# robots.txt for storagewise.ie
# Policy: Block AI training crawlers. Allow AI search engines and answer bots.
#
# Content signals (EU DSM Directive 2019/790 Article 4 reservation of rights):
#   search=yes       — permitted to index for search results
#   ai-input=yes     — permitted for real-time AI retrieval / RAG / answer engines
#   ai-train=no      — NOT permitted to use content for AI model training or fine-tuning

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /readme.html
Disallow: /refer/
Disallow: /*add_to_wishlist=*
Disallow: /*add-to-cart=*
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/

# --- AI ANSWER ENGINES & SEARCH BOTS (explicitly allowed) ---
# These bots retrieve content in real-time on behalf of users — permitted.

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Amazonbot
Allow: /

# --- AI TRAINING CRAWLERS (blocked) ---
# These bots are used primarily for dataset collection and model training — not permitted.

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: Diffbot
Disallow: /

# --- STANDARD SEARCH ENGINES (always allowed) ---

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

Sitemap: https://westpark.ie/sitemap_index.xml