# 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

# Rules for IPS (https://www.ragepros.com/)

# Allow social preview crawlers

User-agent: facebookexternalhit
Allow: /

User-agent: Facebot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: Discordbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slackbot
Allow: /

User-Agent: *

# Block pages with no unique content

Disallow: /startTopic/
Disallow: /discover/unread/
Disallow: /markallread/
Disallow: /staff/
Disallow: /cookie/
Disallow: /online/
Disallow: /discover/
Disallow: /leaderboard/
Disallow: /search/
Disallow: /tags/
Disallow: /*?advancedSearchForm=
Disallow: /register/
Disallow: /lostpassword/
Disallow: /login/

# Block faceted pages and duplicate parameter pages

Disallow: /*?sortby=
Disallow: /*?filter=
Disallow: /*?tab=
Disallow: /*?do=
Disallow: /*ref=
Disallow: /*?forumId*
Disallow: /*?&controller=embed

# Reduce duplicate pagination crawling

Disallow: /*?page=
Disallow: /*&page=

# Block profile pages

Disallow: /profile/

# Block attachment duplication crawling

Disallow: /applications/core/interface/file/attachment.php

# Block account and private user areas

Disallow: /messenger/
Disallow: /notifications/
Disallow: /clients/

# Sitemap

Sitemap: https://www.ragepros.com/sitemap.xml