# ===========================================
# Twig & Olive Photography - robots.txt
# Updated: July 15, 2026
# ===========================================
#
# Strategy: Maximum AI + search visibility, with an
# identical CMS/crawl-trap restriction set applied to
# every crawler class. robots.txt is advisory only;
# enforcement for non-compliant bots lives at the
# Cloudflare/WAF layer.
# AI-readable site summary: https://twigandolive.com/llms.txt
#
# MAINTENANCE RULE (RFC 9309): a crawler obeys ONLY its
# most specific matching User-agent group and ignores
# all others. Any rule added to one group MUST be
# copied to every other restricted group below, or the
# named bots will never see it.

# ----- Global Rules (All Crawlers) -----
# Search engines (Googlebot, Bingbot, Applebot, etc.)
# intentionally have no dedicated group, so they
# inherit this one with full restriction coverage.
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /wp-content/uploads/wpforms/
Disallow: /wp-json/
Disallow: /?rest_route=
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /*?s=
Disallow: /search/
Disallow: /*?replytocom=
Disallow: /*?add-to-cart=
Disallow: /*&add-to-cart=
Disallow: /*add-to-cart=*
Disallow: /*?product_count=
Disallow: /*?orderby=

# ----- SEO Tool Crawlers (Neil Patel / Ubersuggest) -----
# RSiteAuditor is the vendor-documented Ubersuggest
# site-audit crawler (their support docs instruct
# allowing it by name). UberSuggestBot and NeilPatelBot
# are not vendor-documented; retained as harmless
# insurance tokens at owner request. Extra faceted-
# navigation limits prevent crawl traps in the shop
# and category archives.
User-agent: RSiteAuditor
User-agent: UberSuggestBot
User-agent: NeilPatelBot
Allow: /
Disallow: /shop/*?
Disallow: /product-category/*?
Disallow: /category/*/page/
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /wp-content/uploads/wpforms/
Disallow: /wp-json/
Disallow: /?rest_route=
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /*?s=
Disallow: /search/
Disallow: /*?replytocom=
Disallow: /*?add-to-cart=
Disallow: /*&add-to-cart=
Disallow: /*?product_count=
Disallow: /*?orderby=

# ----- AI Crawlers (Explicitly Welcome) -----
# Training crawlers, retrieval/search indexers, and
# user-triggered fetchers. Note: Google-Extended and
# Applebot-Extended are declarative policy tokens that
# never send HTTP requests; Googlebot and Applebot read
# them to determine AI-training permissions.
# Restriction set is byte-identical to the global
# group; this dedicated group exists so future edits
# to * can never accidentally lock AI crawlers out.
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Google-Extended
User-agent: Google-CloudVertexBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: MistralAI-Index
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: meta-webindexer
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Amazonbot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: YouBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /wp-content/uploads/wpforms/
Disallow: /wp-json/
Disallow: /?rest_route=
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /*?s=
Disallow: /search/
Disallow: /*?replytocom=
Disallow: /*?add-to-cart=
Disallow: /*&add-to-cart=
Disallow: /*?product_count=
Disallow: /*?orderby=

# ----- Social / Link-Preview Fetchers -----
# These fetch a page only when its URL is shared, to
# read OG meta tags. Preview-only agents belong here.
# Full-crawl bots (Applebot, Meta-ExternalAgent) do
# NOT: they inherit * or the AI group above.
User-agent: facebookexternalhit
User-agent: LinkedInBot
User-agent: Twitterbot
Allow: /

# ----- Block: Scrapers with No Discovery Benefit -----
# Bulk content and image-dataset harvesters. robots.txt
# compliance from these is unreliable; the authoritative
# block is the Cloudflare/WAF rule.
User-agent: Bytespider
Disallow: /

User-agent: TikTokSpider
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: ImagesiftBot
Disallow: /

# ----- Sitemaps -----
Sitemap: https://twigandolive.com/sitemap_index.xml