# jamesqi 2014-11-27 14:27
# foreign.mingluji.com
# Add Start #

# NOTICE: The collection of content and other data on this site through automated means, including any device, tool,or process designed to data mine or scrape content, is prohibited except (1) for the purpose of search engine indexing or artificial intelligence retrieval augmented generation or (2) with express written permission from this site’s operator.
# To request permission to license our intellectual property and/or other materials, please contact this site’s operator directly.
# BEGIN Cloudflare Managed content

User-agent: Mediapartners-Google
Disallow:

User-agent: Baiduspider
User-agent: 360spider
User-agent: Yisouspider
User-agent: Sogou web spider
User-agent: Sogoubot
User-agent: Bytespider 
User-agent: haosouspider
User-agent: YodaoBot
User-agent: Bingbot
User-agent: Googlebot
User-agent: msnbot
User-agent: *

Disallow: /*Special:UserLogin
#Disallow: /Talk
Disallow: /%E8%AE%A8%E8%AE%BA

Disallow: /thumb.php
Disallow: /index.php
# 2018-12-18 comment below line because google webmaster tools can not get resouce of load.php
# Disallow: /load.php
# Disallow: /images/
Disallow: /skins/
Disallow: /Special
Disallow: /%E7%89%B9%E6%AE%8A
Disallow: /*action=
Disallow: /*oldid=
Disallow: /*diff=
Disallow: /*printable=
Disallow: /1027280/

# Directory refused to crawl.
User-agent: Amazonbot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT
Disallow: /
# END Cloudflare Managed Content

# sitemap start
Sitemap: https://foreign.mingluji.com/sitemap.xml
Sitemap: https://foreign.mingluji.com/rss.xml
# sitemap end


Crawl-delay: 10
Allow: /index.php?title=%E7%89%B9%E6%AE%8A:%E6%9C%80%E8%BF%91%E6%9B%B4%E6%94%B9
Allow: /index.php?title=%E7%89%B9%E6%AE%8A:%E6%9C%80%E6%96%B0%E9%A1%B5%E9%9D%A2
Allow: /index.php?title=Special:%E6%9C%80%E8%BF%91%E6%9B%B4%E6%94%B9
Allow: /index.php?title=Special:%E6%9C%80%E6%96%B0%E9%A1%B5%E9%9D%A2
Allow: /index.php?title=Special:Recentchanges
Allow: /index.php?title=Special:Newpages
Allow: /index.php?title=Category:
Allow: /index.php?title=%E5%88%86%E7%B1%BB:

##Crawl-delay: 300           # set to 300 seconds to wait between successive requests to the same server for Yahoo Slurp
##Request-rate: 1/10         # maximum rate is one page every 5 seconds
#Visit-time: 0000-0800
#Request-rate: 1/20s 1020-1200 # between 10:20 to 12:00, 1 visit in 20s

# Add End #

# Crawlers that are kind enough to obey, but which we'd rather not have
# unless they're feeding search engines.

User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

# Some bots are known to be trouble, particularly those designed to copy
# entire sites. Please obey robots.txt.

User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
Disallow: /

User-agent: MSIECrawler
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Fetch
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: Microsoft.URL.Control
Disallow: /

User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

# Sorry, wget in its recursive mode is a frequent problem.
# Please read the man page and use it properly; there is a
# --wait option you can use to set the delay between hits,
# for instance.

User-agent: wget
Disallow: /

# The 'grub' distributed client has been *very* poorly behaved.

User-agent: grub-client
Disallow: /

# Doesn't follow robots.txt anyway, but...

User-agent: k2spider
Disallow: /

# Hits many times per second, not acceptable
# http://www.nameprotect.com/botinfo.html

User-agent: NPBot
Disallow: /

# A capture bot, downloads gazillions of pages with no public benefit
# http://www.webreaper.net/

User-agent: WebReaper
Disallow: /

# Don't allow the wayback-maschine to index user-pages
#User-agent: ia_archiver
#Disallow: /wiki/User
#Disallow: /wiki/Benutzer

#
# Friendly, low-speed bots are welcome viewing article pages, but not
# dynamically-generated pages please.
#
# Inktomi's "Slurp" can read a minimum delay between hits; if your
# bot supports such a thing using the 'Crawl-delay' or another
# instruction, please let us know.
#