#
# 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

Sitemap: https://aiweekly.co/sitemap.xml
Sitemap: https://aiweekly.co/news-sitemap.xml
Sitemap: https://aiweekly.co/fr/sitemap.xml
Sitemap: https://aiweekly.co/es/sitemap.xml
Sitemap: https://aiweekly.co/pt/sitemap.xml

User-agent: Googlebot-News
Allow: /alerts/
Allow: /issues/

# ──────────────────────────────────────────────────────────────────
# AI crawlers — explicitly welcomed. AI Weekly's whole value is being
# the cited source on AI news, so both the answer/citation crawlers and
# the training/index crawlers get full access to editorial content
# (everything except admin / API / search / user paths). A named
# user-agent group does NOT inherit "User-agent: *", so this group
# carries its own ruleset. Consecutive User-agent lines share the rules
# beneath them (standard robots.txt grouping).
# ──────────────────────────────────────────────────────────────────
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: GPTBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: CCBot
User-agent: Bytespider
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
Disallow: /admin/
Disallow: /node/add/
Disallow: /comment/reply/
Disallow: /search/
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout
Disallow: /media/oembed
Disallow: /*/media/oembed
Disallow: /api/
Allow: /

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
# API endpoints — machine-readable, not for indexing
Disallow: /api/