# 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

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/
# Disallow: /*?
# Disallow: /de/component/*
# Disallow: /en/component/*
# Disallow: /es/component/*
# Disallow: /fr/component/*
# Disallow: /nl/component/*

Allow: /plugins/system/jce/css/content.css*
Allow: /nl/sitemap?view=html&id=1
Allow: /en/sitemap?view=html&id=1
Allow: /de/sitemap?view=html&id=1
Allow: /fr/sitemap?view=html&id=1
Allow: /es/sitemap?view=html&id=1

Sitemap: https://db8.nl/nl/sitemap-xml
Sitemap: https://db8.nl/en/sitemap-xml
Sitemap: https://db8.nl/de/sitemap-xml
Sitemap: https://db8.nl/fr/sitemap-xml
Sitemap: https://db8.nl/es/sitemap-xml

# Reference for LLM crawlers
#LLMS: https://db8.nl/llms.txt

# OpenAI (ChatGPT / GPTBot)
User-agent: GPTBot
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Google AI (Bard / Gemini)
User-agent: Google-Extended
Allow: /

# Microsoft Bing / Copilot
User-agent: bingbot
Allow: /
User-agent: BingPreview
Allow: /

# Common crawlers
User-agent: CCBot
Allow: /