# 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: /
Disallow: /removal

# Named groups for crawlers that ignore the generic Disallow above.
# Cloudflare's edge-injected managed robots.txt prepends its own
# "User-agent: * / Allow: /" group; crawlers that first-match instead of
# RFC 9309-merging duplicate * groups never see our Disallow. Named groups
# outrank * in every parser. Both bots hammered /removal?url= (1.17M unique
# variants) and /api/og/ cards in Aug 2026 — 99% of meta-webindexer's crawl.
User-agent: meta-webindexer
Disallow: /removal
Disallow: /api/og/

User-agent: Amzn-SearchBot
Disallow: /removal
Disallow: /api/og/

# SEO crawlers: blocked. These crawl all 1.2M pages and provide us no value.
# (Also enforced at the Cloudflare WAF by user-agent, which is what actually stops them.)
User-agent: SemrushBot
Disallow: /

User-agent: SiteAuditBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: AhrefsSiteAudit
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSEOBot
Disallow: /

User-agent: Barkrowler
Disallow: /

User-agent: SplitSignalBot
Disallow: /

User-agent: ThinkBot
Disallow: /

User-agent: Brightbot
Disallow: /

Sitemap: https://patronview.com/sitemap.xml