The Atlantic / robots.txt snapshot
← back to theatlantic.com · fetched 2026-06-20T01:10:30Z (18h ago) · HTTP 200 · 3649 bytes · sha256 4ec505c89c42a966 · raw
final URL: https://www.theatlantic.com/robots.txt
| 1 | # As a condition of accessing this website, you agree to abide by the |
| 2 | # following content signals: |
| 3 | |
| 4 | # (a) If a content-signal = yes, you may collect content for the |
| 5 | # corresponding use. |
| 6 | # (b) If a content-signal = no, you may not collect content for the |
| 7 | # corresponding use. |
| 8 | # (c) If the website operator does not include a content signal for a |
| 9 | # corresponding use, the website operator neither grants nor restricts |
| 10 | # permission via content signal with respect to the corresponding use. |
| 11 | |
| 12 | # The content signals and their meanings are: |
| 13 | |
| 14 | # search: building a search index and providing search results (e.g., returning |
| 15 | # hyperlinks and short excerpts from your website's contents). Search |
| 16 | # does not include providing AI-generated search summaries. |
| 17 | # ai-input: inputting content into one or more AI models (e.g., retrieval |
| 18 | # augmented generation, grounding, or other real-time taking of |
| 19 | # content for generative AI search answers). |
| 20 | # ai-train: training or fine-tuning AI models. |
| 21 | |
| 22 | # ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF |
| 23 | # RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT |
| 24 | # AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET. |
| 25 | |
| 26 | User-agent: * |
| 27 | Disallow: /4624/TheAtlanticOnline/* |
| 28 | Disallow: /magazine/archive/2010/11/letters-to-the-editor/308258/ |
| 29 | Disallow: /magazine/archive/2010/11/letters-to-the-editor/308258/* |
| 30 | Disallow: /ab/* |
| 31 | Disallow: /video/embed/ |
| 32 | Disallow: /zephr/* |
| 33 | Disallow: /video/iframe/* |
| 34 | Disallow: /search/?*q=* |
| 35 | Allow: /magazine/archive/2001/02/bill-clinton-and-his-consequences/303383/$ |
| 36 | Disallow: /magazine/archive/2001/02/bill-clinton-and-his-consequences/303383/* |
| 37 | Crawl-delay: 1 |
| 38 | Allow: / |
| 39 | |
| 40 | User-agent: AmazonAdBot |
| 41 | Allow: / |
| 42 | |
| 43 | User-agent: Amazonbot |
| 44 | Disallow: / |
| 45 | Allow: /feed/* |
| 46 | |
| 47 | User-agent: anthropic-ai |
| 48 | Disallow: / |
| 49 | |
| 50 | User-agent: Applebot |
| 51 | Disallow: / |
| 52 | |
| 53 | User-agent: Applebot-Extended |
| 54 | Disallow: / |
| 55 | |
| 56 | User-agent: ArcSpanScraper |
| 57 | Allow: / |
| 58 | |
| 59 | User-agent: AwarioRssBot |
| 60 | User-agent: AwarioSmartBot |
| 61 | Disallow: / |
| 62 | |
| 63 | User-agent: BingBot |
| 64 | Content-signal: search=yes, ai-input=no, ai-train=no |
| 65 | Allow: / |
| 66 | |
| 67 | User-agent: Bytespider |
| 68 | Disallow: / |
| 69 | |
| 70 | User-agent: CCBot |
| 71 | Disallow: / |
| 72 | |
| 73 | User-agent: ChatGPT-User |
| 74 | Allow: / |
| 75 | |
| 76 | User-agent: ClaudeBot |
| 77 | Disallow: / |
| 78 | |
| 79 | User-agent: Claude-SearchBot |
| 80 | Disallow: / |
| 81 | |
| 82 | User-agent: Claude-User |
| 83 | Disallow: / |
| 84 | |
| 85 | User-agent: Claude-Web |
| 86 | Disallow: / |
| 87 | |
| 88 | User-agent: cohere-ai |
| 89 | Disallow: / |
| 90 | |
| 91 | User-agent: DataForSeoBot |
| 92 | Disallow: / |
| 93 | |
| 94 | User-agent: Diffbot |
| 95 | Disallow: / |
| 96 | |
| 97 | User-agent: DuckAssistBot |
| 98 | Content-signal: search=yes, ai-input=no, ai-train=no |
| 99 | Allow: / |
| 100 | |
| 101 | User-agent: FacebookBot |
| 102 | Content-signal: search=yes, ai-input=no, ai-train=no |
| 103 | Allow: / |
| 104 | |
| 105 | User-agent: Google-Extended |
| 106 | Disallow: / |
| 107 | |
| 108 | User-agent: Googlebot |
| 109 | Content-signal: search=yes, ai-input=no, ai-train=no |
| 110 | Disallow: /zephr/* |
| 111 | Allow: / |
| 112 | |
| 113 | User-agent: GPTBot |
| 114 | Allow: / |
| 115 | |
| 116 | User-agent: magpie-crawler |
| 117 | Disallow: / |
| 118 | |
| 119 | User-agent: Meta-ExternalAgent |
| 120 | Disallow: / |
| 121 | |
| 122 | User-agent: Meta-ExternalFetcher |
| 123 | Disallow: / |
| 124 | |
| 125 | User-agent: MistralAI-User |
| 126 | Disallow: / |
| 127 | |
| 128 | User-agent: NewsNow |
| 129 | Disallow: / |
| 130 | |
| 131 | User-agent: news-please |
| 132 | Disallow: / |
| 133 | |
| 134 | User-agent: omgili |
| 135 | Disallow: / |
| 136 | |
| 137 | User-agent: omgilibot |
| 138 | Disallow: / |
| 139 | |
| 140 | User-agent: OAI-SearchBot |
| 141 | Allow: / |
| 142 | |
| 143 | User-agent: Operator |
| 144 | Allow: / |
| 145 | |
| 146 | User-agent: PetalBot |
| 147 | Disallow: / |
| 148 | |
| 149 | User-agent: PerplexityBot |
| 150 | Disallow: / |
| 151 | |
| 152 | User-agent: Perplexity-User |
| 153 | Disallow: / |
| 154 | |
| 155 | User-agent: ProRataInc |
| 156 | Allow: / |
| 157 | |
| 158 | User-agent: Quora-Bot |
| 159 | Disallow: / |
| 160 | |
| 161 | User-agent: Scrapy |
| 162 | Disallow: / |
| 163 | |
| 164 | User-agent: TerraCotta |
| 165 | Allow: / |
| 166 | |
| 167 | User-agent: TimpiBot |
| 168 | Disallow: / |
| 169 | |
| 170 | User-agent: TurnitinBot |
| 171 | Disallow: / |
| 172 | |
| 173 | User-agent: archive.org_bot |
| 174 | Disallow: / |
| 175 | |
| 176 | Sitemap: https://www.theatlantic.com/sitemap.xml |
| 177 | Sitemap: https://www.theatlantic.com/sponsored/sitemap.xml |