Change robots.txt to exclude some URLs (#10037)

- Exclude static assets
- Exclude uploaded files
- Exclude alternate versions of the profile page
- Exclude media proxy URLs

diff --git a/public/robots.txt b/public/robots.txt
index 3c9c7c01f30b90e009de2d15952ae83230f8e37a..36afc85eff582b40a6ee4f87f4389aecc53f904f 100644 (file)
--- a/public/robots.txt
+++ b/public/robots.txt
@@ -1,5 +1,13 @@
-# See http://www.robotstxt.org/robotstxt.html for documentation on how to use the robots.txt file
-#
-# To ban all spiders from the entire site uncomment the next two lines:
-# User-agent: *
-# Disallow: /
+User-Agent: *
+Disallow: /users/*/followers
+Disallow: /users/*/following
+Disallow: /@*/media
+Disallow: /@*/with_replies
+Disallow: /@*/tagged/*
+Disallow: /media_proxy/*
+Disallow: /emoji/*
+Disallow: /packs/*
+Disallow: /sounds/*
+Disallow: /system/*
+Disallow: /avatars/*
+Disallow: /headers/*