# robots.txt for waikato.ac.nz # If you're a search engine or crawl operator and want to make contact with us - webmaster@waikato.ac.nz # default disallow rules for crawlers not grouped below # Rules are intentionally duplicated across User-agent groups below. # Per RFC 9309, crawlers apply only rules from a matching User-agent group; # The wildcard (*) group is used only if no other group matches. # Duplication is therefore required to enforce consistent Disallow rules. User-agent: * Disallow: /admin Disallow: /Security/ Disallow: /search/ Disallow: /int/search/ # discourage previous site paths Disallow: /calculator.php Disallow: /cgi-bin/ Disallow: /contact-us/feedback Disallow: /__data/assets/excel_doc/ Disallow: /__data/assets/pdf_file/ Disallow: /__data/assets/powerpoint_doc/ Disallow: /__data/assets/thumbnail/ Disallow: /__data/assets/word_doc/ Disallow: /healthandsafety/ Disallow: /human-resources/ Disallow: /odw/ Disallow: /staff/ Disallow: /tehowhao/ # discourage past papers by year Disallow: /study/papers/*/2025 Disallow: /int/study/papers/*/2025 Disallow: /study/papers/2025/ Disallow: /study/papers/*/2024 Disallow: /int/study/papers/*/2024 Disallow: /study/papers/2024/ Disallow: /study/papers/*/2023 Disallow: /int/study/papers/*/2023 Disallow: /study/papers/2023/ Disallow: /study/papers/*/2022 Disallow: /int/study/papers/*/2022 Disallow: /study/papers/2022/ Disallow: /study/papers/*/2021 Disallow: /int/study/papers/*/2021 Disallow: /study/papers/2021/ Disallow: /study/papers/*/2020 Disallow: /int/study/papers/*/2020 Disallow: /study/papers/2020/ Disallow: /study/papers/*/201* Disallow: /int/study/papers/*/201* Disallow: /study/papers/201* # discourage requests such as "/about/faculties-schools/science/home/?q=warbirds+over+wanaka+2026" Disallow: /home Disallow: /about/faculties-schools/science/home # crawldelay 5 - 17280 crawls per day User-agent: Amzn-SearchBot User-agent: anthropic-ai User-agent: Applebot User-agent: Applebot-Extended User-agent: Baiduspider User-agent: CCBot User-agent: ChatGPT-User User-agent: ClaudeBot User-agent: Claude-SearchBot User-agent: Claude-User User-agent: Diffbot User-agent: GPTBot User-agent: meta-externalagent User-agent: meta-webindexer User-agent: PerplexityBot User-agent: SemanticScholarBot User-agent: SemrushBot User-agent: SemrushBot-BA User-agent: SemrushBot-SI User-agent: simplecrawler User-agent: SiteAuditBot User-agent: SnapchatAdsBot User-agent: VelenPublicWebCrawler User-agent: YouBot Crawl-delay: 5 Disallow: /admin Disallow: /Security/ Disallow: /search/ Disallow: /int/search/ # discourage previous site paths Disallow: /calculator.php Disallow: /cgi-bin/ Disallow: /contact-us/feedback Disallow: /__data/assets/excel_doc/ Disallow: /__data/assets/pdf_file/ Disallow: /__data/assets/powerpoint_doc/ Disallow: /__data/assets/thumbnail/ Disallow: /__data/assets/word_doc/ Disallow: /healthandsafety/ Disallow: /human-resources/ Disallow: /odw/ Disallow: /staff/ Disallow: /tehowhao/ # discourage past papers by year Disallow: /study/papers/*/2025 Disallow: /int/study/papers/*/2025 Disallow: /study/papers/2025/ Disallow: /study/papers/*/2024 Disallow: /int/study/papers/*/2024 Disallow: /study/papers/2024/ Disallow: /study/papers/*/2023 Disallow: /int/study/papers/*/2023 Disallow: /study/papers/2023/ Disallow: /study/papers/*/2022 Disallow: /int/study/papers/*/2022 Disallow: /study/papers/2022/ Disallow: /study/papers/*/2021 Disallow: /int/study/papers/*/2021 Disallow: /study/papers/2021/ Disallow: /study/papers/*/2020 Disallow: /int/study/papers/*/2020 Disallow: /study/papers/2020/ Disallow: /study/papers/*/201* Disallow: /int/study/papers/*/201* Disallow: /study/papers/201* # discourage requests such as "/about/faculties-schools/science/home/?q=warbirds+over+wanaka+2026" Disallow: /home Disallow: /about/faculties-schools/science/home # crawldelay 10 - 8640 crawls per day User-agent: AhrefsBot User-agent: Bingbot User-agent: Caliperbot User-agent: DataForSeoBot User-agent: Lanai User-agent: Monsidobot User-agent: SleepBot User-agent: SogouMSE User-agent: SogouSpider User-agent: Sogou Pic spider User-agent: Sogou web spider Crawl-delay: 10 Disallow: /admin Disallow: /Security/ Disallow: /search/ Disallow: /int/search/ # discourage previous site paths Disallow: /calculator.php Disallow: /cgi-bin/ Disallow: /contact-us/feedback Disallow: /__data/assets/excel_doc/ Disallow: /__data/assets/pdf_file/ Disallow: /__data/assets/powerpoint_doc/ Disallow: /__data/assets/thumbnail/ Disallow: /__data/assets/word_doc/ Disallow: /healthandsafety/ Disallow: /human-resources/ Disallow: /odw/ Disallow: /staff/ Disallow: /tehowhao/ # discourage past papers by year Disallow: /study/papers/*/2025 Disallow: /int/study/papers/*/2025 Disallow: /study/papers/2025/ Disallow: /study/papers/*/2024 Disallow: /int/study/papers/*/2024 Disallow: /study/papers/2024/ Disallow: /study/papers/*/2023 Disallow: /int/study/papers/*/2023 Disallow: /study/papers/2023/ Disallow: /study/papers/*/2022 Disallow: /int/study/papers/*/2022 Disallow: /study/papers/2022/ Disallow: /study/papers/*/2021 Disallow: /int/study/papers/*/2021 Disallow: /study/papers/2021/ Disallow: /study/papers/*/2020 Disallow: /int/study/papers/*/2020 Disallow: /study/papers/2020/ Disallow: /study/papers/*/201* Disallow: /int/study/papers/*/201* Disallow: /study/papers/201* # discourage requests such as "/about/faculties-schools/science/home/?q=warbirds+over+wanaka+2026" Disallow: /home Disallow: /about/faculties-schools/science/home # crawldelay 30 - 2880 crawls per day # Crawl-delay: 30 # crawldelay 60 - 1440 crawls per day # Crawl-delay: 60 # disallowed agents User-agent: Amazonbot User-agent: BLEXBot User-agent: Bytespider User-agent: DotBot User-agent: ImagesiftBot User-agent: Linespider User-agent: MegaIndex.ru User-agent: MJ12bot User-agent: omgili User-agent: omgilibot User-agent: PetalBot User-agent: Seekr User-agent: SEOkicks User-agent: serpstatbot User-agent: spbot User-agent: TikTokSpider User-agent: ZoominfoBot Disallow: / Sitemap: https://www.waikato.ac.nz/sitemap.xml