# Ontario Community Church — robots.txt
# Self-managed (no Cloudflare auto-injection of Content-Signal directives).
#
# Policy (2026-05-11): block AI *training* bots, allow AI *search/citation* bots.
# Training bots ingest our content into model weights without attribution.
# Search/citation bots fetch content on behalf of a user and cite us with a link
# — same value as Google: visibility in answer pages.

# ─── AI search & citation bots — ALLOWED (cite with link back) ───────────
User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Claude-Web
Allow: /

# ─── AI training bots — BLOCKED (no attribution, model-weight ingestion) ─
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: ai2bot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: PanguBot
Disallow: /

# ─── Data scrapers / SEO bots — BLOCKED ──────────────────────────────────
User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

# ─── Everyone else (Googlebot, Bingbot, social previews, etc.) — allowed ─
User-agent: *
Allow: /

Sitemap: https://ontariocommunitychurch.org/sitemap.xml
Sitemap: https://ontariocommunitychurch.org/sermons/sitemap.xml