# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
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

# VIP Transport - robots.txt
# https://viptransport.com

# ============================================================================
# Wildcard rules — apply to every crawler that doesn't have its own block below.
#
# Important: when a crawler matches a more-specific User-agent block, it
# IGNORES this wildcard block entirely (per Google's spec). So every per-bot
# block below repeats the core Disallows. Don't add a per-bot section without
# copying these in, or that bot will be free to crawl admin paths and WP junk.
# ============================================================================
User-agent: *
Allow: /

# Sitemaps
Sitemap: https://viptransport.com/sitemap.xml

# Crawl-delay for politeness (Google ignores this; other crawlers honor it)
Crawl-delay: 1

# Admin / internal paths
Disallow: /api/
Disallow: /_next/
Disallow: /thank-you
Disallow: /studio
Disallow: /admin

# WordPress-era leftovers — Google still hits these years later because they
# were in the old index. Telling Googlebot to stop crawling them frees up
# crawl budget for real pages. Most are also 301'd in netlify.toml.
Disallow: /wp-admin/
Disallow: /wp-content/
Disallow: /wp-json/
Disallow: /wp-login.php
Disallow: /cart
Disallow: /cart/
Disallow: /checkout
Disallow: /my-account
Disallow: /edit-profile
Disallow: /log-in
Disallow: /register
Disallow: /erp-subscription
Disallow: /product/
Disallow: /product-category/
Disallow: /category/
Disallow: /tag/
Disallow: /faq_category/

# RSS feeds — never indexed by Google anyway, just wastes crawls
Disallow: /feed
Disallow: /feed/
Disallow: /*/feed
Disallow: /*/feed/

# WP plugin and tracking-parameter duplicate URLs
# (MailOptin alone generated ~80 dupe URLs in our GSC report)
Disallow: /*?mailoptin-ajax=
Disallow: /*?add-to-cart=
Disallow: /*?remove_item=
Disallow: /*?_wpnonce=
Disallow: /*?share=
Disallow: /*?wc-ajax=
Disallow: /*?ref=aftership

# Old WP team-page image gallery artifacts (each photo became a "page")
Disallow: /team-vip/img_
Disallow: /team-vip/image-
Disallow: /team-vip/15917_
Disallow: /team-vip/camppendletontrees

# ============================================================================
# AI assistants — explicit allow for AEO (Answer Engine Optimization)
# Listed explicitly because some AI crawlers default to opt-out and we want them in.
# Each block repeats the core Disallows so AI bots don't waste cycles on WP junk.
# ============================================================================
User-agent: GPTBot
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /admin
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /cart
Disallow: /checkout
Disallow: /my-account
Disallow: /product/
Disallow: /category/

User-agent: ChatGPT-User
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /admin
Disallow: /wp-admin/

User-agent: Claude-Web
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /admin
Disallow: /wp-admin/

User-agent: Anthropic-AI
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /admin
Disallow: /wp-admin/

User-agent: PerplexityBot
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /admin
Disallow: /wp-admin/

User-agent: Google-Extended
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /admin
Disallow: /wp-admin/