# 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

# robots.txt – Version 1.3 – 2025-10-17
# Purpose: Control crawler access to sensitive or irrelevant parts of the site
# Notes:
#  - Validated for Google and AdSense compliance
#  - Includes selective AI crawler disallow rules
#  - Multisite: TaSty, KACHEN, REESEN
#  - AI-training policy: This site disallows AI model training crawlers.

# ------------------------------------------------------------
# General rules for all user agents
# ------------------------------------------------------------
User-agent: *
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /?s=
Disallow: /comments/feed/
Allow: /wp-admin/admin-ajax.php
Allow: /wp-content/uploads/

# ------------------------------------------------------------
# Google crawlers (explicit allow for AdSense and Search)
# ------------------------------------------------------------
User-agent: Googlebot
Allow: /
User-agent: Googlebot-Mobile
Allow: /
User-agent: Googlebot-Image
Allow: /

# ------------------------------------------------------------
# Bing and major SEO crawlers
# ------------------------------------------------------------
User-agent: Bingbot
Allow: /
User-agent: AhrefsBot
Allow: /
User-agent: Amazonbot
Allow: /
User-agent: SemrushBot
Disallow: /
User-agent: MJ12bot
Allow: /
User-agent: DotBot
Allow: /

# ------------------------------------------------------------
# Pinterest crawler (for Rich Pins and sharing)
# ------------------------------------------------------------
User-agent: Pinterestbot
Allow: /
Crawl-delay: 2

# ------------------------------------------------------------
# AI, data-mining, and LLM crawlers (blocked)
# ------------------------------------------------------------
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: /
User-agent: PetalBot
Disallow: /
User-agent: SeekportBot
Disallow: /

# ------------------------------------------------------------
# Sitemaps
# ------------------------------------------------------------
Sitemap: https://luxetastestyle.online/sitemap_index.xml
Sitemap: https://kachen.online/sitemap_index.xml
Sitemap: https://reesen.online/sitemap_index.xml