.txt (content usage policy)
# ====================================
User-agent: *
Allow: /llms.txt

# ====================================
# Social media bots / Link preview bots
# ====================================
User-agent: facebookexternalhit
Allow: /

# ====================================
# AI / LLM - Explicit permission for crawling & indexing
# Full technical access granted to public content, but strictly excluding 
# administrative paths and non-public Drupal cores (avoids isolation inheritance issues).
# Subject to the restrictions defined in https://petitefontaine.be/llms.txt
# ====================================
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: GPTBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: claude-web
User-agent: Google-Extended
User-agent: Google-CloudVertexBot
User-agent: Google-NotebookLM
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: MistralAI-User
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: FacebookBot
User-agent: Amazonbot
User-agent: Applebot-Extended
User-agent: Applebot
User-agent: bingbot
User-agent: DuckAssistBot
User-agent: Bytespider
User-agent: cohere-ai
User-agent: YouBot
User-agent: Diffbot
User-agent: CCBot

# CSS, JS, Images (Explicitly allowed for processing layout/assets)
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg

# Strict exclusions applied directly to AI agents to prevent crawling private/sensitive paths
Disallow: /core/
Disallow: /profiles/
Disallow: /README.md
Disallow: /composer/Metapackage/README.txt
Disallow: /composer/Plugin/ProjectMessage/README.md
Disallow: /composer/Plugin/Scaffold/README.md
Disallow: /composer/Plugin/VendorHardening/README.txt
Disallow: /composer/Template/README.txt
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/README.txt
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout
Disallow: /media/oembed
Disallow: /*/media/oembed
Disallow: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/user/password
Disallow: /index.php/user/register
Disallow: /index.php/user/login
Disallow: /index.php/user/logout
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed

# Allow everything else public
Allow: /

# ====================================
# Drupal default rules for general search engines (Googlebot, Bingbot, etc.)
# ====================================
User-agent: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.md
Disallow: /composer/Metapackage/README.txt
Disallow: /composer/Plugin/ProjectMessage/README.md
Disallow: /composer/Plugin/Scaffold/README.md
Disallow: /composer/Plugin/VendorHardening/README.txt
Disallow: /composer/Template/README.txt
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/README.txt
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout
Disallow: /media/oembed
Disallow: /*/media/oembed
# Paths (no clean URLs)
Disallow: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/user/password
Disallow: /index.php/user/register
Disallow: /index.php/user/login
Disallow: /index.php/user/logout
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed

# End of file