linkchecker/config/linkcheckerrc

# Sample resource file; see linkchecker -h for help on these options.
# Commandline options override these settings.

[output]
# interactive operation
#interactive=0
# enable debug messages; see 'linkchecker -h' for valid debug names
#debug=all
# print status output
#status=1
# change the logging type
#log=xml
# turn on/off --verbose
#verbose=1
# turn on/off --warnings
#warnings=0
# turn on/off --quiet
#quiet=1
# additional file output
#fileoutput = text, html, gml, sql

##################### logger configuration ##########################
# logger output part names:
# all       (for all parts)
# realurl   (the full url link)
# result    (valid or invalid, with messages)
# extern    (1 or 0, only in some logger types reported)
# base      (base href=...)
# name      (<a href=...>name</a> and <img alt="name">)
# parenturl (if any)
# info      (some additional info, e.g. FTP welcome messages)
# warning   (warnings)
# dltime    (download time)
# checktime (check time)
# url       (the original url name, can be relative)
# intro     (the blurb at the beginning, "starting at ...")
# outro     (the blurb at the end, "found x errors ...")

# each Logger can have separate configuration parameters

# standard text logger
[text]
#filename=linkchecker-out.txt
#parts=all
# colors for the various parts, syntax is <color> or <type>;<color>
# type can be bold, light, blink, invert
# color can be default, black, red, green, yellow, blue, purple, cyan, white,
# Black, Red, Green, Yellow, Blue, Purple, Cyan, White
#colorparent=white
#colorurl=default
#colorname=default
#colorreal=cyan
#colorbase=purple
#colorvalid=bold;green
#colorinvalid=bold;red
#colorinfo=default
#colorwarning=bold;yellow
#colordltime=default
#colorreset=default

# GML logger
[gml]
#filename=linkchecker-out.gml
#parts=all
# valid encodings are listed in http://docs.python.org/lib/node127.html
# default encoding is iso-8859-15
#encoding=utf_16

# DOT logger
[dot]
#filename=linkchecker-out.dot
#parts=all
# valid encodings are listed in http://docs.python.org/lib/node127.html
# default encoding is ascii since the original DOT format does not
# support other charsets
#encoding=iso-8859-15

# CSV logger
[csv]
#filename=linkchecker-out.csv
#separator=,
#quotechar="
#parts=all

# SQL logger
[sql]
#filename=linkchecker-out.sql
#dbname=linksdb
#separator=;
#parts=all

# HTML logger
[html]
#filename=linkchecker-out.html
# colors for the various parts
#colorbackground=#fff7e5
#colorurl=#dcd5cf
#colorborder=#000000
#colorlink=#191c83
#colorwarning=#e0954e
#colorerror=#db4930
#colorok=#3ba557
#parts=all

# blacklist logger
[blacklist]
#filename=~/.linkchecker/blacklist

# custom xml logger
[xml]
#encoding=iso-8859-1

# GraphXML logger
[gxml]
#encoding=iso-8859-1

# checking options
[checking]
# number of threads
#threads=5
# connection timeout in seconds
#timeout=60
# check anchors?
#anchors=0
#recursionlevel=1
# supply a regular expression for which warnings are printed if found
# in any HTML files.
#warningregex=Oracle DB Error
# Basic NNTP server. Overrides NNTP_SERVER environment variable.
# warn if size info exceeds given maximum of bytes
#warnsizebytes=2000
#nntpserver=
# disable anchor caching
#noanchorcaching=1
# check HTML or CSS syntax locally with HTML tidy or cssutils
#checkhtml=1
#checkcss=1
# check HTML or CSS syntax online with W3C validators
#checkhtmlw3=1
#checkcssw3=1
# scan URL content for viruses with ClamAV
#scanvirus=1
# ClamAV config file
#clamavconf=/etc/clamav/clamd.conf

# filtering options
[filtering]
#ignore=
# ignore everything with 'lconline' in the URL name
#  lconline
# and ignore everything with 'bookmark' in the URL name
#  bookmark
# and ignore all mailto: URLs
#  ^mailto:
# do not recurse into the following URLs

#nofollow=
# just a homepage
#  http://justahomepage/bla

# specify hosts to contact directly without a proxy
# value is a regular expression
#noproxyfor=
#  *\.intra
#  .*myinternurl.*

# Ignore specified warnings (see linkchecker -h for the list of
# recognized warnings). Add a comma-separated list of warnings here
# that prevent a valid URL from being logged. Note that the warning
# will be logged in invalid URLs.
#ignorewarnings=url-unnormed,url-unicode-domain,anchor-not-found
# Regular expression to add more URLs recognized as internal links.
# Default is that URLs given on the command line are internal.

#internlinks=^http://www\.my(other)?domain\.net/

# You can provide different user/password pairs for different link types.
# Entries are a triple (link regular expression, username, password),
# separated by whitespace.
# If the regular expression matches, the given user/password pair is used
# for authentication. The commandline options -u,-p match every link
# and therefore override the entries given here. The first match wins.
# At the moment, authentication is used/needed for http[s] and ftp links.
[authentication]
#entry=
#  ^http://treasure\.calvinsplayground\.de/~calvin/isnichmehr/ lebowski lebowski
#  ^ftp://void.cs.uni-sb.de calvin hutzli