# ----------------------------------------------------------------------
# Global default for all other crawlers (Applicable to both WordPress & AEM if paths match)
# ----------------------------------------------------------------------

User-agent: *
Allow: /
# Disallow WordPress admin area
Disallow: /wp-admin/
# Disallow common search query parameters to prevent duplicate content
Disallow: *?s=
Disallow: *&s=

# ----------------------------------------------------------------------
# AEM (Adobe Experience Manager) specific rules
# ----------------------------------------------------------------------

# Standard AEM authoring, system, and temporary paths
Disallow: /apps/
Disallow: /bin/
Disallow: /crx/
Disallow: /etc/
Disallow: /etc/clientlibs/
Disallow: /libs/
Disallow: /system/
Disallow: /tmp/
Disallow: /var/
# Disallow JCR content exposure
Disallow: /jcr:content/
# Disallow JCR content exposure in subpages
Disallow: /*/_jcr_content/
# Common AEM dispatcher cache invalidation path
Disallow: /_/
# Disallow AEM's infinity.json selectors
Disallow: /*.infinity.json$
Disallow: /*.tidy.json$
Disallow: /*.sysview.xml$
# If you have specific feeds to allow, add Allow rules before this
Disallow: /*.feed.xml$
#RITM0480998
Disallow: /content/experience-fragments/

# AEM DAM rules
# Allow specific legal PDFs in English
Allow: /content/dam/snowflake-site/en/legal/*.pdf

# Disallow other PDFs within the main snowflake-site DAM path
Disallow: /content/dam/snowflake-site/*.pdf

# Allow crawling of the general DAM path (if it contains browsable content or other allowed assets)
Allow: /content/dam/snowflake-site/

# ----------------------------------------------------------------------
# WordPress specific rules
# ----------------------------------------------------------------------

# Disallow theme directory
Disallow: /wp-content/themes/snowflake/

# Allow WordPress AJAX handler (important for some plugin/theme functionality)
Allow: /wp-admin/admin-ajax.php

# Disallow other common WordPress paths that don't need indexing
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
# WordPress REST API, usually not for direct crawling unless specific endpoints are public
Disallow: /wp-json/
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /trackback/
# If you want specific feeds crawled, use Allow rules. Otherwise, sitemap is preferred.
Disallow: /feed/
Disallow: */feed/$
Disallow: */trackback/$
Disallow: /*?replytocom=

# ----------------------------------------------------------------------
# Sitemap Directives
# ----------------------------------------------------------------------

Sitemap: https://www.snowflake.com/sitemap_index.xml
Sitemap: https://www.snowflake.com/content/snowflake-site/global.sitemap.xml