# robots.txt for https://blytheco.com
# Updated: 2026-07-30

# ---------------------------------------------------------------
# Default rules — all crawlers
# ---------------------------------------------------------------
User-agent: *
Allow: /

# Internal search results (thin/duplicate pages — keep out of the index)
Disallow: /search
Disallow: /search?
Disallow: /*?q=
Disallow: /*?s=

# Form thank-you / confirmation pages (no SEO value, skews conversion data)
Disallow: /thank-you
Disallow: /*thank-you$
Disallow: /*-thank-you$

# Gated / authenticated areas
Disallow: /training-center-access
Disallow: /billpay

# Tracking & session parameters (prevents duplicate-URL crawling)
Disallow: /*?utm_
Disallow: /*&utm_
Disallow: /*?gclid=
Disallow: /*?fbclid=
Disallow: /*?msclkid=
Disallow: /*?hsCtaTracking=
Disallow: /*?_hsenc=
Disallow: /*?_hsmi=

# Webflow system paths
Disallow: /404
Disallow: /401

# ---------------------------------------------------------------
# Search engines — explicit full access
# ---------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# ---------------------------------------------------------------
# AI / LLM crawlers — allowed
# Blytheco wants to be discoverable and citable in AI-assisted search
# (answer-engine optimization for ERP/CRM partner queries).
# ---------------------------------------------------------------
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /

# ---------------------------------------------------------------
# Aggressive SEO scrapers — blocked to reduce server load
# ---------------------------------------------------------------
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

# ---------------------------------------------------------------
# Sitemaps
# ---------------------------------------------------------------
Sitemap: https://blytheco.com/sitemap.xml

Sitemap: https://blytheco.com/sitemap.xml