my $call_dir = "Bing/1Parsed/Html3";
my $contents_of_file = 1;
#my $tidy = HTML::Tidy->new();
my $tidy = HTML::Tidy->new({
tidy_mark => 1,
#output_xhtml => 1, # yes
#output_xhtml => 1, # yes
add_xml_decl => 1, # no
wrap => 76,
error_file => errs.txt,
char_encoding => utf8,
indent_cdata => 1,
clean => 1,
fix_bad_comments =>1
});
my @files = glob "$call_dir/*.html";
printf "Got %d files\n", scalar @files;
for my $file (@files) {
open my $in_fh, '<', $file
or die "Could not open $file : $!";
my $contents_of_file = do { local $/;<$in_fh> };
close $in_fh;
$tidy->parse( $file, $contents_of_file );
open OUT,'>',$file or die "$!";
print OUT $tidy->clean( $file, $contents_of_file );
print "cleaning" . $file;
for my $message ( $tidy->messages ) {
#print $message->as_string;
}