Commit c2549849 authored by Holger Levsen's avatar Holger Levsen
Browse files

block some bots for good

parent b0fe38dd
Loading
Loading
Loading
Loading
+39 −20
Original line number Diff line number Diff line
@@ -20,36 +20,61 @@
	ServerAdmin holger@layer-acht.org

	#block bad bots with a 403
	SetEnvIfNoCase User-Agent "facebookexternalhit" bad_bot
	SetEnvIfNoCase User-Agent "Twitterbot" bad_bot
	SetEnvIfNoCase User-Agent "AhrefsBot" bad_bot
	SetEnvIfNoCase User-Agent "Baiduspider" bad_bot
	SetEnvIfNoCase User-Agent "MetaURI" bad_bot
	SetEnvIfNoCase User-Agent "mediawords" bad_bot
	SetEnvIfNoCase User-Agent "Exabot" bad_bot
	SetEnvIfNoCase User-Agent "Experibot" bad_bot
	SetEnvIfNoCase User-Agent "facebookexternalhit" bad_bot
	SetEnvIfNoCase User-Agent "FlipboardProxy" bad_bot
	SetEnvIfNoCase User-Agent "ltx71" bad_bot
	SetEnvIfNoCase User-Agent "mediawords" bad_bot
	SetEnvIfNoCase User-Agent "MetaURI" bad_bot
	SetEnvIfNoCase User-Agent "SemrushBot" bad_bot
	SetEnvIfNoCase User-Agent "Sogou web spider" bad_bot
	SetEnvIfNoCase User-Agent "Twitterbot" bad_bot
	SetEnvIfNoCase User-Agent "yacybot" bad_bot
	#end block bad bots

	<Directory />
		Options FollowSymLinks
		AllowOverride None
		<Limit GET POST HEAD>
		  Order Allow,Deny
		  Allow from all
		  Deny from env=bad_bot
		</Limit>
	</Directory>
	<Directory /var/www/>
		Options Indexes FollowSymLinks MultiViews
		AllowOverride None
		Require all granted
		AddType text/plain .log
		<Limit GET POST HEAD>
		  Order Allow,Deny
		  Allow from all
		  Deny from env=bad_bot
		</Limit>
	</Directory>
	<Directory /var/lib/jenkins/userContent>
		Options Indexes FollowSymLinks MultiViews
		AllowOverride None
		Require all granted
		AddType text/plain .log
		<Limit GET POST HEAD>
		  Order Allow,Deny
		  Allow from all
		  Deny from env=bad_bot
		</Limit>
	</Directory>
	<Directory /srv/reproducible-builds.org/lfs>
		Options Indexes FollowSymlinks MultiViews
		AllowOverride None
		Require all granted
		<Limit GET POST HEAD>
		  Order Allow,Deny
		  Allow from all
		  Deny from env=bad_bot
		</Limit>
	</Directory>

	<FilesMatch "\.gz$">
@@ -80,11 +105,6 @@ Use https-redirect www.diffoscope.org
	Use common-directives tests.reproducible-builds.org
	RedirectMatch permanent "^/((?!debian/repository/debian/).*)" https://tests.reproducible-builds.org/$1
	DocumentRoot /var/lib/jenkins/userContent/reproducible
	<Limit GET POST HEAD>
	  Order Allow,Deny
	  Allow from all
	  Deny from env=bad_bot
	</Limit>
</VirtualHost>

<VirtualHost *:443>
@@ -107,11 +127,6 @@ Use https-redirect www.diffoscope.org
	DocumentRoot /var/www
	AddDefaultCharset utf-8

	<Limit GET POST HEAD>
	  Order Allow,Deny
	  Allow from all
	  Deny from env=bad_bot
	</Limit>

	Alias /userContent /var/lib/jenkins/userContent
	Alias /robots.txt /var/lib/jenkins/userContent/robots.txt
@@ -172,16 +187,15 @@ Use https-redirect www.diffoscope.org
	DocumentRoot /var/lib/jenkins/userContent/reproducible
	AddDefaultCharset utf-8

	Include reproduciblemap.conf

	<Directory /var/lib/jenkins/userContent/reproducible/debian/artifacts>
		HeaderName .HEADER.html
		<Limit GET POST HEAD>
		  Order Allow,Deny
		  Allow from all
		  Deny from env=bad_bot
		</Limit>

	Include reproduciblemap.conf

	<Directory /var/lib/jenkins/userContent/reproducible/debian/artifacts>
		HeaderName .HEADER.html
	</Directory>

	# for watching service logfiles
@@ -190,6 +204,11 @@ Use https-redirect www.diffoscope.org
	    AllowOverride None
	    Options +ExecCGI -MultiViews +SymLinksIfOwnerMatch
	    Require all granted
		<Limit GET POST HEAD>
		  Order Allow,Deny
		  Allow from all
		  Deny from env=bad_bot
		</Limit>
	</Directory>
	# Use the sso.debian.org CA to validate client certificates
	# Keep these files up to date with update-debsso-ca