# Robots.txt for JournalsHub.online
# https://www.robotstxt.org/

User-agent: *
Allow: /

# Allow all major search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

# Allow AI crawlers for LLM indexing
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Anthropic-AI
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: CCBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Cohere-AI
Allow: /

# AdSense / AdMob crawlers — must reach every monetizable page + assets so
# ad targeting and policy review work. Explicitly allowed for re-review clarity.
User-agent: Mediapartners-Google
Allow: /

User-agent: AdsBot-Google
Allow: /

User-agent: AdsBot-Google-Mobile
Allow: /

# Disallow admin and private endpoints
Disallow: /admin/
Disallow: /subscribe/
Disallow: /autocomplete/

# Noindex, thin OpenAlex-backed pages: millions of author/paper/institution
# URLs that are noindex and deliberately 404 for crawlers (to save OpenAlex
# quota). Google was discovering them via internal links and wasting crawl
# budget on a 2M+ dead-URL space — the bulk of the "Not found (404)" report.
# Blocking them here stops that crawl waste and frees budget for the journal /
# hub / article pages we actually want indexed. Humans still reach them (robots
# does not block users); /papers/ (search) stays crawlable — the trailing slash
# scopes this to /paper/<id>/ only.
Disallow: /author/
Disallow: /paper/
Disallow: /institution/

# Crawl-delay for polite crawling
Crawl-delay: 1

# Sitemap location
Sitemap: https://journalshub.online/sitemap.xml

# LLMs.txt for AI models
# See: https://journalshub.online/llms.txt