# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# condogo.ca robots.txt — v=650 (AI-traffic capture: AI crawlers ALLOWED)
#
# Policy: open to all major search + AI training/inference crawlers.
# RECO/TRREB IDX rules apply at the data-feed level (VOW sold data is
# auth-gated, not indexed publicly); the active-listing IDX feed is
# licensed for public display so indexability is the right default.
#
# Content-Signal (per Cloudflare's published spec): we ALLOW search,
# ai-input (real-time grounding for AI search answers), and ai-train.
#
# Cloudflare zone gate: the CF "AI Bots / Block AI Scrapers" feature, if
# enabled, blocks AI crawlers at the edge regardless of what this file
# says. Operator confirmed AI Bots Protection is DISABLED at the zone
# (2026-06-02 overnight). The blocks below are the file-level allow;
# the CF dashboard is the runtime gate.

User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=yes
Allow: /
Disallow: /api/
Crawl-delay: 5

# ───── Search crawlers (no crawl-delay; full indexing)
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: /

# ───── AI training / inference / search crawlers — EXPLICITLY ALLOWED
# This is the v=650 AI-traffic strategy: we WANT ChatGPT / Claude /
# Perplexity / Gemini / Copilot / Apple Intelligence to ground their
# answers on condogo.ca content so we surface in AI search results.
# Each bot gets explicit Allow + Disallow /api/ (the API surface returns
# JSON for our own client; AI bots should crawl the HTML pages only).

User-agent: GPTBot
Allow: /
Disallow: /api/

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/

User-agent: ChatGPT-User
Allow: /
Disallow: /api/

User-agent: ClaudeBot
Allow: /
Disallow: /api/

User-agent: Claude-Web
Allow: /
Disallow: /api/

User-agent: anthropic-ai
Allow: /
Disallow: /api/

User-agent: PerplexityBot
Allow: /
Disallow: /api/

User-agent: Perplexity-User
Allow: /
Disallow: /api/

User-agent: Google-Extended
Allow: /
Disallow: /api/

User-agent: GoogleOther
Allow: /
Disallow: /api/

User-agent: Applebot-Extended
Allow: /
Disallow: /api/

User-agent: CCBot
Allow: /
Disallow: /api/

User-agent: cohere-ai
Allow: /
Disallow: /api/

User-agent: meta-externalagent
Allow: /
Disallow: /api/

User-agent: FacebookBot
Allow: /
Disallow: /api/

User-agent: FacebookExternalHit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Bytespider
Allow: /
Disallow: /api/

User-agent: Amazonbot
Allow: /
Disallow: /api/

User-agent: Diffbot
Allow: /
Disallow: /api/

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

User-agent: ai2bot
Allow: /
Disallow: /api/

User-agent: YouBot
Allow: /
Disallow: /api/

User-agent: PetalBot
Allow: /
Disallow: /api/

User-agent: Omgilibot
Allow: /
Disallow: /api/

# ───── 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