# robots.txt — v=673d (VOW compliance: AI crawlers BLOCKED)
#
# Shared by both brands in the unified bundle (condogo + propertyhub). The
# brand split is host-aware at request time; this file is served verbatim.
#
# Policy: open to mainstream SEARCH crawlers (Google, Bing, etc.) for SEO,
# but EXPLICITLY BLOCK every AI training / inference / answer-engine crawler.
#
# Why: the PropTx VOW Datafeed Agreement (Article 6.2(a)) forbids providing
# any content "retrieved or derived from the Services or VOW Data Feed to any
# AI System for any purpose." Once TRREB/PropTx listing data is on the site,
# inviting AI crawlers would be a compliance violation. We remove the AI
# allowlist ENTIRELY (not just gate listing paths) for zero VOW risk. The
# llms.txt / ai.txt AI-discovery files have also been removed (now 404 via the
# _middleware VOW guard).
#
# This reverses the v=650 "AI-traffic capture" strategy. See
# TRREB-COMPLIANCE-AUDIT.md.
#
# Cloudflare zone gate: on propertyhub.ca the CF "Managed robots.txt" feature
# also prepends an AI-blocking content-signal block at the edge (extra defense
# in depth). This file is the file-level block; the CF dashboard is the
# runtime gate.

User-agent: *
Allow: /
Disallow: /api/
Crawl-delay: 5

# ───── Search crawlers — ALLOWED (SEO indexing; no AI use)
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Applebot
Allow: /

# ───── Social-preview / link-unfurl bots — ALLOWED (share cards, not AI)
User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: FacebookExternalHit
Allow: /

# ───── AI training / inference / answer-engine crawlers — BLOCKED (VOW Art. 6.2(a))
# Explicit Disallow: / for every known AI System crawler. This is the
# defense-in-depth block that replaces the removed v=650 AI allowlist.
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: PerplexityCanonicalBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Mistral-AI-User
Disallow: /

User-agent: ai2bot
Disallow: /

User-agent: PetalBot
Disallow: /

# ───── SEO-audit crawlers — keep blocked (bandwidth / competitive intel only)
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: rogerbot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: SeznamBot
Disallow: /

# ───── Sitemaps (machine-readable index)
Sitemap: https://condogo.ca/sitemap.xml
Sitemap: https://condogo.ca/sitemap-listings.xml
Sitemap: https://condogo.ca/sitemap-buildings.xml
Sitemap: https://condogo.ca/sitemap-hoods.xml
Sitemap: https://condogo.ca/sitemap-guide-articles.xml
Sitemap: https://condogo.ca/sitemap-areas.xml
Sitemap: https://condogo.ca/sitemap-precon.xml
Sitemap: https://condogo.ca/sitemap-guides.xml