User-agent: *
Crawl-delay: 8
Disallow: /_hp/
Disallow: /artist/
Disallow: /searchresults/

# This is the robots.txt file for News Broadcasting Onic brands.
# Onic and News Broadcasting does not permit the unlicensed use of our content for large language models.
# Terms of Use may be found at https://broadcasting.news/terms-of-use
# Contact enquiries@newslicensing.com for assistance.

User-agent: *
Disallow: /

User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-Video
User-agent: Googlebot-News
User-agent: Google-InspectionTool
User-agent: GoogleOther
User-agent: APIs-Google
User-agent: Mediapartners-Google
User-agent: DuckDuckBot
User-agent: Slurp
User-agent: Twitterbot
User-agent: Bingbot
User-agent: adidxbot
User-agent: MicrosoftPreview
User-agent: Applebot
User-agent: AdsBot-Google
User-agent: AmazonAdBot
User-agent: facebookexternalhit
User-agent: Yahoo Ad Monitoring
User-agent: parse.ly scraper
User-agent: Screaming Frog SEO Spider
User-agent: SemrushBot
User-agent: Botify
User-agent: Chrome-Lighthouse
User-agent: Slackbot-LinkExpanding
User-agent: Slack-ImgProxy
User-agent: Slackbot
User-agent: Snap URL Preview Service
User-agent: proximic
User-agent: GumGum-Bot
User-agent: ias_crawler
User-agent: outbrain
User-agent: Leikibot
User-agent: weborama-fetcher
User-agent: HyScore
User-agent: AHC
User-agent: SirdataBot
User-agent: peer39_crawler
User-agent: EchoboxBot
User-agent: CriteoBot
User-agent: AdDefend Site Context Crawler
User-agent: ChatGPT-User
User-agent: GPTBot
User-agent: NewsNow

Allow: /
Allow: /ads.txt

Disallow: /internal-use-only-how-to/
Disallow: /not-currently-used-features/

# Mirroring auto-gen disallows to maintain block for allowed UAs
Disallow: /_hp/
Disallow: /artist/
Disallow: /searchresults/


User-agent: facebookexternalhit
Allow: /

Sitemap: https://www.onic.ie/sitemap.xml