# Open Well Records. Terms of use: /terms/ . Licence: CC BY-NC 4.0 (commercial use, including AI training, needs prior
# written permission (contact@openwellrecords.org, /permission/).
# Text and data mining rights in the data files (/data/) are reserved under Art. 4(3) Directive (EU) 2019/790.
# Crawlers that collect AI training data: not allowed anywhere.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Bytespider
User-agent: CCBot
User-agent: cohere-training-data-crawler
User-agent: MistralAI-Training
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: PanguBot
User-agent: DeepSeekBot
User-agent: Diffbot
User-agent: omgili
User-agent: omgilibot
User-agent: Webzio-Extended
User-agent: Timpibot
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: LAIONDownloader
User-agent: laion-huggingface-processor
User-agent: YandexAdditional
User-agent: YandexAdditionalBot
User-agent: ICC-Crawler
User-agent: Cotoyogi
User-agent: SBIntuitionsBot
User-agent: BeansLLM-CorpusBot
User-agent: recraft-image-dataset
User-agent: __usage_ai-training
Disallow: /

# Other AI and dataset crawlers: pages yes, data files no.
User-agent: Google-CloudVertexBot
User-agent: CloudVertexBot
User-agent: TikTokSpider
User-agent: DoubaoBot
User-agent: cohere-ai
User-agent: xAI-Grok
User-agent: QwenBot
User-agent: ERNIEBot
User-agent: Hunyuan
User-agent: MoonshotBot
User-agent: KimiBot
User-agent: YiBot
User-agent: ChatGLM-Spider
User-agent: ElevenlabsCrawler
User-agent: Factset_spyderbot
User-agent: Brightbot
User-agent: FirecrawlAgent
User-agent: ApifyBot
User-agent: ApifyWebsiteContentCrawler
User-agent: Crawl4AI
User-agent: CloudflareBrowserRenderingCrawler
User-agent: Crawlspace
User-agent: CragCrawler
User-agent: BixelBot
User-agent: HenkBot
User-agent: AgentDataBot
User-agent: TerraCotta
User-agent: ShapBot
User-agent: VelenPublicWebCrawler
User-agent: FriendlyCrawler
User-agent: ISSCyberRiskCrawler
User-agent: Panscient
User-agent: panscient.com
User-agent: aiHitBot
User-agent: YaK
User-agent: EchoboxBot
User-agent: Awario
User-agent: WARDBot
User-agent: NagetBot
User-agent: Thinkbot
User-agent: QuillBot
User-agent: quillbot.com
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SWA
User-agent: amazon-kendra
User-agent: bedrockbot
User-agent: Cloudflare-AutoRAG
User-agent: Amazonbot
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: YouBot
User-agent: ExaBot
User-agent: ExaSearchBot
User-agent: TavilyBot
User-agent: LinkupBot
User-agent: Scrapy
User-agent: Kangaroo Bot
User-agent: Brightbot 1.0
User-agent: Sidetrade indexer bot
User-agent: Echobot Bot
User-agent: Datenbank Crawler
User-agent: netEstate Imprint Crawler
User-agent: Poseidon Research Crawler
User-agent: Terra Cotta
User-agent: Linguee Bot
User-agent: CohereBot
User-agent: MistralBot
User-agent: KimiCrawler
User-agent: MoonSpider
User-agent: imageSpider
User-agent: ImageBot
User-agent: micro-crawl
User-agent: SalamandraVLM
User-agent: Reflectionbot
User-agent: LCC
User-agent: Spider
User-agent: MyCentralAIScraperBot
User-agent: newsai
User-agent: Lightpanda
User-agent: AgentTimes
User-agent: artsdata-crawler
User-agent: DesearchBot
User-agent: Quartr Crawler
User-agent: SofyaBot
User-agent: TalarionFrontierCrawler
User-agent: KeenableBot
User-agent: Keenable-User
User-agent: Mozilla-Tabstack
User-agent: QueritBot
User-agent: Querit-SearchBot
User-agent: ScryBot
User-agent: KunatoCrawler
User-agent: WRTNBot
User-agent: Aranet-SearchBot
User-agent: SomethinggBot
User-agent: ZenphonyBot
User-agent: iAskBot
User-agent: iaskspider
User-agent: wpbot
User-agent: BuddyBot
User-agent: FishBot
User-agent: Novellum
User-agent: NavuBot
User-agent: SelectikaScraper
User-agent: BorderxBot
User-agent: CitibotSiteCrawler
User-agent: ygs-scraper-bot
User-agent: magpie-crawler
User-agent: web-image-collection-research
User-agent: AgentQL
User-agent: Browser Use
User-agent: Skyvern
User-agent: Stagehand
User-agent: Bytebot
User-agent: PulsarRPA
User-agent: Thordata
User-agent: AIBot
User-agent: Aipbot
User-agent: GigaChat
User-agent: Genspark
User-agent: IbouBot
User-agent: KomoBot
User-agent: Paperlibot
User-agent: SummalyBot
User-agent: trafilatura
User-agent: jina-ai
User-agent: Grok-DeepSearch
User-agent: AISearchBot
User-agent: AgentRadar-Research
User-agent: IBM-Watson-NLU
User-agent: TextRazor Downloader
User-agent: ArenaUnfurlBot
User-agent: LMArenaUnfurlBot
User-agent: KimeBot
User-agent: Qwairy-Bot
User-agent: RankshiftFetcher
User-agent: PoweredByBot
User-agent: NeuwoBot
User-agent: osentix-crawler
User-agent: QuuuBot
User-agent: GroovinaAdsbot
Disallow: /data/
Allow: /

User-agent: *
Allow: /
Sitemap: https://openwellrecords.org/sitemap.xml