# Heart & Home Estate Sales

User-agent: *
Allow: /

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

# Crawl-delay for polite bots
Crawl-delay: 1

# Search crawlers and answer-engine fetchers
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: bingbot
Allow: /

User-agent: BingPreview
Allow: /

User-agent: MicrosoftPreview
Allow: /

User-agent: Applebot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: DuckAssistBot
Allow: /

# Google-Extended is intentionally not disallowed here, so this robots.txt does
# not opt out of Google's Gemini training or grounding control. Googlebot remains
# allowed for Google Search.

# Block selected non-search training and bulk dataset crawlers
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

# Legacy Anthropic crawler names already blocked by this project
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Allow social media crawlers for rich previews
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /