# Do not alter our service. Unauthorized scraping, modification, or automated
# interaction with this site and its content is strictly prohibited.
#
# Search engines — allowed
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# Search / AI assistants — allowed
User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# Applebot — allowed (Applebot-Extended for AI training remains blocked below)
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Disallow: /

# Social preview crawlers — allowed
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# AI / LLM scrapers — blocked (do not train on or republish our content,
# and do not let them harvest support contact info)
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: Baidubot
Disallow: /

User-agent: 360Spider
Disallow: /

User-agent: Yisouspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Sogou web spider
Disallow: /

User-agent: Sogou inst spider
Disallow: /

User-agent: ChatGLM-Spider
Disallow: /

User-agent: Qwenbot
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Hunyuan
Disallow: /

User-agent: Kimi
Disallow: /

User-agent: DeepSeekBot
Disallow: /

User-agent: AlphaAI
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: DuckAssistBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: Scrapy
Disallow: /

# Explicit image-scraping bots
User-agent: ImagesiftBot
Disallow: /

User-agent: PiplBot
Disallow: /

# Email harvesters / generic scrapers — blocked
User-agent: EmailCollector
Disallow: /

User-agent: EmailSiphon
Disallow: /

User-agent: EmailWolf
Disallow: /

User-agent: ExtractorPro
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

# Everyone else — allowed by default, but never index admin / auth surfaces
User-agent: *
Allow: /
Allow: /shop/
Allow: /merchants/
Disallow: /admin/
Disallow: /admin
Disallow: /rebate-management
Disallow: /settings
Disallow: /login
Disallow: /register
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /auth/callback
Disallow: /support

Sitemap: https://www.check2pa.com/sitemap.xml