HuffPost / robots.txt snapshot
← back to huffpost.com · fetched 2026-06-20T01:10:30Z (18h ago) · HTTP 200 · 2562 bytes · sha256 a7c45b9f6a0cb53b · raw
final URL: https://www.huffpost.com/robots.txt
| 1 | # Cambria robots |
| 2 | |
| 3 | User-agent: grapeshot |
| 4 | Disallow: /member |
| 5 | Disallow: /*?*err_code=404 |
| 6 | Disallow: /search |
| 7 | Disallow: /search/?* |
| 8 | |
| 9 | User-agent: * |
| 10 | Disallow: /*?*page= |
| 11 | Disallow: /member |
| 12 | Disallow: /*?*err_code=404 |
| 13 | Disallow: /search |
| 14 | Disallow: /search/?* |
| 15 | Disallow: /mapi/v4/*/user/* |
| 16 | Disallow: /embed |
| 17 | Disallow: /*/webview |
| 18 | Disallow: /api |
| 19 | |
| 20 | User-agent: Amazonbot |
| 21 | Disallow: / |
| 22 | |
| 23 | User-agent: anthropic-ai |
| 24 | Disallow: / |
| 25 | |
| 26 | User-agent: Applebot-Extended |
| 27 | Disallow: / |
| 28 | |
| 29 | User-agent: Bytespider |
| 30 | Disallow: / |
| 31 | |
| 32 | User-agent: CCBot |
| 33 | Disallow: / |
| 34 | |
| 35 | User-agent: ChatGPT-User |
| 36 | Disallow: / |
| 37 | |
| 38 | User-agent: Claude-Web |
| 39 | Disallow: / |
| 40 | |
| 41 | User-agent: ClaudeBot |
| 42 | Disallow: / |
| 43 | |
| 44 | User-agent: cohere-ai |
| 45 | Disallow: / |
| 46 | |
| 47 | User-agent: Diffbot |
| 48 | Disallow: / |
| 49 | |
| 50 | User-agent: DuckAssistBot |
| 51 | Disallow: / |
| 52 | |
| 53 | User-agent: FacebookBot |
| 54 | Disallow: / |
| 55 | |
| 56 | User-agent: GPTBot |
| 57 | Disallow: / |
| 58 | |
| 59 | User-agent: Google-Extended |
| 60 | Disallow: / |
| 61 | |
| 62 | User-agent: Googlebot |
| 63 | Allow: / |
| 64 | Disallow: /*?*err_code=404 |
| 65 | Disallow: /search |
| 66 | Disallow: /search/?* |
| 67 | |
| 68 | User-agent: magpie-crawler |
| 69 | Disallow: / |
| 70 | |
| 71 | User-agent: meta-externalagent |
| 72 | Disallow: / |
| 73 | |
| 74 | User-agent: Meta-ExternalFetcher |
| 75 | Disallow: / |
| 76 | |
| 77 | User-agent: OAI-SearchBot |
| 78 | Disallow: / |
| 79 | |
| 80 | User-agent: Perplexity-User |
| 81 | Disallow: / |
| 82 | |
| 83 | User-agent: PerplexityBot |
| 84 | Disallow: / |
| 85 | |
| 86 | User-agent: Timpibot |
| 87 | Disallow: / |
| 88 | |
| 89 | User-agent: TurnitinBot |
| 90 | Disallow: / |
| 91 | |
| 92 | User-agent: Ai2Bot-Dolma |
| 93 | Disallow: / |
| 94 | |
| 95 | User-agent: Claude-SearchBot |
| 96 | Disallow: / |
| 97 | |
| 98 | User-agent: Claude-User |
| 99 | Disallow: / |
| 100 | |
| 101 | User-agent: omgilibot |
| 102 | Disallow: / |
| 103 | |
| 104 | User-agent: TtoYouBot |
| 105 | Disallow: / |
| 106 | |
| 107 | User-agent: WebGPTBot |
| 108 | Disallow: / |
| 109 | |
| 110 | User-agent: Scope3/2.0 (scope3.com) |
| 111 | Allow: /$ |
| 112 | Allow: /* |
| 113 | Disallow: /*?*page= |
| 114 | Disallow: /member |
| 115 | Disallow: /*?*err_code=404 |
| 116 | Disallow: /search |
| 117 | Disallow: /search/?* |
| 118 | Disallow: /mapi/v4/*/user/* |
| 119 | Disallow: /embed |
| 120 | Disallow: /api |
| 121 | |
| 122 | User-agent: AmazonAdBot |
| 123 | Allow: /$ |
| 124 | Allow: /* |
| 125 | Disallow: /*?*page= |
| 126 | Disallow: /member |
| 127 | Disallow: /*?*err_code=404 |
| 128 | Disallow: /search |
| 129 | Disallow: /search/?* |
| 130 | Disallow: /mapi/v4/*/user/* |
| 131 | Disallow: /embed |
| 132 | Disallow: /api |
| 133 | |
| 134 | # archives |
| 135 | Sitemap: https://www.huffpost.com/static-assets/isolated/huffpostsitemapgeneratorjob-prod-public/us/sitemaps/sitemap-v1.xml |
| 136 | Sitemap: https://www.huffpost.com/static-assets/isolated/huffpostsitemapgeneratorjob-prod-public/us/sitemaps/sitemap-google-news.xml |
| 137 | Sitemap: https://www.huffpost.com/static-assets/isolated/huffpostsitemapgeneratorjob-prod-public/us/sitemaps/sitemap-google-video.xml |
| 138 | Sitemap: https://www.huffpost.com/static-assets/isolated/huffpostsitemapgeneratorjob-prod-public/us/sitemaps/sections.xml |
| 139 | Sitemap: https://www.huffpost.com/static-assets/isolated/huffpostsitemapgeneratorjob-prod-public/us/sitemaps/sitemap-top-sections.xml |