# 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: /admin/
Disallow: /seller/

# Search Console reported 104,000 pages as "Blocked due to access forbidden
# (403)". Every one of them carried page= or sort_by=: a Cloudflare rule
# challenges those URLs, and a challenge answers anything that cannot run
# JavaScript with a 403, which is what Googlebot gets.
#
# Crawling them was never useful. Every listing can be sorted several ways and
# paged past a hundred, so the same products sit behind an endless number of
# addresses and the crawl budget goes there instead of on product pages. The
# three sitemaps carry 26,814 clean URLs with no parameters at all, so nothing
# is reachable only through a paginated link.
#
# The patterns have no ? or & in front on purpose. Written as /*?page= they only
# match when the parameter comes first, and a URL like ?other=1&page=3 slips
# past; without it both positions are covered. Checked against Protego, which
# implements Google's matching rules.
Disallow: /*page=
Disallow: /*sort_by=

Sitemap: https://www.romegamart.com/sitemap.xml
Sitemap: https://www.romegamart.com/sitemap2.xml
Sitemap: https://www.romegamart.com/sitemap3.xml