# robots.txt for www.johnpricemusic.com
# Canonical domain: https://www.johnpricemusic.com/
# Updated: 2026-05-08

User-agent: *
Allow: /
Allow: /about
Allow: /spotify
Allow: /tour
Allow: /videos
Allow: /epk
Allow: /press
Allow: /blog
Allow: /faq
Allow: /contact
Allow: /remixes
Allow: /jp-radio
Allow: /edm-music
Allow: /top-edm-songs
Allow: /john-price-edm-dj
Allow: /book-john-price
Allow: /music
Allow: /shows
Allow: /genres

# Disallow admin and utility pages
Disallow: /admin/
Disallow: /auth/
Disallow: /portal/
Disallow: /client-portal/
Disallow: /api/
Disallow: /tmp/
Disallow: /private/
Disallow: /cgi-bin/
Disallow: /image-optimizer/
Disallow: /sitemap-health/
Disallow: /travel-info

# OAuth / callbacks / automation endpoints
Disallow: /spotify-callback/
Disallow: /zapier-setup/

# Crawl-trap / tracking parameters
Disallow: /*?*utm_
Disallow: /*?*gclid=
Disallow: /*?*fbclid=
Disallow: /*?*ref=
Disallow: /*?*sort=
Disallow: /*?*filter=
Disallow: /*?*page=

# Search / query parameters — block duplicate-content crawl traps
# (GSC: "Duplicate without user-selected canonical")
Disallow: /*?q=*
Disallow: /*?*q=
Disallow: /*?search=*
Disallow: /*?*search=
Disallow: /blog?*

# Crawl rate optimization
Crawl-delay: 1

# Allow specific important crawlers full access
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Bingbot
Allow: /
Crawl-delay: 1

# FacebookBot allowed — needed for OG link previews on Facebook/Messenger
User-agent: FacebookBot
Allow: /

# AI Search crawlers — ALLOWED for search visibility
# OAI-SearchBot: Powers ChatGPT Search results
User-agent: OAI-SearchBot
Allow: /

# PerplexityBot: Powers Perplexity search results
User-agent: PerplexityBot
Allow: /

# Google-Extended: Controls Gemini/AI content use (does NOT affect Google Search ranking)
User-agent: Google-Extended
Allow: /

# ChatGPT-User: User-initiated fetches, not search indexing — allow for link previews
User-agent: ChatGPT-User
Allow: /

# Claude search crawlers — ALLOWED for search visibility
User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Block AI training-only crawlers (not search)
User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Omgilibot
Disallow: /

# Allow Applebot for Siri/Apple Intelligence search
User-agent: Applebot
Allow: /

# Sitemaps - canonical www domain
Sitemap: https://www.johnpricemusic.com/sitemap-index.xml
Sitemap: https://www.johnpricemusic.com/sitemap.xml
Sitemap: https://www.johnpricemusic.com/image-sitemap.xml
Sitemap: https://www.johnpricemusic.com/video-sitemap.xml