# If the Joomla site is installed within a folder
# eg www.example.com/joomla/ then the robots.txt file
# MUST be moved to the site root
# eg www.example.com/robots.txt
# AND the joomla folder name MUST be prefixed to all of the
# paths.
# eg the Disallow rule for the /administrator/ folder MUST
# be changed to read
# Disallow: /joomla/administrator/
#
# For more information about the robots.txt standard, see:
# https://www.robotstxt.org/orig.html

# AI-Bots
# -------------------------------
# OpenAI
# -------------------------------
User-agent: ChatGPT-User
User-agent: GPTBot
User-agent: OAI-SearchBot

# -------------------------------
# Anthropic
# -------------------------------
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai

# -------------------------------
# Google / Alphabet
# -------------------------------
User-agent: Google-Extended
User-agent: Google-CloudVertexBot

# -------------------------------
# Apple
# -------------------------------
User-agent: Applebot
User-agent: Applebot-Extended

# -------------------------------
# Microsoft / Bing
# -------------------------------
User-agent: BingAI-Bot

# -------------------------------
# Perplexity AI
# -------------------------------
User-agent: PerplexityBot

# -------------------------------
# Cohere AI
# -------------------------------
User-agent: cohere-ai
User-agent: cohere-training-data-crawler

# -------------------------------
# Meta / Facebook
# -------------------------------
User-agent: FacebookBot
User-agent: Meta-ExternalAgent

# -------------------------------
# Amazon / Alexa
# -------------------------------
User-agent: Amazonbot

# -------------------------------
# Notion
# -------------------------------
User-agent: NotionBot

# -------------------------------
# Diffbot
# -------------------------------
User-agent: Diffbot

# -------------------------------
# Brave Search
# -------------------------------
User-agent: BraveBot

# -------------------------------
# You.com
# -------------------------------
User-agent: YouBot

# -------------------------------
# Andi AI
# -------------------------------
User-agent: AndiBot

# -------------------------------
# ExaBot
# -------------------------------
User-agent: ExaBot

# -------------------------------
# Phind AI
# -------------------------------
User-agent: PhindBot

# -------------------------------
# Firecrawl
# -------------------------------
User-agent: FirecrawlAgent

# -------------------------------
# Common Crawl
# -------------------------------
User-agent: CCBot

# -------------------------------
# Security / Monitoring AI
# -------------------------------
User-agent: Novaact
User-agent: Ns.Tools Bot
User-agent: Odin
User-agent: PingAdmin.Ru

# -------------------------------
# Web Scraping / Rendering AI
# -------------------------------
User-agent: Photon
User-agent: PhxBot
User-agent: PhantomJsCloud.com
User-agent: Bytespider

# -------------------------------
# DuckDuckGo / DuckAssist
# -------------------------------
User-agent: DuckAssistBot
User-agent: DuckDuckBot

# -------------------------------
# Neeva AI
# -------------------------------
User-agent: NeevaBot

Disallow: /administrator/
Disallow: /api/
Disallow: /bin/
Disallow: /cache/
Disallow: /cli/
Disallow: /components/
Disallow: /includes/
Disallow: /installation/
Disallow: /language/
Disallow: /layouts/
Disallow: /libraries/
Disallow: /logs/
Disallow: /modules/
Disallow: /plugins/
Disallow: /tmp/
Crawl-delay: 15

# Disallow AI training data collection
# User-agent: GPTBot
# User-agent: CCBot
# User-agent: Google-Extended
# Disallow: /
# Crawl-delay: 30

# Everyone else
User-agent: *
Disallow: /administrator/
Disallow: /api/
Disallow: /bin/
Disallow: /cache/
Disallow: /cli/
Disallow: /components/
Disallow: /includes/
Disallow: /installation/
Disallow: /language/
Disallow: /layouts/
Disallow: /libraries/
Disallow: /logs/
Disallow: /modules/
Disallow: /plugins/
Disallow: /tmp/
Crawl-delay: 15