# llms.txt for jhwallpaints.com
# Purpose: Guidance for Large Language Model (LLM) and AI crawlers about access and permitted use.
# Policy-Version: 1.0
# Updated: 2025-10-02
# Owner: JH Wall Paints (Pvt) Ltd.
# Contact: info@jhwallpaints.com
# Website: https://www.jhwallpaints.com
# Sitemap: https://www.jhwallpaints.com/sitemap.xml

########################################################################
# 1) ACCESS POLICY
########################################################################
User-agent: *
# We allow crawling for AI search, answer generation, and citations.
Allow: /

# But DO NOT crawl/ingest sensitive, user-specific, or non-content paths:
Disallow: /a/downloads/-/*
Disallow: /admin
Disallow: /account
Disallow: /cart
Disallow: /carts
Disallow: /orders
Disallow: /checkouts/
Disallow: /checkout
Disallow: /27536097347/checkouts
Disallow: /27536097347/orders
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: /blogs/*+*
Disallow: /blogs/*%2B*
Disallow: /blogs/*%2b*
Disallow: /*/blogs/*+*
Disallow: /*/blogs/*%2B*
Disallow: /*/blogs/*%2b*
Disallow: /*?*oseid=*
Disallow: /*preview_theme_id*
Disallow: /*preview_script_id*
Disallow: /policies/
Disallow: /*/policies/
Disallow: /*/*?*ls=*&ls=*
Disallow: /*/*?*ls%3D*%3Fls%3D*
Disallow: /*/*?*ls%3d*%3fls%3d*
Disallow: /search
Disallow: /apple-app-site-association
Disallow: /.well-known/shopify/monorail
Disallow: /cdn/wpm/*.js
Disallow: /recommendations/products
Disallow: /*/recommendations/products

########################################################################
# 2) AI USER-AGENT WHITELIST (explicitly welcome common LLM crawlers)
########################################################################
User-agent: GPTBot                  # OpenAI / ChatGPT
Allow: /
User-agent: ChatGPT-User            # ChatGPT retrieval
Allow: /
User-agent: ChatGPT                 # legacy id
Allow: /
User-agent: Google-Extended         # Google AI data access
Allow: /
User-agent: Applebot-Extended       # Apple Intelligence
Allow: /
User-agent: anthropic-ai            # Anthropic / Claude
Allow: /
User-agent: ClaudeBot               # Anthropic bot id
Allow: /
User-agent: PerplexityBot           # Perplexity.ai
Allow: /
User-agent: CCBot                   # Common Crawl
Allow: /

########################################################################
# 3) CRAWL RULES & RATE LIMITS
########################################################################
# Use the sitemap above as your primary discovery source.
# Respect the following polite limits to avoid service disruption:
Crawl-Delay: 5           # seconds between requests per bot
Request-Rate: 60/1m      # max 60 requests per minute per bot
Max-Depth: 3             # avoid deep parameterized crawling
Preferred-Fetch: GET https only

########################################################################
# 4) PERMITTED USES (AI & LLMs)
########################################################################
# ✅ Allowed (without separate license):
# - Indexing/public web search, answer generation, and snippets.
# - Non-commercial evaluation, safety testing, and retrieval-augmented responses.
# - Quoted citations with a visible link attribution to jhwallpaints.com.
#
# ❌ Not allowed (without prior written permission/license):
# - Training or fine-tuning foundation models on our content.
# - Creating derivative datasets, embeddings, or vectors for resale/redistribution.
# - Commercial content licensing or syndication beyond transient caching for search.
# - Storing or processing personal data from prohibited paths (see Disallow above).

########################################################################
# 5) ATTRIBUTION REQUIREMENTS
########################################################################
# When our content is used in answers/snippets:
# - Provide a visible source link to the exact page on https://www.jhwallpaints.com
# - Include our brand name "JH Wall Paints" in the source line where feasible.

########################################################################
# 6) CONTENT OWNERSHIP & LEGAL
########################################################################
# All on-site content is © JH Wall Paints (Pvt) Ltd. All rights reserved.
# No rights are granted for model training or dataset creation unless explicitly licensed.
# If you believe a crawler of yours accessed disallowed data