[Scribus] PDF Script to reduce PDF sizes no longer works the same under Gutsy

Julian Robbins julian.robbins
Wed Oct 17 14:02:50 CEST 2007


Sorry to post again, but no-one picked up on this. I hope someone can 
help. I'm sure this will be very useful for others if we can fix this.

Hopefully someone will remember this particularly useful script 
documented here http://wiki.scribus.net/index.php/Web_optimised_PDF.

This is a very useful script that massively reduces PDF size, this is 
especially useful when you want to mail a PDF. Scribus PDF's are great 
but are not particularly small. It converts a Scribus PDF to PS then 
from PS back to PDF using Ghostscript.

But using Scribus in Ubuntu Gutsy Gibbon, with same Scribus version as 
before but newer Ghostscript 8.61SVN (previously 8.5), the 
script reduces the size as before, but gets rid of all the text items as 
full text and instead converts them into an image objects instead.

So you get a nice small PDF, but not really a well formed PDF, it really
ends up as a collection of compressed images stapled together.
Bizarrely, PDF transparency couldn't be handled successfully before, but
does now, so at least it helps to flatten files if required.

Here is the script below:-

If anyone can work out what's changed I' really need to know !!

Is there any other means to reduce a Scribus generated PDF to be
suitable for web download ? Apart from the obvious answers like reducing 
image res, not embedding fonts, etc, etc ..


Julian Robbins


#  -*-Perl-*-
# ====================================================================== #
# Run the right perl version:
if [ -x /usr/local/bin/perl ]; then
elif [ -x /usr/bin/perl ]; then
  perl=`which perl| sed 's/.*aliased to *//'`

exec $perl -x -S $0 "$@"     # -x: start from the following line
# ====================================================================== #
#! /Good_Path/perl -w
# line 17

# Name:   compress-newsletter
# Author: wd (Wolfgang.Dobler at ucalgary.ca)
# Date:   03-Oct-2005
# Description:
#   Use ghostscript's pdfwrite device (? la ps2pdf) to reduce the
#   Newsletter's PDF file size, and add meta information like author,
#   date, etc.
#   The preferred route is currently:
#                 [scribus>=]
#                        |
#                    file.pdf
#                        |
#                 [pdftops>=3.00]
#                        |
#                     file.ps
#                        |
#            [pstopdf14 (gs-gnu-8.16 or higher)]
#                        |
#                        V
#                    final.pdf
# Usage:
#   compress-newletter [-i col:gray:mono] Newsletter_big.pdf
# Options:
#   -i col:gray:mono
#   --imgres=col:gray:mono   Set resolution for downsampling color,
#                            grayscale and black-and-white images
#                            (default is 144:300:300)
#   --debug                  Be verbose and keep temporary files around
use strict;
use File::Temp qw/ :mktemp /;

use Getopt::Long;
# Allow for `-Plp' as equivalent to `-P lp' etc:

my (%opts);            # Options hash for GetOptions
my $doll='\$';            # Need this to trick CVS

## Process command line
       qw( -h   --help
           -i=s --imgres=s
           -q   --quiet
               -v   --version ));

my $debug = ($opts{'debug'} ? 1 : 0 ); # undocumented debug option
if ($debug) {
    print "\@ARGV = `@ARGV'\n";

if ($opts{'h'} || $opts{'help'})    { die usage();   }
if ($opts{'v'} || $opts{'version'}) { die version(); }

my $quiet  = ($opts{'q'} || $opts{'quiet'}  || ''           );
my $imgres = ($opts{'i'} || $opts{'imgres'} || '144:300:300');

my ($gs,      @gsargs     ) = ('gs'     );
my ($pdftops, @pdftopsargs) = ('pdftops');
my ($pdfopt,  @pdfoptargs ) = ('pdfopt' );

my $infile = shift or die usage();
(my $root=$infile) =~ s/\.(pdf|ps).*//;
(my $outfile=$infile) =~ s/(.*)(\.(pdf|ps))/${1}_web${2}/;
my $tmpfile = mktemp("${root}.tmp_XXXXXX");

## 0. Extract all sorts of information

# Extract Scribus version, creation date, bookmarks from original PDF:
print "Running pdftk ...\n";
print STDERR "pdftk $infile dump_data output\n" if ($debug);
my $meta = `pdftk $infile dump_data output -`;
my ($creator) = ( $meta =~
          m{InfoKey: Creator\s+InfoValue:\s*(.+)$}m
$creator = 'Scribus' unless defined($creator);
my $datestring = extract_CreationDate($meta);
my @bookmarks = extract_bookmarks($meta);

# Extract desired image resolutions
my ($colres,$grayres,$monores) = ($imgres =~ /([0-9]+):([0-9]+):([0-9]+)/);
die "Image resolution must be of form `col:gray:mono'\n"
    unless defined($monores);

## 1. Run pdftops
push @pdftopsargs, "-level3";
my $psfile = mktemp("${root}.ps_XXXXXX");
push @pdftopsargs, $infile, $psfile;
print "Running pdftops ...\n";
print STDERR "$pdftops @pdftopsargs\n" if ($debug);
system($pdftops, at pdftopsargs);

## 2. Run gs
# a) Prepare options
push @gsargs, qw{-q -dNOPAUSE -dBATCH};
push @gsargs, '-sDEVICE=pdfwrite';
push @gsargs, '-dCompatibilityLevel=1.3';
# One of /printer, /screen, /prepress, /ebook, /default; see Ps2pdf.htm:
push @gsargs, '-dPDFSETTINGS=/screen';
push @gsargs, '-dEmbedAllFonts=true';
push @gsargs, '-dSubsetFonts=true';
push @gsargs, '-dColorImageDownsampleType=/Bicubic';
push @gsargs, "-dColorImageResolution=$colres";
push @gsargs, '-dGrayImageDownsampleType=/Bicubic';
push @gsargs, "-dGrayImageResolution=$grayres";
push @gsargs, '-dMonoImageDownsampleType=/Bicubic';
push @gsargs, "-dMonoImageResolution=$monores";
push @gsargs, "-sOutputFile=$tmpfile";
push @gsargs, "-c .setpdfwrite";

# b) Write meta information to temporary file
#my $metafile = mktemp("metainfo.tmp_XXXXXX");
my $metafile = "${root}.meta";
open(META, "> $metafile");
% Document information
/CreationDate (D:$datestring)
/ModDate (D:$datestring)
/Creator ($creator)
/Title (WBH2-8N13 2 - 8 GHz Ridged Wide band Horn Antenna)
/Subject (Wide Band Horn Antennas)
/Keywords (Microwave antenna, Linear polarisation, Vertical polarisation)
/Author (Janette Morgan, Q-par Angus Ltd)
/DOCINFO pdfmark

% Initial view on opening the document
[/View [/Fit] % Fit page in window
/Page 1
% /PageMode /UseOutlines % /UseNone /UserOutlines /UseThumbs /FullScreen
/DOCVIEW pdfmark


## Bookmarks. [Commented out for acroread 7.0 has problems] Currently at
## the mercy of the original bookmarks (and Scribus 1.2.2 does not allow
## to edit the bookmark names) and the encoding that pdftk understands
## (most quotation marks get mapped to `?').
## Ideally, one would write out the meta information file with
## `compress-newsletter -m CC.pdf' and use it then with
## `compress-newsletter CC.pdf'.
## % Bookmarks: @bookmarks

push @gsargs, '-f', $psfile, $metafile;
print "Running gs-gpl ...\n";
print STDERR "$gs @gsargs\n" if ($debug);
system($gs, at gsargs);

## 3. Run pdfopt
print "Running pdfopt ...\n";
print STDERR "$pdfopt @pdfoptargs $tmpfile $outfile\n" if ($debug);
system($pdfopt, at pdfoptargs,$tmpfile,$outfile);

# Some diagnostics:
system('ls', '-l', $infile, $psfile, $tmpfile, $outfile);

    # Clean up even in case of an error:
    unless ($debug) {
        foreach my $file ($psfile,$tmpfile) {
        unlink $file if (defined($file) && -f $file);

# ---------------------------------------------------------------------- #
sub extract_CreationDate {

    use POSIX qw(strftime);

    my $meta = shift;

    my ($cdate) = ( $meta =~
            m{InfoKey: CreationDate\s+InfoValue:\s*(.+)$}m
    # Time string: need to splice in "'" after hours and minutes of time
    # definition. To me this looks like the technical documentation was
    # too literally and now applications (and Acroread 7) insist on these
    # stupid markers.
    my $datestring;
    # JTR 12/10/2006 remmed out as date from Scribsu didnt coem out
correctly to parse into Adobe reader.
    # if ($cdate =~ /[0-9]{14}/) { # managed to extract CreationDate
from $meta
    #$datestring = "$cdate";
    # } else {                 # Creation date unknown -- use current date
    {my $tz = strftime "%z", localtime();
    $tz =~ s/([0-9][0-9])([0-9][0-9])/$1'$2'/;
    $datestring = strftime "%Y%m%d%H%M%S$tz", localtime();

# ---------------------------------------------------------------------- #
sub extract_bookmarks {

    my $meta = shift;

    my @bm;

    while ($meta =~ /^BookmarkTitle:      \s* (.*) \n
                      BookmarkLevel:      \s* (.*) \n
                      BookmarkPageNumber: \s* (.*) /xmg) {
    my ($title,$level,$page) = ($1,$2,$3);
    push @bm, "[/Title ($title /Page $page /OUT pdfmark\n";

# ---------------------------------------------------------------------- #
sub printopts {
# Print command line options
    my $optsref = shift;
    my %opts = %$optsref;
    foreach my $opt (keys(%opts)) {
    print STDERR "\$opts{$opt} = `$opts{$opt}'\n";
# ---------------------------------------------------------------------- #
sub usage {
# Extract description and usage information from this file's header.
    my $thisfile = __FILE__;
    local $/ = '';              # Read paragraphs
    open(FILE, "<$thisfile") or die "Cannot open $thisfile\n";
    while (<FILE>) {
    # Paragraph _must_ contain `Description:' or `Usage:'
        next unless /^\s*\#\s*(Description|Usage):/m;
        # Drop `Author:', etc. (anything before `Description:' or `Usage:')
        # Don't print comment sign:
        s/^\s*# ?//mg;
        last;                        # ignore body
    $_ or "<No usage information found>\n";
# ---------------------------------------------------------------------- #
sub version {
# Return CVS data and version info.
    my $doll='\$';        # Need this to trick CVS
    my $cmdname = (split('/', $0))[-1];
    my $rev = '$Revision: 1.8 $';
    my $date = '$Date: 2006/02/02 09:38:52 $';
    $rev =~ s/${doll}Revision:\s*(\S+).*/$1/;
    $date =~ s/${doll}Date:\s*(\S+).*/$1/;
    "$cmdname version $rev ($date)\n";
# ---------------------------------------------------------------------- #

# End of file compress-newsletter

More information about the scribus mailing list