User-agent: *
Disallow:

# ------ SEARCH ENGINES ------
# allowing search engines to index

# Google
User-agent: Googlebot
Disallow:

# Bing
User-agent: bingbot
Disallow:

# Baidu (Chinese)
User-agent: baiduspider
Disallow:

# DuckDuckGo
User-agent: DuckDuckBot
Disallow:

# Apple (Siri, Spotlight)
User-agent: Applebot
Disallow:

# Yahoo!
User-agent: Slurp
Disallow:

# ------ SOCIAL MEDIA ------
# allowing agents that fetch preview data for shared links

# LinkedIn
User-agent: LinkedInBot
Disallow:

# Meta (Facebook, Instagram, Messenger)
User-agent: FacebookExternalHit
Disallow:

# Twitter / X
User-agent: Twitterbot
Disallow:

# ------ AI TOOLS ------
# blocking training data scrapers
# allowing search and user-initiated crawlers and fetchers for page previews and AI summaries

# --- OpenAI: ChatGPT ---

User-agent: GPTBot
Disallow: /

User-agent: OAI-SearchBot
Disallow:

User-agent: ChatGPT-User
Disallow:

# --- Anthropic: Claude ---

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-User
Disallow:

User-agent: Claude-SearchBot
Disallow:

# --- Perplexity ---

User-agent: PerplexityBot
Disallow:

User-agent: Perplexity-User
Disallow:

# --- Google: Gemini ---

User-agent: Google-Extended
Disallow: /

# --- Mistral ---

User-agent: MistralAI-User
Disallow:

# --- Microsoft: Copilot, Bing AI ---

User-agent: BingPreview
Disallow:

User-agent: MicrosoftPreview
Disallow:

# --- Meta ---

User-agent: Meta-WebIndexer
Disallow:

User-agent: Meta-ExternalFetcher
Disallow:

User-agent: Meta-ExternalAgent
Disallow: /

# --- Apple ---

User-agent: Apple-Extended
Disallow: /

# --- Amazon ---

User-agent: Amazonbot
Disallow: /

User-agent: Amzn-SearchBot
Disallow: 

User-agent: Amzn-User
Disallow: 

# --- Common Crawl ---

User-agent: CCBot
Disallow: /

Sitemap: https://www.icare-world.com/sitemap_index.xml