#
# 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


# Allow specific search engine bots
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-Mobile
User-agent: Googlebot-News
User-agent: Googlebot-Video
User-agent: AdsBot-Google

# 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

# Explicitly block other aggressive crawlers found in logs
User-agent: AASA-Bot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: AliyunSecBot
Disallow: /

User-agent: bingbot
Crawl-delay: 10

User-agent: CCBot
Disallow: /

User-agent: DuckAssistBot
Disallow: /

User-agent: DuckDuckBot
Disallow: /

User-agent: FullStoryBot
Disallow: /

User-agent: LamarkBot
Disallow: /

User-agent: LivelapBot
Disallow: /

User-agent: Mediatoolkitbot
Disallow: /

User-agent: MoodleBot
Disallow: /

User-agent: SEBot-WA
Disallow: /

User-agent: Sleuth
Disallow: /

User-agent: Sogou
Disallow: /

User-agent: SottopopNone
Disallow: /

User-agent: StartmeBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Turnitin
Disallow: /

User-agent: Twitterbot
Disallow: /

User-agent: UnsplashBot
Disallow: /

User-agent: YisouSpider
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: adbeat-check-access-script
Disallow: /

User-agent: daumoa
Disallow: /

User-agent: dobot
Disallow: /


User-agent: meta-externalagent
Disallow: /

User-agent: meta-webindexer
Disallow: /

# Block all other bots
User-agent: *
Crawl-delay: 10
Disallow: /