# robots.txt https://www.wn.de
User-agent: *
Disallow: /api/

# Disallow indexation of content copiers and other unwanted robots
User-agent: UbiCrawler
User-agent: DOC
User-agent: Zao
User-agent: sitecheck.internetseer.com
User-agent: Zealbot
User-agent: MSIECrawler
User-agent: SiteSnagger
User-agent: WebStripper
User-agent: WebCopier
User-agent: Amazonbot
User-agent: Offline Explorer
User-agent: Teleport
User-agent: TeleportPro
User-agent: WebZIP
User-agent: linko
User-agent: HTTrack
User-agent: Microsoft.URL.Control
User-agent: Xenu
User-agent: larbin
User-agent: libwww
User-agent: ZyBORG
User-agent: Download Ninja
User-agent: grub-client
User-agent: k2spider
User-agent: NPBot
User-agent: WebReaper
User-agent: CrystalSemanticsBot
User-agent: CompSpyBot
User-agent: Curious George
User-agent: CybEye.com
User-agent: DoCoMo
User-agent: ExB Language Crawler
User-agent: Ezooms
User-agent: Flamingo_SearchEngine
User-agent: Genieo
User-agent: Genio
User-agent: LWNutch
User-agent: LexxeBot
User-agent: OpenWebIndex
User-agent: RediffNewsBot
User-agent: SEOENGWorldBot
User-agent: Scanmine
User-agent: ShopWiki
User-agent: ShowyouBot
User-agent: Sosospider
User-agent: WocBot
User-agent: Yeti
User-agent: YoudaoBot
User-agent: daumoa
User-agent: gsa-crawler
User-agent: libcrawl
User-agent: linkdex
User-agent: magpie-crawler
User-agent: repparser
User-agent: rogerbot
User-agent: sindice-site-manager
User-agent: sogou spider
User-agent: sogou
User-agent: woriobot
User-agent: yacybot
User-agent: yolinkBot
User-agent: UnisterBot
User-agent: JikeSpider
User-agent: Orthogaffe
User-agent: Wget
User-agent: Yandex
user-agent: AhrefsBot
User-Agent: trendictionbot
User-agent: SeznamBot
User-agent: search:robot
User-agent: MJ12bot
User-agent: XoviBot
User-agent: xovi
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: GPTBot
User-agent: Cutbot
User-agent: TurnitinBot
User-agent: PiplBot
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
Disallow: /

# http://linkfluence.net/
User-agent: Kraken
Disallow: /

# AI and Data Analysis
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: CCBot
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: cohere-ai
User-agent: FacebookBot
User-agent: FriendlyCrawler
User-agent: Google-Extended
User-agent: iaskspider/2.0
User-agent: ICC-Crawler
User-agent: img2dataset
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: OAI-SearchBot
User-agent: OpenAI GPTBot
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: You.com Bot
User-agent: YouBot
User-agent: DataForSeoBot
User-agent: AwarioRssBot
User-agent: YandexBot
User-agent: NewsNow
User-agent: news-please
User-agent: Quora-Bot
Disallow: /

# Archiving and Data Collection
User-agent: CommonCrawler
User-agent: MegauploadBot
User-agent: NetcraftSurveyAgent
User-agent: archive.org_bot
User-agent: Arquivo-web-crawler
User-agent: peer39_crawler
User-agent: peer39_crawler/1.0
Disallow: /

# Data Extraction and Analysis
User-agent: CocoonBot
User-agent: DatanyzeBot
User-agent: Diffbot
User-agent: Favicon Checker
User-agent: GoogleOther
User-agent: Nutch
User-agent: omgili
User-agent: omgilibot
User-agent: Scrapy
User-agent: ZoominfoBot
User-agent: Scraping Robot
User-agent: Axiom AI
User-agent: Axiom
User-agnet: Spinn3r
Disallow: /

# Image Analysis
User-agent: ImagesiftBot
Disallow: /

# Bing
User-agent: bingbot
Crawl-delay: 2
Sitemap: https://www.wn.de/sitemaps/sitemap-index.xml
Sitemap: https://www.wn.de/sitemaps/newssitemap-index.xml