Costa Rica (Presidencia) / robots.txt snapshot
← back to presidencia.go.cr · fetched 2026-06-20T01:10:30Z (18h ago) · HTTP 200 · 3743 bytes · sha256 c48294001a13c338 · raw
final URL: https://presidencia.go.cr/robots.txt
| 1 | # As a condition of accessing this website, you agree to abide by the following |
| 2 | # content signals: |
| 3 | |
| 4 | # (a) If a Content-Signal = yes, you may collect content for the corresponding |
| 5 | # use. |
| 6 | # (b) If a Content-Signal = no, you may not collect content for the |
| 7 | # corresponding use. |
| 8 | # (c) If the website operator does not include a Content-Signal for a |
| 9 | # corresponding use, the website operator neither grants nor restricts |
| 10 | # permission via Content-Signal with respect to the corresponding use. |
| 11 | |
| 12 | # The content signals and their meanings are: |
| 13 | |
| 14 | # search: building a search index and providing search results (e.g., returning |
| 15 | # hyperlinks and short excerpts from your website's contents). Search does not |
| 16 | # include providing AI-generated search summaries. |
| 17 | # ai-input: inputting content into one or more AI models (e.g., retrieval |
| 18 | # augmented generation, grounding, or other real-time taking of content for |
| 19 | # generative AI search answers). |
| 20 | # ai-train: training or fine-tuning AI models. |
| 21 | |
| 22 | # ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF |
| 23 | # RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT |
| 24 | # AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET. |
| 25 | |
| 26 | # BEGIN Cloudflare Managed content |
| 27 | |
| 28 | User-agent: * |
| 29 | Content-Signal: search=yes,ai-train=no |
| 30 | Allow: / |
| 31 | |
| 32 | User-agent: Amazonbot |
| 33 | Disallow: / |
| 34 | |
| 35 | User-agent: Applebot-Extended |
| 36 | Disallow: / |
| 37 | |
| 38 | User-agent: Bytespider |
| 39 | Disallow: / |
| 40 | |
| 41 | User-agent: CCBot |
| 42 | Disallow: / |
| 43 | |
| 44 | User-agent: ClaudeBot |
| 45 | Disallow: / |
| 46 | |
| 47 | User-agent: CloudflareBrowserRenderingCrawler |
| 48 | Disallow: / |
| 49 | |
| 50 | User-agent: Google-Extended |
| 51 | Disallow: / |
| 52 | |
| 53 | User-agent: GPTBot |
| 54 | Disallow: / |
| 55 | |
| 56 | User-agent: meta-externalagent |
| 57 | Disallow: / |
| 58 | |
| 59 | # END Cloudflare Managed Content |
| 60 | |
| 61 | # |
| 62 | # robots.txt |
| 63 | # |
| 64 | # This file is to prevent the crawling and indexing of certain parts |
| 65 | # of your site by web crawlers and spiders run by sites like Yahoo! |
| 66 | # and Google. By telling these "robots" where not to go on your site, |
| 67 | # you save bandwidth and server resources. |
| 68 | # |
| 69 | # This file will be ignored unless it is at the root of your host: |
| 70 | # Used: http://example.com/robots.txt |
| 71 | # Ignored: http://example.com/site/robots.txt |
| 72 | # |
| 73 | # For more information about the robots.txt standard, see: |
| 74 | # http://www.robotstxt.org/robotstxt.html |
| 75 | |
| 76 | User-agent: * |
| 77 | # CSS, JS, Images |
| 78 | Allow: /core/*.css$ |
| 79 | Allow: /core/*.css? |
| 80 | Allow: /core/*.js$ |
| 81 | Allow: /core/*.js? |
| 82 | Allow: /core/*.gif |
| 83 | Allow: /core/*.jpg |
| 84 | Allow: /core/*.jpeg |
| 85 | Allow: /core/*.png |
| 86 | Allow: /core/*.svg |
| 87 | Allow: /profiles/*.css$ |
| 88 | Allow: /profiles/*.css? |
| 89 | Allow: /profiles/*.js$ |
| 90 | Allow: /profiles/*.js? |
| 91 | Allow: /profiles/*.gif |
| 92 | Allow: /profiles/*.jpg |
| 93 | Allow: /profiles/*.jpeg |
| 94 | Allow: /profiles/*.png |
| 95 | Allow: /profiles/*.svg |
| 96 | # Directories |
| 97 | Disallow: /core/ |
| 98 | Disallow: /profiles/ |
| 99 | # Files |
| 100 | Disallow: /README.md |
| 101 | Disallow: /composer/Metapackage/README.txt |
| 102 | Disallow: /composer/Plugin/ProjectMessage/README.md |
| 103 | Disallow: /composer/Plugin/Scaffold/README.md |
| 104 | Disallow: /composer/Plugin/VendorHardening/README.txt |
| 105 | Disallow: /composer/Template/README.txt |
| 106 | Disallow: /modules/README.txt |
| 107 | Disallow: /sites/README.txt |
| 108 | Disallow: /themes/README.txt |
| 109 | # Paths (clean URLs) |
| 110 | Disallow: /admin/ |
| 111 | Disallow: /comment/reply/ |
| 112 | Disallow: /filter/tips |
| 113 | Disallow: /node/add/ |
| 114 | Disallow: /search/ |
| 115 | Disallow: /user/register |
| 116 | Disallow: /user/password |
| 117 | Disallow: /user/login |
| 118 | Disallow: /user/logout |
| 119 | Disallow: /media/oembed |
| 120 | Disallow: /*/media/oembed |
| 121 | # Paths (no clean URLs) |
| 122 | Disallow: /index.php/admin/ |
| 123 | Disallow: /index.php/comment/reply/ |
| 124 | Disallow: /index.php/filter/tips |
| 125 | Disallow: /index.php/node/add/ |
| 126 | Disallow: /index.php/search/ |
| 127 | Disallow: /index.php/user/password |
| 128 | Disallow: /index.php/user/register |
| 129 | Disallow: /index.php/user/login |
| 130 | Disallow: /index.php/user/logout |
| 131 | Disallow: /index.php/media/oembed |
| 132 | Disallow: /index.php/*/media/oembed |