#
# 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.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
# 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
# Junk query-string crawl traps (spam/injection leftovers indexed by Google)
Disallow: /*?h=
Disallow: /*quot
Disallow: /*qt-qulanichlar=
# Domain-parking / scraper-injected params (teaminternet "ts=", AppAgg "from=", FB "fbclid=")
Disallow: /*?ts=
Disallow: /*&ts=
Disallow: /*?from=
Disallow: /*&from=
Disallow: /*fbclid=
# Legacy / low-value paths
Disallow: /node/*/backlinks
Disallow: /user/
Disallow: /users/
# JSON APIs. They serve the mobile app and the reader's word lookup; every one
# of them returns data that already exists on an HTML page, so crawling them
# only produces duplicate, unrenderable URLs. /api/v1/library/lookup is the
# worst of them: one URL per word of every book. X-Robots-Tag: noindex is set
# on the responses as well, for anything that reaches them without reading this.
Disallow: /api/
# Narration files: mp3 audio and the word-timing JSON that drives the
# highlighting. The reader pages carry the whole chapter text in their HTML —
# that is the asset worth crawling; these are the raw media behind it, and the
# sync files are megabytes of coordinates with no reader.
Disallow: /sites/default/files/audiobooks/

# AI search crawlers — explicitly allowed
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bingbot
Allow: /

# AI training-only crawlers — blocked
User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

Sitemap: https://ana-yurt.com/sitemap.xml