User-agent: *
Disallow: /index.php/
Disallow: /*?
Disallow: /checkout/
Disallow: /app/
Disallow: /lib/
Disallow: /*.php$
Disallow: /pkginfo/
Disallow: /report/
Disallow: /var/
Disallow: /catalog/
Disallow: /customer/
Disallow: /sendfriend/
Disallow: /review/
Disallow: /*SID=

# DarkVisitors API generated block list for AI Data Scraper, Undocumented AI Agent, AI Search Crawler, AI Assistant

# 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/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: /

# Manual Block List
User-agent: 008
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: Buck
Disallow: /

User-agent: Cliqzbot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: Exabot
Disallow: /

User-agent: Ezooms
Disallow: /

User-agent: Go-http-client
Disallow: /

User-agent: GrapeshotCrawler
Disallow: /

User-agent: LinkpadBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: MauiBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: rogerbot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: seoscanners.net
Disallow: /

User-agent: Sogou web spider
Disallow: /

# Rate Limited But Not Blocked

User-Agent: facebookexternalhit/1.1 
Crawl-delay: 10

User-Agent: facebookexternalhit/* 
Crawl-delay: 10

User-Agent: meta-externalagent/1.1 
Crawl-delay: 10

User-Agent: meta-externalagent/* 
Crawl-delay: 10

Sitemap: https://www.halonen.fi/sitemaps/halonen_sitemap.xml
Sitemap: https://www.halonen.fi/sitemaps/halonen_sitemap.xml