diff --git a/public/robots.txt b/public/robots.txt index 3d1e9388..eeda15b2 100644 --- a/public/robots.txt +++ b/public/robots.txt @@ -1,5 +1,16 @@ -# no caching -User-agent: ia_archiver +# block all spiders by default +User-agent: * Disallow: / -User-agent: archive.org_bot + +# but allow major ones +User-agent: Googlebot +Allow: / + +User-agent: Slurp +Allow: / + +User-Agent: msnbot +Disallow: + +User-agent: Baiduspider Disallow: /