# 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

#
# robots.txt - Popeye's Supplements Canada
#
# The "User-agent: *" group governs general crawling. The legacy X-Cart
# boilerplate shipped a blanket "Disallow: /" here, which (merged per RFC 9309)
# blocked Googlebot from the entire site. That line is removed. Only non-public
# X-Cart internals are disallowed below.
#
# AI / LLM crawler policy (approved by Craig 2026-06-04): allow retrieval
# crawlers so the brand can be cited in ChatGPT, Claude, Perplexity and Google
# AI Overviews, and block training-only / bulk-scraping crawlers. The retrieval
# crawlers (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-User,
# PerplexityBot) are covered by the permissive "User-agent: *" group below; the
# training-only crawlers are denied in the explicit groups that follow. Edge
# enforcement for non-compliant scrapers is handled separately at Cloudflare.
#

# AI training / bulk-scraping crawlers (denied; retrieval crawlers stay allowed)
User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# General crawl policy
User-agent: *

# X-Cart internals (non-public)
Disallow: /Includes/
Disallow: /classes/
Disallow: /etc/
Disallow: /files/service/
Disallow: /lib/
Disallow: /sql/
Disallow: /modules_manager/
Disallow: /service/
Disallow: /upgrade/
Disallow: /var/export/
Disallow: /var/html/
Disallow: /var/import/
Disallow: /var/locale/
Disallow: /var/log/
Disallow: /var/run/
Disallow: /var/tmp/
Disallow: /support_dev/

# Non-public PHP entry points and error assets
Disallow: /admin.php
Disallow: /console.php
Disallow: /error_handler.php
Disallow: /https_check.php
Disallow: /install.php
Disallow: /LICENSE.txt
Disallow: /probe.php
Disallow: /public/error.css
Disallow: /public/error.html
Disallow: /public/error_image.png
Disallow: /top.inc.PHP53.php
Disallow: /top.inc.php
Disallow: /rebuild.php
Disallow: /service.php
Disallow: /top.inc.const.php
Disallow: /top.inc.rebuild.php

# Transactional / account pages (also carry meta robots noindex)
Disallow: /cart
Disallow: /checkout
Disallow: /account

Sitemap: https://www.popeyessupplements.com/sitemap.xml