# 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

# Block bots.


User-agent: SemrushBot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: Mj12bot
Disallow: /
User-agent: AhrefsBot
Disallow: /
User-agent: BLEXBot
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: Sogou
Disallow: /
User-agent: MJ12Bot
Disallow: /

# Website Sitemap
Sitemap: https://www.speedcrete.co.uk/sitemap.xml

User-agent: Googlebot
Disallow:

User-agent: Googlebot-Image
Disallow: /
Allow: /media/catalog/product/

# Crawlers Setup
User-agent: *

# Directories
User-agent: *
Disallow: /app/
Disallow: /cgi-bin/
Disallow: /downloader/
Disallow: /includes/
Disallow: /lib/
Disallow: /pkginfo/
Disallow: /shell/
Disallow: /var/

# Paths (clean URLs)
User-agent: *
Disallow: /index.php/
Disallow: /catalog/product_compare/
Disallow: /catalog/category/view/
Disallow: /catalog/product/view/
Disallow: /catalogsearch/
Disallow: /checkout/
Disallow: /control/
Disallow: /customer/
Disallow: /customize/
Disallow: /review/
Disallow: /sendfriend/
Disallow: /wishlist/

# Files
User-agent: *
Disallow: /cron.php
Disallow: /cron.sh
Disallow: /error_log
Disallow: /install.php
Disallow: /LICENSE.html
Disallow: /LICENSE.txt
Disallow: /LICENSE_AFL.txt
Disallow: /api.php
Disallow: /get.php
Disallow: /mage


# Paths (no clean URLs)
User-agent: *
Disallow: /*.js$
Disallow: /*.css$
Disallow: /*.php$
Disallow: /*?p=*&
Disallow: /*?SID=