The Hill / robots.txt snapshot
← back to thehill.com · fetched 2026-06-20T01:10:30Z (18h ago) · HTTP 200 · 2143 bytes · sha256 5e0c73fd451e413b · raw
final URL: https://thehill.com/robots.txt
| 1 | User-agent: * |
| 2 | Disallow: /wp-admin/ |
| 3 | Allow: /wp-admin/admin-ajax.php |
| 4 | |
| 5 | Sitemap: https://thehill.com/sitemap.xml |
| 6 | Sitemap: https://thehill.com/news-sitemap.xml |
| 7 | Sitemap: https://thehill.com/video-sitemap.xml |
| 8 | Disallow: */?s= |
| 9 | Disallow: */search/ |
| 10 | Disallow: /*.woff |
| 11 | Disallow: /*.woff2 |
| 12 | Disallow: /page/ |
| 13 | Disallow: /wp-content/plugins/ |
| 14 | Allow: /wp-content/plugins/liveblog/ |
| 15 | Disallow: /wp-content/client-mu-plugins/ |
| 16 | Disallow: /wp-includes/css/ |
| 17 | Disallow: /wp-includes/js/ |
| 18 | Disallow: /wp-content/themes/nexstar/client/build/js/ |
| 19 | Disallow: /wp-content/themes/nexstar/client/build/css/ |
| 20 | Disallow: /nxs-video-player/ |
| 21 | |
| 22 | |
| 23 | # --- (configured to see /advertise/ ONLY) --- |
| 24 | |
| 25 | User-agent: GPTBot |
| 26 | User-agent: OAI-SearchBot |
| 27 | Disallow: / |
| 28 | Allow: /advertise/ |
| 29 | |
| 30 | User-Agent: PerplexityBot |
| 31 | Disallow: / |
| 32 | Allow: /advertise/ |
| 33 | |
| 34 | User-agent: ia_archiver |
| 35 | Disallow: / |
| 36 | |
| 37 | User-agent: Google-Extended |
| 38 | Disallow: / |
| 39 | Allow: /advertise/ |
| 40 | |
| 41 | User-agent: ClaudeBot |
| 42 | User-agent: Claude-Web |
| 43 | User-agent: anthropic-ai |
| 44 | Disallow: / |
| 45 | Allow: /advertise/ |
| 46 | |
| 47 | # --- Other Agents (Strict Block or Delays) --- |
| 48 | |
| 49 | User-agent: CCBot |
| 50 | Disallow: / |
| 51 | |
| 52 | User-Agent: FacebookBot |
| 53 | Disallow: / |
| 54 | |
| 55 | User-agent: proximic |
| 56 | Crawl-Delay: 20 |
| 57 | |
| 58 | User-agent: Moreover |
| 59 | Crawl-Delay: 20 |
| 60 | |
| 61 | User-agent: AhrefsBot |
| 62 | Crawl-Delay: 20 |
| 63 | |
| 64 | User-agent: Applebot-Extended |
| 65 | Disallow: / |
| 66 | |
| 67 | User-agent: GumGum |
| 68 | Crawl-Delay: 10 |
| 69 | |
| 70 | User-agent: Verity |
| 71 | Crawl-Delay: 10 |
| 72 | |
| 73 | User-agent: AwarioRssBot |
| 74 | User-agent: AwarioSmartBot |
| 75 | Disallow: / |
| 76 | |
| 77 | User-agent: Bytespider |
| 78 | Disallow: / |
| 79 | |
| 80 | User-agent: ChatGPT-User |
| 81 | Disallow: / |
| 82 | |
| 83 | User-agent: cohere-ai |
| 84 | Disallow: / |
| 85 | |
| 86 | User-agent: DataForSeoBot |
| 87 | Disallow: / |
| 88 | |
| 89 | User-agent: Diffbot |
| 90 | Disallow: / |
| 91 | |
| 92 | User-agent: FriendlyCrawler |
| 93 | Disallow: / |
| 94 | |
| 95 | User-agent: Google-CloudVertexBot |
| 96 | Disallow: / |
| 97 | Allow: /wirecutter/ |
| 98 | |
| 99 | User-agent: ImagesiftBot |
| 100 | Disallow: / |
| 101 | |
| 102 | User-agent: magpie-crawler |
| 103 | Disallow: / |
| 104 | |
| 105 | User-agent: Meta-ExternalAgent |
| 106 | User-agent: meta-externalagent |
| 107 | Disallow: / |
| 108 | |
| 109 | User-agent: NewsNow |
| 110 | Disallow: / |
| 111 | |
| 112 | User-agent: news-please |
| 113 | Disallow: / |
| 114 | |
| 115 | User-agent: omgili |
| 116 | Disallow: / |
| 117 | |
| 118 | User-agent: omgilibot |
| 119 | Disallow: / |
| 120 | |
| 121 | User-agent: peer39_crawler |
| 122 | User-agent: peer39_crawler/1.0 |
| 123 | Disallow: / |
| 124 | |
| 125 | User-agent: Quora-Bot |
| 126 | Disallow: / |
| 127 | |
| 128 | User-agent: Scrapy |
| 129 | Disallow: / |
| 130 | |
| 131 | User-agent: TurnitinBot |
| 132 | Disallow: / |