larbin~1.con

来自「一百个病毒的源代码 包括熊猫烧香等 极其具有研究价值」· CON 代码 · 共 96 行

###############################################
# Who are you ?
# mail of the one who launched larbin (YOUR mail)
From [e-mail]
# name of the bot (sent with http headers)
UserAgent larbin


############################################
# What are the inputs and ouputs of larbin
# port on which is launched the http statistic webserver
httpPort 8081
# port on which you can submit urls to fetch
inputPort 1976


############################################
# parameters to adapt depending on your network
# Number of connexions in parallel (to adapt depending of your network speed)
pagesConnexions 300
# Number of dns calls in parallel
dnsConnexions 20
# How deep do you want to go in a site
depthInSite 5
# time between 2 calls on the same server (in sec) : NEVER less than 30
waitDuration 60

# Make requests through a proxy (use with care)
#proxy localhost 8080


##############################################
# now, let's customize the search

# first page to fetch
startUrl http://www.lwn.net/

#########
# Do you want to limit your search to a specific domain ?
# if yes, uncomment the following line
#limitToDomain .fr .dk .uk end

#########
# Is it a specific search ?
# Give the content type you look for and the usual extension
# The extension is optional, it just allows early detection (little speedup)

# uncomment the following line for searching xml
#specificSearch text/xml .xml end
# uncomment the following line for searching mp3
#specificSearch audio/mpeg .mp3 end

#########
# What are the extensions you surely don't want
# never forbid .html, .htm and so on : larbin needs them
forbiddenExtensions
.tar
.gz
.tgz
.zip
.Z
.rpm
.deb
.ps
.dvi
.pdf
.gif
.png
.jpg
.jpeg
.mov
.avi
.mpeg
.mpg
.qt
.jar
.java
.class
.doc
.xls
.ppt
.mdb
.wav
.bmp
.rtf
.exe
.diff
.ram
.rm
.smi
.tiff
.pps
.so
.psd
end