#!perl
use strict;
use warnings;
use HTML::Strip;
my $hs = HTML::Strip->new();
my $files_dir = 'C:\Dwimperl\Perl';
my $write_dir = 'G:\research\sec filings 10k and 10Q\data\filing docs\
+1993\Clean';
opendir (my $dir_handle, $files_dir);
while (my $filename = readdir($dir_handle)){
next unless -f $files_dir.'/'.$filename;
print "Procesing $filename\n";
open my $fh_in, '<', $files_dir.'/'.$filename
or die "failed to open '$filename' for read";
open my $fh_out, '>', $write_dir.'/'.$filename
or die "failed to open '$filename' for write";
my $count=0;
while (my $line = <$fh_in>) {
my $clean_text = $hs->parse($line);
print $fh_out "$clean_text\n";
++$count;
}
$hs->eof;
print "$count lines read from $filename\n;"
}