# 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

User-agent: *
Allow: /

# Google and Bing specific optimizations
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 1

# Social Media Crawlers
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# Security and System Protection
Disallow: /_astro/
Disallow: /_image/
Disallow: /admin/
Disallow: /draft/
Disallow: /tmp/
Disallow: /components/
Disallow: /*.json$
Disallow: /*.config$
Disallow: /*.env$

# Prevent duplicate content from tracking parameters
Disallow: /*?*utm_*
Disallow: /*?*fbclid=*
Disallow: /*?*gclid=*

# Block conversion-only pages from direct search entry
Disallow: /*-confirmation/
Disallow: /thank-you/

# Explicitly allow High-Value Content Paths
Allow: /pilot-training-programs/
Allow: /pilot-training-programs/*
Allow: /pilot-training-programs/certified-flight-instructor-cfi-program/
Allow: /locations/
Allow: /locations/*
Allow: /fleet/
Allow: /fleet/*
Allow: /services/
Allow: /services/*
Allow: /about/
Allow: /about/*
Allow: /about/our-pilots/
Allow: /about/our-pilots/*
Allow: /blog/
Allow: /blog/*
Allow: /contact/
Allow: /enroll/
Allow: /financing/
Allow: /new-to-flying/
Allow: /faqs/

# Asset indexing
Allow: /*.css$
Allow: /*.js$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.png$
Allow: /*.webp$
Allow: /*.svg$

# AI Scraper Protection
User-agent: CCBot
Disallow: /

# Block SEO Spiders
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

# Sitemaps and Host
Sitemap: https://magnoliaaviation.com/sitemap-index.xml
Sitemap: https://magnoliaaviation.com/rss.xml
Host: magnoliaaviation.com