parse.pl
1	#!/usr/bin/perl
2
3 use strict;
4 use warnings;
5
6 # Scratch pad for parsing webpages for lists
7 # of different words/names, for the seed file
8
9 my @page = split("\n", `cat saints.html`);
10
11 foreach my $line ( @page ) {
12 if ( $line =~ m/title="(.*)">.*/ ) {
13 my $line1 = $1;
14 if ( $line1 =~ m/ctx/ ) {
15 next;
16 } else {
17 print "$line1\n";
18 }
19
20 #if ( $line1 =~ m/^([a-zA-z0-9\ ,-]{1,})/ ) {
21 # print "$1\n";
22 #}
23 }
24 }