Convert the image in .zip to PDF with Python

Overview

--This is the code to convert the images in the .zip in the same directory to PDF. --A4 PDF (variable)

code

First, move the current directory (cd) to the location of the .py file

zip2pdf.py

import os

os.chdir(os.path.dirname(os.path.abspath(__file__)))

Get all zips in cd Here we use the glob module

zip2pdf.py

import glob

zips_ = glob.glob("./*.zip")

Get the file name (excluding extension) for each .zip Create a decompression directory under cd from the file name

zip2pdf.py

for zip_path_ in zips_:
    filename_ = os.path.split(zip_path_)[1].split(".")[0]
    unzip_dir_ = os.path.join(".", filename_)

Now that you have a decompression directory, unzip the zip Unzip the zip using the zipfile module as follows

import zipfile
zip_ = zipfile.ZipFile(zip_path_)
zip_.extractall(unzip_dir_)
zip_.close()

List only the unzipped zip files with the image extension (.png / .jpg / .jpeg)

    image_list_ = []
    for item_ in os.listdir(unzip_dir_):
        image_path_ = os.path.join(unzip_dir_, item_)
        if os.path.isfile(image_path_):
            fileext = os.path.splitext(image_path_)[-1].lower()
            if fileext in [".jpg ", ".jpeg ", ".png "]:
                image_list_.append(image_path_)
            else:
                continue
        else:
            continue

Create a pdf directory under cd and convert to pdf The simplest way to create a directory is to set exist_ok = True with the option of os.makedirs.

import img2pdf
os.makedirs("./pdf", exist_ok=True)
pdf_path_ = os.path.join(".", "pdf", "{}.pdf".format(filename_))

layout = img2pdf.get_layout_fun(params_.pagesize_)
with open(pdf_path_, 'wb') as f:
    f.write(img2pdf.convert(image_list_, layout_fun=layout))

Delete the directory used for decompression Delete the contents of the directory with rmtree of the shutil module

import shutil
shutil.rmtree(unzip_dir_)

Complete system

zip2pdf.py

import os
import glob
import zipfile
import img2pdf
import shutil

#cd Where this file is located
os.chdir(os.path.dirname(os.path.abspath(__file__)))

class params_:
    pagesize_ = (img2pdf.mm_to_pt(210), img2pdf.mm_to_pt(297))#A4size

def zip_to_pdf():
    #Get all cd zip
    zips_ = glob.glob("./*.zip")

    for zip_path_ in zips_:
        print(os.path.split(zip_path_)[1])

        #Get only the name of the zip
        filename_ = os.path.split(zip_path_)[1].split(".")[0]

        unzip_dir_ = os.path.join(".", filename_)

        #Create dir with the same name as zip on cd → unzip
        zip_ = zipfile.ZipFile(zip_path_)
        zip_.extractall(unzip_dir_)
        zip_.close()

        image_list_ = []
        #List the contents of the unzipped files(Image only)
        for item_ in os.listdir(unzip_dir_):
            image_path_ = os.path.join(unzip_dir_, item_)
            if os.path.isfile(image_path_):
                fileext = os.path.splitext(image_path_)[-1].lower()
                if fileext in [".jpg ", ".jpeg ", ".png "]:
                    image_list_.append(image_path_)
                else:
                    continue
            else:
                continue

        if len(image_list_) == 0:
            print("no image files")
            continue

        image_list_.sort()
        
        os.makedirs("./pdf", exist_ok=True)
        pdf_path_ = os.path.join(".", "pdf", "{}.pdf".format(filename_))

        layout = img2pdf.get_layout_fun(params_.pagesize_)
        with open(pdf_path_, 'wb') as f:
            f.write(img2pdf.convert(image_list_, layout_fun=layout))

        #Unzip destination dir deleted
        shutil.rmtree(unzip_dir_)

if __name__ == "__main__":
    zip_to_pdf()

Reference link

For the PDF conversion part, I referred to Collecting image files into PDF with Python.