The Economist / robots.txt snapshot
← back to economist.com · fetched 2026-08-20T18:05:43Z (3d ago) · HTTP 200 · 2650 bytes · sha256 d4669509e95e5a45 · raw
final URL: https://www.economist.com/robots.txt
| 1 | # robots.txt |
| 2 | |
| 3 | # Sitemaps |
| 4 | |
| 5 | Sitemap: https://www.economist.com/sitemap.xml |
| 6 | Sitemap: https://www.economist.com/googlenews.xml |
| 7 | |
| 8 | # ========================================== |
| 9 | # USER-FACING LLM BOTS |
| 10 | # Allowed to fetch on behalf of a user |
| 11 | # ========================================== |
| 12 | |
| 13 | User-agent: ChatGPT-User |
| 14 | Allow: /pro$ |
| 15 | Allow: /pro/ |
| 16 | Allow: /syndication$ |
| 17 | Allow: /syndication/ |
| 18 | Disallow: / |
| 19 | |
| 20 | User-agent: Claude-SearchBot |
| 21 | Allow: /pro$ |
| 22 | Allow: /pro/ |
| 23 | Allow: /syndication$ |
| 24 | Allow: /syndication/ |
| 25 | Disallow: / |
| 26 | |
| 27 | User-agent: Claude-User |
| 28 | Allow: /pro$ |
| 29 | Allow: /pro/ |
| 30 | Allow: /syndication$ |
| 31 | Allow: /syndication/ |
| 32 | Disallow: / |
| 33 | |
| 34 | User-agent: Claude-Web |
| 35 | Allow: /pro$ |
| 36 | Allow: /pro/ |
| 37 | Allow: /syndication$ |
| 38 | Allow: /syndication/ |
| 39 | Disallow: / |
| 40 | |
| 41 | User-agent: PerplexityBot |
| 42 | Allow: /pro$ |
| 43 | Allow: /pro/ |
| 44 | Allow: /syndication$ |
| 45 | Allow: /syndication/ |
| 46 | Disallow: / |
| 47 | |
| 48 | User-agent: Perplexity-User |
| 49 | Allow: /pro$ |
| 50 | Allow: /pro/ |
| 51 | Allow: /syndication$ |
| 52 | Allow: /syndication/ |
| 53 | Disallow: / |
| 54 | |
| 55 | # I have added OAI-SearchBot (OpenAI's live search agent) |
| 56 | # as it behaves the same way as ChatGPT-User. |
| 57 | User-agent: OAI-SearchBot |
| 58 | Allow: /pro$ |
| 59 | Allow: /pro/ |
| 60 | Allow: /syndication$ |
| 61 | Allow: /syndication/ |
| 62 | Disallow: / |
| 63 | |
| 64 | # ========================================== |
| 65 | # TRAINING BOTS & MASS SCRAPERS |
| 66 | # Completely blocked from the entire site |
| 67 | # ========================================== |
| 68 | |
| 69 | User-agent: GPTBot |
| 70 | Disallow: / |
| 71 | |
| 72 | # Google-Extended is used by the Gemini app for searches on |
| 73 | # behalf of the user but it also used for training |
| 74 | User-agent: Google-Extended |
| 75 | Allow: /pro$ |
| 76 | Allow: /pro/ |
| 77 | Allow: /syndication$ |
| 78 | Allow: /syndication/ |
| 79 | Disallow: / |
| 80 | |
| 81 | User-agent: anthropic-ai |
| 82 | Disallow: / |
| 83 | |
| 84 | User-agent: Applebot-Extended |
| 85 | Disallow: / |
| 86 | |
| 87 | User-Agent: Bytespider |
| 88 | Disallow: / |
| 89 | |
| 90 | User-agent: CCBot |
| 91 | Disallow: / |
| 92 | |
| 93 | User-agent: ClaudeBot |
| 94 | Disallow: / |
| 95 | |
| 96 | # ========================================== |
| 97 | # OTHER MISCELLANEOUS BOTS |
| 98 | # Completely blocked |
| 99 | # ========================================== |
| 100 | |
| 101 | User-agent: PiplBot |
| 102 | Disallow: / |
| 103 | |
| 104 | User-agent: TurnitinBot |
| 105 | Disallow: / |
| 106 | |
| 107 | User-agent: PetalBot |
| 108 | Disallow: / |
| 109 | |
| 110 | User-agent: MoodleBot |
| 111 | Disallow: / |
| 112 | |
| 113 | User-agent: magpie-crawler |
| 114 | Disallow: / |
| 115 | |
| 116 | User-agent: ia_archiver |
| 117 | Disallow: / |
| 118 | |
| 119 | User-Agent: Mozilla/5.0 (compatible; parse.ly scraper/0.16; +http://parsely.com) |
| 120 | Disallow: /checkout |
| 121 | |
| 122 | # ========================================== |
| 123 | # GENERAL CRAWLERS (e.g., Googlebot, Bingbot) |
| 124 | # Allowed by default, but blocked from select paths |
| 125 | # ========================================== |
| 126 | User-agent: * |
| 127 | Disallow: /5605/ |
| 128 | Disallow: /pubads.g.doubleclick.net/ |
| 129 | Disallow: /assets/infographic/ |
| 130 | Disallow: /search/ |
| 131 | Disallow: /search?q= |
| 132 | Disallow: /graphql |
| 133 | Disallow: /subscribe/getstarted/ |
| 134 | Disallow: /checkout |
| 135 | Disallow: /switch* |
| 136 | Disallow: /audio-edition-podcast/*/index.xml |