Infrastructure

# www.robotstxt.org/
# www.google.com/support/webmasters/bin/answer.py?hl=en&answer=156449

# Ziff Davis content is made available for your non-commercial use subject to our
# Terms of Use here: https://www.ziffdavis.com/terms-of-use
# Use of any robot, crawler, or other tool to scrape, harvest, extract, or retrieve any content on
# this website using automated means is prohibited without written permission from Ziff Davis.
# Prohibited uses include but are not limited to:
# (1) text and data mining under Art. 4 of the EU Directive on Copyright in the Digital Single
# Market;
# (2) development or operation of artificial intelligence or machine learning software or
# databases, including by training, fine-tuning, embedding, and retrieval-augmented generation;
# (3) creating data sets containing our content or sharing it with others; and
# (4) any commercial purposes.
# Contact licensing@ziffdavis.com for assistance.

User-agent: *

Disallow: /user/*
Disallow: /members/
Disallow: /members/newsletters/
Disallow: /members/alerts/add/
Disallow: /search/
Disallow: *Xhr*
Disallow: */xhr*
Disallow: */ajax/*
Disallow: */fly/*/bundles/flyjs/*
Disallow: */libs/*
Disallow: */version!libs/*
Disallow: /.well-known/*
Disallow: /index.php/*
Disallow: *?beta=*
Disallow: *?ftag=*

User-agent: msnbot
Crawl-delay: 1

# Ziff Davis bot list
User-agent: AddSearchBot
User-agent: AI2Bot
User-Agent: Ai2Bot-DeepResearchEval
User-agent: Ai2Bot-Dolma
User-agent: Amazonbot
User-agent: AmazonBuyForMe
User-Agent: Anchor Browser
User-agent: anthropic-ai
User-agent: Applebot
User-agent: Applebot-extended
User-Agent: atlassian-bot
User-Agent: AutoRAG
User-agent: AwarioSmartBot
User-Agent: Big Sur AI
User-agent: bigsur.ai
User-Agent: Brandwatch
User-Agent: Bravebot
User-agent: Bytespider
User-agent: CCBot
User-agent: Channel3Bot
User-agent: ChatGLM-Spider
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: ClaudeBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: Crawl4AI
User-agent: Datenbank Crawler
User-agent: DeepSeekBot
User-agent: Devin
User-agent: Diffbot
User-Agent: Direqt Anomura
User-agent: DuckAssistBot
User-Agent: Echobot Bot
User-agent: FacebookBot
User-Agent: Factset_spyderbot
User-agent: GPTBot
User-agent: iAsk
User-agent: iaskspider
User-Agent: ICC Crawler
User-agent: ICC-Crawler
User-agent: ImageSiftBot
User-agent: imageSpider
User-agent: Kangaroo Bot
User-Agent: KlaviyoAIBot
User-agent: Kunato
User-agent: laion-huggingface-processor
User-agent: LCC
User-Agent: LINER Bot
User-agent: LinerBot
User-agent: LinkupBot
User-agent: Manus-User
User-agent: meta-externalagent
User-agent: meta-externalfetcher
User-Agent: meta-webindexer
User-agent: mistral.ai
User-agent: MistralAI-User
User-agent: netEstate Imprint Crawler
User-agent: NovaAct
User-Agent: Novellum AI Crawl
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: PanguBot
User-agent: PeopleInc-DCipher-Scraper/1.1.0
User-agent: Perplexity-User
User-agent: PerplexityBot
User-agent: PetalBot
User-agent: Poggio-Citations
User-agent: QualifiedBot
User-agent: SBIntuitionsBot
User-agent: SeekrBot
User-Agent: SemrushBot-OCOB
User-Agent: SemrushBotSwa
User-Agent: ShapBot
User-agent: Spider
User-agent: TavilyBot
User-agent: Timpibot
User-agent: TwinAgent
User-agent: Velen Crawler
User-Agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: Wrtn
User-agent: YouBot
User-agent: ZanistaBot

Allow: /article/how-ai-companies-are-secretly-collecting-training-data-from-the-web-and-why-it-matters/
Allow: /article/how-proxy-servers-actually-work-and-why-theyre-so-valuable/
Allow: /article/how-to-remove-your-personal-information-from-whitepages-in-5-steps-and-why-you-should/
Allow: /article/how-to-undo-a-reconciliation-in-quickbooks-online-the-easy-way/
Allow: /article/i-found-the-easiest-way-to-delete-myself-from-the-internet-and-why-you-shouldnt-wait-to-use-it-too/
Allow: /article/incogni-vs-deleteme/
Allow: /article/this-proxy-provider-i-tested-is-the-best-for-web-scraping-and-its-not-iproyal-or-marsproxies/
Disallow: /

# ZDnet bot list
User-agent: "008"
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: DDM-DCipher/1.0.7
User-agent: HTTrack
User-agent: Magpie-crawler
User-agent: Nutch
User-agent: Offline Explorer
User-agent: Omgilibot
User-agent: Peer39_crawler/1.0
User-agent: Scrapy
Disallow: /

Sitemap: https://www.zdnet.com/sitemaps/news.xml
Sitemap: https://www.zdnet.com/sitemaps/topics.xml
Sitemap: https://www.zdnet.com/sitemaps/article/index.xml
Sitemap: https://www.zdnet.com/sitemaps/gallery/index.xml
Sitemap: https://www.zdnet.com/sitemaps/video/index.xml
Sitemap: https://www.zdnet.com/sitemaps/review/index.xml