# 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

# KCT Menswear Robots.txt
# Sitemap Locations (All 4 sitemaps for complete coverage)
Sitemap: https://kctmenswear.com/sitemap.xml
Sitemap: https://kctmenswear.com/sitemap-pages.xml
Sitemap: https://kctmenswear.com/sitemap-products.xml
Sitemap: https://kctmenswear.com/sitemap-blog.xml

# AI Training Bots
User-agent: GPTBot
Allow: /
Crawl-delay: 10

User-agent: ChatGPT-User
Allow: /
Crawl-delay: 10

User-agent: CCBot
Allow: /
Crawl-delay: 10

User-agent: anthropic-ai
Allow: /
Crawl-delay: 10

User-agent: Claude-Web
Allow: /
Crawl-delay: 10

# Major Search Engines
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: Slurp
Allow: /
Crawl-delay: 1

# Social Media Crawlers
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# Bad Bots - Block These
User-agent: MJ12bot
Disallow: /

User-agent: AhrefsBot
Disallow: /

# TEMPORARY: Allow SemrushBot for site audit
# User-agent: SemrushBot
# Disallow: /

User-agent: MauiBot
Disallow: /

User-agent: AlexaBot
Disallow: /

# Protected Areas
User-agent: *
Disallow: /admin/
Disallow: /api/
Disallow: /checkout/
Disallow: /account/orders/
Disallow: /*.json$
Disallow: /*?*utm_*
Disallow: /*?*sessionid*
Allow: /

# Crawl Delays
Crawl-delay: 5