3 # Copyright 2015 Tamil s.a.r.l.
5 # This file is part of Koha.
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.
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.
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>.
24 use Pod::Usage qw( pod2usage );
25 use Getopt::Long qw( GetOptions );
27 use Koha::Script -cron;
31 my ($verbose, $help, $url, $dir, $short) = (0, 0, '', '.', 1);
34 'verbose' => \$verbose,
43 pod2usage( -verbose => 2 );
50 $url = C4::Context->preference("OPACBaseURL");
52 say "OPACBaseURL syspref isn't defined. You can use --url parameter.";
58 my $sitemapper = Koha::Sitemapper->new(
64 $sitemapper->run($where);
71 =item sitemap.pl [--verbose|--help|--short|--noshort|--url|--dir|--where ]
78 sitemap.pl --noshort --dir /home/koha/mylibrary/www
79 sitemap.pl --url opac.myDNSname.org
80 sitemap.pl --where 'biblionumber<100'
84 Process all biblio records from a Koha instance and generate Sitemap files
85 complying with this protocol as described on L<http://sitemaps.org>. The goal of
86 this script is to be able to provide to search engines direct access to biblio
87 records. It avoid leaving search engine browsing Koha OPAC and so generating
88 a lot of traffic, and workload, for a bad result.
90 A file name F<sitemapindex.xml> is generated. It contains references to Sitemap
91 multiples files. Each file contains at most 50,000 urls, and is named
94 The files must be stored on Koha OPAC root directory, ie
95 F<<koha-root>/koha-tmpl/>. Place also in this directory a F<robots.txt> file
98 Sitemap: sitemapindex.xml
106 =item B<--url=Koha OPAC base URL>
108 If omitted, OPACBaseURL syspref is used.
110 =item B<--short|noshort>
112 By default, --short. With --short, URL to bib record ends with
113 /bib/biblionumber. With --noshort, URL ends with
114 /cgi-bin/koha/opac-detail.pl?biblionumber=bibnum
118 Directory where to write sitemap files. By default, the current directory.
120 =item B<--verbose|-v>
122 Enable script verbose mode: a message is displayed for each 10,000 biblio
127 Print this help page.
131 Add a filter to limit the selection of biblio records. May be useful when testing the feature.