#!C:/STRAWB~1/perl/bin/perl.exe -w

use Data::Dumper;
use HTML::TreeBuilder;
use HTML::TreeBuilder::XPath;
use utf8;

#------------------------------------------
if (!$ARGV[0] || !$ARGV[1]) {
    print "\n\n htmlParser-V.1.0.pl: Error: missing input and/or outpu
+t directories.\n\n";
    print "Example of use: htmlParser-V.1.0.pl <input-path> <output-pa
+th>\n\n";
    exit;
}
my $inputpath = $ARGV[0];
my $outputpath = $ARGV[1];

#================# Read the files from the inputpath
opendir(DIR, $inputpath) || die "\n - ERROR: Can't open the input path
+: '$inputpath' !!";
my @files = grep { -f "$inputpath/$_" } readdir(DIR);
closedir DIR;
#================# First, check if outputpath exists. If not, we creat
+e it.
if (not -e $outputpath){
    mkdir $outputpath;
    print "\n - Output path created!";
    }
#=====================================================================
+=====#
foreach  $file (@files){
   open (FILE, '<:encoding(UTF-8)', "$inputpath/$file") || die "can't 
+openfile $file: $!";
    print "\n - Scanning file '$file' ... ";
    my $root = HTML::TreeBuilder->new_from_file("$inputpath/$file");
        $root->parse("$inputpath/$file");
#=======First Attribute========
        my @div_class = $root->find_by_attribute("id","maincontent");
        #_by_attribute("id","ctl00_ContentPlaceHolder1_FormView1_Label
+2");
        foreach my $node (@div_class) {
        open (OUT,">>$outputpath/Bank\-$inputpath\-$file\.txt") || die
+("\n - ERROR: Can't create the output file !!");
        print OUT $node->as_text, "\n";
        
        print OUT "\n";
        }###foreach
 }#foreach
print "OK";
close FILE;
close OUT;
[download]