#
# 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/*.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

# ONS-305. Disallowing known AI Bots.
# @see https://github.com/healsdata/ai-training-opt-out/blob/main/robots.txt
# The following was taken from this commit: f8829dc

# The example for img2dataset, although the default is *None*
User-agent: img2dataset
Disallow: /

# Brandwatch - "AI to discover new trends"
User-agent: magpie-crawler
Disallow: /

# webz.io - they sell data for training LLMs.
User-agent: Omgilibot
Disallow: /

# Items below were sourced from darkvisitors.com
# Categories included: "AI Data Scraper", "AI Assistant", "AI Search Crawler", "Undocumented AI Agent"

# AI Search Crawler
# https://darkvisitors.com/agents/amazonbot

User-agent: Amazonbot
Disallow: /

# Undocumented AI Agent
# https://darkvisitors.com/agents/anthropic-ai

User-agent: anthropic-ai
Disallow: /

# AI Search Crawler
# https://darkvisitors.com/agents/applebot

User-agent: Applebot
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/applebot-extended

User-agent: Applebot-Extended
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/bytespider

User-agent: Bytespider
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/ccbot

User-agent: CCBot
Disallow: /

# AI Assistant
# https://darkvisitors.com/agents/chatgpt-user

User-agent: ChatGPT-User
Disallow: /

# Undocumented AI Agent
# https://darkvisitors.com/agents/claude-web

User-agent: Claude-Web
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/claudebot

User-agent: ClaudeBot
Disallow: /

# Undocumented AI Agent
# https://darkvisitors.com/agents/cohere-ai

User-agent: cohere-ai
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/diffbot

User-agent: Diffbot
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/facebookbot

User-agent: FacebookBot
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/google-extended

User-agent: Google-Extended
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/gptbot

User-agent: GPTBot
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/omgili

User-agent: omgili
Disallow: /

# AI Search Crawler
# https://darkvisitors.com/agents/perplexitybot

User-agent: PerplexityBot
Disallow: /

# AI Search Crawler
# https://darkvisitors.com/agents/youbot

User-agent: YouBot
Disallow: /