# 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.
# 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
Allow: /
User-agent: Amazonbot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: GPTBot
Disallow: /
User-agent: meta-externalagent
Disallow: /
# END Cloudflare Managed Content
User-agent: Googlebot
Disallow:
User-agent: AdsBot-Google
Disallow:
User-agent: Googlebot-Image
Disallow:
# ==== [GLOBAL ALLOWS FOR COMMON ASSETS] ====
# These assets should always be accessible to all crawlers
User-agent: *
Allow: /favicon.ico
Allow: /favicon-*.png
Allow: /apple-touch-icon.png
Allow: /site.webmanifest
# ==== [PRIMARY SEARCH ENGINES - FULL ACCESS] ====
User-agent: Googlebot
Allow: /
User-agent: Googlebot-Image
Allow: /
User-agent: Googlebot-News
Allow: /
User-agent: Bingbot
Allow: /
Crawl-delay: 10
User-agent: Applebot
Allow: /
Crawl-delay: 10
# ==== [SEO TOOLS & AUDIT BOTS - LIMITED THROTTLING] ====
User-agent: SiteAuditBot
Crawl-delay: 1
Allow: /
User-agent: Semrushbot-SI
Allow: /
# ==== [DEFAULT CATCH-ALL] ====
User-agent: *
# ==== [TRAP ROUTES] ====
# Fake or legacy paths — instant block or monitoring triggers
Disallow: /honeypot-
Disallow: /hidden-
Disallow: /admin.php
Disallow: /wp-json/
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /preview/
Disallow: /wprm_print/
Disallow: /gins/
Disallow: /*wp-help*
Disallow: /*/colors/
Disallow: /redirect/
# ==== [SENSITIVE BUT LEGITIMATE ROUTES] ====
# Real pages, but not for indexing
Disallow: /admin/
Disallow: /contributor/
Disallow: /api/
Disallow: /api
Disallow: /member/
Disallow: /login
Disallow: /register
Disallow: /password
Disallow: /cart/
Disallow: /checkout/
Disallow: /feed/
Disallow: /livewire/
Disallow: /newsletter/fi-weekly-*
# ==== [DISCOURAGED PATTERNS] ====
# Keep minimal to avoid blocking SEO-critical URLs
# Disallow: /?*