# If the Joomla site is installed within a folder such as at
# e.g. www.example.com/joomla/ the robots.txt file MUST be
# moved to the site root at e.g. www.example.com/robots.txt
# AND the joomla folder name MUST be prefixed to the disallowed
# path, e.g. the Disallow rule for the /administrator/ folder
# MUST be changed to read Disallow: /joomla/administrator/
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/orig.html
#
# For syntax checking, see:
# http://www.sxw.org.uk/computing/robots/check.html
# 屏蔽指定爬虫
User-agent: AhrefsBot
Disallow: /

User-agent: Dotbot
Disallow: /

User-agent: BlexBot
Disallow: /

User-agent: Dataprovider
Disallow: /

User-agent: Semantify.it
Disallow: /

User-agent: Sistrix
Disallow: /

User-agent: Cliqzbot
Disallow: /

User-agent: SiteSucker
Disallow: /

User-agent: wget
Disallow: /

User-agent: curl
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: Python-urllib
Disallow: /

User-agent: Java
Disallow: /

User-agent: BadBotNameHere
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: rogerbot
Disallow: /

User-agent: Screaming Frog SEO Spider
Disallow: /

# 防止爬虫（Spider/Bot）对特定 URL 过度抓取
User-agent: *
Crawl-delay: 10
Disallow: /@ningbomh8
Disallow: /@mhchin

# 允许其他所有爬虫访问网站，并禁止访问特定目录
User-agent: *
Allow: /*.js*
Allow: /*.css*
Allow: /*.png*
Allow: /*.jpg*
Allow: /*.gif*

Disallow: /administrator/
Disallow: /bin/
# 4SEO-opt Disallow: /cache/
Disallow: /cli/
# 4SEO-opt 
Disallow: /includes/
Disallow: /installation/
Disallow: /language/
Disallow: /libraries/
Disallow: /logs/
# 4SEO-opt 
# 4SEO-opt 
Disallow: /question/
Disallow: /tmp/


# JSitemap entries
Sitemap: https://www.mh-chine.com/index.php?option=com_jmap&view=sitemap&format=xml
Sitemap: https://www.mh-chine.com/index.php?option=com_jmap&view=sitemap&format=mobile