# Empora for WooCommerce Docs — robots.txt
# Maintained by Ahsan Mahmood (https://aoneahsan.com)
# Public crawl policy for https://empora-docs.aoneahsan.com
#
# Search engines and reputable AI/answer-engine bots are allowed.
# Low-value scraper bots are blocked. The Sitemap directive lets crawlers
# discover the URL space without spidering.

# --- Search engines (full crawl allowed) -------------------------------------

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: Slurp
Allow: /

# --- AI / answer-engine bots (citation surface — keep allowed) ---------------

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: YouBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: MistralAI-User
Allow: /

# --- Block low-value scraper bots --------------------------------------------

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

# --- Default policy ----------------------------------------------------------

User-agent: *
Allow: /

# --- Sitemap discovery -------------------------------------------------------

Sitemap: https://empora-docs.aoneahsan.com/sitemap.xml