#!/usr/local/bin/perl -w

# this script builds a cache of web pages, which can be searched
# by sitesearch.pl; shd be run each time web site content changes

use strict;
use CGI qw(:standard);
use Data::Dumper;

my $dir = 'your_file_path';    # dir to search.
my $ext = 'htm';               # page types to search.
my $cache = 'sitesearch.dat';  # cache file.
my (@Results,$file,$title);

# optional boundaries for search area, to avoid
# searching on repeated text:
my $startstring = 'unique_ident_1';	
my $endstring = 'unique_ident_2';

chdir $dir;

# get all the relevant pages, strip out title, file name and
# searchable text, store in array of hashes:
while (<*.$ext>) {
    open FILE, $_;
    read FILE, $file, -s(FILE);
    $file =~ m#<title>(.*?)</title>#i;
    $title = $1;
    $file =~ s/^.*$startstring/$startstring/s;  # delete these 2 lines if
    $file =~ s/$endstring.*$//s;                # you want to search the whole page
    $file =~ s/<[^>]*>/ /g;
    push @Results, {filename => $_, title => $title, text => $file};
}

# save the results in the cache file:
open SAVE, ">$cache" or die "could not open $cache $!";
print SAVE Dumper(\@Results);
close SAVE;

# check what has been saved in the cache file, and display it:
open RETRIEVE, $cache or die "could not open $cache $!";
my $data = do { local $/; <RETRIEVE> };
my @Retrieves = @{ my $VAR1; eval $data };
print header,h2('You have successfully cached the following pages:');
print $_->{title},br for @Retrieves;