From f276e10d676df842cadd8d327f226c7498f486ff Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jakub=20Klinkovsk=C3=BD?= <lahwaacz@archlinux.org>
Date: Sun, 24 Dec 2023 21:08:02 +0100
Subject: [PATCH] archwiki: update robots.txt

- The /index.php? rule disallows all URLs with this prefix, so using
  longer prefixes does not make sense.
- Allow indexing of the Help: namespace which contains relevant text.
- Keep the intention of disallowing special namespaces, including the
  File: alias for Image: and using the /title/ path and colon separator
  for the namespace prefix.
---
 roles/archwiki/files/robots.txt | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/roles/archwiki/files/robots.txt b/roles/archwiki/files/robots.txt
index 4cc557d42..489957f5c 100644
--- a/roles/archwiki/files/robots.txt
+++ b/roles/archwiki/files/robots.txt
@@ -1,11 +1,8 @@
 User-agent: *
 Disallow: /index.php?
-Disallow: /index.php?diff=
-Disallow: /index.php?oldid=
-Disallow: /index.php?curid=
-Disallow: /index.php?title=Help
-Disallow: /index.php?title=Image
-Disallow: /index.php?title=MediaWiki
-Disallow: /index.php?title=Special:
-Disallow: /index.php?title=Template
 Disallow: /skins/
+Disallow: /title/File:
+Disallow: /title/Image:
+Disallow: /title/MediaWiki:
+Disallow: /title/Special:
+Disallow: /title/Template:
-- 
GitLab