From 5b455a2e0fdaec6b5b9c324ffbbe4bddd8c617ee Mon Sep 17 00:00:00 2001
From: Dries Buytaert <dries@buytaert.net>
Date: Mon, 14 Aug 2006 10:41:52 +0000
Subject: [PATCH] - Patch #75916 by Robert: re-introduced default robot.txt.
---
CHANGELOG.txt | 2 +-
robots.txt | 57 +++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 58 insertions(+), 1 deletion(-)
create mode 100644 robots.txt
diff --git a/CHANGELOG.txt b/CHANGELOG.txt
index 55a689b6f760..ee539a5fb70a 100644
--- a/CHANGELOG.txt
+++ b/CHANGELOG.txt
@@ -24,7 +24,7 @@ Drupal x.x.x, xxxx-xx-xx (development version)
* optionally allow people to cancel their vote.
- distributed authentication:
* added default server option.
-- fixed critical SQL issue, see SA-2006-005
+- added default robots.txt to control crawlers.
- database API:
* added db_table_exists().
- blogapi module:
diff --git a/robots.txt b/robots.txt
new file mode 100644
index 000000000000..c41c1a4243e1
--- /dev/null
+++ b/robots.txt
@@ -0,0 +1,57 @@
+# robots.txt
+#
+# This file aims to prevent the crawling and idexing of certain parts
+# of your site by web crawlers and spiders run by sites like Yahoo!
+# and Google. By telling these "robots" where not to go on your site,
+# you save bandwidth and server resources.
+#
+# For more information about the robots.txt standard, see:
+# http://www.robotstxt.org/wc/robots.html
+#
+# See this site for syntax checking:
+# http://www.sxw.org.uk/computing/robots/check.html
+
+User-agent: *
+Crawl-delay: 10
+# Directories
+Disallow: /files/
+Disallow: /database/
+Disallow: /includes/
+Disallow: /misc/
+Disallow: /modules/
+Disallow: /sites/
+Disallow: /themes/
+Disallow: /scripts/
+Disallow: /updates/
+Disallow: /profiles/
+# Files
+Disallow: /xmlrpc.php
+Disallow: /cron.php
+Disallow: /update.php
+Disallow: /install.php
+Disallow: /INSTALL.mysql.txt
+Disallow: /INSTALL.pgsql.txt
+Disallow: /CHANGELOG.txt
+Disallow: /MAINTAINERS.txt
+Disallow: /LICENSE.txt
+Disallow: /UPGRADE.txt
+# Paths (clean URLs)
+Disallow: /admin/
+Disallow: /aggregator/
+Disallow: /comment/reply/
+Disallow: /contact/
+Disallow: /logout/
+Disallow: /node/add/
+Disallow: /search/
+Disallow: /user/register/
+Disallow: /user/password/
+# Paths (no clean URLs)
+Disallow: /?q=admin/
+Disallow: /?q=aggregator/
+Disallow: /?q=comment/reply/
+Disallow: /?q=contact/
+Disallow: /?q=logout/
+Disallow: /?q=node/add/
+Disallow: /?q=search/
+Disallow: /?q=user/password/
+Disallow: /?q=user/register/
--
GitLab