The Economist / robots.txt snapshot
← back to economist.com · fetched 2026-07-20T19:11:56Z (16d ago) · HTTP 200 · 2288 bytes · sha256 c170a2eaf0933e81 · 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 | Disallow: / |
| 17 | |
| 18 | User-agent: Claude-SearchBot |
| 19 | Allow: /pro$ |
| 20 | Allow: /pro/ |
| 21 | Disallow: / |
| 22 | |
| 23 | User-agent: Claude-User |
| 24 | Allow: /pro$ |
| 25 | Allow: /pro/ |
| 26 | Disallow: / |
| 27 | |
| 28 | User-agent: Claude-Web |
| 29 | Allow: /pro$ |
| 30 | Allow: /pro/ |
| 31 | Disallow: / |
| 32 | |
| 33 | User-agent: PerplexityBot |
| 34 | Allow: /pro$ |
| 35 | Allow: /pro/ |
| 36 | Disallow: / |
| 37 | |
| 38 | User-agent: Perplexity-User |
| 39 | Allow: /pro$ |
| 40 | Allow: /pro/ |
| 41 | Disallow: / |
| 42 | |
| 43 | # I have added OAI-SearchBot (OpenAI's live search agent) |
| 44 | # as it behaves the same way as ChatGPT-User. |
| 45 | User-agent: OAI-SearchBot |
| 46 | Allow: /pro$ |
| 47 | Allow: /pro/ |
| 48 | Disallow: / |
| 49 | |
| 50 | # ========================================== |
| 51 | # TRAINING BOTS & MASS SCRAPERS |
| 52 | # Completely blocked from the entire site |
| 53 | # ========================================== |
| 54 | |
| 55 | User-agent: GPTBot |
| 56 | Disallow: / |
| 57 | |
| 58 | # Google-Extended is used by the Gemini app for searches on |
| 59 | # behalf of the user but it also used for training |
| 60 | User-agent: Google-Extended |
| 61 | Disallow: / |
| 62 | |
| 63 | User-agent: anthropic-ai |
| 64 | Disallow: / |
| 65 | |
| 66 | User-agent: Applebot-Extended |
| 67 | Disallow: / |
| 68 | |
| 69 | User-Agent: Bytespider |
| 70 | Disallow: / |
| 71 | |
| 72 | User-agent: CCBot |
| 73 | Disallow: / |
| 74 | |
| 75 | User-agent: ClaudeBot |
| 76 | Disallow: / |
| 77 | |
| 78 | # ========================================== |
| 79 | # OTHER MISCELLANEOUS BOTS |
| 80 | # Completely blocked |
| 81 | # ========================================== |
| 82 | |
| 83 | User-agent: PiplBot |
| 84 | Disallow: / |
| 85 | |
| 86 | User-agent: TurnitinBot |
| 87 | Disallow: / |
| 88 | |
| 89 | User-agent: PetalBot |
| 90 | Disallow: / |
| 91 | |
| 92 | User-agent: MoodleBot |
| 93 | Disallow: / |
| 94 | |
| 95 | User-agent: magpie-crawler |
| 96 | Disallow: / |
| 97 | |
| 98 | User-agent: ia_archiver |
| 99 | Disallow: / |
| 100 | |
| 101 | User-Agent: Mozilla/5.0 (compatible; parse.ly scraper/0.16; +http://parsely.com) |
| 102 | Disallow: /checkout |
| 103 | |
| 104 | # ========================================== |
| 105 | # GENERAL CRAWLERS (e.g., Googlebot, Bingbot) |
| 106 | # Allowed by default, but blocked from select paths |
| 107 | # ========================================== |
| 108 | User-agent: * |
| 109 | Disallow: /5605/ |
| 110 | Disallow: /pubads.g.doubleclick.net/ |
| 111 | Disallow: /assets/infographic/ |
| 112 | Disallow: /search/ |
| 113 | Disallow: /search?q= |
| 114 | Disallow: /graphql |
| 115 | Disallow: /subscribe/getstarted/ |
| 116 | Disallow: /checkout |
| 117 | Disallow: /switch* |
| 118 | Disallow: /audio-edition-podcast/*/index.xml |