# 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: /

# Authenticated app + auth routes — gated, no SEO value, dilute crawl budget.
# English is the default locale at the ROOT (no prefix), so each route is
# disallowed both bare (/dashboard) and locale-prefixed (/ru/dashboard,
# /ua/dashboard) via the wildcard form.
Disallow: /dashboard
# /ads is the authenticated product feed — gated. The PUBLIC demo at /demo is
# intentionally NOT listed here (SPY-449): it carries noindex (meta in the
# prerendered HTML + nginx X-Robots-Tag), and crawlers must be able to FETCH
# it to see that rule — a Disallow would hide the noindex and let the bare
# URL linger in search results ("Indexed, though blocked by robots.txt").
Disallow: /ads
Disallow: /hubs
Disallow: /creo
Disallow: /webmaster
Disallow: /advertisers
Disallow: /trends
Disallow: /settings
Disallow: /keyword-discovery
Disallow: /content
Disallow: /admin
Disallow: /login
Disallow: /register
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /verify-email
Disallow: /activate
Disallow: /*/dashboard
Disallow: /*/ads
Disallow: /*/hubs
Disallow: /*/creo
Disallow: /*/webmaster
Disallow: /*/advertisers
Disallow: /*/trends
Disallow: /*/settings
Disallow: /*/keyword-discovery
Disallow: /*/content
Disallow: /*/admin
Disallow: /*/login
Disallow: /*/register
Disallow: /*/forgot-password
Disallow: /*/reset-password
Disallow: /*/verify-email
Disallow: /*/activate

# /demo and its subsections are noindex'ed (SPY-449) and deliberately have NO
# Disallow here: engines must crawl them to read the noindex, and they lower
# the crawl frequency on such pages by themselves once it registers.

# AI / LLM crawler access is governed at the Cloudflare edge (bot management),
# NOT here — this file intentionally allows all user-agents. Retrieval bots
# (OAI-SearchBot, ChatGPT-User, Claude-SearchBot, Claude-User, PerplexityBot,
# DuckAssistBot) are ALLOWED through by the zone WAF skip-rule "Allow AI
# retrieval bots" (agent-readiness, 2026-06-23) — verified 2026-08-06 in the
# origin nginx logs: OAI-SearchBot / Claude-SearchBot / Claude-User /
# ChatGPT-User fetch pages daily, including /blog articles. Training bots
# (GPTBot, ClaudeBot, CCBot, …) stay blocked via Cloudflare Managed robots.txt
# + bot management — a deliberate business choice.

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