The Asahi Shimbun / robots.txt snapshot
← back to asahi.com · fetched 2026-10-30T05:39:55Z (8d ago) · HTTP 200 · 2452 bytes · sha256 9f51e548f1bb2dc3 · raw
final URL: https://www.asahi.com/robots.txt
| 1 | User-Agent: * |
| 2 | Disallow: /travel/event/search/ |
| 3 | Disallow: /car/index.html |
| 4 | Disallow: /housing/index.html |
| 5 | Disallow: /english/newsfeatures.html |
| 6 | Disallow: /english/business.html |
| 7 | Disallow: /english/cooljapan.html |
| 8 | Disallow: /english/sports.html |
| 9 | Disallow: /*/search/results* |
| 10 | Allow: / |
| 11 | Allow: /.well-known/assetlinks.json |
| 12 | Allow: /ads/ |
| 13 | Allow: /corporate/ |
| 14 | |
| 15 | |
| 16 | User-agent: Googlebot |
| 17 | Disallow: /*klpuid=* |
| 18 | Allow: /ads/ |
| 19 | Allow: /corporate/ |
| 20 | |
| 21 | User-agent: CCBot |
| 22 | Disallow: / |
| 23 | |
| 24 | User-agent: OAI-SearchBot |
| 25 | Disallow: / |
| 26 | Allow: /ads/ |
| 27 | Allow: /corporate/ |
| 28 | |
| 29 | User-agent: ChatGPT-User |
| 30 | Disallow: / |
| 31 | Allow: /ads/ |
| 32 | Allow: /corporate/ |
| 33 | |
| 34 | User-agent: GPTBot |
| 35 | Disallow: / |
| 36 | Allow: /ads/ |
| 37 | Allow: /corporate/ |
| 38 | |
| 39 | User-agent: Google-Extended |
| 40 | Disallow: / |
| 41 | Allow: /ads/ |
| 42 | Allow: /corporate/ |
| 43 | |
| 44 | User-agent: Google-CloudVertexBot |
| 45 | Disallow: / |
| 46 | Allow: /ads/ |
| 47 | Allow: /corporate/ |
| 48 | |
| 49 | User-agent: ICC-Crawler |
| 50 | Disallow: / |
| 51 | Allow: /ads/ |
| 52 | Allow: /corporate/ |
| 53 | |
| 54 | User-agent: anthropic-ai |
| 55 | Disallow: / |
| 56 | Allow: /ads/ |
| 57 | Allow: /corporate/ |
| 58 | |
| 59 | User-agent: ClaudeBot |
| 60 | Disallow: / |
| 61 | Allow: /ads/ |
| 62 | Allow: /corporate/ |
| 63 | |
| 64 | User-agent: Claude-Web |
| 65 | Disallow: / |
| 66 | Allow: /ads/ |
| 67 | Allow: /corporate/ |
| 68 | |
| 69 | User-agent: Claude-SearchBot |
| 70 | Disallow: / |
| 71 | Allow: /ads/ |
| 72 | Allow: /corporate/ |
| 73 | |
| 74 | User-agent: Claude-User |
| 75 | Disallow: / |
| 76 | Allow: /ads/ |
| 77 | Allow: /corporate/ |
| 78 | |
| 79 | User-agent: Applebot-Extended |
| 80 | Disallow: / |
| 81 | Allow: /ads/ |
| 82 | Allow: /corporate/ |
| 83 | |
| 84 | User-agent: cohere-ai |
| 85 | Disallow: / |
| 86 | Allow: /ads/ |
| 87 | Allow: /corporate/ |
| 88 | |
| 89 | User-agent: Cohere-training-data-crawler |
| 90 | Disallow: / |
| 91 | Allow: /ads/ |
| 92 | Allow: /corporate/ |
| 93 | |
| 94 | User-agent: omgili |
| 95 | Disallow: / |
| 96 | Allow: /ads/ |
| 97 | Allow: /corporate/ |
| 98 | |
| 99 | User-agent: omgilibot |
| 100 | Disallow: / |
| 101 | Allow: /ads/ |
| 102 | Allow: /corporate/ |
| 103 | |
| 104 | User-agent: PerplexityBot |
| 105 | Disallow: / |
| 106 | |
| 107 | User-agent: Perplexity-ai |
| 108 | Disallow: / |
| 109 | |
| 110 | User-agent: Perplexity-User |
| 111 | Disallow: / |
| 112 | |
| 113 | User-agent: FacebookBot |
| 114 | Disallow: / |
| 115 | Allow: /ads/ |
| 116 | Allow: /corporate/ |
| 117 | |
| 118 | User-agent: Meta-ExternalAgent |
| 119 | Disallow: / |
| 120 | Allow: /ads/ |
| 121 | Allow: /corporate/ |
| 122 | |
| 123 | User-agent: Meta-externalfetcher |
| 124 | Disallow: / |
| 125 | Allow: /ads/ |
| 126 | Allow: /corporate/ |
| 127 | |
| 128 | User-agent: Bytespider |
| 129 | Disallow: / |
| 130 | |
| 131 | User-agent: Gensparkbot |
| 132 | Disallow: / |
| 133 | |
| 134 | User-agent: AmazonBot |
| 135 | Disallow: / |
| 136 | Allow: /ads/ |
| 137 | Allow: /corporate/ |
| 138 | |
| 139 | User-agent: Diffbot |
| 140 | Disallow: / |
| 141 | |
| 142 | User-agent: Magpie-crawler |
| 143 | Disallow: / |
| 144 | |
| 145 | User-agent: Scrapy |
| 146 | Disallow: / |
| 147 | |
| 148 | User-agent: Timpibot |
| 149 | Disallow: / |
| 150 | |
| 151 | User-agent: Webzio-Extended |
| 152 | Disallow: / |
| 153 | |
| 154 | User-agent: SBIntuitionsBot |
| 155 | Disallow: / |
| 156 | |
| 157 | User-agent: SBIntuitions-SearchBot |
| 158 | Disallow: / |
| 159 | |
| 160 | User-agent: OpenindexSpider |
| 161 | Disallow: / |
| 162 | |
| 163 | User-agent: AI2Bot |
| 164 | Disallow: / |
| 165 | |
| 166 | sitemap: https://www.asahi.com/sitemap.xml |