# 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 for getindexchecker.com
# Last updated: 2026-04-01

User-agent: *
Allow: /

# Block admin and app areas from indexing
Disallow: /admin/
Disallow: /app/
Disallow: /api/
Disallow: /dashboard/
Disallow: /signin.html
Disallow: /signup.html
Disallow: /forgot-password.html
Disallow: /reset-password
Disallow: /login
Disallow: /signup
Disallow: /settings/
Disallow: /billing/

# Block search result and dynamic pages
Disallow: /search?
Disallow: /*?utm_
Disallow: /*?ref=
Disallow: /*?fbclid=
Disallow: /*?gclid=

# Allow static assets
Allow: /assets/
Allow: /*.css$
Allow: /*.js$
Allow: /*.svg$
Allow: /*.png$
Allow: /*.jpg$
Allow: /*.webp$

# Crawl delay for aggressive bots (in seconds)
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: MJ12bot
Crawl-delay: 10

# Block known bad bots
User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

# Sitemap location
Sitemap: https://getindexchecker.com/sitemap.xml