# 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: CloudflareBrowserRenderingCrawler
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: GPTBot
Disallow: /
User-agent: meta-externalagent
Disallow: /
# END Cloudflare Managed Content
# Sitemaps
Sitemap: https://www.brothers-brick.com/sitemap_index.xml
# Good bots - full access (except share links)
User-agent: Googlebot
Allow: /
Disallow: /*?share=
Disallow: /*&share=
User-agent: bingbot
Allow: /
Disallow: /*?share=
Disallow: /*&share=
User-agent: Slurp
Allow: /
Disallow: /*?share=
Disallow: /*&share=
User-agent: Pinterestbot
Allow: /
Disallow: /*?share=
Disallow: /*&share=
User-agent: Mediapartners-Google*
Disallow:
# Bad bots but maybe important, slow them down
User-agent: Verity
Crawl-delay: 10
# Amazonbot - allow articles, block API and attachment spam
User-agent: Amazonbot
Crawl-delay: 10
Disallow: /wp-json/oembed/
Disallow: /*?attachment_id=
# SEO crawlers - generate load with no reader benefit
User-agent: Sogou
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: AhrefsBot
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: BLEXBot
Disallow: /
# AI training crawlers
User-agent: GPTBot
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: GoogleOther
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: Claude-User
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: YouBot
Disallow: /
User-agent: DeepSeekBot
Disallow: /
# Ad verification crawlers - allow (needed for ad revenue)
# peer39_crawler, IAS Crawler - don't block these
# Global rules for all other bots
User-agent: *
Crawl-delay: 2
# WordPress core
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /xmlrpc.php
Allow: /wp-admin/admin-ajax.php
# Share and attachment spam
Disallow: /*?share=
Disallow: /*&share=
Disallow: /*?attachment_id=
Disallow: /*&replytocom=
Disallow: /*?relatedposts=
# Pagination (reduces crawl of duplicate content)
Disallow: /tag/*/page/
Disallow: /category/*/page/
Disallow: /author/*/page/
Disallow: /page/
# Legacy rules
Disallow: /wp-content/plugins/
Disallow: /readme.html
Disallow: /cgi-bin/
Disallow: /privacy/
Disallow: /terms-of-service/
Disallow: /downloads/
Disallow: /ads/
Disallow: /graphics/
Disallow: */comment-page-*
# Feeds and trackbacks
Disallow: */feed/
Disallow: */trackback/
Disallow: /rss/
# File extensions
Disallow: /*.php$
Disallow: /*.inc$