PageRenderTime 45ms CodeModel.GetById 20ms RepoModel.GetById 1ms app.codeStats 0ms

/alert/assets/templates/simple_pages/robots.txt

https://bitbucket.org/mlissner/search-and-awareness-platform-courtlistener
Plain Text | 69 lines | 59 code | 10 blank | 0 comment | 0 complexity | 1c63eaf458ce45f438142babe9d90cd5 MD5 | raw file
Possible License(s): MPL-2.0-no-copyleft-exception
  1. # Google, AOL, Bing, Yahoo!, DuckDuckGo
  2. # These support meta robots and x-robots-tag or are otherwise harmless (DDG)
  3. # Crawl everything except a few explicit blocks
  4. User-agent: Googlebot
  5. Disallow: /robots.txt
  6. Disallow: /dumps/
  7. Disallow: /assets/
  8. Disallow: /api/rest/v1/
  9. User-agent: bingbot
  10. Disallow: /robots.txt
  11. Disallow: /dumps/
  12. Disallow: /assets/
  13. Disallow: /api/rest/v1/
  14. User-agent: Slurp
  15. Disallow: /robots.txt
  16. Disallow: /dumps/
  17. Disallow: /assets/
  18. Disallow: /api/rest/v1/
  19. User-agent: DuckDuckBot
  20. Disallow: /robots.txt
  21. Disallow: /dumps/
  22. Disallow: /assets/
  23. Disallow: /api/rest/v1/
  24. # Yandex, Ask
  25. # These support meta robots, but not x-robots-tag
  26. # Crawl everything except real files
  27. User-agent: YandexBot
  28. Disallow: /robots.txt
  29. Disallow: /dumps/
  30. Disallow: /assets/
  31. Disallow: /api/rest/v1/
  32. Disallow: /pdf/
  33. Disallow: /wpd/
  34. Disallow: /txt/
  35. Disallow: /doc/
  36. User-agent: teoma
  37. Disallow: /robots.txt
  38. Disallow: /dumps/
  39. Disallow: /assets/
  40. Disallow: /api/rest/v1/
  41. Disallow: /pdf/
  42. Disallow: /wpd/
  43. Disallow: /txt/
  44. Disallow: /doc/
  45. User-agent: ia_archiver
  46. Disallow: /robots.txt
  47. Disallow: /dumps/
  48. Disallow: /assets/
  49. Disallow: /api/rest/v1/
  50. Disallow: /pdf/
  51. Disallow: /wpd/
  52. Disallow: /txt/
  53. Disallow: /doc/
  54. # Baidu, Blekko, Others
  55. # No support for robots meta tag nor x-robots-tag.
  56. # Be conservative; Block everything.
  57. User-agent: *
  58. Disallow: /
  59. Sitemap: https://www.courtlistener.com/sitemap.xml