| 1 |
# Sample configuration file; see the linkcheckerrc(5) man page or |
| 2 |
# execute linkchecker -h for help on these options. |
| 3 |
# Commandline options override these settings. |
| 4 |
|
| 5 |
##################### output configuration ########################## |
| 6 |
[output] |
| 7 |
# enable debug messages; see 'linkchecker -h' for valid debug names, example: |
| 8 |
#debug=all |
| 9 |
# print status output |
| 10 |
#status=1 |
| 11 |
# change the logging type |
| 12 |
#log=text |
| 13 |
# turn on/off --verbose |
| 14 |
#verbose=0 |
| 15 |
# turn on/off --warnings |
| 16 |
#warnings=1 |
| 17 |
# turn on/off --quiet |
| 18 |
#quiet=0 |
| 19 |
# additional file output, example: |
| 20 |
#fileoutput = text, html, gml, sql |
| 21 |
# errors to ignore (URL regular expression, message regular expression) |
| 22 |
#ignoreerrors= |
| 23 |
# ignore all errors for broken.example.com: |
| 24 |
# ^https?://broken.example.com/ |
| 25 |
# ignore SSL errors for dev.example.com: |
| 26 |
# ^https://dev.example.com/ ^SSLError |
| 27 |
|
| 28 |
|
| 29 |
##################### logger configuration ########################## |
| 30 |
# logger output part names: |
| 31 |
# all For all parts |
| 32 |
# realurl The full url link |
| 33 |
# result Valid or invalid, with messages |
| 34 |
# extern 1 or 0, only in some logger types reported |
| 35 |
# base <base href=...> |
| 36 |
# name <a href=...>name</a> and <img alt="name"> |
| 37 |
# parenturl The referrer URL if there is any |
| 38 |
# info Some additional info, e.g. FTP welcome messages |
| 39 |
# warning Warnings |
| 40 |
# dltime Download time |
| 41 |
# checktime Check time |
| 42 |
# url The original url name, can be relative |
| 43 |
# intro The blurb at the beginning, "starting at ..." |
| 44 |
# outro The blurb at the end, "found x errors ..." |
| 45 |
# stats Statistics including URL lengths and contents. |
| 46 |
|
| 47 |
# each Logger can have separate configuration parameters |
| 48 |
|
| 49 |
# standard text logger |
| 50 |
[text] |
| 51 |
#filename=linkchecker-out.txt |
| 52 |
#parts=all |
| 53 |
#wraplength=65 |
| 54 |
# colors for the various parts, syntax is <color> or <type>;<color> |
| 55 |
# type can be bold, light, blink, invert |
| 56 |
# color can be default, black, red, green, yellow, blue, purple, cyan, white, |
| 57 |
# Black, Red, Green, Yellow, Blue, Purple, Cyan, White |
| 58 |
#colorparent=default |
| 59 |
#colorurl=default |
| 60 |
#colorname=default |
| 61 |
#colorreal=cyan |
| 62 |
#colorbase=purple |
| 63 |
#colorvalid=bold;green |
| 64 |
#colorinvalid=bold;red |
| 65 |
#colorinfo=default |
| 66 |
#colorwarning=bold;yellow |
| 67 |
#colordltime=default |
| 68 |
#colorreset=default |
| 69 |
|
| 70 |
# GML logger |
| 71 |
[gml] |
| 72 |
#filename=linkchecker-out.gml |
| 73 |
#parts=all |
| 74 |
# valid encodings are listed in http://docs.python.org/library/codecs.html#standard-encodings |
| 75 |
# example: |
| 76 |
#encoding=utf_16 |
| 77 |
|
| 78 |
# DOT logger |
| 79 |
[dot] |
| 80 |
#filename=linkchecker-out.dot |
| 81 |
#parts=all |
| 82 |
# default encoding is ascii since the original DOT format does not |
| 83 |
# support other charsets, example: |
| 84 |
#encoding=iso-8859-15 |
| 85 |
|
| 86 |
# CSV logger |
| 87 |
[csv] |
| 88 |
#filename=linkchecker-out.csv |
| 89 |
#separator=; |
| 90 |
#quotechar=" |
| 91 |
#dialect=excel |
| 92 |
#parts=all |
| 93 |
|
| 94 |
# SQL logger |
| 95 |
[sql] |
| 96 |
#filename=linkchecker-out.sql |
| 97 |
#dbname=linksdb |
| 98 |
#separator=; |
| 99 |
#parts=all |
| 100 |
|
| 101 |
# HTML logger |
| 102 |
[html] |
| 103 |
#filename=linkchecker-out.html |
| 104 |
# colors for the various parts |
| 105 |
#colorbackground=#fff7e5 |
| 106 |
#colorurl=#dcd5cf |
| 107 |
#colorborder=#000000 |
| 108 |
#colorlink=#191c83 |
| 109 |
#colorwarning=#e0954e |
| 110 |
#colorerror=#db4930 |
| 111 |
#colorok=#3ba557 |
| 112 |
#parts=all |
| 113 |
|
| 114 |
# failures logger |
| 115 |
[failures] |
| 116 |
#filename=$XDG_DATA_HOME/linkchecker/failures |
| 117 |
|
| 118 |
# custom xml logger |
| 119 |
[xml] |
| 120 |
#filename=linkchecker-out.xml |
| 121 |
# system encoding is used by default. Example: |
| 122 |
#encoding=iso-8859-1 |
| 123 |
|
| 124 |
# GraphXML logger |
| 125 |
[gxml] |
| 126 |
#filename=linkchecker-out.gxml |
| 127 |
# system encoding is used by default. Example: |
| 128 |
#encoding=iso-8859-1 |
| 129 |
|
| 130 |
# Sitemap logger |
| 131 |
[sitemap] |
| 132 |
#filename=linkchecker-out.sitemap.xml |
| 133 |
#encoding=utf-8 |
| 134 |
#priority=0.5 |
| 135 |
#frequency=daily |
| 136 |
|
| 137 |
|
| 138 |
##################### checking options ########################## |
| 139 |
[checking] |
| 140 |
# number of threads |
| 141 |
#threads=10 |
| 142 |
# connection timeout in seconds |
| 143 |
#timeout=60 |
| 144 |
# Time to wait for checks to finish after the user aborts the first time |
| 145 |
# (with Ctrl-C or the abort button). |
| 146 |
#aborttimeout=300 |
| 147 |
# The recursion level determines how many times links inside pages are followed. |
| 148 |
#recursionlevel=-1 |
| 149 |
# parse a cookiefile for initial cookie data, example: |
| 150 |
#cookiefile=/path/to/cookies.txt |
| 151 |
# User-Agent header string to send to HTTP web servers |
| 152 |
# Note that robots.txt are always checked with the original User-Agent. Example: |
| 153 |
#useragent=Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html) |
| 154 |
# When checking finishes, write a memory dump to a temporary file. |
| 155 |
# The memory dump is written both when checking finishes normally |
| 156 |
# and when checking gets canceled. |
| 157 |
# The memory dump only works if the python-meliae package is installed. |
| 158 |
# Otherwise a warning is printed to install it. |
| 159 |
#debugmemory=0 |
| 160 |
# When checking absolute URLs inside local files, the given root directory |
| 161 |
# is used as base URL. |
| 162 |
# Note that the given directory must have URL syntax, so it must use a slash |
| 163 |
# to join directories instead of a backslash. |
| 164 |
# And the given directory must end with a slash. |
| 165 |
# Unix example: |
| 166 |
#localwebroot=/var/www/ |
| 167 |
# Windows example: |
| 168 |
#localwebroot=/C|/public_html/ |
| 169 |
# Check SSL certificates. Set to an absolute pathname for a custom |
| 170 |
# CA cert bundle to use. Set to zero to disable SSL certificate verification. |
| 171 |
#sslverify=1 |
| 172 |
# Stop checking new URLs after the given number of seconds. Same as if the |
| 173 |
# user hits Ctrl-C after X seconds. Example: |
| 174 |
#maxrunseconds=600 |
| 175 |
# Don't download files larger than the given number of bytes |
| 176 |
#maxfilesizedownload=5242880 |
| 177 |
# Don't parse files larger than the given number of bytes |
| 178 |
#maxfilesizeparse=1048576 |
| 179 |
# Maximum number of URLs to check. New URLs will not be queued after the |
| 180 |
# given number of URLs is checked. Example: |
| 181 |
#maxnumurls=153 |
| 182 |
# Maximum number of requests per second to one host. |
| 183 |
#maxrequestspersecond=10 |
| 184 |
# Respect the instructions in any robots.txt files |
| 185 |
#robotstxt=1 |
| 186 |
# Allowed URL schemes as a comma-separated list. Example: |
| 187 |
#allowedschemes=http,https |
| 188 |
# Size of the result cache. Checking more urls might increase memory usage during runtime |
| 189 |
#resultcachesize=100000 |
| 190 |
|
| 191 |
##################### filtering options ########################## |
| 192 |
[filtering] |
| 193 |
#ignore= |
| 194 |
# ignore everything with 'lconline' in the URL name |
| 195 |
# lconline |
| 196 |
# and ignore everything with 'bookmark' in the URL name |
| 197 |
# bookmark |
| 198 |
# and ignore all mailto: URLs |
| 199 |
# ^mailto: |
| 200 |
# do not recurse into the following URLs |
| 201 |
|
| 202 |
#nofollow= |
| 203 |
# just an example |
| 204 |
# http://www\.example\.com/bla |
| 205 |
|
| 206 |
# Ignore specified warnings (see linkchecker -h for the list of |
| 207 |
# recognized warnings). Add a comma-separated list of warnings here |
| 208 |
# that prevent a valid URL from being logged. Note that the warning |
| 209 |
# will be logged for invalid URLs. Example: |
| 210 |
#ignorewarnings=url-unicode-domain |
| 211 |
# Regular expression to add more URLs recognized as internal links. |
| 212 |
# Default is that URLs given on the command line are internal. |
| 213 |
#internlinks=^http://www\.example\.net/ |
| 214 |
# Check external links |
| 215 |
#checkextern=0 |
| 216 |
|
| 217 |
|
| 218 |
##################### password authentication ########################## |
| 219 |
[authentication] |
| 220 |
# WARNING: if you store passwords in this configuration entry, make sure the |
| 221 |
# configuration file is not readable by other users. |
| 222 |
# Different user/password pairs for different URLs can be provided. |
| 223 |
# Entries are a triple (URL regular expression, username, password), |
| 224 |
# separated by whitespace. |
| 225 |
# If the regular expression matches, the given user/password pair is used |
| 226 |
# for authentication. The commandline options -u,-p match every link |
| 227 |
# and therefore override the entries given here. The first match wins. |
| 228 |
# At the moment, authentication is used for http[s] and ftp links. |
| 229 |
#entry= |
| 230 |
# Note that passwords are optional. If any passwords are stored here, |
| 231 |
# this file should not readable by other users. |
| 232 |
# ^https?://www\.example\.com/~calvin/ calvin mypass |
| 233 |
# ^ftp://www\.example\.com/secret/ calvin |
| 234 |
|
| 235 |
# if the website requires a login via a page with an HTML form the URL of the |
| 236 |
# page and optionally the username and password input element name attributes |
| 237 |
# can be provided. |
| 238 |
#loginurl=http://www.example.com/ |
| 239 |
|
| 240 |
# The name attributes of the username and password HTML input elements |
| 241 |
#loginuserfield=login |
| 242 |
#loginpasswordfield=password |
| 243 |
# Optionally the name attributes of any additional input elements and the values |
| 244 |
# to populate them with. Note that these are submitted without checking |
| 245 |
# whether matching input elements exist in the HTML form. Example: |
| 246 |
#loginextrafields= |
| 247 |
# name1:value1 |
| 248 |
# name 2:value 2 |
| 249 |
|
| 250 |
############################ Plugins ################################### |
| 251 |
# |
| 252 |
# uncomment sections to enable plugins |
| 253 |
|
| 254 |
# Check HTML anchors |
| 255 |
#[AnchorCheck] |
| 256 |
|
| 257 |
# Print HTTP header info |
| 258 |
#[HttpHeaderInfo] |
| 259 |
# Comma separated list of header prefixes to print. |
| 260 |
# The names are case insensitive. |
| 261 |
# The default list is empty, so it should be non-empty when activating |
| 262 |
# this plugin. Example: |
| 263 |
#prefixes=Server,X- |
| 264 |
|
| 265 |
# Add country info to URLs |
| 266 |
#[LocationInfo] |
| 267 |
|
| 268 |
# Run W3C syntax checks |
| 269 |
#[CssSyntaxCheck] |
| 270 |
#[HtmlSyntaxCheck] |
| 271 |
|
| 272 |
# Search for regular expression in page contents |
| 273 |
#[RegexCheck] |
| 274 |
# Example: |
| 275 |
#warningregex=Oracle Error |
| 276 |
|
| 277 |
# Search for viruses in page contents |
| 278 |
#[VirusCheck] |
| 279 |
#clamavconf=/etc/clamav/clamd.conf |
| 280 |
|
| 281 |
# Check that SSL certificates have at least the given number of days validity. |
| 282 |
#[SslCertificateCheck] |
| 283 |
#sslcertwarndays=30 |
| 284 |
|
| 285 |
# Parse and check links in PDF files |
| 286 |
#[PdfParser] |
| 287 |
|
| 288 |
# Parse and check links in Word files |
| 289 |
#[WordParser] |
| 290 |
|
| 291 |
# Parse and check links in Markdown files. |
| 292 |
# Supported links are: |
| 293 |
# <http://autolink.com> |
| 294 |
# [name](http://link.com "Optional title") |
| 295 |
# [id]: http://link.com "Optional title" |
| 296 |
#[MarkdownCheck] |
| 297 |
# Regexp of filename |
| 298 |
#filename_re=.*\.(markdown|md(own)?|mkdn?)$ |