Reduce all pdf file size in a directory with PDFNetPython

# '#' hash and delimiter (“””) symbol in Python script is meant for statements without functions, it serves as an explanation or notes you would like to add-on

# Install Ananconda 3 from https://www.anaconda.com/products/individual

# What is anaconda:- Anaconda® is a package manager, an environment manager, a Python/R data science distribution, and a collection of over 7,500+ open-source packages. Anaconda is free and easy to install, and it offers free community support.

# Install Python3 from https://www.python.org/downloads/

# Goto window command prompt - type 'anaconda' to call out anaconda prompt

# at anaconda prompt - type 'pip install Jupyter' (install Jupyter Notebook)

# at anaconda prompt - type 'pip install PDFNetPython3' (install PDFNetPython3)

# Update all packages - type 'conda update --all' (Update all packages)

# at anaconda prompt - type 'Jupyter Notebook' (Call out Jupyter Notebook in preferred browser e.g. google chrome)

# at Jupyter Notebook - click 'new' > Python3 > copy paste Python Script in blue below into the Jupyter window.

# ------------------------------------

# you can also run scripts in a web browser: https://colab.research.google.com/notebooks/intro.ipynb#scrollTo=IqIkXkLmG7uS

# ------------------------------------

# The script below is aimed to reduce pdf file size in a folder

import site

import sys

from os import *

# to test iteration by printing/showing the items

# import pprint

# pprint is just a python package to print the items nicely line by line

from PDFNetPython3 import *

input_path = 'C:/Directory_Input/'

output_path = 'C:/Directory_Output/'

#input_filename = 'filename'

pdf_files = [pdf for pdf in listdir(input_path)]

# pdf_files is a list

# pprint.pprint (pdf_files) 

# to create a list with all items in the folder and use for loop to iterate the function()

# create a function

def optimise():

    PDFNet.Initialize()

    doc = PDFDoc(input_path + pdf)

    doc.InitSecurityHandler()

    image_settings = ImageSettings()

    image_settings.SetCompressionMode(ImageSettings.e_jpeg)

    image_settings.SetQuality(1)

    image_settings.SetImageDPI(144,96)

    image_settings.ForceRecompression(True)

    Optimizer.Optimize(doc)

    doc.Save(output_path + pdf, SDFDoc.e_linearized)

    doc.Close()

# iterate all items with the created function

for pdf in pdf_files:

    # pdf is items in the pdf_files list

    # pprint.pprint (pdf)

    

    optimise()

Source and reference: 

• https://www.pdftron.com/documentation/python/get-started/python3
• https://www.pdftron.com/documentation/samples/py/OptimizerTest

Related links:

• http://carrefax.com/new-blog/2017/1/16/draft
• https://stackoverflow.com/questions/19932130/iterate-through-folders-then-subfolders-and-print-filenames-with-path-to-text-f
• https://github.com/theeko74/pdfc/blob/master/README.md
• https://pypi.org/project/pdfminify/#description