# Manor Spirits robots.txt
# Sitemap
Sitemap: https://manorspirits.com/sitemap_index.xml

# Default rules for all crawlers
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-content/uploads/wc-logs/
Disallow: /wp-content/uploads/woocommerce_transient_files/
Disallow: /wp-content/uploads/woocommerce_uploads/
Disallow: /basket/
Disallow: /checkout/
Disallow: /account/
Disallow: /*?add-to-cart=
Disallow: /*?*add-to-cart=
Disallow: /*?removed_item=
Disallow: /*?undo_item=
Disallow: /*?wc-ajax=
Content-Signal: ai-train=no, search=yes, ai-input=yes

# AI retrieval bots – allowed
User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Applebot
Allow: /

# AI training crawlers — blocked
User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Timpibot
Disallow: /

# ─────────────────────────────────────────────────────────────────────
# Content Signal terms
#
# 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
#              this 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 and summaries).
#
# - 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.
# ─────────────────────────────────────────────────────────────────────