#
# robots.txt
#
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/robotstxt.html

User-agent: *
Allow: /*.css$
Allow: /*.js$
Allow: /*.gif$
Allow: /*.jpe?g$
Allow: /*.png$
Allow: /*.svg$

# Core back-office pages
Disallow: /admin/
Disallow: /user/
Disallow: /comment/reply/
Disallow: /node/add/
Disallow: /filter/tips
Disallow: /search/
Disallow: /media/oembed
Disallow: /*/media/oembed

# Same paths when someone forces /index.php/ (no-clean URLs)
Disallow: /index.php/*

# Entire code-base folders
Disallow: /core/
Disallow: /profiles/
Disallow: /modules/
Disallow: /themes/
Disallow: /vendor/

# One-off sensitive files
Disallow: /xmlrpc.php
Disallow: /web.config
Disallow: /README*

Sitemap: https://www.discovergreece.com/sitemap.xml
# LLM guidance: https://www.discovergreece.com/llms.txt