# 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
# This robots.txt file is optimized for Magento 2.
# It is designed to provide a balanced approach to SEO, allowing search engines
# to crawl and index all public content while preventing access to
# administrative, system, and user-specific areas.
# ====================================================================
# Default Rules for all Search Engine Bots (e.g., Google, Bing, etc.)
# ====================================================================
User-agent: *
# Disallow access to backend, administrative, and system files.
# These directories are critical for the store's operation but should not be indexed.
Disallow: /admin/
Disallow: /app/
Disallow: /bin/
Disallow: /dev/
Disallow: /lib/
Disallow: /phpserver/
Disallow: /setup/
Disallow: /update/
Disallow: /var/
Disallow: /vendor/
Disallow: /errors/
# Disallow access to user-specific and internal process pages.
# It is a best practice to keep these private and out of search results.
Disallow: /checkout/
Disallow: /customer/
Disallow: /catalogsearch/
Disallow: /newsletter/
Disallow: /review/
Disallow: /wishlist/
Disallow: /downloader/
Disallow: /includes/
Disallow: /pkginfo/
Disallow: /report/
Disallow: /scripts/
Disallow: /shell/
# Disallow system files that should not be indexed.
Disallow: /cron.php
Disallow: /cron.sh
Disallow: /error_log
Disallow: /install.php
Disallow: /LICENSE.html
Disallow: /LICENSE.txt
Disallow: /STATUS.txt
Disallow: /mage
# ====================================================================
# Specific Rules for Googlebot
# ====================================================================
# We explicitly allow Googlebot to crawl CSS, JS, and image files in
# the /media/ and /static/ directories, which is crucial for
# mobile-first indexing and rendering.
User-agent: Googlebot
Allow: /media/
Allow: /static/
Allow: /catalog/
Allow: /product/
# ====================================================================
# Sitemaps
# ====================================================================
# Specify the location of your sitemap to help search engines discover your pages.
# Replace the URL below with the actual URL of your XML sitemap.
Sitemap: https://knockout.ee/sitemap_com_est.xml
Sitemap: https://knockout24.com/sitemap_com_rus.xml
Sitemap: https://knockout24.com/sitemap_com_eng.xml