# 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

# =============================
# General settings for all bots
# =============================
User-agent: *
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /cgi-bin/
Disallow: /xmlrpc.php
Disallow: /wp-config.php
Disallow: /?s=
Disallow: /*add-to-cart=*

# =============================
# BLOCK FILTER/FACETED NAV PARAMETERS (Filter Everything PRO)
# Prevents index bloat from faceted navigation URLs.
# The specific parameter rules below cover all known attack vectors.
# Note: /*-or-* removed — too broad, blocks legitimate product slugs
# containing "or" (e.g. /product/kill-or-be-killed/) from Google indexing.
# OR-chain attacks are handled by Shield v3.5 and Cloudflare WAF instead.
# =============================
Disallow: /*product_cat-*
Disallow: /*variant_cover-*
Disallow: /*inc_ratio-*
Disallow: /*pre_order_cat-*
Disallow: /*cut_off-*

# =============================
# Crawl-delay for aggressive bots
# =============================
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: PetalBot
Crawl-delay: 10

User-agent: Baiduspider
Crawl-delay: 10

# =============================
# Block known bad bots entirely
# =============================
User-agent: Wget
Disallow: /

User-agent: curl
Disallow: /

User-agent: MJ12bot
Disallow: /

# =============================
# Facebook/Meta crawlers
# Crawl-delay removed — Meta's aggressive crawler attack is now blocked
# at the Cloudflare WAF level (ASN 2a03:2880:f800::/48).
# Filter parameter Disallows retained as a polite signal to well-behaved
# Meta crawlers and to preserve Facebook link preview functionality
# (facebookexternalhit needs access to product/homepage URLs for previews).
# =============================
User-agent: facebookexternalhit
User-agent: Facebot
Disallow: /*product_cat-*
Disallow: /*variant_cover-*
Disallow: /*inc_ratio-*
Disallow: /*pre_order_cat-*
Disallow: /*cut_off-*
Disallow: /*add-to-cart=*

# =============================
# Sitemap
# =============================
Sitemap: https://comicbookshop.co.nz/sitemap_index.xml