# 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: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# =====================================================================
# robots.txt - Khushbindu Technologies (KIT)
# https://khushbindutechnologies.com
# =====================================================================

# --- Default: allow everything except internal dirs ---
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /content/
Disallow: /scripts/
Disallow: /blogs/tag/
Disallow: /css/*.map$
Disallow: /js/*.map$

# --- Googlebot: full access, no crawl-delay ---
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /img/
Allow: /blogs/

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

# --- Block AI training scrapers that don't respect noindex ---
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: FacebookExternalHit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Twitterbot
Allow: /

# --- Sitemaps ---
Sitemap: https://khushbindutechnologies.com/sitemap.xml

# --- Host (Yandex) ---
Host: https://khushbindutechnologies.com