# NOTICE: The collection of content and other data on this
# site through automated means, including any device, tool,
# or process designed to data mine or scrape content, is
# prohibited except (1) for the purpose of search engine indexing or
# artificial intelligence retrieval augmented generation or (2) with express
# written permission from this site’s operator.
#
# To request permission to license our intellectual
# property and/or other materials, please contact this
# site’s operator directly.
#
# Policy mirror of config/bots.php — keep these in sync.

# ---------------------------------------------------------------
# Search engines & AI assistants — explicitly welcome
# (Crawl freely, respect the disallowed paths below.)
# ---------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yahoo
Allow: /

User-agent: Slurp
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: YouBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: CCBot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Amazonbot
Allow: /

# ---------------------------------------------------------------
# Aggressive SEO / data-harvester crawlers — blocked
# (Also enforced at HTTP level in App\Http\Middleware\AbortBadBots.)
# ---------------------------------------------------------------
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: MauiBot
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: Barkrowler
Disallow: /

User-agent: Cliqzbot
Disallow: /

User-agent: AspiegelBot
Disallow: /

User-agent: Exabot
Disallow: /

User-agent: WallabyupBot
Disallow: /

User-agent: SiteAuditBot
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: MeltwaterNews
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

# ---------------------------------------------------------------
# Default policy for everyone else (incl. social link-preview bots
# like facebookexternalhit, LinkedInBot, Twitterbot, Slackbot, etc.)
# ---------------------------------------------------------------
User-agent: *
Disallow: /seeker/
Disallow: /member/
Disallow: /preview-article/
Disallow: /search-results/
Disallow: /nova-helper/
Disallow: /extend-session
Disallow: /impersonation
Disallow: /advertiser/
Disallow: /mob/
Disallow: /posts/tag/
Disallow: /events/tag/

# Sitemap location for all bots
Sitemap: https://nit.com.au/sitemap.xml