# 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.

# 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
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

User-agent: *
Allow: /

# Block admin and private paths
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /admin/
Disallow: /api/
Disallow: /*.json$
Disallow: /*?*

# ── Allow popular LLM / AI crawler bots ──────────────────────────────────────
# OpenAI GPTBot
User-agent: GPTBot
Allow: /

# OpenAI ChatGPT-User (browsing plugin)
User-agent: ChatGPT-User
Allow: /

# Anthropic ClaudeBot
User-agent: ClaudeBot
Allow: /

# Anthropic claude-web (browsing)
User-agent: claude-web
Allow: /

# Google Gemini / Search Generative Experience
User-agent: Google-Extended
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Cohere AI
User-agent: cohere-ai
Allow: /

# Meta AI (LLaMA crawlers)
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

# ByteDance / TikTok AI
User-agent: Bytespider
Allow: /

# Amazon Alexa / Alexa AI
User-agent: Amazonbot
Allow: /

# Apple Applebot-Extended (Apple AI features)
User-agent: Applebot-Extended
Allow: /

# Common Crawl (training data foundation for many LLMs)
User-agent: CCBot
Allow: /

# Diffbot (AI-powered data extraction)
User-agent: Diffbot
Allow: /

# You.com AI search
User-agent: YouBot
Allow: /

# Sitemap
Sitemap: https://emergencyplumberwilton.xyz/sitemap.xml
Sitemap: https://emergencyplumberwilton.xyz/llm.txt

# Crawl-delay (optional — uncomment if needed)
# Crawl-delay: 5