# 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: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# robots.txt - Viralix
# https://beta.viralix.org/

# Allow all well-behaved crawlers
User-agent: *
Allow: /
Disallow: /api/

# Sitemap
Sitemap: https://beta.viralix.org/sitemap.xml

# =====================================================================
# AI CRAWLERS - two groups, handled differently on purpose.
#
# TRAINING crawlers fetch to build or refresh a model. These stay
# blocked under the EU Directive 2019/790 Article 4 rights reservation:
# we do not consent to our work being used for model training.
#
# RETRIEVAL and CITATION crawlers fetch because a person asked, or to
# build a search index that quotes us back to them. Blocking those buys
# no copyright protection at all - nothing is trained on the fetch -
# while removing the site from the answers people are actually reading.
# So they are allowed, and stated explicitly rather than left to fall
# through the wildcard, so a later cleanup cannot remove them silently.
#
# Removed: Claude-Web and anthropic-ai. Anthropic replaced those two
# strings with the three-bot structure below; the old directives no
# longer matched anything, so they gave a false impression of a stricter
# policy than was actually in force.
# =====================================================================

# --- Training: blocked -----------------------------------------------
User-agent: GPTBot
Disallow: /

# Anthropic's training crawler. Note this is NOT the citation bot -
# that is Claude-SearchBot below.
User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: cohere-ai
Disallow: /

# --- Retrieval and citation: allowed ---------------------------------

# ChatGPT fetching a page a user asked it to read
User-agent: ChatGPT-User
Allow: /

# Claude search indexing. Anthropic's own wording: blocking this
# "prevents our system from indexing your content for search
# optimization" - the equivalent of blocking Bingbot for Bing Search.
User-agent: Claude-SearchBot
Allow: /

# Claude fetching a page a user asked it about
User-agent: Claude-User
Allow: /

# Perplexity fetching to answer, and a source of referral traffic
User-agent: PerplexityBot
Allow: /

# OpenAI's ChatGPT search index. If this string is not the exact one in
# use, the rule is inert and the crawler falls through to * anyway, so
# it is safe either way.
User-agent: OAI-SearchBot
Allow: /

# --- Google ----------------------------------------------------------
# Googlebot is not declared here. It drives Search AND AI Overviews and
# AI Mode, and is allowed via the wildcard above.
#
# An earlier version of this file credited Google-Extended with powering
# AI Overviews. That was wrong. Google-Extended is a separate opt-out
# token governing Gemini and Vertex training use, and it is allowed:
# we permit that training.
User-agent: Google-Extended
Allow: /

# --- Apple -----------------------------------------------------------
# Applebot-Extended indexes for Apple Spotlight
User-agent: Applebot-Extended
Allow: /