Imperial College London / robots.txt
← back to imperial.ac.uk · change detected 2mo ago (2026-08-26T20:03:19Z) · modified +144 −0
What changed
- Added rules for user-agent ‘terminalfour-nutch-spider’
Diff old (2026-06-26T14:15:22Z) → new (2026-08-26T20:03:19Z)
| @@ -1,5 +1,149 @@ | ||
| 1 | 1 | User-agent: slurp |
| 2 | 2 | Crawl-delay: 0.5 |
| 3 | + | |
| 4 | + # Terminalfour Search Platform / SearchStax crawler | |
| 5 | + User-agent: terminalfour-nutch-spider | |
| 6 | + Crawl-delay: 0.5 | |
| 7 | + Allow: /ib-redesign/ | |
| 8 | + | |
| 9 | + Disallow: /terminalfour/SiteManager/ | |
| 10 | + Disallow: /business-school/icbs-apis/ | |
| 11 | + # CSS, JS, Images | |
| 12 | + Allow: /business-school/core/*.css$ | |
| 13 | + Allow: /business-school/core/*.css? | |
| 14 | + Allow: /business-school/core/*.js$ | |
| 15 | + Allow: /business-school/core/*.js? | |
| 16 | + Allow: /business-school/core/*.gif | |
| 17 | + Allow: /business-school/core/*.jpg | |
| 18 | + Allow: /business-school/core/*.jpeg | |
| 19 | + Allow: /business-school/core/*.png | |
| 20 | + Allow: /business-school/core/*.svg | |
| 21 | + Allow: /business-school/profiles/*.css$ | |
| 22 | + Allow: /business-school/profiles/*.css? | |
| 23 | + Allow: /business-school/profiles/*.js$ | |
| 24 | + Allow: /business-school/profiles/*.js? | |
| 25 | + Allow: /business-school/profiles/*.gif | |
| 26 | + Allow: /business-school/profiles/*.jpg | |
| 27 | + Allow: /business-school/profiles/*.jpeg | |
| 28 | + Allow: /business-school/profiles/*.png | |
| 29 | + Allow: /business-school/profiles/*.svg | |
| 30 | + # Directories | |
| 31 | + Disallow: /business-school/core/ | |
| 32 | + Disallow: /business-school/profiles/ | |
| 33 | + # Files | |
| 34 | + Disallow: /business-school/README.txt | |
| 35 | + Disallow: /business-school/web.config | |
| 36 | + # Paths (clean URLs) | |
| 37 | + Disallow: /business-school/admin/ | |
| 38 | + Disallow: /business-school/comment/reply/ | |
| 39 | + Disallow: /business-school/filter/tips | |
| 40 | + Disallow: /business-school/node/add/ | |
| 41 | + Disallow: /business-school/search/ | |
| 42 | + Disallow: /business-school/user/register/ | |
| 43 | + Disallow: /business-school/user/password/ | |
| 44 | + Disallow: /business-school/user/login/ | |
| 45 | + Disallow: /business-school/user/logout/ | |
| 46 | + | |
| 47 | + # Paths (no clean URLs) | |
| 48 | + Disallow: /business-school/index.php/admin/ | |
| 49 | + Disallow: /business-school/index.php/comment/reply/ | |
| 50 | + Disallow: /business-school/index.php/filter/tips | |
| 51 | + Disallow: /business-school/index.php/node/add/ | |
| 52 | + Disallow: /business-school/index.php/search/ | |
| 53 | + Disallow: /business-school/index.php/user/password/ | |
| 54 | + Disallow: /business-school/index.php/user/register/ | |
| 55 | + Disallow: /business-school/index.php/user/login/ | |
| 56 | + Disallow: /business-school/index.php/user/logout/ | |
| 57 | + | |
| 58 | + # business school thank you pages and others | |
| 59 | + Disallow: /business-school/phd/mailing-list/thank-you/ | |
| 60 | + Disallow: /business-school/phd/brochure/thank-you/ | |
| 61 | + Disallow: /business-school/undergraduate/summer-school/mailing-list/thank-you/ | |
| 62 | + Disallow: /business-school/undergraduate/summer-school/brochure/thank-you/ | |
| 63 | + Disallow: /business-school/undergraduate/mailing-list/thank-you | |
| 64 | + Disallow: /business-school/undergraduate/brochure/thank-you | |
| 65 | + Disallow: /business-school/masters/mailing-list/thank-you | |
| 66 | + Disallow: /business-school/masters/brochure/thank-you | |
| 67 | + Disallow: /business-school/mba/full-time-mba/class-profile/thank-you/ | |
| 68 | + Disallow: /business-school/mba/full-time-mba/career-impact/thank-you/ | |
| 69 | + Disallow: /business-school/mba/executive-mba/class-profile/thank-you/ | |
| 70 | + Disallow: /business-school/mba/executive-mba/consultation/thank-you/ | |
| 71 | + Disallow: /business-school/mba/weekend-mba/career-impact/thank-you/ | |
| 72 | + Disallow: /business-school/mba/weekend-mba/class-profile/thank-you/ | |
| 73 | + Disallow: /business-school/mba/weekend-mba/consultation/thank-you/ | |
| 74 | + Disallow: /business-school/mba/global-online-mba/consultation/thank-you/ | |
| 75 | + Disallow: /business-school/mba/global-online-mba/career-impact/thank-you/ | |
| 76 | + Disallow: /business-school/mba/brochure/thank-you | |
| 77 | + Disallow: /business-school/mba/mailing-list/thank-you | |
| 78 | + Disallow: /business-school/programmes/gmat-waiver/thank-you | |
| 79 | + Disallow: /business-school/masters/finance-employment-report-thank-you | |
| 80 | + Disallow: /business-school/masters/international-management/career-impact/thank-you/ | |
| 81 | + Disallow: /business-school/masters/international-management/consultation/thank-you/ | |
| 82 | + Disallow: /business-school/programmes/thank-you-for-registering/ | |
| 83 | + Disallow: /business-school/executive-education/virtual-programmes/request-call-back/thank-you/ | |
| 84 | + Disallow: /business-school/executive-education/staff-training-and-development/thank-you/ | |
| 85 | + Disallow: /business-school/executive-education/download-virtual-brochure/thank-you/ | |
| 86 | + Disallow: /business-school/executive-education/download-brochure/thank-you/ | |
| 87 | + Disallow: /business-school/executive-education/download-calendar/thank-you/ | |
| 88 | + Disallow: /business-school/executive-education/alumni-discount/thank-you/ | |
| 89 | + Disallow: /business-school/executive-education/application-form/group-bookings/thank-you/ | |
| 90 | + Disallow: /business-school/executive-education/request-call-back/thank-you/ | |
| 91 | + Disallow: /business-school/executive-education/application-form/virtual-programmes/thank-you/ | |
| 92 | + Disallow: /business-school/executive-education/custom-programmes/closed-group-programme-enquiry/thank-you/ | |
| 93 | + Disallow: /business-school/executive-education/events/webinar-thank-you/ | |
| 94 | + Disallow: /business-school/executive-education/contact-us/customised-programmes-enquiries/thank-you/ | |
| 95 | + Disallow: /business-school/executive-education/contact-us/short-courses-enquiry-form/thank-you/ | |
| 96 | + Disallow: /business-school/executive-education/events/sign-up/thank-you/ | |
| 97 | + Disallow: /business-school/executive-education/application-form/thank-you/ | |
| 98 | + Disallow: /business-school/news-and-events/sign-news-and-events/thank-you/ | |
| 99 | + Disallow: /business-school/events/webinar-thank-you-for-registering/ | |
| 100 | + Disallow: /business-school/corporate-relations/recruit-new-talent/request-student-cvs-and-profile-books/thank-you/ | |
| 101 | + Disallow: /business-school/sign-ib-knowledge/thank-you/ | |
| 102 | + Disallow: /business-school/programmes/one-to-one-thank-you/ | |
| 103 | + | |
| 104 | + # search | |
| 105 | + Disallow: /search/ | |
| 106 | + | |
| 107 | + # old courses, update yearly | |
| 108 | + Disallow: /study/ug/courses/archived/ | |
| 109 | + Disallow: /study/pg/courses/2018/ | |
| 110 | + Disallow: /study/courses/undergraduate/2023/ | |
| 111 | + Disallow: /study/courses/postgraduate-taught/2023/ | |
| 112 | + Disallow: /study/courses/undergraduate/2024/ | |
| 113 | + Disallow: /study/courses/postgraduate-taught/2024/ | |
| 114 | + Disallow: /study/courses/undergraduate/2025/ | |
| 115 | + Disallow: /study/courses/postgraduate-taught/2025/ | |
| 116 | + Disallow: /study/courses/undergraduate/2026/ | |
| 117 | + | |
| 118 | + # old open days | |
| 119 | + Disallow: /study/visit/undergraduate/on-demand/ | |
| 120 | + | |
| 121 | + # chat to graduates | |
| 122 | + Disallow: /study/chat-to-our-graduates/ | |
| 123 | + | |
| 124 | + # Campaigns WIP | |
| 125 | + Disallow: /campaigns/ | |
| 126 | + | |
| 127 | + # development sites and redesign content branches | |
| 128 | + Disallow: /dev-sites/ | |
| 129 | + Disallow: /redesign-content/ | |
| 130 | + Disallow: /website-testing/ | |
| 131 | + | |
| 132 | + # reporter | |
| 133 | + Disallow: /staff/reporter/ | |
| 134 | + | |
| 135 | + #Academic Strategy | |
| 136 | + Disallow: /academic-strategy/ | |
| 137 | + | |
| 138 | + #Welcome week | |
| 139 | + Disallow: /students/new-students/welcome/ | |
| 140 | + | |
| 141 | + #News redesign and test | |
| 142 | + Disallow: /redesign-news/ | |
| 143 | + Disallow: /news/training/ | |
| 144 | + | |
| 145 | + #College directory | |
| 146 | + Disallow: /collegedirectory/ | |
| 3 | 147 | |
| 4 | 148 | User-agent: * |
| 5 | 149 | Disallow: /terminalfour/SiteManager/ |