TSMC / robots.txt snapshot
← back to tsmc.com · fetched 2026-06-20T11:49:25Z (7h ago) · HTTP 200 · 1197 bytes · sha256 da0b4d32079977e5 · raw
final URL: manual:file
| 1 | # |
| 2 | # robots.txt |
| 3 | # |
| 4 | # This file is to prevent the crawling and indexing of certain parts |
| 5 | # of your site by web crawlers and spiders run by sites like Yahoo! |
| 6 | # and Google. By telling these "robots" where not to go on your site, |
| 7 | # you save bandwidth and server resources. |
| 8 | # |
| 9 | # This file will be ignored unless it is at the root of your host: |
| 10 | # Used: http://example.com/robots.txt |
| 11 | # Ignored: http://example.com/site/robots.txt |
| 12 | # |
| 13 | # For more information about the robots.txt standard, see: |
| 14 | # http://www.robotstxt.org/robotstxt.html |
| 15 | |
| 16 | User-agent: * |
| 17 | # CSS, JS, Images |
| 18 | Allow: /core/*.css$ |
| 19 | Allow: /core/*.css? |
| 20 | Allow: /core/*.js$ |
| 21 | Allow: /core/*.js? |
| 22 | Allow: /core/*.gif |
| 23 | Allow: /core/*.jpg |
| 24 | Allow: /core/*.jpeg |
| 25 | Allow: /core/*.png |
| 26 | Allow: /core/*.svg |
| 27 | Allow: /profiles/*.css$ |
| 28 | Allow: /profiles/*.css? |
| 29 | Allow: /profiles/*.js$ |
| 30 | Allow: /profiles/*.js? |
| 31 | Allow: /profiles/*.gif |
| 32 | Allow: /profiles/*.jpg |
| 33 | Allow: /profiles/*.jpeg |
| 34 | Allow: /profiles/*.png |
| 35 | Allow: /profiles/*.svg |
| 36 | # Directories |
| 37 | Disallow: /core/ |
| 38 | Disallow: /profiles/ |
| 39 | # Files |
| 40 | Disallow: /README.txt |
| 41 | Disallow: /web.config |
| 42 | # Paths (clean URLs) |
| 43 | Disallow: /filter/tips |
| 44 | Disallow: /search/ |
| 45 | # Paths (no clean URLs) |
| 46 | Disallow: /index.php/filter/tips |
| 47 | Disallow: /index.php/search/ |
| 48 |