# 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

# --- Known aggressive bots blocked sitewide ---
User-agent: PetalBot
User-agent: AspiegelBot
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: SemRush
User-agent: DotBot
User-agent: MauiBot
User-agent: MJ12bot
Disallow: /

# --- Forum-specific rule ---
User-agent: Amazonbot
Disallow: /threads/*/reply

# --- Global default allow (forum paths sanitized) ---
User-agent: *
Disallow: /whats-new/
Disallow: /account/
Disallow: /members/
Disallow: /attachments/
Disallow: /goto/
Disallow: /help/
Disallow: /posts/
Disallow: /login/
Disallow: /search/
Disallow: /admin.php
Allow: /

Sitemap: https://uoalive.com/forum/sitemap.xml
Sitemap: https://uoalive.com/wiki/sitemap-index-u641889600_IuQvd-odpz_.xml


# =========================
# Wiki crawling controls
# =========================

# Slow polite bots a bit (some respect this, some don't)
User-agent: *
Crawl-delay: 5

# Don't crawl noisy endpoints that create load but add little SEO value
# (Remove lines for api.php/rest.php if you rely on public API clients)
Disallow: /wiki/rest.php
Disallow: /wiki/api.php
Disallow: /*?action=render
Disallow: /*?action=purge
Disallow: /*?oldid=

# Optional: block some Special: pages that are high-cost / low-value to index
Disallow: /wiki/Special:RecentChanges
Disallow: /wiki/Special:Random
Disallow: /wiki/Special:AllPages
Disallow: /wiki/Special:UserLogin
Disallow: /wiki/Special:UserLogout