@@ -82,6 +82,11 @@ if ( defined $ARGV[1] && $ARGV[1] eq "--gen-seed" ) {
open(my $fh, '>', "generated_seed.txt");
print $fh $word_list;
close $fh;
+ my $sorted_list = `cat generated_seed.txt | sort | uniq`;
+ open(my $fh2, '>', "generated_seed.txt");
+ print $fh2 $sorted_list;
+ close $fh2;
+
exit 0;
}
@@ -0,0 +1,18 @@
+#!/usr/bin/perl
+use strict;
+use warnings;
+# Scratch pad for parsing webpages for lists
+# of different words/names, for the seed file
+my @page = split("\n", `cat saints.html`);
+foreach my $line ( @page ) {
+ if ( $line =~ m/<td data-sort-value=.*<a\ href=.*title="(.*)"/ ) {
+ my $line1 = $1;
+ if ( $line1 =~ m/^([a-zA-z0-9\ ,-]{1,})/ ) {
+ print "$1\n";
+ }
+}