#
# 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

User-agent: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.avif
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /core/*.webp
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.avif
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg
Allow: /profiles/*.webp
# 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: /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/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

# Facebook/Meta Crawler
User-agent: facebookexternalhit
Disallow: /search
Disallow: /admin
Allow: /
Crawl-delay: 5

# OpenAI GPTBot
User-agent: GPTBot
Disallow: /search
Disallow: /admin
Crawl-delay: 10

# Anthropic Claude Bot
User-agent: anthropic-ai
Disallow: /search
Disallow: /admin
Crawl-delay: 10

User-agent: Claude-Web
Disallow: /search
Disallow: /admin
Crawl-delay: 10

# Google Gemini
User-agent: Google-Extended
Disallow: /search
Disallow: /admin
Crawl-delay: 10

# Common Crawlers
User-agent: CCBot
Disallow: /search
Disallow: /admin
Crawl-delay: 10

# Cohere AI
User-agent: cohere-ai
Disallow: /search
Disallow: /admin
Crawl-delay: 10

# Perplexity AI
User-agent: PerplexityBot
Disallow: /search
Disallow: /admin
Crawl-delay: 10

# Applebot Extended (for AI training)
User-agent: Applebot-Extended
Disallow: /search
Disallow: /admin
Crawl-delay: 10

# Amazon Omgilibot
User-agent: Omgilibot
Disallow: /search
Disallow: /admin
Crawl-delay: 10

# Bytedance/TikTok
User-agent: Bytespider
Disallow: /search
Disallow: /admin
Crawl-delay: 10

# Meta AI (additional)
User-agent: Meta-ExternalAgent
Disallow: /search
Disallow: /admin
Crawl-delay: 5

User-agent: FacebookBot
Disallow: /search
Disallow: /admin
Crawl-delay: 5

# Scrapers and aggressive crawlers
User-agent: SemrushBot
Disallow: /search
Disallow: /admin
Crawl-delay: 30

User-agent: AhrefsBot
Disallow: /search
Disallow: /admin
Crawl-delay: 30

User-agent: DotBot
Disallow: /search
Disallow: /admin
Crawl-delay: 30

User-agent: MJ12bot
Disallow: /search
Disallow: /admin
Crawl-delay: 30

# Allow good search engine bots (Google, Bing, etc.)
User-agent: Googlebot
Allow: /
Disallow: /admin
Crawl-delay: 2

User-agent: Bingbot
Allow: /
Disallow: /admin
Crawl-delay: 2

User-agent: Slurp
Allow: /
Disallow: /admin
Crawl-delay: 2

# Default for all others
User-agent: *
Disallow: /admin
Disallow: /user
Disallow: /search?*
Allow: /