# 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

# HostRankly — https://hostrankly.com
# Crawlers: prefer HTML meta robots on pages; this file is the crawl allow-list.

User-agent: *
Allow: /

# Legal / company utility (HTML also uses noindex,nofollow)
Disallow: /about/
Disallow: /contact/
Disallow: /disclosure/
Disallow: /privacy/
Disallow: /terms/
Disallow: /cookies/

# Interactive tool (noindex; not a landing page)
Disallow: /matrix/compare/

# Host paths that only 301 to full reviews (avoid soft-duplicate crawl)
Disallow: /hosts/hostinger/
Disallow: /hosts/siteground/
Disallow: /hosts/bluehost/
Disallow: /hosts/cloudways/
Disallow: /hosts/greengeeks/
Disallow: /hosts/dreamhost/
Disallow: /hosts/hostgator/
Disallow: /hosts/godaddy/
Disallow: /hosts/scalahosting/
Disallow: /hosts/spaceship/
Disallow: /hosts/hosting-com/

# XML sitemaps (both entry points)
Sitemap: https://hostrankly.com/sitemap.xml
Sitemap: https://hostrankly.com/sitemap-index.xml

# Human-readable site index
# https://hostrankly.com/sitemap/