# 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

# ==============================================================================
# Default robots.txt for Magento 2
# ==============================================================================

# Allow all search engines full access initially.
# This rule also applies to AI bots since they are not explicitly blocked.
User-agent: *
Allow: /sitemap.xml
Allow: /sitemap/
Allow: /
User-agent: *
Disallow: /*.htm$

# General rules for all bots
User-agent: *

# Disallow technical and system folders/files
Disallow: /app/
Disallow: /bin/
Disallow: /dev/
Disallow: /lib/
Disallow: /phpserver/
Disallow: /pkginfo/
Disallow: /report/
Disallow: /setup/
Disallow: /update/
Disallow: /var/
Disallow: /vendor/
Disallow: /index.php
Disallow: /cron.php
Disallow: /cron.sh

# Disallow customer-specific and checkout paths
Disallow: /checkout/
Disallow: /customer/
Disallow: /wishlist/
Disallow: /newsletter/
Disallow: /sendfriend/
Disallow: /review/

# Disallow internal search results and filtering/sorting parameters
Disallow: /catalogsearch/
Disallow: /search/
Disallow: /tag/
Disallow: /*?dir=
Disallow: /*?limit=
Disallow: /*?mode=
Disallow: /*?order=

# Disallow other non-content pages
Disallow: /catalog/product_compare/
Disallow: /sales/guest/
Disallow: /downloadable/
Disallow: /no-route

# Sitemap location
Sitemap: https://nosugar.com.iq/sitemap.xml
Sitemap: https://nosugar.com.iq/sitemap/sitemap_ar.xml
Sitemap: https://nosugar.com.iq/sitemap/sitemap_en.xml
Sitemap: https://nosugar.com.iq/sitemap/blog_sitemap_ar.xml
Sitemap: https://nosugar.com.iq/sitemap/blog_sitemap_en.xml