# 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

# NOTICE: Automated scraping and unauthorized data collection is prohibited
# except for search engine indexing or with explicit permission.

# Allow all essential bots for SEO
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /xmlrpc.php
Disallow: /cgi-bin/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/

# Block duplicate query parameters (use canonical for SEO)
Disallow: /*?replytocom=
Disallow: /*?add-to-cart=
Disallow: /*?utm_

# Allow CSS & JS for proper rendering
Allow: /*.css$
Allow: /*.js$

# Major Search Engines
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Yandex
Allow: /

# AI & Extended Bots (only trusted)
User-agent: Google-Extended
Allow: /
User-agent: GPTBot
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: meta-externalagent
Allow: /

# Disallow aggressive AI scrapers
User-agent: Bytespider
Disallow: /
User-agent: Amazonbot
allow: /
User-agent: CCBot
allow: /

# Optional: Crawl Delay for all others (prevents overload)
Crawl-delay: 10

# Sitemap for indexing
Sitemap: https://www.amarpackaging.com/sitemap_index.xml