.htaccess 规则从 URL 中删除（如果存在）？

Question

我们的一个网站出现问题，有时我们会看到一个与我们网站上的任何真实页面无关的长 URL。例如 URL 应该是

https://example.com/browse 

但是一百分之一我们得到这个

https://example.com/index.php/module/action/param1/static/PFBC/js/jquery/rss/signup/static/js/jquery/templates/themes/love/img/icon/asset/css/legal/user/album/tipocorneo/me/browse

它并不总是相同的 URL，它会不时更改，但我的问题是……是否有我们可以使用的重写规则来简单地删除 URL 的额外部分（如果存在）？

RewriteEngine On
RewriteCond %{HTTPS} off
RewriteRule ^(.*)$ https://%{HTTP_HOST}%{REQUEST_URI} [L,R=301]

<IfModule mod_rewrite.c>
    <IfModule mod_negotiation.c>
        Options -MultiViews -Indexes
    </IfModule>
    Options +FollowSymLinks

</IfModule>

<IfModule mod_php5.c>
    php_flag allow_url_include Off
    php_flag expose_php Off
</IfModule>

### Security and Spam ###

# Protect the repository directory
<IfModule mod_rewrite.c>
    RewriteRule "(^|/)\.git" - [F,L]
</IfModule>

ServerSignature Off

# Deny access to all CGI, Perl, Python, Bash, SQL, Template, INI configuration, cache, log, temporary and text files
<FilesMatch "\.(cgi|pl|py|sh|bash|sql|tpl|ini|cache|log|tmp|txt)$">
    <IfModule mod_authz_core.c>
        Require all denied
    </IfModule>
</FilesMatch>

# Leave open the humans.txt and robots.txt file
<FilesMatch "humans\.txt|robots\.txt">
    <IfModule mod_authz_core.c>
        Require all granted
    </IfModule>
</FilesMatch>

# Deny access for "composer.json"
<FilesMatch "composer\.json|sample\.htaccess">
    <IfModule mod_authz_core.c>
        Require all denied
    </IfModule>
</FilesMatch>

# Prevent .htaccess/.htpasswd from being downloaded
<Files ~ "^\.ht">
    <IfModule mod_authz_core.c>
        Require all denied
    </IfModule>
</Files>

<Limit GET POST PUT DELETE HEAD>
    <IfModule mod_authz_core.c>
        <RequireAll>
            Require all granted
            Require not env bad_bot
        </RequireAll>
    </IfModule>
</Limit>

ErrorDocument 400 /error/http/index?code=400
ErrorDocument 401 /error/http/index?code=401
ErrorDocument 402 /error/http/index?code=402
ErrorDocument 403 /error/http/index?code=403
ErrorDocument 404 /error
ErrorDocument 405 /error/http/index?code=405
ErrorDocument 500 /error/http/index?code=500
ErrorDocument 501 /error/http/index?code=501
ErrorDocument 502 /error/http/index?code=502
ErrorDocument 504 /error/http/index?code=504
ErrorDocument 505 /error/http/index?code=505

# URL Rewrite
<IfModule mod_rewrite.c>
    <IfModule mod_env.c>
        # Tell PHP that the mod_rewrite module is ENABLED.
        SetEnv HTTP_MOD_REWRITE On
    </IfModule>

    # Uncomment the following only if HTTPS is enabled. HSTS header increases security of your website & SEO
    # <IfModule mod_headers.c>
    # Header set Strict-Transport-Security "max-age=31536000; preload" env=HTTPS
    # </IfModule>

    # Remove www subdomain in the URL
    # RewriteCond %{HTTP_HOST} ^www\.(.+)$ [NC]
    # RewriteRule ^(.*)$ http://%1/$1 [R=301,L]

    # Force the URL to be https (only if you have an SSL certificate). May not be necessary if HSTS is enabled
    # RewriteCond %{SERVER_PORT} 80
    # RewriteRule ^(.*)$ https://%{HTTP_HOST}%{REQUEST_URI} [R=301,L]

    RewriteCond %{REQUEST_FILENAME} !-f
    RewriteCond %{REQUEST_FILENAME} !-d

    RewriteRule ^(.*)$ index.php?$1 [L,QSA]

    # Start Bad Bot Prvention
    RewriteCond %{HTTP_USER_AGENT} ^BackWeb [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Bandit [OR]
    RewriteCond %{HTTP_USER_AGENT} ^BatchFTP [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Buddy [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Collector [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Copier [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Download\Wonder [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Downloader [OR]
    RewriteCond %{HTTP_USER_AGENT} ^LinkWalker [OR]
    RewriteCond %{HTTP_USER_AGENT} ^BlackWidow [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Bot\ mailto:craftbot@yahoo.com [OR]
    RewriteCond %{HTTP_USER_AGENT} ^ChinaClaw [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Custo [OR]
    RewriteCond %{HTTP_USER_AGENT} ^DISCo [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Download\ Demon [OR]
    RewriteCond %{HTTP_USER_AGENT} ^eCatch [OR]
    RewriteCond %{HTTP_USER_AGENT} ^EirGrabber [OR]
    RewriteCond %{HTTP_USER_AGENT} ^EmailSiphon [OR]
    RewriteCond %{HTTP_USER_AGENT} ^EmailWolf [OR]
    RewriteCond %{HTTP_USER_AGENT} ^EmailCollector [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Crescent [OR]
    RewriteCond %{HTTP_USER_AGENT} ^CherryPicker [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Express\ WebPictures [OR]
    RewriteCond %{HTTP_USER_AGENT} ^ExtractorPro [OR]
    RewriteCond %{HTTP_USER_AGENT} ^EyeNetIE [OR]
    RewriteCond %{HTTP_USER_AGENT} ^FlashGet [OR]
    RewriteCond %{HTTP_USER_AGENT} ^GetRight [OR]
    RewriteCond %{HTTP_USER_AGENT} ^GetWeb! [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Go!Zilla [OR]
    RewriteCond %{HTTP_USER_AGENT} ^gotit [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Go-Ahead-Got-It [OR]
    RewriteCond %{HTTP_USER_AGENT} ^GrabNet [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Grafula [OR]
    RewriteCond %{HTTP_USER_AGENT} ^HMView [OR]
    RewriteCond %{HTTP_USER_AGENT} HTTrack [NC,OR]
    RewriteCond %{HTTP_USER_AGENT} ^Image\ Stripper [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Image\ Sucker [OR]
    RewriteCond %{HTTP_USER_AGENT} Indy\ Library [NC,OR]
    RewriteCond %{HTTP_USER_AGENT} ^InterGET [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Internet\ Ninja [OR]
    RewriteCond %{HTTP_USER_AGENT} ^JetCar [OR]
    RewriteCond %{HTTP_USER_AGENT} ^JOC\ Web\ Spider [OR]
    RewriteCond %{HTTP_USER_AGENT} ^larbin [OR]
    RewriteCond %{HTTP_USER_AGENT} ^libghttp [OR]
    RewriteCond %{HTTP_USER_AGENT} ^LeechFTP [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Mass\ Downloader [OR]
    RewriteCond %{HTTP_USER_AGENT} ^MIDown\ tool [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Mister\ PiX [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Navroad [OR]
    RewriteCond %{HTTP_USER_AGENT} ^NearSite [OR]
    RewriteCond %{HTTP_USER_AGENT} ^NetAnts [OR]
    RewriteCond %{HTTP_USER_AGENT} ^NetSpider [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Net\ Vampire [OR]
    RewriteCond %{HTTP_USER_AGENT} ^NetZIP [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Octopus [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Offline\ Explorer [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Offline\ Navigator [OR]
    RewriteCond %{HTTP_USER_AGENT} ^PageGrabber [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Papa\ Foto [OR]
    RewriteCond %{HTTP_USER_AGENT} ^pavuk [OR]
    RewriteCond %{HTTP_USER_AGENT} ^pcBrowser [OR]
    RewriteCond %{HTTP_USER_AGENT} libwww-perl.* [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Pockey [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Pump [OR]
    RewriteCond %{HTTP_USER_AGENT} ^RealDownload [OR]
    RewriteCond %{HTTP_USER_AGENT} ^ReGet [OR]
    RewriteCond %{HTTP_USER_AGENT} ^SiteSnagger [OR]
    RewriteCond %{HTTP_USER_AGENT} ^SmartDownload [OR]
    RewriteCond %{HTTP_USER_AGENT} ^SuperBot [OR]
    RewriteCond %{HTTP_USER_AGENT} ^SuperHTTP [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Surfbot [OR]
    RewriteCond %{HTTP_USER_AGENT} ^tAkeOut [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Teleport\ Pro [OR]
    RewriteCond %{HTTP_USER_AGENT} ^VoidEYE [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Web\ Image\ Collector [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Web\ Sucker [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebAuto [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebCopier [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebFetch [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebGo\ IS [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebLeacher [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebReaper [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebSauger [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Website\ eXtractor [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Website\ Quester [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebStripper [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebWhacker [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WebZIP [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Wget [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Widow [OR]
    RewriteCond %{HTTP_USER_AGENT} ^WWWOFFLE [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Xaldon\ WebSpider [OR]
    RewriteCond %{HTTP_USER_AGENT} ^Zeus
    RewriteRule ^.* - [F,L]
    # End Bad Bot Prevention
</IfModule>

# Modify Headers
<IfModule mod_headers.c>
    # Cache files
    <FilesMatch "\.(jpe?g|png|gif|ico|webp|swf|mp3|mp4|flv|webm|pdf)$">
        Header set Cache-Control "public"
        Header set Expires "Mon, 20 Apr 2060 20:00:00 GMT"
        Header unset Last-Modified
    </FilesMatch>

    # Cache JavaScript & CSS
    <FilesMatch "\.(js|css)$">
        Header set Cache-Control "public"
        Header set Expires "Mon, 20 Apr 2060 20:00:00 GMT"
        Header unset Last-Modified
    </FilesMatch>
</IfModule>

# Compress files
<IfModule mod_deflate.c>
    # Insert filter
    SetOutputFilter DEFLATE
    <IfModule mod_setenvif.c>
        # Netscape 4.x has some problems...
        BrowserMatch ^Mozilla/4 gzip-only-text/html
        # Netscape 4.06-4.08 have some more problems
        BrowserMatch ^Mozilla/4\.0[678] no-gzip
        # MSIE masquerades as Netscape, but it is fine
        BrowserMatch \bMSIE !no-gzip !gzip-only-text/html
        # Don't compress images/archives/music/video/etc
        SetEnvIfNoCase Request_URI \.(?:gif|jpe?g|png)$ no-gzip dont-vary
        SetEnvIfNoCase Request_URI \.(?:exe|t?gz|zip|bz2|sit|rar)$ no-gzip dont-vary
        SetEnvIfNoCase Request_URI \.(?:avi|mov|mp3|mp4|rm|flv|swf|mp?g)$ no-gzip dont-vary
    </IfModule>
    <IfModule mod_headers.c>
        # Make sure proxies don't deliver the wrong content
        Header append Vary User-Agent env=!dont-vary
    </IfModule>
</IfModule>

# Enable Expirations
<IfModule mod_expires.c>
    ExpiresActive On
    ExpiresDefault "access plus 1 month"
    # expire images/css/js/swf files after a month in the client's cache
    ExpiresByType text/css "access plus 31 days"
    ExpiresByType text/javascript "access plus 31 days"
    ExpiresByType application/javascript "access plus 31 days"
    ExpiresByType application/x-javascript "access plus 31 days"
    ExpiresByType application/x-gzip "access plus 31 days"
    ExpiresByType image/gif "access plus 31 days"
    ExpiresByType image/jpeg "access plus 31 days"
    ExpiresByType image/png "access plus 31 days"
    ExpiresByType application/x-shockwave-flash "access plus 31 days"
    ExpiresByType image/vnd.microsoft.icon "access plus 31 days"
    ExpiresByType image/x-icon "access plus 1 year"
</IfModule>

# For the videos extensions
#AddType video/ogg .ogg
AddType video/webm .webm
AddType video/mp4 .mp4
AddType application/rss+xml .xml

Answer 1

要将/index.php/foo/bar/baz/something 重定向到/something，您可以在.htaccess 文件的最顶部执行以下操作：

RewriteRule ^index\.php/[\w/]+/([\w]+)$ https://%{HTTP_HOST}/$1 [R=302,L]

速记字符类 \w 匹配单词字符（a-z、A-Z、0-9 和 _），因此匹配给定的示例 URL。

此重定向还规范了该方案，因此将此指令放置在 HTTP 到 HTTPS 重定向之前，以避免在请求 HTTP 时进行第二次重定向。

但是，这种性质的 URL 确实表明您的站点/应用程序中存在错误配置。虽然，它也可能是一个恶意请求（尽管 URL 中的非垃圾邮件内容并没有真正暗示这一点）。

您应该检查服务器访问日志中的 Referer 是否有这些请求，这应该可以为您提供有关其来源的线索。

Answer 2

这是donatJ写的正确答案

    RewriteEngine On

    RewriteRule ^index\.php/module/action/param1/.*/(.*+)$ /$1 [L,R=301]