# 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

# ── 1. GOOGLEBOT: full access, no Disallow, but request a modest delay
User-agent: Googlebot
Disallow:
Crawl-delay: 10

# ── 2. BINGBOT: full access, but request slower crawl
User-agent: bingbot
Disallow:
Crawl-delay: 10

# ── 3. OTHER “POLITE” SEARCH CRAWLERS (if you want to allow them similarly)
#   (e.g. DuckDuckBot, Yandex, etc.; add here if desired)
#User-agent: DuckDuckBot
#Disallow:
#Crawl-delay: 10

# ── 4. BLOCK “BAD” / RESOURCE‐INTENSIVE BOT UAs ENTIRELY
User-agent: CCBot
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GeedoProductSearch
Disallow: /

User-agent: serpstatbot
Disallow: /

# ── 5. DEFAULT RULES FOR ALL OTHER CRAWLERS
User-agent: *
# Block sensitive WooCommerce upload directories
Disallow: /wp-content/uploads/wc-logs/
Disallow: /wp-content/uploads/woocommerce_uploads/
Disallow: /wp-content/uploads/woocommerce_transient_files/

# Block internal search result pages
Disallow: /?s=
Disallow: /search/
Disallow: /page/*/?s=

# Block add-to-cart URLs (so bots don’t index cart actions)
Disallow: /*add-to-cart=*

# Block RSS and comment feeds to reduce duplicate/low-value content
Disallow: /feed/
Disallow: */feed/
Disallow: /comments/feed/

# Block WordPress admin area, but still allow AJAX functionality
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# Allow access to uploads (images, PDFs, etc.)
Allow: /wp-content/uploads/

# Point to your sitemap
Sitemap: https://biomazing.ch/sitemaps.xml

User-agent: *
Disallow: /*add_to_wishlist=*
Disallow: /*add-to-cart=*

# Default WooCommerce rules
user-agent: *
Disallow: /wp-content/uploads/wc-logs/
Disallow: /wp-content/uploads/woocommerce_transient_files/
Disallow: /wp-content/uploads/woocommerce_uploads/

# Default WP rules
user-agent: *
disallow: /wp-admin/
allow: /wp-admin/admin-ajax.php

User-agent: *
Disallow: /*?filter_*