Project-Pro/wyczarujprezent.pl
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Dodano blokowanie niepożądanych botów w pliku .htaccess

Browse Source
This commit is contained in:
Jacek Pyziak
2026-02-18 15:00:12 +01:00
parent 764d54f8d5
commit 34bd10e1d9
1 changed files with 96 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

96
.htaccess
View File

@@ -112,3 +112,99 @@ ErrorDocument 404 /index.php?controller=404
# ~~end~~ Do not remove this comment, Prestashop will keep automatically the code outside this comment when .htaccess will be generated again
# =============================================================================
# BLOKOWANIE NIEPOZADANYCH BOTOW
# Dodano: 2026-02-18
# =============================================================================
<IfModule mod_rewrite.c>
RewriteEngine On
# --- Duzy ruch, brak korzysci ---
# Python scrapers (10% ruchu)
RewriteCond %{HTTP_USER_AGENT} python [NC]
RewriteRule .* - [F,L]
# AhrefsBot - komercyjny crawler SEO (9.9% ruchu, 2.9GB)
RewriteCond %{HTTP_USER_AGENT} ahrefsbot [NC]
RewriteRule .* - [F,L]
# MJ12bot - Majestic SEO (5.4% ruchu, 1.4GB)
RewriteCond %{HTTP_USER_AGENT} mj12bot [NC]
RewriteRule .* - [F,L]
# Wget - narzedzie do pobierania/scrapowania (4.8% ruchu)
RewriteCond %{HTTP_USER_AGENT} wget [NC]
RewriteRule .* - [F,L]
# SemrushBot - crawler SEO (1.5% ruchu)
RewriteCond %{HTTP_USER_AGENT} semrushbot [NC]
RewriteRule .* - [F,L]
# BaiduSpider - chinska wyszukiwarka (bezuzyteczna dla PL)
RewriteCond %{HTTP_USER_AGENT} baiduspider [NC]
RewriteRule .* - [F,L]
# Brak User-Agent - podejrzany ruch (1.2% ruchu, 2.4GB!)
RewriteCond %{HTTP_USER_AGENT} ^-?$
RewriteRule .* - [F,L]
# CCBot - Common Crawl (zbieranie danych do AI)
RewriteCond %{HTTP_USER_AGENT} ccbot [NC]
RewriteRule .* - [F,L]
# 360Spider - chinska wyszukiwarka
RewriteCond %{HTTP_USER_AGENT} 360spider [NC]
RewriteRule .* - [F,L]
# --- Maly ruch, bezuzyteczne ---
# DotBot - Moz crawler
RewriteCond %{HTTP_USER_AGENT} dotbot [NC]
RewriteRule .* - [F,L]
# Yandex - rosyjska wyszukiwarka
RewriteCond %{HTTP_USER_AGENT} yandex [NC]
RewriteRule .* - [F,L]
# Scanner - skanery bezpieczenstwa
RewriteCond %{HTTP_USER_AGENT} scanner [NC]
RewriteRule .* - [F,L]
# curl - narzedzie CLI
RewriteCond %{HTTP_USER_AGENT} ^curl [NC]
RewriteRule .* - [F,L]
# libwww - biblioteka Perl
RewriteCond %{HTTP_USER_AGENT} libwww [NC]
RewriteRule .* - [F,L]
# Java bot
RewriteCond %{HTTP_USER_AGENT} ^java [NC]
RewriteRule .* - [F,L]
# Falszywy/okrojony User-Agent (dokladnie "Mozilla/5.0" i nic wiecej)
RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0$
RewriteRule .* - [F,L]
# PHP bot
RewriteCond %{HTTP_USER_AGENT} ^php [NC]
RewriteRule .* - [F,L]
# fast-webcrawler
RewriteCond %{HTTP_USER_AGENT} fast-webcrawler [NC]
RewriteRule .* - [F,L]
# Netcraft - skaner
RewriteCond %{HTTP_USER_AGENT} netcraft [NC]
RewriteRule .* - [F,L]
# Motor - nieznany bot
RewriteCond %{HTTP_USER_AGENT} ^motor [NC]
RewriteRule .* - [F,L]
</IfModule>
# =============================================================================
# KONIEC BLOKOWANIA BOTOW
# =============================================================================