# 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

User-agent: *

Disallow: /wp-admin/

Allow: /wp-admin/admin-ajax.php

Sitemap: https://sanimoo.com/sitemap_index.xml

Sitemap: https://sanimoo.com/mag/sitemap.xml

# Block preview pages
Disallow: /*?preview=true

# Block AMP versions (if AMP is not in use)
Disallow: /*?amp=

Disallow: /amp/

# Block search pages and their parameters
Disallow: /?s=

Disallow: /search/

Disallow: /search/*

# Block magazine category archives
# ENABLED-FOR-INDEXING: Disallow: /mag/category/

Disallow: /mag/?amp=*

# Block internal WordPress paths that don't need crawling


Disallow: /wp-content/cache/


Disallow: /xmlrpc.php

Disallow: /trackback/

# Block product filter parameters (attributes, size, color, etc.)
# Note: the * before each parameter name matches it anywhere in the query string,
# not just when it's the first parameter (this was the bug in the previous version)
Disallow: /*?*attribute_pa_*

Disallow: /*?*query_type_*

# TEMP-DISABLED-FOR-DEINDEX: Disallow: /*?*filter_*

Disallow: /*?*source_*

Disallow: /*?*variation_id=*

Disallow: /*?*orderby=*

Disallow: /*?*per_page=*

Disallow: /*?*paged=*

# TEMP-DISABLED-FOR-DEINDEX: Disallow: /*?*max_price=*

# TEMP-DISABLED-FOR-DEINDEX: Disallow: /*?*min_price=*

# TEMP-DISABLED-FOR-DEINDEX: Disallow: /*?*stock_status=*

# Block duplicate/low-value shop pages
Disallow: /shop/page/

Disallow: /shop/*?*filter_*

# Block site feeds and RSS pages
Disallow: /*/feed/

Disallow: /*?feed=

Disallow: /*/rss/

Disallow: /*?rss

# Block order tracking and account pages
Disallow: /order-tracking/

Disallow: /login/

Disallow: /my-account/

Disallow: /account/

Disallow: /checkout/

Disallow: /cart/

# Block UTM tracking parameters
Disallow: /*?*utm_source=*

Disallow: /*?*utm_medium=*

Disallow: /*?*utm_campaign=*

# Block pagination and unnecessary archive pages

Disallow: /category/*/page/

Disallow: /tag/*/page/

Disallow: /author/*/page/

# Block add-to-cart action pages
Disallow: /?add-to-cart

Disallow: /*?*add-to-cart=*

# Allow Google to index important site images
Allow: /wp-content/uploads/*.jpg

Allow: /wp-content/uploads/*.png

Allow: /wp-content/uploads/*.gif

Allow: /wp-content/uploads/*.svg

Allow: /wp-content/uploads/*.webp