#
# robots.txt
#
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/robotstxt.html

Sitemap: https://the3million.org.uk/sitemap.xml
LLMs: https://the3million.org.uk/llms.txt
LLMs-Full: https://the3million.org.uk/llms-full.txt
AI: https://the3million.org.uk/ai.txt

# ----------------------------
# Global rules
# ----------------------------
User-agent: *
Crawl-delay: 2

# Allow essential rendering 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

# ----------------------------
# Block system/internal paths
# ----------------------------
Disallow: /core/
Disallow: /profiles/

# Composer / documentation files
Disallow: /README.md
Disallow: /README.txt
Disallow: /composer/
Disallow: /web.config
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/README.txt

# Admin & user flows
Disallow: /admin/
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout
Disallow: /node/add/

# Low-value or duplicate content
Disallow: /search/
Disallow: /filter/tips
Disallow: /comment/reply/

# Embedded/oEmbed endpoints
Disallow: /media/oembed
Disallow: /*/media/oembed

# Non-clean URLs (Drupal fallback)
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/register
Disallow: /index.php/user/password
Disallow: /index.php/user/login
Disallow: /index.php/user/logout
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed

# ----------------------------
# AI Crawlers (explicit allow)
# ----------------------------
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

# ----------------------------
# Optional: block aggressive scrapers
# (uncomment if needed)
# ----------------------------
# User-agent: AhrefsBot
# Disallow: /
# User-agent: SemrushBot
# Disallow: /