# 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

# Universal robots.txt for WordPress, WooCommerce, and Elementor websites

User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

Disallow: /wp-content/cache/
Allow: /wp-content/uploads/

Disallow: /trackback/
Disallow: /cgi-bin/
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt

# Low-value WordPress crawl areas
Disallow: /feed/
Disallow: /comments/
Disallow: /comment-page-
Disallow: /category/*/feed/
Disallow: /tag/*/feed/
Disallow: /author/*/feed/
Disallow: /search/
Disallow: /?s=
Disallow: /*?s=

# WooCommerce crawl-trap control
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /*?*add-to-cart=
Disallow: /*?*wc-ajax=
Disallow: /*?*filter_
Disallow: /*?*filter_cat=
Disallow: /*?*orderby=
Disallow: /*?*on_sale=
Disallow: /*?*stock_status=
Disallow: /*?*min_price=
Disallow: /*?*max_price=

# Tracking/query URL cleanup
Disallow: /*?*utm_
Disallow: /*?*fbclid=
Disallow: /*?*gclid=
Disallow: /*?*msclkid=

# Block non-essential Meta crawlers
User-agent: meta-webindexer
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: meta-externalfetcher
Disallow: /

Sitemap: https://imperialee.edu.au/sitemap_index.xml