3

共享访问主机上的 Liteserver 在这里。

我正试图摆脱许多无缘无故浪费我资源的机器人。

我可以使用特定的用户代理成功地限制对其中一些人的访问，但我不能禁止他们的 IP 地址，以及许多不断扫描我网站的中国人的 IP 地址。我仍然在访问日志中看到 AhrefsBot IP (5.10.83.44)，即使它的 IP 被禁止（参见 htaccess 文件的最后一行）。/gallery 子文件夹应该已经继承了这些规则。

5.10.83.44 - - [07/Sep/2013:00:56:42 +0200] "GET /gallery/addfav.php?pid=858&referer=displayimage.php%3Fpid%3D858 HTTP/1.1" 302 156 "-" " Mozilla/5.0（兼容；AhrefsBot/5.0；+ http://ahrefs.com/robot/）"

根的.htaccess

AddDefaultCharset UTF-8

<IfModule mod_headers.c>
  <FilesMatch "\.(js|css)$">
    Header append Vary Accept-Encoding
    Cache-Control: Private
  </FilesMatch>
</IfModule>

RewriteEngine on

#inherit from root htaccess and append at last, necessary in root too
RewriteOptions inherit

#block bad bots
RewriteCond %{HTTP_USER_AGENT} ^$ [OR]
RewriteCond %{HTTP_USER_AGENT} ^spider$ [OR]
RewriteCond %{HTTP_USER_AGENT} ^robot$ [OR]
RewriteCond %{HTTP_USER_AGENT} ^crawl$ [OR]
RewriteCond %{HTTP_USER_AGENT} ^(.*)AhrefsBot(.*) [OR]
RewriteCond %{HTTP_USER_AGENT} ^discovery$ [OR]
RewriteCond %{HTTP_USER_AGENT} ^Wget [OR]
RewriteCond %{HTTP_USER_AGENT} 360Spider [OR]
RewriteCond %{HTTP_USER_AGENT} Ezooms/1.0 [OR]
RewriteCond %{HTTP_USER_AGENT} MJ12bot/v1.4.4
RewriteRule ^(.*)$ http://go.away/

#include caching for images
<IfModule mod_expires.c>
    ExpiresActive On
    ExpiresByType image/gif "access plus 1 week"
    ExpiresByType image/jpg "access plus 1 week"
    ExpiresByType image/png "access plus 1 week"
    ExpiresByType image/x-icon "access plus 360 days"
    ExpiresByType text/css "access plus 1 day"
    ExpiresByType text/html "access plus 1 week"
    ExpiresByType text/javascript "access plus 1 week"  
    ExpiresByType text/x-javascript "access plus 1 week"
    ExpiresByType application/javascript "access plus 1 week"
    ExpiresByType application/x-javascript "access plus 1 week"
    ExpiresByType application/x-shockwave-flash "access plus 1 week"
    ExpiresByType font/truetype "access plus 1 month"
    ExpiresByType font/opentype "access plus 1 month"
    ExpiresByType application/x-font-otf "access plus 1 month"
</IfModule>


RewriteCond %{HTTP_HOST} ^id.foo.com$ [OR]
RewriteCond %{HTTP_HOST} ^www.id.foo.com$
RewriteRule ^/?$ "http\:\/\/foo\.myopenid\.com\/" [R=301,L]

Options +FollowSymLinks
RewriteCond %{HTTP_HOST} !^www\.
RewriteRule ^(.*)$ http://www.%{HTTP_HOST}/$1 [R=301,L]

#ban bots and stuff
order allow,deny
deny from 113.212.68.114
deny from 77.232.159.95
deny from 1.12.0.0/14
deny from 1.24.0.0/13
deny from 1.32.0.0/16
[...]
deny from 5.10.83.0/23
allow from all

/gallery 子文件夹 .htaccess

RewriteEngine On

#inherit from root htaccess and append at last
RewriteOptions inherit

##/**************************************************
##  Coppermine 1.5.x Plugin - sef_urls
##  *************************************************
##  Copyright (c) 2003-2007 Coppermine Dev Team
##  *************************************************
##  This program is free software; you can redistribute it and/or modify
##  it under the terms of the GNU General Public License as published by
##  the Free Software Foundation; either version 3 of the License, or
##  (at your option) any later version.
##  ********************************************
##  $HeadURL$
##  $Revision$
##  $LastChangedBy$
##  $Date$
##  **************************************************/

#Options FollowSymLinks SymLinksIfOwnerMatch

# RewriteEngine on

#  Uncomment the following line if your webserver's
#  URL is not directly related to physical file paths.
#  Update "YOUR_COPPERMINE_ROOT" (just / for root)

#RewriteBase /gallery

#
# Language translation
#

RewriteRule cerca.html(.*) search.php$1 [NC]

RewriteRule contatti.html(.*) contact.php$1 [NC]

RewriteRule (.*)migliore(.*) $1toprated$2 [NC]

RewriteRule (.*)popolari(.*) $1topn$2 [NC]

RewriteRule (.*)osservazionedi(.*) $1lastcomby$2 [NC]

RewriteRule (.*)osservazione(.*) $1lastcom$2 [NC]

RewriteRule (.*)pagina(.*) $1page$2 [NC]

RewriteRule (.*)listautenti(.*) $1usermgr$2 [NC]

RewriteRule (.*)profilo(.*) $1profile$2 [NC]

RewriteRule (.*)miniature(.*) $1thumbnails$2 [NC]

RewriteRule (.*)mostra(.*) $1displayimage$2 [NC]

RewriteRule (.*)novitadi(.*) $1lastupby$2 [NC]

RewriteRule (.*)novita(.*) $1lastup$2 [NC]

RewriteRule (.*)cerca(.*) $1search$2 [NC]

RewriteRule (.*)top(.*) $1top_display_media$2 [NC]


#
# Rewrite usrmgr urls
#

RewriteRule usermgr-page-([0-9]*).html(.*) usermgr.php?page=$1$2 [NC]

RewriteRule usermgr.html(.*) usermgr.php$1 [NC]

#
# Rewrite index urls
#

RewriteRule index.html(.*) index.php$1 [NC]

RewriteRule index-([0-9]*)\.html(.*) index.php?cat=$1$2 [NC]

RewriteRule index-([0-9]*)-page-([0-9]*)\.html(.*) index.php?cat=$1&page=$2$3 [NC]


#
# Rewrite thumbnail urls
#

RewriteRule thumbnails-lastupby-([0-9]+)\.html(.*) thumbnails.php?album=lastupby&uid=$1$2 [NC]

RewriteRule thumbnails-lastcomby-([0-9]+)\.html(.*) thumbnails.php?album=lastcomby&uid=$1$2 [NC]

RewriteRule thumbnails-lastupby-([0-9]+)-([0-9]+)-page-([0-9]+)\.html(.*) thumbnails.php?album=lastupby&cat=$1&uid=$2&page=$3$4 [NC]

RewriteRule thumbnails-lastcomby-([0-9]+)-([0-9]+)-page-([0-9]+)\.html(.*) thumbnails.php?album=lastcomby&cat=$1&uid=$2&page=$3$4 [NC]

RewriteRule thumbnails-([a-z0-9]*)-([\-]?[0-9]*)\.html(.*) thumbnails.php?album=$1&cat=$2$3 [NC]

RewriteRule thumbnails-page-([0-9]*)-([a-z0-9]*).*\.html(.*) thumbnails.php?album=$2&page=$1$3 [NC]

RewriteRule thumbnails-([a-z0-9]*)-([\-]?[0-9]*)-page-([0-9]*)\.html(.*) thumbnails.php?album=$1&cat=$2&page=$3$4 [NC]

RewriteRule thumbnails-search-keyword-(.*)\.html(.*) thumbnails.php?album=search&keywords=on&search=$1$2 [NC]

RewriteRule thumbnails-search-(.*)\.html(.*) thumbnails.php?album=search&search=$1$2 [NC]

RewriteRule thumbnails-([0-9a-z]*).*\.html(.*) thumbnails.php?album=$1$2 [NC]


#
# Rewrite displayimage urls
#

RewriteRule displayimage-lastcom-([\-]?[0-9]+)-([\-]?[0-9]+)-([\-]?[0-9]+)-page-([\-]?[0-9]+).html(.*) displayimage.php?album=lastcom&cat=$1&pid=$2&msg_id=$3&page=$4$5 [NC]

RewriteRule displayimage-([a-z0-9]+)-([\-]?[0-9]+)-([\-]?[0-9]+)-([\-]?[0-9]+)-([\-]?[0-9]+)-([\-]?[0-9]+)\.html(.*) displayimage.php?album=$1&cat=$2&pid=$3&uid=$4&msg_id=$5&page=$6$7 [NC]

RewriteRule displayimage-([a-z0-9]+)-([\-]?[0-9]+)-([\-]?[0-9]+)-([\-]?[0-9]+)\.html(.*) displayimage.php?album=$1&cat=$2&pid=$3&uid=$4$5 [NC]

RewriteRule displayimage-([a-z0-9]+)-([\-]?[0-9]+)-([\-]?[0-9]+).*\.html(.*) displayimage.php?album=$1&cat=$2&pid=$3$4 [NC]

RewriteRule displayimage-([a-z0-9]+)-([\-]?[0-9]+).*\.html(.*) displayimage.php?album=$1&pid=$2$3 [NC]

RewriteRule displayimage-([0-9]+).*\.html(.*) displayimage.php?pid=$1$2 [NC]


#
# Rewrite users profiles
#

RewriteRule profile-op-([a-z0-9_]+)\.html(.*) profile.php?op=$1 [NC]

RewriteRule profile-([0-9]+).*\.html(.*) profile.php?uid=$1$2 [NC]

我确定我错过了一些东西，但不幸的是我不知道。

有什么提示吗？

4

1 回答 1

1

根据那个AhrefBot 的链接，这就是停止该特定机器人所需要做的一切：

user-agent: AhrefsBot
disallow: /

通过将上述内容添加到robots.txt文档根目录中的文件中。

另一件事是这样的：

order allow,deny

顺序错误。根据apache 的 mod_access 文档：

允许否认

首先，评估所有Allow指令；至少一个必须匹配，否则请求将被拒绝。接下来，评估所有拒绝指令。如果有任何匹配，则拒绝该请求。最后，默认情况下拒绝任何与Allow或Deny指令不匹配的请求。

因为你有“全部允许”，它首先被评估，不同的“拒绝”永远不会被评估。所以你要：

Order Deny,Allow
于 2013-09-06T23:37:16.380 回答