Extract a region of a PDF page by coordinates

Question

I am looking for a tool to extract a given rectangular region (by coordinates) of a 1-page PDF file and produce a 1-page PDF file with the specified region:

# in         


        

Answer 1

using pyPdf, you could do something like this:

import sys
import pyPdf

def extract(in_file, coords, out_file):
    with open(in_file, 'rb') as infp:
        reader = pyPdf.PdfFileReader(infp)
        page = reader.getPage(0)
        writer = pyPdf.PdfFileWriter()
        page.mediaBox.lowerLeft = coords[:2]
        page.mediaBox.upperRight = coords[2:]
        # you could do the same for page.trimBox and page.cropBox
        writer.addPage(page)
        with open(out_file, 'wb') as outfp:
            writer.write(outfp)

if __name__ == '__main__':
    in_file = sys.argv[1]
    coords = [int(i) for i in sys.argv[2:6]]
    out_file = sys.argv[6]

    extract(in_file, coords, out_file)

Answer 2

The following script found in http://snipplr.com/view.php?codeview&id=18924 splits each page of a pdf into 2.

#!/usr/bin/env perl
use strict; use warnings;
use PDF::API2;

my $filename = shift;
my $oldpdf = PDF::API2->open($filename);
my $newpdf = PDF::API2->new;

for my $page_nb (1..$oldpdf->pages) {
  my ($page, @cropdata);

  $page = $newpdf->importpage($oldpdf, $page_nb);
  @cropdata = $page->get_mediabox;
  $cropdata[2] /= 2;
  $page->cropbox(@cropdata);
  $page->trimbox(@cropdata);
  $page->mediabox(@cropdata);

  $page = $newpdf->importpage($oldpdf, $page_nb);
  @cropdata = $page->get_mediabox;
  $cropdata[0] = $cropdata[2] / 2;
  $page->cropbox(@cropdata);
  $page->trimbox(@cropdata);
  $page->mediabox(@cropdata);
}

(my $newfilename = $filename) =~ s/(.*)\.(\w+)$/$1.clean.$2/;
$newpdf->saveas('destination_path/myfile.pdf');