# 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: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Clay Oven Restaurant – robots.txt
# Site: https://www.clayoven.ca/
# Last Updated: 2026-05-02

# ---- Default rules for all crawlers ----
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /config/
Disallow: /search/
Disallow: /api/
Disallow: /static/
Disallow: /logs/
Disallow: /*?*
Disallow: /*&*
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html
# llms.txt is intended for LLM agents only and must not be indexed.
# Disallow blocks crawl, and an X-Robots-Tag: noindex header should be set
# at the server / hosting layer for /llms.txt for full noindex enforcement.
Disallow: /llms.txt
Noindex: /llms.txt

# ---- AI / LLM training & crawler bots ----
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: cohere-ai
User-agent: FacebookBot
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Amazonbot
Allow: /
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html
Disallow: /llms.txt
Noindex: /llms.txt

# ---- Google Ads bots ----
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# ---- Crawl-delay for heavy bots ----
User-agent: Baiduspider
Crawl-delay: 10

User-agent: Yandex
Crawl-delay: 10

# ---- Sitemap ----
Sitemap: https://www.clayoven.ca/sitemap.xml