Python 3 Script to Compress PDF Document Using GhostScript in Command Line

Welcome folks today in this blog post we will be compressing pdf document using ghostscript in command line using python.All the full source code of the application is shown below.

Get Started

In order to get started you need to download the ghostscript library from the below url and then install it on the machine by adding it inside the environment variables.

https://ghostscript.com/releases/gsdnld.html

And now you need to make an app.py file and copy paste the following code

app.py

import argparse
import subprocess
import os.path
import sys
import shutil


def main():
    parser = argparse.ArgumentParser(
        description=__doc__,
        formatter_class=argparse.RawDescriptionHelpFormatter
    )
    parser.add_argument('input', help='Relative or absolute path of the input PDF file')
    parser.add_argument('-o', '--out', help='Relative or absolute path of the output PDF file')
    parser.add_argument('-c', '--compress', type=int, help='Compression level from 0 to 4')
    parser.add_argument('-b', '--backup', action='store_true', help="Backup the old PDF file")
    parser.add_argument('--open', action='store_true', default=False,
                        help='Open PDF after compression')
    args = parser.parse_args()

    # In case no compression level is specified, default is 2 '/ printer'
    if not args.compress:
        args.compress = 2
    # In case no output file is specified, store in temp file
    if not args.out:
        args.out = 'temp.pdf'

    # Run
    compress(args.input, args.out, power=args.compress)

    # In case no output file is specified, erase original file
    if args.out == 'temp.pdf':
        if args.backup:
            shutil.copyfile(args.input, args.input.replace(".pdf", "_BACKUP.pdf"))
        shutil.copyfile(args.out, args.input)
        os.remove(args.out)

    # In case we want to open the file after compression
    if args.open:
        if args.out == 'temp.pdf' and args.backup:
            subprocess.call(['open', args.input])
        else:
            subprocess.call(['open', args.out])

if __name__ == '__main__':
    main()

import argparse

import subprocess

import os.path

import sys

import shutil

def main():

parser = argparse.ArgumentParser(

description=__doc__,

formatter_class=argparse.RawDescriptionHelpFormatter

)

parser.add_argument('input', help='Relative or absolute path of the input PDF file')

parser.add_argument('-o', '--out', help='Relative or absolute path of the output PDF file')

parser.add_argument('-c', '--compress', type=int, help='Compression level from 0 to 4')

parser.add_argument('-b', '--backup', action='store_true', help="Backup the old PDF file")

parser.add_argument('--open', action='store_true', default=False,

help='Open PDF after compression')

args = parser.parse_args()

# In case no compression level is specified, default is 2 '/ printer'

if not args.compress:

args.compress = 2

# In case no output file is specified, store in temp file

if not args.out:

args.out = 'temp.pdf'

# Run

compress(args.input, args.out, power=args.compress)

# In case no output file is specified, erase original file

if args.out == 'temp.pdf':

if args.backup:

shutil.copyfile(args.input, args.input.replace(".pdf", "_BACKUP.pdf"))

shutil.copyfile(args.out, args.input)

os.remove(args.out)

# In case we want to open the file after compression

if args.open:

if args.out == 'temp.pdf' and args.backup:

subprocess.call(['open', args.input])

else:

subprocess.call(['open', args.out])

if __name__ == '__main__':

main()

As you can see we are importing all the libraries and then we are defining the main() function inside which we are adding the command line arguments to compress the pdf document using different options. We are adding arguments to the command using the add_argument() method. And then we are calling the compress() function where we define the logic to actually compress the text and images present inside the pdf document. And now we need to define the compress() function as shown below

def compress(input_file_path, output_file_path, power=0):
    """Function to compress PDF via Ghostscript command line interface"""
    quality = {
        0: '/default',
        1: '/prepress',
        2: '/printer',
        3: '/ebook',
        4: '/screen'
    }

    # Basic controls
    # Check if valid path
    if not os.path.isfile(input_file_path):
        print("Error: invalid path for input PDF file")
        sys.exit(1)

    # Check if file is a PDF by extension
    if input_file_path.split('.')[-1].lower() != 'pdf':
        print("Error: input file is not a PDF")
        sys.exit(1)

    gs = get_ghostscript_path()
    print("Compress PDF...")
    initial_size = os.path.getsize(input_file_path)
    subprocess.call([gs, '-sDEVICE=pdfwrite', '-dCompatibilityLevel=1.4',
                    '-dPDFSETTINGS={}'.format(quality[power]),
                    '-dNOPAUSE', '-dQUIET', '-dBATCH',
                    '-sOutputFile={}'.format(output_file_path),
                     input_file_path]
    )
    final_size = os.path.getsize(output_file_path)
    ratio = 1 - (final_size / initial_size)
    print("Compression by {0:.0%}.".format(ratio))
    print("Final file size is {0:.1f}MB".format(final_size / 1000000))
    print("Done.")


def get_ghostscript_path():
    gs_names = ['gs', 'gswin32', 'gswin64']
    for name in gs_names:
        if shutil.which(name):
            return shutil.which(name)
    raise FileNotFoundError(f'No GhostScript executable was found on path ({"/".join(gs_names)})')

def compress(input_file_path, output_file_path, power=0):

"""Function to compress PDF via Ghostscript command line interface"""

quality = {

0: '/default',

1: '/prepress',

2: '/printer',

3: '/ebook',

4: '/screen'

}

# Basic controls

# Check if valid path

if not os.path.isfile(input_file_path):

print("Error: invalid path for input PDF file")

sys.exit(1)

# Check if file is a PDF by extension

if input_file_path.split('.')[-1].lower() != 'pdf':

print("Error: input file is not a PDF")

sys.exit(1)

gs = get_ghostscript_path()

print("Compress PDF...")

initial_size = os.path.getsize(input_file_path)

subprocess.call([gs, '-sDEVICE=pdfwrite', '-dCompatibilityLevel=1.4',

'-dPDFSETTINGS={}'.format(quality[power]),

'-dNOPAUSE', '-dQUIET', '-dBATCH',

'-sOutputFile={}'.format(output_file_path),

input_file_path]

)

final_size = os.path.getsize(output_file_path)

ratio = 1 - (final_size / initial_size)

print("Compression by {0:.0%}.".format(ratio))

print("Final file size is {0:.1f}MB".format(final_size / 1000000))

print("Done.")

def get_ghostscript_path():

gs_names = ['gs', 'gswin32', 'gswin64']

for name in gs_names:

if shutil.which(name):

return shutil.which(name)

raise FileNotFoundError(f'No GhostScript executable was found on path ({"/".join(gs_names)})')

As you can see we are first of all getting the ghostscript library executable path using the get_ghostscript_path() method and then we are calling the subprocess module to execute the ghostscript command to reduce the pdf size and then it is saving it as the output pdf file.

Usage

Now to run this pdf compression script you need to execute the below command as shown below

python app.py input.pdf -o output.pdf

Here input.pdf is the path of the input pdf file

Here output.pdf is the path of the output pdf file

Now if you see the size of the output.pdf file it is compressed to 44 KB from 3.6 MB