How can I extract data in a Word document using Perl?

Question

How to extract the data from a word doc using Perl?

Answer 1

use Win32::OLE;
use Win32::OLE::Enum;

$document = Win32::OLE -> GetObject($ARGV[1]);
open (FH,">$ARGV[0]");

print "Extracting Text ...\n";

$paragraphs = $document->Paragraphs();
$enumerate = new Win32::OLE::Enum($paragraphs);
while(defined($paragraph = $enumerate->Next()))
{
    $style = $paragraph->{Style}->{NameLocal};
    print FH "+$style\n";
    $text = $paragraph->{Range}->{Text};
    $text =~ s/[\n\r]//g;
    $text =~ s/\x0b/\n/g;
    print FH "=$text\n";
}

stolen from here