Re: Parsing, searching, replacing content in MS Word documents

[t0mas]

You could try something like this:

#!/usr/bin/perl -w

# Uses
use strict;
use Win32::OLE;
use Win32::OLE::Variant;
use Win32::OLE::Const;
use File::Find;

# Variables
use vars qw($MSWord $wd $startdir);

# Where to start the doc search
$startdir='c:\tmp';

# Create new MSWord object and load constants
$MSWord=Win32::OLE->new('Word.Application','Quit') or
    die "Could not load MS Word";
$wd=Win32::OLE::Const->Load($MSWord);

# Find documents
find(\&rTxt,$startdir);

sub rTxt {

    # We only want .doc files (no links...)
    return unless /\.doc$/ && -f && ! -l;

    # Open document
    my $doc = $MSWord->Documents->Open({FileName=>$File::Find::name});

    # Exit nicely if we couldn't open doc
    return unless $doc;

    # Print some info
    print $File::Find::name,"\n";

    # Content object
    my $content=$doc->Content;

    # Find object
    my $find=$content->Find;
    $find->ClearFormatting;
    $find->{Text}="Yoo";
    $find->Replacement->ClearFormatting;
    $find->Replacement->{Text}="Hello";
    $find->Execute({Replace=>$wd->{wdReplaceAll},Forward=>$wd->{True}}
+);

    # Close document
    $doc->Close({SaveChanges=>$wd->{wdSaveChanges}});
}

It uses the built-in Find-And-Replace function that comes with MS Word. If you want to do any other more complex things (like s/^Yoo/Hello/i) you'll have to do stuff to the whole Content object.
The major problem with OLE Automation in my opinion is that it is painfully slow. If you have a large ammount of MS Word docs, this stunt will probably take ages.


/brother t0mas