misc/cronjobs/sitemap.pl

   1 #!/usr/bin/perl
   2
   3 # Copyright 2015 Tamil s.a.r.l.
   4 #
   5 # This file is part of Koha.
   6 #
   7 # Koha is free software; you can redistribute it and/or modify it
   8 # under the terms of the GNU General Public License as published by
   9 # the Free Software Foundation; either version 3 of the License, or
  10 # (at your option) any later version.
  11 #
  12 # Koha is distributed in the hope that it will be useful, but
  13 # WITHOUT ANY WARRANTY; without even the implied warranty of
  14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  15 # GNU General Public License for more details.
  16 #
  17 # You should have received a copy of the GNU General Public License
  18 # along with Koha; if not, see <http://www.gnu.org/licenses>.
  19
  20 package Main;
  21
  22 use Modern::Perl;
  23 use utf8;
  24 use Pod::Usage;
  25 use Getopt::Long;
  26
  27 use Koha::Script -cron;
  28 use C4::Biblio;
  29 use Koha::Sitemapper;
  30
  31
  32 my ($verbose, $help, $url, $dir, $short) = (0, 0, '', '.', 1);
  33 GetOptions(
  34     'verbose'   => \$verbose,
  35     'help'      => \$help,
  36     'url=s'     => \$url,
  37     'dir=s'     => \$dir,
  38     'short!'    => \$short,
  39 );
  40
  41 sub usage {
  42     pod2usage( -verbose => 2 );
  43     exit;
  44 }
  45
  46 usage() if $help;
  47
  48 unless ($url) {
  49     $url = C4::Context->preference("OPACBaseURL");
  50     unless ($url) {
  51         say "OPACBaseURL syspref isn't defined. You can use --url parameter.";
  52         exit;
  53     }
  54 }
  55 $url =~ s/\/*$//g;
  56
  57 my $sitemapper = Koha::Sitemapper->new(
  58     verbose => $verbose,
  59     url     => $url,
  60     dir     => $dir,
  61     short   => $short,
  62 );
  63 $sitemapper->run();
  64
  65
  66 =head1 USAGE
  67
  68 =over
  69
  70 =item sitemap.pl [--verbose|--help|--short|--noshort|--url|--dir]
  71
  72 =back
  73
  74 =head1 SYNOPSIS
  75
  76   sitemap.pl --verbose
  77   sitemap.pl --noshort --dir /home/koha/mylibrary/www
  78   sitemap.pl --url opac.myDNSname.org
  79
  80 =head1 DESCRIPTION
  81
  82 Process all biblio records from a Koha instance and generate Sitemap files
  83 complying with this protocol as described on L<http://sitemaps.org>. The goal of
  84 this script is to be able to provide to search engines direct access to biblio
  85 records. It avoid leaving search engine browsing Koha OPAC and so generating
  86 a lot of traffic, and workload, for a bad result.
  87
  88 A file name F<sitemapindex.xml> is generated. It contains references to Sitemap
  89 multiples files. Each file contains at most 50,000 urls, and is named
  90 F<sitemapXXXX.xml>.
  91
  92 The files must be stored on Koha OPAC root directory, ie
  93 F<<koha-root>/koha-tmpl/>. Place also in this directory a F<robots.txt> file
  94 like this one:
  95
  96  Sitemap: sitemapindex.xml
  97  User-agent: *
  98  Disallow: /cgi-bin/
  99
 100 =head1 PARAMETERS
 101
 102 =over
 103
 104 =item B<--url=Koha OPAC base URL>
 105
 106 If omitted, OPACBaseURL syspref is used.
 107
 108 =item B<--short|noshort>
 109
 110 By default, --short. With --short, URL to bib record ends with
 111 /bib/biblionumber. With --noshort, URL ends with
 112 /cgi-bin/koha/opac-detail.pl?biblionumber=bibnum
 113
 114 =item B<--dir>
 115
 116 Directory where to write sitemap files. By default, the current directory.
 117
 118 =item B<--verbose|-v>
 119
 120 Enable script verbose mode: a message is displayed for each 10,000 biblio
 121 records processed.
 122
 123 =item B<--help|-h>
 124
 125 Print this help page.
 126
 127 =back
 128
 129 =cut