# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
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

# Lola Health — Shopify store (primary domain: lolahealth.com)######################################################
# 1) GLOBAL RULES (apply to every crawler by default)
######################################################
User-agent: *
# — AI content usage preferences (draft-romm-aipref-contentsignals)
#   ai-train=no  : do not use this content to train AI models
#   search=yes   : allow indexing for traditional & AI-powered search
#   ai-input=yes : allow use as context/input in AI assistant answers (consistent
#                  with the explicit Allow for ChatGPT-User, Claude-User, etc. below)
Content-Signal: ai-train=no, search=yes, ai-input=yes
# — Shopify system & customer-specific paths
Disallow: /a/downloads/-/*
Disallow: /admin
Disallow: /cart
Disallow: /carts
Disallow: /orders
Disallow: /checkouts
Disallow: /checkouts/
Disallow: /64088309912/checkouts
Disallow: /64088309912/orders
Disallow: /account

# — Faceted collection URLs that waste crawl budget (path form)
# Allow basic sorting but block complex multi-parameter filters
Disallow: /collections/*sort_by*&*
Disallow: /*/collections/*sort_by*&*
Disallow: /collections/*+*
Disallow: /collections/*%2B*
Disallow: /*/collections/*+*
Disallow: /*/collections/*%2B*
Disallow: */collections/*filter*&*filter*

# — Faceted & filter parameters (query-string form)
# Block filter/faceted URLs but allow variant+country (Google Shopping needs these)
Disallow: /*?*filter.p.*
Disallow: /*?*price_from=*
Disallow: /*?*constraint=*
Allow: /products/*?variant=*&country=*
Disallow: /*?*variant=*&*filter*
Disallow: /*?*variant=*&*sort_by*

# — Preview, tracking & other low-value URLs
Disallow: /*?*oseid=*
Disallow: /*preview_theme_id*
Disallow: /*preview_script_id*
Disallow: /search
Disallow: /apple-app-site-association
Disallow: /.well-known/shopify/monorail
Disallow: /cdn/wpm/*.js
Disallow: /recommendations/products
Disallow: /*/recommendations/products

# — Trust/Policy pages: allow indexing for E-E-A-T signals
Allow: /policies/
Allow: /*/policies/

# — Blogs are key content: keep fully crawlable
Allow: /blogs/
Allow: /*/blogs/

# — Ensure core theme assets are retrievable
Allow: /assets/
Allow: /cdn/shop/*.css
Allow: /cdn/shop/*.js

######################################################
# 2) AI / LLM & MODERN DISCOVERY BOTS — segmented
######################################################
# 2a) Trusted / cooperative AI & extended crawlers — full access
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ChatGPT-User/2.0
User-agent: Google-Extended
User-agent: anthropic-ai
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: claude-web
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: MistralAI-User/1.0
User-agent: cohere-ai
User-agent: CCBot
User-agent: AI2Bot
User-agent: DuckAssistBot
User-agent: Bingbot
User-agent: Amazonbot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: FacebookBot
User-agent: meta-externalagent
Allow: /

# 2b) Restricted / scraper-like bots — content-only, throttle if supported
#    (Keep marketing content open; block transactional & faceted noise)
User-agent: Diffbot
User-agent: omgili
Crawl-delay: 2
Allow: /blogs/
Allow: /pages/
Allow: /collections/
Allow: /products/
Disallow: /cart
Disallow: /carts
Disallow: /checkouts
Disallow: /orders
Disallow: /account
Disallow: /search
Disallow: /*?*filter.p.*
Disallow: /*?*price_from=*
Disallow: /*?*constraint=*
Disallow: /*?*variant=*&*
Disallow: /recommendations/products
Disallow: /*/recommendations/products

######################################################
# 3) ADS-FOCUSED GOOGLE CRAWLER (stricter rules)
######################################################
User-agent: adsbot-google
Disallow: /checkouts
Disallow: /checkouts/
Disallow: /carts
Disallow: /orders
Disallow: /64088309912/checkouts
Disallow: /64088309912/orders
Disallow: /*?*oseid=*
Disallow: /*preview_theme_id*
Disallow: /*preview_script_id*
Disallow: /cdn/wpm/*.js

######################################################
# 4) RATE-LIMITED SEO-AUDIT BOTS
######################################################
User-agent: AhrefsBot
User-agent: AhrefsSiteAudit
User-agent: MJ12bot
Crawl-delay: 10

User-agent: Pinterest
Crawl-delay: 1

######################################################
# 5) FULLY BLOCKED BOTS
######################################################
User-agent: Nutch
Disallow: /

##############################
# 6) XML SITEMAP (visible to all)
##############################
Sitemap: https://lolahealth.com/sitemap.xml
# Optional legacy line for retired domain:
# Sitemap: https://lolahealth.com/sitemap.xml