Daily Mail / robots.txt snapshot
← back to dailymail.co.uk · fetched 2026-07-07T20:35:12Z (1mo ago) · HTTP 200 · 5996 bytes · sha256 eb8299f3cbd42d8a · raw
final URL: https://www.dailymail.com/robots.txt
| 1 | # Robots.txt for https://www.dailymail.com/ updated 07/07/2026 |
| 2 | # |
| 3 | # |
| 4 | # Daily Mail content is made available for your personal and non-commercial |
| 5 | # use subject to our Terms and Conditions of use: |
| 6 | # https://www.dailymail.com/terms |
| 7 | # Use of any device, tool, or process designed to data mine or scrape the content |
| 8 | # using automated means is prohibited without prior written permission from |
| 9 | # DMG MEDIA LIMITED. Prohibited uses include but are not limited to: |
| 10 | # (1) text and data mining activities under Art. 4 of the EU Directive on Copyright in |
| 11 | # the Digital Single Market; |
| 12 | # (2) the development of any software, machine learning, artificial intelligence (AI), |
| 13 | # and/or large language models (LLMs); |
| 14 | # (3) creating or providing archived or cached data sets containing our content to others; and/or |
| 15 | # (4) any commercial purposes. |
| 16 | # For any licensing queries please contact [email protected]. |
| 17 | # |
| 18 | # |
| 19 | # All Robots |
| 20 | User-agent: * |
| 21 | # |
| 22 | # Begin Standard Rules |
| 23 | Disallow: /*readcommentshtml* |
| 24 | Disallow: /*login?redirectPath= |
| 25 | Disallow: /*logout?redirectPath= |
| 26 | Disallow: /*nextThread.html |
| 27 | Disallow: /*previousThread.html |
| 28 | Disallow: /*questionId* |
| 29 | Disallow: /*selectedImage* |
| 30 | Disallow: /*threadIndex=* |
| 31 | Disallow: /*topGallery* |
| 32 | Disallow: /ce/item.cms* |
| 33 | Disallow: /guide/* |
| 34 | Disallow: /registration/* |
| 35 | Disallow: /best-buys/clickout/* |
| 36 | Disallow: /best-buys/m/clickout/* |
| 37 | Disallow: /weather.html?latitude=* |
| 38 | Disallow: /weather.html?old=* |
| 39 | Disallow: /home/search.html* |
| 40 | Disallow: /best-buys/mercury/out* |
| 41 | Disallow: /api/infinite-list.html |
| 42 | Disallow: /api/infinite-list.html |
| 43 | Disallow: /mobileapps/* |
| 44 | |
| 45 | # |
| 46 | # Disallow Money for Google News |
| 47 | User-agent: Googlebot-News |
| 48 | Disallow: /tmoney/* |
| 49 | # |
| 50 | # Allow Adsense |
| 51 | User-agent: Mediapartners-Google |
| 52 | Disallow: |
| 53 | # |
| 54 | # |
| 55 | User-agent: CrystalSemanticsBot |
| 56 | Disallow: / |
| 57 | # |
| 58 | User-agent: archive-it.org |
| 59 | User-agent: archive.org_bot |
| 60 | User-agent: ArchiveBot |
| 61 | User-agent: Arquivo-web-crawler |
| 62 | User-agent: Authory |
| 63 | User-agent: babel |
| 64 | User-agent: bl.uk_ldfc_bot |
| 65 | User-agent: bl.uk_ldfc_renderbot |
| 66 | User-agent: bne.es_bot |
| 67 | User-agent: bnf.fr_bot |
| 68 | User-agent: ecoresearch |
| 69 | User-agent: ecoresearchCrawler |
| 70 | User-agent: Europarchive.org |
| 71 | User-agent: kb.dk_bot |
| 72 | User-agent: Kulturarw3 |
| 73 | User-agent: LivelapBot |
| 74 | User-agent: mediacloud |
| 75 | User-agent: mirrorweb |
| 76 | User-agent: MSIECrawler |
| 77 | User-agent: nationalarchives.gov.uk |
| 78 | User-agent: netarkivet.dk |
| 79 | User-agent: netEstate NE Crawler |
| 80 | User-agent: Nicecrawler |
| 81 | User-agent: nl-israel_iaharvester2026 |
| 82 | User-agent: nlnbot |
| 83 | User-agent: nlncrawler |
| 84 | User-agent: PageFreezer |
| 85 | User-agent: SafeDNS |
| 86 | User-agent: SmarshBot |
| 87 | User-agent: special_archiver |
| 88 | User-agent: tkl.iis.u-tokyo.ac.jp |
| 89 | User-agent: TurnitinBot |
| 90 | User-agent: webarchiv.cz |
| 91 | User-agent: WordPress.com mShots |
| 92 | User-agent: XY-Archive-Compliance-Archiver |
| 93 | User-agent: XY-Archive-Compliance-Crawler |
| 94 | Disallow: / |
| 95 | # |
| 96 | User-agent: AhrefsBot |
| 97 | User-agent: AI2Bot |
| 98 | User-agent: Ai2Bot-Dolma |
| 99 | User-agent: Amazonbot |
| 100 | User-agent: amazon-kendra- |
| 101 | User-agent: anthropic-ai |
| 102 | User-agent: Applebot-Extended |
| 103 | User-agent: bedrockbot |
| 104 | User-agent: Bytespider |
| 105 | User-agent: CloudflareBrowserRenderingCrawler |
| 106 | User-agent: CCBot |
| 107 | User-agent: ChatGLM-Spider |
| 108 | User-agent: ChatGPT-User |
| 109 | User-agent: ClaudeBot |
| 110 | User-agent: Claude-SearchBot |
| 111 | User-agent: Claude-User |
| 112 | User-agent: Claude-Web |
| 113 | User-agent: cohere-ai |
| 114 | User-agent: Cotoyogi |
| 115 | User-agent: DeepSeekBot |
| 116 | User-agent: Diffbot |
| 117 | User-agent: DuckAssistBot |
| 118 | User-agent: EchoboxBot |
| 119 | User-agent: FacebookBot |
| 120 | User-agent: FriendlyCrawler |
| 121 | User-agent: Gemini-Deep-Research |
| 122 | User-agent: Google-CloudVertexBot |
| 123 | User-agent: Google-Extended |
| 124 | User-agent: GoogleOther-Image |
| 125 | User-agent: GoogleOther-Video |
| 126 | User-agent: GPTBot |
| 127 | User-agent: Grok |
| 128 | User-agent: iaskspider/2.0 |
| 129 | User-agent: ICC-Crawler |
| 130 | User-agent: ImagesiftBot |
| 131 | User-agent: img2dataset |
| 132 | User-agent: ISSCyberRiskCrawler |
| 133 | User-agent: Kangaroo Bot |
| 134 | User-agent: KunatoCrawler |
| 135 | User-agent: LinerBot |
| 136 | User-agent: Meltwater |
| 137 | User-agent: Meta-ExternalAgent |
| 138 | User-agent: Meta-ExternalFetcher |
| 139 | User-agent: MistralAI-User |
| 140 | User-agent: OAI-Operator |
| 141 | User-agent: OAI-SearchBot |
| 142 | User-agent: omgili |
| 143 | User-agent: omgilibot |
| 144 | User-agent: PanguBot |
| 145 | User-agent: PerplexityBot |
| 146 | User-agent: Perplexity-User |
| 147 | User-agent: PetalBot |
| 148 | User-agent: QualifiedBot |
| 149 | User-agent: Scrapy |
| 150 | User-agent: Seekr |
| 151 | User-agent: Sidetrade indexer bot |
| 152 | User-agent: TaraGroup Intelligent Bot |
| 153 | User-agent: TikTokSpider |
| 154 | User-agent: Timpibot |
| 155 | User-agent: VelenPublicWebCrawler |
| 156 | User-agent: WARDBot |
| 157 | User-agent: Webzio-Extended |
| 158 | User-agent: wpbot |
| 159 | User-agent: WRTNBot |
| 160 | User-agent: YouBot |
| 161 | Allow: /buyline/ |
| 162 | Allow: /*_.html |
| 163 | Disallow: / |
| 164 | # |
| 165 | #Allow Google sandbox privacy testing |
| 166 | User-agent: GoogleOther |
| 167 | Allow: /.well-known/privacy-sandbox-attestations.json |
| 168 | # |
| 169 | # Sitemap Files |
| 170 | Sitemap: https://www.dailymail.com/google-news-sitemap.xml |
| 171 | Sitemap: https://www.dailymail.com/sitemap-channels.xml |
| 172 | Sitemap: https://www.dailymail.com/sitemap-columnist.xml |
| 173 | Sitemap: https://www.dailymail.com/sitemap-topics.xml |
| 174 | Sitemap: https://www.dailymail.com/sitemap-videos-year~2021.xml |
| 175 | Sitemap: https://www.dailymail.com/sitemap-facts-year~2021.xml |
| 176 | Sitemap: https://www.dailymail.com/sitemap-articles-year~2021.xml |
| 177 | Sitemap: https://www.dailymail.com/sitemap-videos-year~2022.xml |
| 178 | Sitemap: https://www.dailymail.com/sitemap-articles-year~2022.xml |
| 179 | Sitemap: https://www.dailymail.com/sitemap-facts-year~2022.xml |
| 180 | Sitemap: https://www.dailymail.com/sitemap-videos-year~2023.xml |
| 181 | Sitemap: https://www.dailymail.com/sitemap-articles-year~2023.xml |
| 182 | Sitemap: https://www.dailymail.com/sitemap-facts-year~2023.xml |
| 183 | Sitemap: https://www.dailymail.com/sitemap-videos-year~2024.xml |
| 184 | Sitemap: https://www.dailymail.com/sitemap-articles-year~2024.xml |
| 185 | Sitemap: https://www.dailymail.com/sitemap-facts-year~2024.xml |
| 186 | Sitemap: https://www.dailymail.com/sitemap-videos-year~2025.xml |
| 187 | Sitemap: https://www.dailymail.com/sitemap-articles-year~2025.xml |
| 188 | Sitemap: https://www.dailymail.com/sitemap-facts-year~2025.xml |
| 189 | Sitemap: https://www.dailymail.com/sitemap-videos-year~2026.xml |
| 190 | Sitemap: https://www.dailymail.com/sitemap-articles-year~2026.xml |
| 191 | Sitemap: https://www.dailymail.com/sitemap-facts-year~2026.xml |
| 192 | Sitemap: https://www.dailymail.com/sitemap-authors.xml |