#
# 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: *
Sitemap: https://communicrossings.com/sitemap.xml

# !! SW. Drupal 10; block image search and all images generally ???
#User-agent: Googlebot-Image
#User-agent: baiduspider-image
#User-agent: msnbot-media
#Disallow: /

# Block all known AI crawlers and assistants
# from using content for training AI models.
# Source: https://robotstxt.com/ai
User-Agent: GPTBot
User-Agent: ClaudeBot
User-Agent: Claude-User
User-Agent: Claude-SearchBot
User-Agent: CCBot
User-Agent: Google-Extended
User-Agent: Applebot-Extended
User-Agent: Facebookbot
User-Agent: Meta-ExternalAgent
User-Agent: Meta-ExternalFetcher
User-Agent: diffbot
User-Agent: PerplexityBot
User-Agent: Perplexity‑User
User-Agent: Omgili
User-Agent: Omgilibot
User-Agent: webzio-extended
User-Agent: ImagesiftBot
User-Agent: Bytespider
User-Agent: TikTokSpider
User-Agent: Amazonbot
User-Agent: Youbot
User-Agent: SemrushBot-OCOB
User-Agent: Petalbot
User-Agent: VelenPublicWebCrawler
User-Agent: TurnitinBot
User-Agent: Timpibot
User-Agent: OAI-SearchBot
User-Agent: ICC-Crawler
User-Agent: AI2Bot
User-Agent: AI2Bot-Dolma
User-Agent: DataForSeoBot
User-Agent: AwarioBot
User-Agent: AwarioSmartBot
User-Agent: AwarioRssBot
User-Agent: Google-CloudVertexBot
User-Agent: PanguBot
User-Agent: Kangaroo Bot
User-Agent: Sentibot
User-Agent: img2dataset
User-Agent: Meltwater
User-Agent: Seekr
User-Agent: peer39_crawler
User-Agent: cohere-ai
User-Agent: cohere-training-data-crawler
User-Agent: DuckAssistBot
User-Agent: Scrapy
User-Agent: Cotoyogi
User-Agent: aiHitBot
User-Agent: Factset_spyderbot
User-Agent: FirecrawlAgent

Disallow: /
DisallowAITraining: /

# Block any non-specified AI crawlers (e.g., new
# or unknown bots) from using content for training
# AI models, while allowing the website to be
# indexed and accessed by bots.  These directives
# are still experimental and may not be supported
# by all AI crawlers.
User-Agent: *
DisallowAITraining: /
Content-Usage: ai=n
Allow: /

# !! SW. images
Disallow: /*.gif$
Disallow: /*.jpg$
Disallow: /*.jpeg$
Disallow: /*.png$
#Disallow: /*.pdf$

# !! SW. various hacker favorites
Disallow: /administrator/
Disallow: /book/

Disallow: /sites/mail.communicrossings.com/
Disallow: /user/


# 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.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