Merge pull request #9564 from bbodenmiller/robots.txt

disallow irrelevant pages by defaults in robots

2 files changed, 63 insertions, 1 deletions

diff --git a/CHANGELOG b/CHANGELOG
index 1683b9ac094..0ed952086d5 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -1,6 +1,7 @@
 Please view this file on the master branch, on stable branches it's out of date.
 
 v 7.14.0 (unreleased)
+  - Update default robots.txt rules to disallow crawling of irrelevant pages (Ben Bodenmiller)
   - Upgrade gitlab_git to 7.2.14 to ignore CRLFs in .gitmodules (Stan Hu)
   - Provide more feedback what went wrong if HipChat service failed test (Stan Hu)
   - Fix bug where backslashes in inline diffs could be dropped (Stan Hu)
diff --git a/public/robots.txt b/public/robots.txt
index 085187fa58b..528f421083e 100644
--- a/public/robots.txt
+++ b/public/robots.txt
@@ -1,5 +1,66 @@
-# See http://www.robotstxt.org/wc/norobots.html for documentation on how to use the robots.txt file
+# 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: *
+
+# Add a 1 second delay between successive requests to the same server, limits resources used by crawler
+# Only some crawlers respect this setting, e.g. Googlebot does not
+# Crawl-delay: 1
+
+# Based on details in https://gitlab.com/gitlab-org/gitlab-ce/blob/master/config/routes.rb, https://gitlab.com/gitlab-org/gitlab-ce/blob/master/spec/routing, and using application
+Disallow: /autocomplete/users
+Disallow: /search
+Disallow: /api
+Disallow: /admin
+Disallow: /profile
+Disallow: /dashboard
+Disallow: /projects/new
+Disallow: /groups/new
+Disallow: /groups/*/edit
+Disallow: /users
+
+# Global snippets
+Disallow: /s
+Disallow: /snippets/new
+Disallow: /snippets/*/edit
+Disallow: /snippets/*/raw
+
+# Project details
+Disallow: /*/*.git
+Disallow: /*/*/fork/new
+Disallow: /*/*/repository/archive*
+Disallow: /*/*/activity
+Disallow: /*/*/new
+Disallow: /*/*/edit
+Disallow: /*/*/raw
+Disallow: /*/*/blame
+Disallow: /*/*/commits/*/*
+Disallow: /*/*/commit
+Disallow: /*/*/compare
+Disallow: /*/*/branches/new
+Disallow: /*/*/tags/new
+Disallow: /*/*/network
+Disallow: /*/*/graphs
+Disallow: /*/*/milestones/new
+Disallow: /*/*/milestones/*/edit
+Disallow: /*/*/issues/new
+Disallow: /*/*/issues/*/edit
+Disallow: /*/*/merge_requests/new
+Disallow: /*/*/merge_requests/*.patch
+Disallow: /*/*/merge_requests/*.diff
+Disallow: /*/*/merge_requests/*/edit
+Disallow: /*/*/merge_requests/*/diffs
+Disallow: /*/*/project_members/import
+Disallow: /*/*/labels/new
+Disallow: /*/*/labels/*/edit
+Disallow: /*/*/wikis/*/edit
+Disallow: /*/*/snippets/new
+Disallow: /*/*/snippets/*/edit
+Disallow: /*/*/snippets/*/raw
+Disallow: /*/*/deploy_keys
+Disallow: /*/*/hooks
+Disallow: /*/*/services
+Disallow: /*/*/protected_branches