# block unwanted bots
User-agent: SemrushBot
User-agent: AhrefsBot
User-agent: DataForSeoBot
User-agent: UptimeRobot
User-agent: relemindbot
User-agent: Applebot
User-agent: Amazonbot
User-agent: SeekportBot
User-agent: Yandex
User-agent: claudebot
User-agent: Claude-Web
User-agent: PerplexityBot
User-agent: RyteBot
User-agent: dotbot
User-agent: DataForSeoBot
User-agent: trendictionbot
User-agent: MJ12bot
User-agent: Paqlebot
User-agent: CriteoBot
User-agent: Verity
User-agent: GumGum-Bot
User-agent: peer39_crawler
User-agent: newsgrab.de
User-agent: Beloud
User-agent: captify-crawler
User-agent: Mediatoolkitbot
Disallow: /

# ChatGPT Plugins
User-agent: ChatGPT-User
Disallow: /

User-agent: GPTBot
Disallow: /

# Common Crawl
User-agent: CCBot
Disallow: /

# Bard
User-agent: Google-Extended
Disallow: /

# Meta’s bot that crawls public web pages to improve language models for their speech recognition technology
User-agent: FacebookBot
Disallow: /

# Used for several purposes, apparently also selling crawled data to LLM companies (http://omgili.com/crawler.html)
User-agent: omgilibot
Disallow: /

User-agent: omgili
Disallow: /

# urls with ?egy_cid= are not crawled
User-agent: *
Disallow: /*?egy_cid=*

User-agent: *
Disallow: /api/
Disallow: /archive/
Disallow: /na/
Disallow: /service/profil/
Disallow: /aidapreview/
Sitemap: https://www.allgemeine-zeitung.de/index-sitemap.xml