| 1 | # |
| 2 | # Sample Webalizer configuration file |
| 3 | # Copyright 1997-2011 by Bradford L. Barrett |
| 4 | # |
| 5 | # Distributed under the GNU General Public License. See the |
| 6 | # files "Copyright" and "COPYING" provided with the webalizer |
| 7 | # distribution for additional information. |
| 8 | # |
| 9 | # This is a sample configuration file for the Webalizer (ver 2.20) |
| 10 | # Lines starting with pound signs '#' are comment lines and are |
| 11 | # ignored. Blank lines are skipped as well. Other lines are considered |
| 12 | # as configuration lines, and have the form "ConfigOption Value" where |
| 13 | # ConfigOption is a valid configuration keyword, and Value is the value |
| 14 | # to assign that configuration option. Invalid keyword/values are |
| 15 | # ignored, with appropriate warnings being displayed. There must be |
| 16 | # at least one space or tab between the keyword and its value. |
| 17 | # |
| 18 | # As of version 0.98, The Webalizer will look for a 'default' configuration |
| 19 | # file named "webalizer.conf" in the current directory, and if not found |
| 20 | # there, will look for "/etc/webalizer.conf". |
| 21 | |
| 22 | |
| 23 | # LogFile defines the web server log file to use. If not specified |
| 24 | # here or on on the command line, input will default to STDIN. If |
| 25 | # the log filename ends in '.gz' (a gzip compressed file), or '.bz2' |
| 26 | # (bzip2 compressed file), it will be decompressed on the fly as it |
| 27 | # is being read. |
| 28 | |
| 29 | #LogFile /var/lib/httpd/logs/access_log |
| 30 | |
| 31 | # LogType defines the log type being processed. Normally, the Webalizer |
| 32 | # expects a CLF or Combined web server log as input. Using this option, |
| 33 | # you can process ftp logs (xferlog as produced by wu-ftp and others), |
| 34 | # Squid native logs or W3C extended format web logs. Values can be 'clf', |
| 35 | # 'ftp', 'squid' or 'w3c'. The default is 'clf'. |
| 36 | |
| 37 | #LogType clf |
| 38 | |
| 39 | # OutputDir is where you want to put the output files. This should |
| 40 | # should be a full path name, however relative ones might work as well. |
| 41 | # If no output directory is specified, the current directory will be used. |
| 42 | |
| 43 | #OutputDir /var/lib/httpd/htdocs/usage |
| 44 | |
| 45 | # HistoryName allows you to specify the name of the history file produced |
| 46 | # by the Webalizer. The history file keeps the data for previous months, |
| 47 | # and is used for generating the main HTML page (index.html). The default |
| 48 | # is a file named "webalizer.hist", stored in the output directory being |
| 49 | # used. The name can include a path, which will be relative to the output |
| 50 | # directory unless absolute (starts with a leading '/'). |
| 51 | |
| 52 | #HistoryName webalizer.hist |
| 53 | |
| 54 | # Incremental processing allows multiple partial log files to be used |
| 55 | # instead of one huge one. Useful for large sites that have to rotate |
| 56 | # their log files more than once a month. The Webalizer will save its |
| 57 | # internal state before exiting, and restore it the next time run, in |
| 58 | # order to continue processing where it left off. This mode also causes |
| 59 | # The Webalizer to scan for and ignore duplicate records (records already |
| 60 | # processed by a previous run). See the README file for additional |
| 61 | # information. The value may be 'yes' or 'no', with a default of 'no'. |
| 62 | # The file 'webalizer.current' is used to store the current state data, |
| 63 | # and is located in the output directory of the program (unless changed |
| 64 | # with the IncrementalName option below). Please read at least the section |
| 65 | # on Incremental processing in the README file before you enable this option. |
| 66 | |
| 67 | #Incremental no |
| 68 | |
| 69 | # IncrementalName allows you to specify the filename for saving the |
| 70 | # incremental data in. It is similar to the HistoryName option where the |
| 71 | # name is relative to the specified output directory, unless an absolute |
| 72 | # filename is specified. The default is a file named "webalizer.current" |
| 73 | # kept in the normal output directory. If you don't specify "Incremental" |
| 74 | # as 'yes' then this option has no meaning. |
| 75 | |
| 76 | #IncrementalName webalizer.current |
| 77 | |
| 78 | # ReportTitle is the text to display as the title. The hostname |
| 79 | # (unless blank) is appended to the end of this string (seperated with |
| 80 | # a space) to generate the final full title string. |
| 81 | # Default is (for english) "Usage Statistics for". |
| 82 | |
| 83 | #ReportTitle Usage Statistics for |
| 84 | |
| 85 | # HostName defines the hostname for the report. This is used in |
| 86 | # the title, and is prepended to the URL table items. This allows |
| 87 | # clicking on URLs in the report to go to the proper location in |
| 88 | # the event you are running the report on a 'virtual' web server, |
| 89 | # or for a server different than the one the report resides on. |
| 90 | # If not specified here, or on the command line, webalizer will |
| 91 | # try to get the hostname via a uname system call. If that fails, |
| 92 | # it will default to "localhost". |
| 93 | |
| 94 | #HostName www.webalizer.org |
| 95 | |
| 96 | # HTMLExtension allows you to specify the filename extension to use |
| 97 | # for generated HTML pages. Normally, this defaults to "html", but |
| 98 | # can be changed for sites who need it (like for PHP embeded pages). |
| 99 | |
| 100 | #HTMLExtension html |
| 101 | |
| 102 | # PageType lets you tell the Webalizer what types of URLs you |
| 103 | # consider a 'page'. Most people consider html and cgi documents |
| 104 | # as pages, while not images and audio files. If no types are |
| 105 | # specified, defaults will be used ('htm*', 'cgi' and HTMLExtension |
| 106 | # if different for web logs, 'txt' for ftp logs). |
| 107 | |
| 108 | PageType htm* |
| 109 | PageType cgi |
| 110 | #PageType phtml |
| 111 | #PageType php3 |
| 112 | #PageType pl |
| 113 | |
| 114 | # PagePrefix allows all requests with a specified prefix to be |
| 115 | # considered as 'pages'. If you want everything under /documents |
| 116 | # to be treated as pages no matter what their extension is. Also |
| 117 | # useful if you have cgi-scripts with PATH_INFO. |
| 118 | |
| 119 | #PagePrefix /documents |
| 120 | #PagePrefix /mycgi/parameters |
| 121 | |
| 122 | # OmitPage lets you tell the Webalizer that certain URLs do not |
| 123 | # contain any pages. No URL matching an OmitPage value will be |
| 124 | # counted as a page, even if it matches a PageType above or has |
| 125 | # no extension (e.g., a directory). They will still be counted |
| 126 | # as a hit. |
| 127 | |
| 128 | #OmitPage /render |
| 129 | |
| 130 | # UseHTTPS should be used if the analysis is being run on a |
| 131 | # secure server, and links to urls should use 'https://' instead |
| 132 | # of the default 'http://'. If you need this, set it to 'yes'. |
| 133 | # Default is 'no'. This only changes the behaviour of the 'Top |
| 134 | # URLs' table. |
| 135 | |
| 136 | #UseHTTPS no |
| 137 | |
| 138 | # HTAccess allows the generation of a default .htaccess file in the |
| 139 | # output directory. If enabled, a default .htaccess file will be |
| 140 | # created (with a single "DirectoryIndex" directive), unless one |
| 141 | # already exists. Values may be 'yes' or 'no', with 'no' |
| 142 | # being the default (don't write .htaccess files). |
| 143 | |
| 144 | #HTAccess no |
| 145 | |
| 146 | # StripCGI determines if URL CGI variables should be striped or not. |
| 147 | # Historically, the Webalizer stripped all CGI variables from the end |
| 148 | # of URLs to improve accuracy. Some sites may prefer to keep the CGI |
| 149 | # variables in place, particularly those with highly dynamic pages. |
| 150 | # Values may be 'yes' or 'no', with the default being 'yes'. |
| 151 | |
| 152 | #StripCGI yes |
| 153 | |
| 154 | # The TrimSquidURL option only has effect on squid type log files. |
| 155 | # When analyzing a squid log, it is usually desirable to have less |
| 156 | # granularity on the URLs. TrimSquidURL = n where n is a number > 0 |
| 157 | # causes all URLs to be truncated after the nth '/' after the http:// |
| 158 | # portion. Setting TrimSquidURL to one (1) will cause all URLs to be |
| 159 | # summarized by domain only. The default is zero (0), which disables |
| 160 | # any such truncation and preserve the URLs as they are in the log. |
| 161 | |
| 162 | # TrimSquidURL 0 |
| 163 | |
| 164 | # DNSCache specifies the DNS cache filename to use for reverse DNS lookups. |
| 165 | # This file must be specified if you wish to perform name lookups on any IP |
| 166 | # addresses found in the log file. If an absolute path is not given as |
| 167 | # part of the filename (ie: starts with a leading '/'), then the name is |
| 168 | # relative to the default output directory. See the DNS.README file for |
| 169 | # additional information. |
| 170 | |
| 171 | #DNSCache dns_cache.db |
| 172 | |
| 173 | # DNSChildren allows you to specify how many "children" processes are |
| 174 | # run to perform DNS lookups to create or update the DNS cache file. |
| 175 | # If a number is specified, the DNS cache file will be created/updated |
| 176 | # each time the Webalizer is run, immediately prior to normal processing, |
| 177 | # by running the specified number of "children" processes to perform |
| 178 | # DNS lookups. If used, the DNS cache filename MUST be specified as |
| 179 | # well. The default value is zero (0), which disables DNS cache file |
| 180 | # creation/updates at run time. The number of children processes to |
| 181 | # run may be anywhere from 1 to 100, however a large number may effect |
| 182 | # normal system operations. Reasonable values should be between 5 and |
| 183 | # 20. See the DNS.README file for additional information. |
| 184 | |
| 185 | #DNSChildren 0 |
| 186 | |
| 187 | # CacheIPs allows unresolved IP addresses to be cached in the DNS |
| 188 | # database. Normally, only resolved addresses are saved. At some |
| 189 | # sites, particularly those with a large number of unresolvable IP |
| 190 | # addresses visiting, it may be useful to enable this feature so |
| 191 | # those addresses are not constantly looked up each time the program |
| 192 | # is run. Values can be 'yes' or 'no', with 'no' being the default. |
| 193 | |
| 194 | #CacheIPs no |
| 195 | |
| 196 | # CacheTTL specifies the time to live (TTL) value for cached DNS |
| 197 | # entries, in days. This value may be anywhere between 1 and 100 |
| 198 | # with the default being 7 days (1 week). |
| 199 | |
| 200 | #CacheTTL 7 |
| 201 | |
| 202 | # The GeoDB option enables or disabled the use of the native |
| 203 | # Webalizer GeoDB geolocation services. This is the preferred |
| 204 | # geolocation option. Values may be 'yes' or 'no', with 'no' |
| 205 | # being the default. |
| 206 | |
| 207 | #GeoDB no |
| 208 | |
| 209 | # GeoDBDatabase specifies an alternate database to use. The |
| 210 | # default database is /usr/share/GeoDB/GeoDB.dat (however the |
| 211 | # path may be changed at compile time; use the -vV command |
| 212 | # line option to determine where). If a different database is |
| 213 | # to be used, it may be specified here. The name is relative |
| 214 | # to the output directory being used unless an absolute name |
| 215 | # (ie: starts with a leading '/') is specified. |
| 216 | |
| 217 | #GeoDBDatabase /usr/share/GeoDB/GeoDB.dat |
| 218 | |
| 219 | # The GeoIP option enables or disables the use of geolocation |
| 220 | # services provided by the GeoIP library (http://www.maxmind.com), |
| 221 | # if available. Values may be 'yes' or 'no, with 'no' being the |
| 222 | # default. Note: if GeoDB is enabled, then this option will have |
| 223 | # no effect (GeoDB will be used regardless of this setting). |
| 224 | |
| 225 | #GeoIP no |
| 226 | |
| 227 | # GeoIPDatabase specifies an alternate database filename to use by the |
| 228 | # GeoIP library. If an absolute path is not given as part of the name |
| 229 | # (ie: starts with a leading '/'), then the name is relative to the |
| 230 | # default output directory. This option should not normally be needed. |
| 231 | |
| 232 | #GeoIPDatabase /usr/share/GeoIP/GeoIP.dat |
| 233 | |
| 234 | # HTMLPre defines HTML code to insert at the very beginning of the |
| 235 | # file. Default is the DOCTYPE line shown below. Max line length |
| 236 | # is 80 characters, so use multiple HTMLPre lines if you need more. |
| 237 | |
| 238 | #HTMLPre <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"> |
| 239 | |
| 240 | # HTMLHead defines HTML code to insert within the <HEAD></HEAD> |
| 241 | # block, immediately after the <TITLE> line. Maximum line length |
| 242 | # is 80 characters, so use multiple lines if needed. |
| 243 | |
| 244 | #HTMLHead <META NAME="author" CONTENT="The Webalizer"> |
| 245 | #HTMLHead <META NAME="ROBOTS" CONTENT="NOINDEX, NOFOLLOW"> |
| 246 | |
| 247 | # HTMLBody defined the HTML code to be inserted, starting with the |
| 248 | # <BODY> tag. If not specified, the default is shown below. If |
| 249 | # used, you MUST include your own <BODY> tag as the first line. |
| 250 | # Maximum line length is 80 char, use multiple lines if needed. |
| 251 | |
| 252 | #HTMLBody <BODY BGCOLOR="#E8E8E8" TEXT="#000000" LINK="#0000FF" VLINK="#FF0000"> |
| 253 | |
| 254 | # HTMLPost defines the HTML code to insert immediately before the |
| 255 | # first <HR> on the document, which is just after the title and |
| 256 | # "summary period"-"Generated on:" lines. If anything, this should |
| 257 | # be used to clean up in case an image was inserted with HTMLBody. |
| 258 | # As with HTMLHead, you can define as many of these as you want and |
| 259 | # they will be inserted in the output stream in order of apperance. |
| 260 | # Max string size is 80 characters. Use multiple lines if you need to. |
| 261 | |
| 262 | #HTMLPost <BR CLEAR="all"> |
| 263 | |
| 264 | # HTMLTail defines the HTML code to insert at the bottom of each |
| 265 | # HTML document, usually to include a link back to your home |
| 266 | # page or insert a small graphic. It is inserted as a table |
| 267 | # data element (ie: <TD> your code here </TD>) and is right |
| 268 | # alligned with the page. Max string size is 80 characters. |
| 269 | |
| 270 | #HTMLTail <IMG SRC="msfree.png" ALT="100% Micro$oft free!"> |
| 271 | |
| 272 | # HTMLEnd defines the HTML code to add at the very end of the |
| 273 | # generated files. It defaults to what is shown below. If |
| 274 | # used, you MUST specify the </BODY> and </HTML> closing tags |
| 275 | # as the last lines. Max string length is 80 characters. |
| 276 | |
| 277 | #HTMLEnd </BODY></HTML> |
| 278 | |
| 279 | # The LinkReferrer option determines if entries in the referrer table |
| 280 | # should be plain text or a HTML link to the referrer. Values can be |
| 281 | # either 'yes' or 'no', with 'no' being the default. |
| 282 | |
| 283 | #LinkReferrer no |
| 284 | |
| 285 | # The Quiet option suppresses output messages... Useful when run |
| 286 | # as a cron job to prevent bogus e-mails. Values can be either |
| 287 | # "yes" or "no". Default is "no". Note: this does not suppress |
| 288 | # warnings and errors (which are printed to stderr). |
| 289 | |
| 290 | #Quiet no |
| 291 | |
| 292 | # ReallyQuiet will supress all messages including errors and |
| 293 | # warnings. Values can be 'yes' or 'no' with 'no' being the |
| 294 | # default. If 'yes' is used here, it cannot be overriden from |
| 295 | # the command line, so use with caution. A value of 'no' has |
| 296 | # no effect. |
| 297 | |
| 298 | #ReallyQuiet no |
| 299 | |
| 300 | # TimeMe allows you to force the display of timing information |
| 301 | # at the end of processing. A value of 'yes' will force the |
| 302 | # timing information to be displayed. A value of 'no' has no |
| 303 | # effect. |
| 304 | |
| 305 | #TimeMe no |
| 306 | |
| 307 | # GMTTime allows reports to show GMT (UTC) time instead of local |
| 308 | # time. Default is to display the time the report was generated |
| 309 | # in the timezone of the local machine, such as EDT or PST. This |
| 310 | # keyword allows you to have times displayed in UTC instead. Use |
| 311 | # only if you really have a good reason, since it will probably |
| 312 | # screw up the reporting periods by however many hours your local |
| 313 | # time zone is off of GMT. |
| 314 | |
| 315 | #GMTTime no |
| 316 | |
| 317 | # Debug prints additional information for error messages. This |
| 318 | # will cause webalizer to dump bad records/fields instead of just |
| 319 | # telling you it found a bad one. As usual, the value can be |
| 320 | # either "yes" or "no". The default is "no". It shouldn't be |
| 321 | # needed unless you start getting a lot of Warning or Error |
| 322 | # messages and want to see why. (Note: warning and error messages |
| 323 | # are printed to stderr, not stdout like normal messages). |
| 324 | |
| 325 | #Debug no |
| 326 | |
| 327 | # FoldSeqErr forces the Webalizer to ignore sequence errors. |
| 328 | # This is useful for Netscape and other web servers that cache |
| 329 | # the writing of log records and do not guarentee that they |
| 330 | # will be in chronological order. The use of the FoldSeqErr |
| 331 | # option will cause out of sequence log records to be treated |
| 332 | # as if they had the same time stamp as the last valid record. |
| 333 | # Default is to ignore out of sequence log records. The use |
| 334 | # of this feature is strongly discouraged and rarely needed. |
| 335 | # (the webalizer already compensates for up to 60 minutes of |
| 336 | # difference between records). |
| 337 | |
| 338 | #FoldSeqErr no |
| 339 | |
| 340 | # VisitTimeout allows you to set the default timeout for a visit |
| 341 | # (sometimes called a 'session'). The default is 30 minutes, |
| 342 | # which should be fine for most sites. |
| 343 | # Visits are determined by looking at the time of the current |
| 344 | # request, and the time of the last request from the site. If |
| 345 | # the time difference is greater than the VisitTimeout value, it |
| 346 | # is considered a new visit, and visit totals are incremented. |
| 347 | # Value is the number of seconds to timeout (default=1800=30min) |
| 348 | |
| 349 | #VisitTimeout 1800 |
| 350 | |
| 351 | # IgnoreHist shouldn't be used in a config file, but it is here |
| 352 | # just because it might be usefull in certain situations. If the |
| 353 | # history file is ignored, the main "index.html" file will only |
| 354 | # report on the current log files contents. Usefull only when you |
| 355 | # want to reproduce the reports from scratch. USE WITH CAUTION! |
| 356 | # Valid values are "yes" or "no". Default is "no". |
| 357 | |
| 358 | #IgnoreHist no |
| 359 | |
| 360 | # IgnoreState also shouldn't be used, but is here anyway. It is |
| 361 | # similar to the IgnoreHist option, but for the incremental data |
| 362 | # file. If this is set to 'yes', any existing incrememtal data |
| 363 | # will be ignored and a new data file will be written at the end |
| 364 | # of processing. USE WITH CAUTION. By ignoring an existing |
| 365 | # incremental data file, all previous processing for the current |
| 366 | # month will be lost, and those logs must be re-processed. |
| 367 | # Valid values are "yes" or "no". Default is "no". |
| 368 | |
| 369 | #IgnoreState no |
| 370 | |
| 371 | # CountryGraph allows the usage by country graph to be disabled. |
| 372 | # Values can be 'yes' or 'no', default is 'yes'. |
| 373 | |
| 374 | #CountryGraph yes |
| 375 | |
| 376 | # CountryFlags allows flags to be displayed in the top country |
| 377 | # table in monthly reports. Values can be 'yes' or 'no', with |
| 378 | # the default being 'no'. |
| 379 | |
| 380 | #CountryFlags no |
| 381 | |
| 382 | # FlagDir specifies the location of flag graphics which will be |
| 383 | # used in the top country table. If not specified, the default |
| 384 | # is to look in the 'flags' directory directly under the output |
| 385 | # directory being used for the reports. If this option is used, |
| 386 | # the display of flag graphics will be enabled by default. |
| 387 | |
| 388 | #FlagDir flags |
| 389 | |
| 390 | # DailyGraph and DailyStats allows the daily statistics graph |
| 391 | # and statistics table to be disabled (not displayed). Values |
| 392 | # may be "yes" or "no". Default is "yes". |
| 393 | |
| 394 | #DailyGraph yes |
| 395 | #DailyStats yes |
| 396 | |
| 397 | # HourlyGraph and HourlyStats allows the hourly statistics graph |
| 398 | # and statistics table to be disabled (not displayed). Values |
| 399 | # may be "yes" or "no". Default is "yes". |
| 400 | |
| 401 | #HourlyGraph yes |
| 402 | #HourlyStats yes |
| 403 | |
| 404 | # GraphLegend allows the color coded legends to be turned on or off |
| 405 | # in the graphs. The default is for them to be displayed. This only |
| 406 | # toggles the color coded legends, the other legends are not changed. |
| 407 | # If you think they are hideous and ugly, say 'no' here :) |
| 408 | |
| 409 | #GraphLegend yes |
| 410 | |
| 411 | # GraphLines allows you to have index lines drawn behind the graphs. |
| 412 | # I personally am not crazy about them, but a lot of people requested |
| 413 | # them and they weren't a big deal to add. The number represents the |
| 414 | # number of lines you want displayed. Default is 2, you can disable |
| 415 | # the lines by using a value of zero ('0'). [max is 20] |
| 416 | # Note, due to rounding errors, some values don't work quite right. |
| 417 | # The lower the better, with 1,2,3,4,6 and 10 producing nice results. |
| 418 | |
| 419 | #GraphLines 2 |
| 420 | |
| 421 | # IndexMonths defines the number of months to display in the main index |
| 422 | # (yearly summary) table. Value can be between 12 and 120, with the |
| 423 | # default being 12 months (1 year). |
| 424 | |
| 425 | #IndexMonths 12 |
| 426 | |
| 427 | # YearHeaders enables/disables the display of year headers in the main |
| 428 | # index (yearly summary) table. If enabled, year headers will be shown |
| 429 | # when the table is displaying more than 16 months worth of data. Values |
| 430 | # can be 'yes' or 'no', with 'yes' being the default. |
| 431 | |
| 432 | #YearHeaders yes |
| 433 | |
| 434 | # YearTotals enables/disables the display of yearly totals in the main |
| 435 | # index (yearly summary) table. If enabled, year totals will be shown |
| 436 | # when the table is displaying more than 16 months worth of data. Values |
| 437 | # can be 'yes' or 'no', with 'yes' being the default. |
| 438 | |
| 439 | #YearTotals yes |
| 440 | |
| 441 | # GraphMonths defines the number of months to display in the main index |
| 442 | # (yearly summary) graph. Value can be between 12 and 72 months, with |
| 443 | # the default being 12 months. |
| 444 | |
| 445 | #GraphMonths 12 |
| 446 | |
| 447 | # The "Top" options below define the number of entries for each table. |
| 448 | # Defaults are Sites=30, URLs=30, Referrers=30 and Agents=15, and |
| 449 | # Countries=30. TopKSites and TopKURLs (by KByte tables) both default |
| 450 | # to 10, as do the top entry/exit tables (TopEntry/TopExit). The top |
| 451 | # search strings and usernames default to 20. Tables may be disabled |
| 452 | # by using zero (0) for the value. |
| 453 | |
| 454 | #TopSites 30 |
| 455 | #TopKSites 10 |
| 456 | #TopURLs 30 |
| 457 | #TopKURLs 10 |
| 458 | #TopReferrers 30 |
| 459 | #TopAgents 15 |
| 460 | #TopCountries 30 |
| 461 | #TopEntry 10 |
| 462 | #TopExit 10 |
| 463 | #TopSearch 20 |
| 464 | #TopUsers 20 |
| 465 | |
| 466 | # The All* keywords allow the display of all URLs, Sites, Referrers |
| 467 | # User Agents, Search Strings and Usernames. If enabled, a seperate |
| 468 | # HTML page will be created, and a link will be added to the bottom |
| 469 | # of the appropriate "Top" table. There are a couple of conditions |
| 470 | # for this to occur.. First, there must be more items than will fit |
| 471 | # in the "Top" table (otherwise it would just be duplicating what is |
| 472 | # already displayed). Second, the listing will only show those items |
| 473 | # that are normally visable, which means it will not show any hidden |
| 474 | # items. Grouped entries will be listed first, followed by individual |
| 475 | # items. The value for these keywords can be either 'yes' or 'no', |
| 476 | # with the default being 'no'. Please be aware that these pages can |
| 477 | # be quite large in size, particularly the sites page, and seperate |
| 478 | # pages are generated for each month, which can consume quite a lot |
| 479 | # of disk space depending on the traffic to your site. |
| 480 | |
| 481 | #AllSites no |
| 482 | #AllURLs no |
| 483 | #AllReferrers no |
| 484 | #AllAgents no |
| 485 | #AllSearchStr no |
| 486 | #AllUsers no |
| 487 | |
| 488 | # The Webalizer normally strips the string 'index.' off the end of |
| 489 | # URLs in order to consolidate URL totals. For example, the URL |
| 490 | # /somedir/index.html is turned into /somedir/ which is really the |
| 491 | # same URL. This option allows you to specify additional strings |
| 492 | # to treat in the same way. You don't need to specify 'index.' as |
| 493 | # it is always scanned for by The Webalizer, this option is just to |
| 494 | # specify _additional_ strings if needed. If you don't need any, |
| 495 | # don't specify any as each string will be scanned for in EVERY |
| 496 | # log record... A bunch of them will degrade performance. Also, |
| 497 | # the string is scanned for anywhere in the URL, so a string of |
| 498 | # 'home' would turn the URL /somedir/homepages/brad/home.html into |
| 499 | # just /somedir/ which is probably not what was intended. |
| 500 | |
| 501 | #IndexAlias home.htm |
| 502 | #IndexAlias homepage.htm |
| 503 | |
| 504 | # The DefaultIndex option is used to enable/disable the use of |
| 505 | # "index." as the default index name to be stripped off the end of |
| 506 | # a URL (as described above). Most sites will not need to use this |
| 507 | # option, but some may, such as those whose default index file name |
| 508 | # is different, or those that use "index.php" or similar URLs in a |
| 509 | # dynamic environment. Values can be 'yes' or 'no', with the default |
| 510 | # being 'yes'. This option does not effect any names added using the |
| 511 | # IndexAlias option, and those names will still function as described |
| 512 | # regardless of this setting. |
| 513 | |
| 514 | #DefaultIndex yes |
| 515 | |
| 516 | # The Hide*, Group* and Ignore* and Include* keywords allow you to |
| 517 | # change the way Sites, URLs, Referrers, User Agents and Usernames |
| 518 | # are manipulated. The Ignore* keywords will cause The Webalizer to |
| 519 | # completely ignore records as if they didn't exist (and thus not |
| 520 | # counted in the main site totals). The Hide* keywords will prevent |
| 521 | # things from being displayed in the 'Top' tables, but will still be |
| 522 | # counted in the main totals. The Group* keywords allow grouping |
| 523 | # similar objects as if they were one. Grouped records are displayed |
| 524 | # in the 'Top' tables and can optionally be displayed in BOLD and/or |
| 525 | # shaded. Groups cannot be hidden, and are not counted in the main |
| 526 | # totals. The Group* options do not, by default, hide all the items |
| 527 | # that it matches. If you want to hide the records that match (so just |
| 528 | # the grouping record is displayed), follow with an identical Hide* |
| 529 | # keyword with the same value. (see example below) In addition, |
| 530 | # Group* keywords may have an optional label which will be displayed |
| 531 | # instead of the keywords value. The label should be seperated from |
| 532 | # the value by at least one 'white-space' character, such as a space |
| 533 | # or tab. If the match string contains whitespace (spaces or tabs), |
| 534 | # the string should be quoted with either single or double quotes. |
| 535 | # |
| 536 | # The value can have either a leading or trailing '*' wildcard |
| 537 | # character. If no wildcard is found, a match can occur anywhere |
| 538 | # in the string. Given a string "www.yourmama.com", the values "your", |
| 539 | # "*mama.com" and "www.your*" will all match. |
| 540 | |
| 541 | # Your own site should be hidden |
| 542 | #HideSite *webalizer.org |
| 543 | #HideSite localhost |
| 544 | |
| 545 | # Your own site gives most referrals |
| 546 | #HideReferrer webalizer.org/ |
| 547 | |
| 548 | # This one hides non-referrers ("-" Direct requests) |
| 549 | #HideReferrer Direct Request |
| 550 | |
| 551 | # Usually you want to hide these |
| 552 | HideURL *.gif |
| 553 | HideURL *.GIF |
| 554 | HideURL *.jpg |
| 555 | HideURL *.JPG |
| 556 | HideURL *.png |
| 557 | HideURL *.PNG |
| 558 | HideURL *.ra |
| 559 | |
| 560 | # Hiding agents is kind of futile |
| 561 | #HideAgent RealPlayer |
| 562 | |
| 563 | # You can also hide based on authenticated username |
| 564 | #HideUser root |
| 565 | #HideUser admin |
| 566 | |
| 567 | # Grouping options |
| 568 | #GroupURL /cgi-bin/* CGI Scripts |
| 569 | #GroupURL /images/* Images |
| 570 | |
| 571 | #GroupSite *.aol.com |
| 572 | #GroupSite *.compuserve.com |
| 573 | |
| 574 | #GroupReferrer yahoo.com/ Yahoo! |
| 575 | #GroupReferrer excite.com/ Excite |
| 576 | #GroupReferrer infoseek.com/ InfoSeek |
| 577 | #GroupReferrer webcrawler.com/ WebCrawler |
| 578 | |
| 579 | #GroupUser root Admin users |
| 580 | #GroupUser admin Admin users |
| 581 | #GroupUser wheel Admin users |
| 582 | |
| 583 | # The following is a great way to get an overall total |
| 584 | # for browsers, and not display all the detail records. |
| 585 | # (You should use MangleAgent to refine further...) |
| 586 | |
| 587 | #GroupAgent Opera/ Opera |
| 588 | #HideAgent Opera/ |
| 589 | #GroupAgent "MSIE 7" Microsoft Internet Exploder 7 |
| 590 | #HideAgent MSIE 7 |
| 591 | #GroupAgent "MSIE 6" Microsoft Internet Exploder 6 |
| 592 | #HideAgent MSIE 6 |
| 593 | #GroupAgent "MSIE " Older Microsoft Exploders |
| 594 | #HideAgent MSIE |
| 595 | #GroupAgent Firefox/2. Firefox 2 |
| 596 | #HideAgent Firefox/2. |
| 597 | #GroupAgent Firefox/1. Firefox 1.x |
| 598 | #HideAgent Firefox/1. |
| 599 | #GroupAgent Konqueror Konqueror |
| 600 | #HideAgent Konqueror |
| 601 | #GroupAgent Safari Safari |
| 602 | #HideAgent Safari |
| 603 | #GroupAgent Lynx* Lynx |
| 604 | #HideAgent Lynx* |
| 605 | #GroupAgent Wget/ WGet |
| 606 | #HideAgent Wget/ |
| 607 | #GroupAgent (compatible; Other Mozilla Compatibles |
| 608 | #HideAgent (compatible; |
| 609 | #GroupAgent Mozilla* Mozilla/Netscape |
| 610 | #HideAgent Mozilla* |
| 611 | |
| 612 | # HideAllSites allows forcing individual sites to be hidden in the |
| 613 | # report. This is particularly useful when used in conjunction |
| 614 | # with the "GroupDomain" feature, but could be useful in other |
| 615 | # situations as well, such as when you only want to display grouped |
| 616 | # sites (with the GroupSite keywords...). The value for this |
| 617 | # keyword can be either 'yes' or 'no', with 'no' the default, |
| 618 | # allowing individual sites to be displayed. |
| 619 | |
| 620 | #HideAllSites no |
| 621 | |
| 622 | # The GroupDomains keyword allows you to group individual hostnames |
| 623 | # into their respective domains. The value specifies the level of |
| 624 | # grouping to perform, and can be thought of as 'the number of dots' |
| 625 | # that will be displayed. For example, if a visiting host is named |
| 626 | # cust1.tnt.mia.uu.net, a domain grouping of 1 will result in just |
| 627 | # "uu.net" being displayed, while a 2 will result in "mia.uu.net". |
| 628 | # The default value of zero disable this feature. Domains will only |
| 629 | # be grouped if they do not match any existing "GroupSite" records, |
| 630 | # which allows overriding this feature with your own if desired. |
| 631 | |
| 632 | #GroupDomains 0 |
| 633 | |
| 634 | # The GroupShading allows grouped rows to be shaded in the report. |
| 635 | # Useful if you have lots of groups and individual records that |
| 636 | # intermingle in the report, and you want to diferentiate the group |
| 637 | # records a little more. Value can be 'yes' or 'no', with 'yes' |
| 638 | # being the default. |
| 639 | |
| 640 | #GroupShading yes |
| 641 | |
| 642 | # GroupHighlight allows the group record to be displayed in BOLD. |
| 643 | # Can be either 'yes' or 'no' with the default 'yes'. |
| 644 | |
| 645 | #GroupHighlight yes |
| 646 | |
| 647 | # The Ignore* keywords allow you to completely ignore log records based |
| 648 | # on hostname, URL, user agent, referrer or username. I hesitated in |
| 649 | # adding these, since the Webalizer was designed to generate _accurate_ |
| 650 | # statistics about a web servers performance. By choosing to ignore |
| 651 | # records, the accuracy of reports become skewed, negating why I wrote |
| 652 | # this program in the first place. However, due to popular demand, here |
| 653 | # they are. Use the same as the Hide* keywords, where the value can have |
| 654 | # a leading or trailing wildcard '*'. Use at your own risk ;) Please |
| 655 | # remember, the use of these will MAKE YOUR STATS INACCURATE and you |
| 656 | # should consider using an equivalent 'Hide*' keyword instead. |
| 657 | |
| 658 | #IgnoreSite bad.site.net |
| 659 | #IgnoreURL /test* |
| 660 | #IgnoreReferrer file:/* |
| 661 | #IgnoreAgent RealPlayer |
| 662 | #IgnoreUser root |
| 663 | |
| 664 | # The Include* keywords allow you to force the inclusion of log records |
| 665 | # based on hostname, URL, user agent, referrer or username. They take |
| 666 | # precidence over the Ignore* keywords. Note: Using Ignore/Include |
| 667 | # combinations to selectivly process parts of a web site is _extremely |
| 668 | # inefficent_!!! Avoid doing so if possible (ie: grep the records to a |
| 669 | # seperate file if you really want that kind of report). |
| 670 | |
| 671 | # Example: Only show stats on Joe User's pages... |
| 672 | #IgnoreURL * |
| 673 | #IncludeURL ~joeuser* |
| 674 | |
| 675 | # Or based on an authenticated username |
| 676 | #IgnoreUser * |
| 677 | #IncludeUser someuser |
| 678 | |
| 679 | # The MangleAgents allows you to specify how much, if any, The Webalizer |
| 680 | # should mangle user agent names. This allows several levels of detail |
| 681 | # to be produced when reporting user agent statistics. There are six |
| 682 | # levels that can be specified, which define different levels of detail |
| 683 | # supression. Level 5 shows only the browser name (MSIE or Mozilla) |
| 684 | # and the major version number. Level 4 adds the minor version number |
| 685 | # (single decimal place). Level 3 displays the minor version to two |
| 686 | # decimal places. Level 2 will add any sub-level designation (such |
| 687 | # as Mozilla/3.01Gold or MSIE 3.0b). Level 1 will attempt to also add |
| 688 | # the system type if it is specified. The default Level 0 displays the |
| 689 | # full user agent field without modification and produces the greatest |
| 690 | # amount of detail. User agent names that can't be mangled will be |
| 691 | # left unmodified. |
| 692 | |
| 693 | #MangleAgents 0 |
| 694 | |
| 695 | # The SearchEngine keywords allow specification of search engines and |
| 696 | # their query strings on the URL. These are used to locate and report |
| 697 | # what search strings are used to find your site. The first word is |
| 698 | # a substring to match in the referrer field that identifies the search |
| 699 | # engine, and the second is the URL variable used by that search engine |
| 700 | # to define it's search terms. |
| 701 | |
| 702 | #SearchEngine .google. q= |
| 703 | #SearchEngine yahoo.com p= |
| 704 | #SearchEngine altavista.com q= |
| 705 | #SearchEngine aolsearch. query= |
| 706 | #SearchEngine ask.co q= |
| 707 | #SearchEngine eureka.com q= |
| 708 | #SearchEngine lycos.com query= |
| 709 | #SearchEngine hotbot.com MT= |
| 710 | #SearchEngine msn.com q= |
| 711 | #SearchEngine infoseek.com qt= |
| 712 | #SearchEngine excite search= |
| 713 | #SearchEngine netscape.com query= |
| 714 | #SearchEngine mamma.com query= |
| 715 | #SearchEngine alltheweb.com q= |
| 716 | #SearchEngine northernlight.com qr= |
| 717 | |
| 718 | # Normally, search strings are converted to lower case in order to |
| 719 | # increase accuracy. The SearchCaseI option allows them to maintain |
| 720 | # case sensitivity, useful for some sites. The value can be 'yes' |
| 721 | # or 'no', with 'yes' (case insensitive) being the default. |
| 722 | |
| 723 | #SearchCaseI yes |
| 724 | |
| 725 | # The Dump* keywords allow the dumping of Sites, URLs, Referrers |
| 726 | # User Agents, Usernames and Search strings to seperate tab delimited |
| 727 | # text files, suitable for import into most database or spreadsheet |
| 728 | # programs. |
| 729 | |
| 730 | # DumpPath specifies the path to dump the files. If not specified, |
| 731 | # it will default to the current output directory. Do not use a |
| 732 | # trailing slash ('/'). |
| 733 | |
| 734 | #DumpPath /var/lib/httpd/logs |
| 735 | |
| 736 | # The DumpHeader keyword specifies if a header record should be |
| 737 | # written to the file. A header record is the first record of the |
| 738 | # file, and contains the labels for each field written. Normally, |
| 739 | # files that are intended to be imported into a database system |
| 740 | # will not need a header record, while spreadsheets usually do. |
| 741 | # Value can be either 'yes' or 'no', with 'no' being the default. |
| 742 | |
| 743 | #DumpHeader no |
| 744 | |
| 745 | # DumpExtension allow you to specify the dump filename extension |
| 746 | # to use. The default is "tab", but some programs are pickey about |
| 747 | # the filenames they use, so you may change it here (for example, |
| 748 | # some people may prefer to use "csv"). |
| 749 | |
| 750 | #DumpExtension tab |
| 751 | |
| 752 | # These control the dumping of each individual table. The value |
| 753 | # can be either 'yes' or 'no'.. the default is 'no'. |
| 754 | |
| 755 | #DumpSites no |
| 756 | #DumpURLs no |
| 757 | #DumpReferrers no |
| 758 | #DumpAgents no |
| 759 | #DumpUsers no |
| 760 | #DumpSearchStr no |
| 761 | |
| 762 | # The custom graph colors are defined here. Declare them |
| 763 | # in the standard hexadecimal way (as HTML, without the '#') |
| 764 | # If none are given, you will get the standard default colors. |
| 765 | |
| 766 | #ColorHit 00805c |
| 767 | #ColorFile 0040ff |
| 768 | #ColorSite ff8000 |
| 769 | #ColorKbyte ff0000 |
| 770 | #ColorPage 00e0ff |
| 771 | #ColorVisit ffff00 |
| 772 | #ColorMisc 00e0ff |
| 773 | |
| 774 | #PieColor1 800080 |
| 775 | #PieColor2 80ffc0 |
| 776 | #PieColor3 ff00ff |
| 777 | #PieColor4 ffc080 |
| 778 | |
| 779 | # End of configuration file... Have a nice day! |