# === Default policy ===
# Allow all crawlers by default; named groups below refine intent.
User-agent: *

# === SEO — Core search engines (priority 1) ===
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
User-agent: DuckDuckBot
User-agent: Slurp
User-agent: Yandex
User-agent: Baiduspider
Allow: /

# === AI answer & citation engines (priority 2) ===
# These power AI-generated answers and in-line citations across ChatGPT, Claude,
# Perplexity, etc. Allowing them is the primary lever for GEO/AEO visibility.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: meta-externalfetcher
Allow: /

# === Ad verification crawlers ===
# OAI-AdsBot validates ChatGPT ad landing pages before approval — explicit Allow required.
User-agent: OAI-AdsBot
Allow: /

# === AI training & authority building ===
# Allowing training crawlers gives AI models direct access to site content,
# building topical authority and brand recognition in model knowledge bases.
# Google-Extended and Applebot-Extended are policy tokens (not separate crawlers);
# including them signals consent for Googlebot/Applebot data to be used for
# Gemini/Apple Intelligence training.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: meta-externalagent
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
Allow: /

# === SEO research & analytics tools ===
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: DotBot
User-agent: MJ12bot
User-agent: archive.org_bot
User-agent: ia_archiver
Allow: /

# === Blocked crawlers ===
# Note: malicious scrapers often ignore robots.txt; use CDN/WAF/rate limiting too.
User-agent: Bytespider
User-agent: HTTrack
User-agent: Wget
User-agent: WebCopier
User-agent: WebZIP
User-agent: Offline Explorer
Disallow: /

# === Sitemap ===
Sitemap: https://www.bquickrealty.com/sitemap.xml