# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
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

##############################
# GOOGLE-SAFE + TOOL-FRIENDLY
##############################

User-agent: Googlebot
Allow: /catalog/view/theme/journal3/assets/
Allow: /image/catalog/
Allow: /*.html$
Disallow: /tag/
Disallow: /*?route=product/search

User-agent: Googlebot-Image
Allow: /image/catalog/
Disallow: /admin/
Disallow: /system/
Disallow: /vqmod/
Disallow: /cache/
Disallow: /logs/
Disallow: /storage/

###############################################
# ALL BOTS (Website Auditor, Ahrefs, ScreamingFrog)
###############################################
User-agent: *

# ✔ Allow ALL clean URLs so tools stop marking them blocked
Allow: /*.html$
Allow: /product/
Allow: /category/
Allow: /information/
Allow: /contact/
Allow: /account/login
Allow: /account/register
Allow: /image/catalog/

# ❗ Block only BAD parameters (the safe list)
Disallow: /*?route=checkout
Disallow: /*?route=account
Disallow: /*?route=affiliate
Disallow: /*?route=product/search

# Keep only the 3 unavoidable bad params:
Disallow: /*?page=
Disallow: /*?limit=
Disallow: /*?sort=

# Remove ALL other wildcard blocks (tools hated those)

##############################
# System folders
##############################
Disallow: /admin/
Disallow: /system/
Disallow: /catalog/controller/
Disallow: /catalog/model/
Disallow: /vqmod/
Disallow: /storage/
Disallow: /download/
Disallow: /logs/
Disallow: /config.php
Disallow: /admin/config.php

##############################
# Journal3 internal AJAX
##############################
# Let Google and tools access CSS/JS, block only heavy AJAX
Allow: /index.php?route=journal3/assets
Allow: /index.php?route=journal3/css
Allow: /index.php?route=journal3/js
Disallow: /index.php?route=journal3/blog_feed
Disallow: /index.php?route=journal3/sitemap

##############################
# Sitemap
##############################
Sitemap: https://biomall.bg/index.php?route=feed/advanced_sitemap

##############################
# AI Crawlers
##############################
#AI: https://biomall.bg/llms.txt