# robots.txt — www.kyivworkshop.com
# Policy: search engines and AI assistants that send traffic or cite sources are allowed.
# Bulk scrapers and data-resale crawlers that return nothing are blocked.
# Machine-readable summary for LLMs: https://www.kyivworkshop.com/llms.txt

# ---------------------------------------------------------------------------
# 1. Default group — all crawlers
# ---------------------------------------------------------------------------

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Private / transactional
Disallow: /admin
Disallow: /cart
Disallow: /cart/
Disallow: /*/cart/
Disallow: /checkout
Disallow: /*/checkout
Disallow: /checkouts/
Disallow: /*/checkouts/
Disallow: /orders
Disallow: /*/orders
Allow: /account/login
Allow: /*/account/login
Disallow: /account
Disallow: /*/account
Disallow: /56870797395
Disallow: /cdn/wpm/*.js

# Shopify-internal endpoints
Disallow: /services
Disallow: /sf_*
Disallow: /apps/
Disallow: /*/apps/
Disallow: /cart.js
Disallow: /*/cart.js
Disallow: /recommendations/products
Disallow: /*/recommendations/products
Disallow: /*/search
Disallow: /search
Disallow: /*?*q=

# Faceted navigation, sorting and preview crawl traps
Disallow: /collections/*sort_by*
Disallow: /*/collections/*sort_by*
Disallow: /collections/*+*
Disallow: /collections/*%2B*
Disallow: /collections/*%2b*
Disallow: /*/collections/*+*
Disallow: /*/collections/*%2B*
Disallow: /*/collections/*%2b*
Disallow: /collections/*filter*&*filter*
Disallow: /*/collections/*filter*&*filter*
Disallow: /blogs/*+*
Disallow: /blogs/*%2B*
Disallow: /blogs/*%2b*
Disallow: /*/blogs/*+*
Disallow: /*/blogs/*%2B*
Disallow: /*/blogs/*%2b*
Disallow: /*?*ls=*&ls=*
Disallow: /*?*ls%3*ls%3*
Disallow: /*?*oseid=*
Disallow: /*?*preview_theme_id=*
Disallow: /*?*preview_script_id=*
Disallow: /*?*_pos=
Disallow: /*?*_sid=
Disallow: /*?*_ss=

# Allow ad and rendering resources needed for correct page evaluation
Allow: /cdn/
Allow: /*.js$
Allow: /*.css$

# ---------------------------------------------------------------------------
# 2. AI assistants and AI search — ALLOWED
# ---------------------------------------------------------------------------

User-agent: OAI-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: ChatGPT-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: bingbot
Allow: /

User-agent: msnbot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: meta-externalfetcher
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: YouBot
Allow: /

User-agent: ShopifyMcpBot
Allow: /

# ---------------------------------------------------------------------------
# 3. Bulk scrapers and data-resale crawlers — BLOCKED
# ---------------------------------------------------------------------------

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: peer39_crawler
Disallow: /

User-agent: TurnitinBot
Disallow: /

# ---------------------------------------------------------------------------
# 4. Google Ads & Merchant Center Crawlers (FIX FOR GMC ERROR)
# ---------------------------------------------------------------------------

User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: Googlebot-Image
User-agent: Googlebot
Allow: /
Allow: /products/
Allow: /*/products/
Allow: /collections/
Allow: /*/collections/
Allow: /pages/
Allow: /*/pages/
Allow: /blogs/
Allow: /*/blogs/
Allow: /cdn/
Allow: /*.js$
Allow: /*.css$

# Only block core non-public areas for Google GMC crawlers
Disallow: /admin
Disallow: /cart
Disallow: /*/cart/
Disallow: /checkout
Disallow: /*/checkout
Disallow: /checkouts/
Disallow: /*/checkouts/
Disallow: /orders
Disallow: /*/orders
Disallow: /account
Disallow: /*/account
Disallow: /services
Disallow: /sf_*
Disallow: /56870797395
Disallow: /cdn/wpm/*.js

# ---------------------------------------------------------------------------
# 5. Agent / commerce notes
# ---------------------------------------------------------------------------

Sitemap: https://www.kyivworkshop.com/sitemap.xml