User-agent: *
Allow: /

# Allow AI search crawlers for Generative Engine Optimization (GEO)
# These crawlers power AI Overviews, ChatGPT browsing, and AI search citations
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

# Allow social media link preview crawlers
User-agent: LinkedInBot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: Slackbot-LinkExpanding
Allow: /

User-agent: Discordbot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

User-agent: Pinterestbot
Allow: /

# Allow SEO tool crawlers for backlink and competitive analysis
User-agent: SemrushBot
Allow: /
Crawl-delay: 2

User-agent: AhrefsBot
Allow: /
Crawl-delay: 2

User-agent: rogerbot
Allow: /
Crawl-delay: 2

# Block SEO backlink crawlers with no search or AI value
User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

# NOTE: everything below belongs to the MJ12bot group above (RFC 9309: rules
# attach to the preceding User-agent line), so it does NOT apply to Googlebot
# or any other crawler. Do not move it under "User-agent: *" without auditing:
# wildcards like /*test-* and /*demo* match real content URLs. (2026-11-13)

# Block admin and development pages
Disallow: /admin/
Disallow: /owner/
Disallow: /api/
Disallow: /claim/
Disallow: /debug/
Disallow: /test/
Disallow: /demo/

# Block specific test/debug pages and patterns
Disallow: /schools/debug/
Disallow: /schools/demo-*
Disallow: /schools/minimal/
Disallow: /search-test/
Disallow: /state-debug/
Disallow: /test-supabase/
Disallow: /*test-*
Disallow: /*debug*
Disallow: /*demo*
Disallow: /*playwright*

# Block duplicate content and tracking parameters only
Disallow: /*?*utm_*
Disallow: /*?*ref=
Disallow: /*?*fbclid=
Disallow: /*?*gclid=
Disallow: /*?*source=

# Block faceted / search / pagination parameters to prevent index bloat
# Pages return noindex for these as a safety net, robots.txt prevents crawl waste.
Disallow: /*?search=
Disallow: /*&search=
Disallow: /*?filter=
Disallow: /*&filter=
Disallow: /*?filters=
Disallow: /*&filters=
Disallow: /*?q=
Disallow: /*&q=
Disallow: /*?query=
Disallow: /*&query=
Disallow: /*?sort=
Disallow: /*&sort=
Disallow: /*?page=
Disallow: /*&page=
Disallow: /*?view=
Disallow: /*&view=
Disallow: /*?category=
Disallow: /*&category=
Disallow: /*?nocache=
Disallow: /*&nocache=

# Explicitly allow important directories (in case of conflicts)
Allow: /schools/
Allow: /states/
Allow: /therapy/
Allow: /blog/
Allow: /free-resources/
Allow: /guides/
Allow: /tools/
Allow: /sitemap*.xml
Allow: /llms.txt
Allow: /llms-full.txt

# Sitemap locations
Sitemap: https://specialneedsusa.com/sitemap.xml

# Security
# See https://specialneedsusa.com/.well-known/security.txt for security contact

# Site verification (improves trust signals)
# About: Special Needs Care Network - Connecting families with specialized resources
# Organization: Mission-driven resource directory for special needs families
# Category: Health, Education, Special Needs Resources