#
# 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: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.md
Disallow: /composer/Metapackage/README.txt
Disallow: /composer/Plugin/ProjectMessage/README.md
Disallow: /composer/Plugin/Scaffold/README.md
Disallow: /composer/Plugin/VendorHardening/README.txt
Disallow: /composer/Template/README.txt
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/README.txt
Disallow: /web.config
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout
Disallow: /media/oembed
Disallow: /*/media/oembed
# Paths (no clean URLs)
Disallow: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/user/password
Disallow: /index.php/user/register
Disallow: /index.php/user/login
Disallow: /index.php/user/logout
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed


# MGoBlog additions (appended to core's robots.txt by drupal-scaffold —
# edit assets/scaffold/robots-additions.txt, not web/robots.txt, which is
# regenerated on every composer build).

# Comment permalinks render full thin-duplicate pages of their parent node
# and account for the bulk of crawler load at the origin.
Disallow: /comment/

# Junk multi-pager combos from the D6 era (?page=0,1,1,0,...) — Yahoo Slurp
# grinds thousands of these into 404s daily. The comma in the pattern means
# normal single-pager URLs (?page=2) stay crawlable. Slurp requests these
# URLs with the comma percent-encoded (?page=0%2C0%2C...), and RFC 9309
# normalization of reserved characters can't be assumed for legacy
# crawlers, so both spellings are listed.
Disallow: /*?page=*,*
Disallow: /*?page=*%2C*

# Machine-readable content policy (contentsignals.org): allow search
# indexing, disallow AI training. An express rights reservation under
# Article 4 of EU Directive 2019/790.
Content-Signal: search=yes, ai-train=no

Sitemap: https://mgoblog.com/sitemap.xml

# AI-training opt-outs. Google-Extended and Applebot-Extended are
# robots.txt-only tokens (Googlebot/Applebot do the crawling; these
# control AI-training use) — no WAF rule can express them.
User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

# AI-training crawlers. Most are also blocked at the Cloudflare WAF
# ("AI Crawl Control" rule, which exempts /robots.txt so they can read
# this); the robots entry asks them not to request pages at all.
User-agent: CCBot
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /