# robots.txt — PHYSICAL FILE (added 2026-08-26).
# NOTE: a physical robots.txt bypasses WordPress entirely. Rank Math's robots.txt
# editor is now INERT for this site — edit THIS FILE, not the plugin setting.

User-agent: *
Disallow: /wp-admin/
Disallow: /wp-content/uploads/wc-logs/
Disallow: /wp-content/uploads/woocommerce_transient_files/
Disallow: /wp-content/uploads/woocommerce_uploads/
Disallow: /*?add-to-cart=
Disallow: /*?*add-to-cart=
Disallow: /*?orderby=
Disallow: /*?filter_
Allow: /wp-admin/admin-ajax.php

# ---------------------------------------------------------------------------
# AI crawlers and retrieval agents — policy reviewed 2026-08-26.
# A named User-agent group REPLACES the "*" group for that bot (RFC 9309);
# it does NOT merge with it. Every Disallow from the "*" group above is
# therefore repeated below on purpose. Do not "de-duplicate" these lines.
# ---------------------------------------------------------------------------

User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: Google-CloudVertexBot
Allow: /
Allow: /llms.txt
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-admin/
Disallow: /wp-content/uploads/wc-logs/
Disallow: /wp-content/uploads/woocommerce_transient_files/
Disallow: /wp-content/uploads/woocommerce_uploads/
Disallow: /*?add-to-cart=
Disallow: /*?*add-to-cart=
Disallow: /*?orderby=
Disallow: /*?filter_
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /wp-json/
Disallow: /*?s=

# PetalBot (Huawei Petal Search) — D20, owner 2026-09-26: SLOWED, not blocked. It made ~70 % of AT's logged bot hits
# (7 days to 09-26), mostly on dead URLs, and sends ~no visitors. A named group REPLACES "*" (RFC 9309), so the
# "*" rules are repeated here on purpose. Do not "de-duplicate" them.
User-agent: PetalBot
Crawl-delay: 10
Disallow: /wp-admin/
Disallow: /wp-content/uploads/wc-logs/
Disallow: /wp-content/uploads/woocommerce_transient_files/
Disallow: /wp-content/uploads/woocommerce_uploads/
Disallow: /*?add-to-cart=
Disallow: /*?*add-to-cart=
Disallow: /*?orderby=
Disallow: /*?filter_
Allow: /wp-admin/admin-ajax.php

# Aggressive, near-zero-value, historically ignores robots.txt.
# This line is a formality; real enforcement is an edge rule.
User-agent: Bytespider
Disallow: /

Sitemap: https://www.artisanthai.com/sitemap_index.xml