# 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: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# Lokuli - AI-Native Local Service Booking
# We welcome AI crawlers. Our content is built for both humans and AI agents.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /shop/*/book
Disallow: /shop/*/buy
Disallow: /es/shop/*/book
Disallow: /es/shop/*/buy

# AI Crawlers - Explicitly Welcome
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
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

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

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

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

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

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

# Checkout endpoints 303-redirect to Stripe and are linked ~9x from every shop page.
# Crawling them wastes budget and files shops under "Page with redirect".
# Repeated per group on purpose: a crawler obeys only its most specific User-agent group.

# Search Engines
User-agent: Googlebot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /shop/*/book
Disallow: /shop/*/buy
Disallow: /es/shop/*/book
Disallow: /es/shop/*/buy

User-agent: Applebot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /shop/*/book
Disallow: /shop/*/buy
Disallow: /es/shop/*/book
Disallow: /es/shop/*/buy

User-agent: bingbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /shop/*/book
Disallow: /shop/*/buy
Disallow: /es/shop/*/book
Disallow: /es/shop/*/buy

# Sitemaps
Sitemap: https://lokuli.com/sitemap.xml
Sitemap: https://lokuli.com/sitemap-backlinks.xml
Sitemap: https://lokuli.com/sitemap-languages.xml
Sitemap: https://lokuli.com/sitemap-callaround.xml
Sitemap: https://lokuli.com/sitemap-shops.xml

# AI Discovery
# llms.txt: https://lokuli.com/llms.txt
# MCP server (prices from local pros): https://lokuli.com/mcp
# Agent guide: https://lokuli.com/llms-full.txt
# AI catalog: https://lokuli.com/.well-known/ai-catalog.json
# AI Plugin: https://lokuli.com/.well-known/ai-plugin.json
Sitemap: https://lokuli.com/sitemap-listings.xml