# 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: *

# WordPress core restrictions
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /*?s=
Disallow: /search/
Disallow: /readme.html
Disallow: /refer/

# Invision Power Board (IPB) Restrictions
Disallow: /forums/startTopic/
Disallow: /forums/discover/unread/
Disallow: /forums/markallread/
Disallow: /forums/staff/
Disallow: /forums/cookies/
Disallow: /forums/online/
Disallow: /forums/discover/
Disallow: /forums/leaderboard/
Disallow: /forums/search/
Disallow: /forums/*advancedSearchForm=
Disallow: /forums/register/
Disallow: /forums/lostpassword/
Disallow: /forums/login/
Disallow: /forums/*currency=
Disallow: /forums/*sortby=
Disallow: /forums/*filter=
Disallow: /forums/*tab=
Disallow: /forums/*do=
Disallow: /forums/*ref=
Disallow: /forums/*forumId
Disallow: /forums/*controller=embed

# Cloudflare & System restrictions
Disallow: /cdn-cgi/

# Sitemaps declarations
Sitemap: https://www.kaldata.com/sitemap_index.xml
Sitemap: https://www.kaldata.com/forums/sitemap.php
Sitemap: https://www.kaldata.com/news-sitemap.xml

# ============================================================
# PURE AI SCRAPERS, SEO AGGRESSORS & DOWNLOADERS (SAFE TO BLOCK)
# ============================================================

User-agent: ManusBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: DiffBot
User-agent: omgili
User-agent: Omgilibot
User-agent: ImagesiftBot
User-agent: SentiBot
User-agent: TurnitinBot
User-agent: webzio
User-agent: webzio-extended
User-agent: Scrapy
User-agent: SemrushBot
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-FT
User-agent: Rogerbot
User-agent: MJ12bot
User-agent: Dotbot
User-agent: Gigabot
User-agent: BlackWidow
User-agent: Zeus
User-agent: magpie-crawler
User-agent: HTTrack
User-agent: wget
User-agent: Teleport Pro
User-agent: Offline Explorer
User-agent: DataForSeoBot
User-agent: Baiduspider
User-agent: AhrefsBot
Disallow: /