Merge all pdf files that are present in a dir

Put the pdf files in a dir. Launch the program. You get one pdf with all the pdfs merged.

import os
from PyPDF2 import PdfFileMerger

x = [a for a in os.listdir() if a.endswith(".pdf")]

merger = PdfFileMerger()

for pdf in x:
    merger.append(open(pdf, 'rb'))

with open("result.pdf", "wb") as fout:
    merger.write(fout)

How would I make the same code above today

from glob import glob
from PyPDF2 import PdfFileMerger



def pdf_merge():
    ''' Merges all the pdf files in current directory '''
    merger = PdfFileMerger()
    allpdfs = [a for a in glob("*.pdf")]
    [merger.append(pdf) for pdf in allpdfs]
    with open("Merged_pdfs.pdf", "wb") as new_file:
        merger.write(new_file)


if __name__ == "__main__":
    pdf_merge()

from PyPDF2 import PdfFileMerger
import webbrowser
import os
dir_path = os.path.dirname(os.path.realpath(__file__))

def list_files(directory, extension):
    return (f for f in os.listdir(directory) if f.endswith('.' + extension))

pdfs = list_files(dir_path, "pdf")

merger = PdfFileMerger()

for pdf in pdfs:
    merger.append(open(pdf, 'rb'))

with open('result.pdf', 'wb') as fout:
    merger.write(fout)

webbrowser.open_new('file://'+ dir_path + '/result.pdf')

Git Repo: https://github.com/mahaguru24/Python_Merge_PDF.git

You can use pikepdf too (source code documentation).

Example code could be (taken from the documentation):

from glob import glob

from pikepdf import Pdf

pdf = Pdf.new()

for file in glob('*.pdf'):  # you can change this to browse directories recursively
    with Pdf.open(file) as src:
        pdf.pages.extend(src.pages)

pdf.save('merged.pdf')
pdf.close()

If you want to exclude pages, you might proceed another way, for instance copying pages to a new pdf (you can select which ones you do not copy, then, the pdf.pages object behaving like a list).

It is still actively maintained, which, as of february 2022, does not seem to be the case of PyPDF2 nor pdfrw.

I haven't benchmarked it, so I don't know if it is quicker or slower than other solutions.

One advantage over PyMuPDF, in my case, is that an official Ubuntu package is available (python3-pikepdf), what is practical to package my own software depending on it.

A slight variation using a dictionary for greater flexibility (e.g. sort, dedup):

import os
from PyPDF2 import PdfFileMerger
# use dict to sort by filepath or filename
file_dict = {}
for subdir, dirs, files in os.walk("<dir>"):
    for file in files:
        filepath = subdir + os.sep + file
        # you can have multiple endswith
        if filepath.endswith((".pdf", ".PDF")):
            file_dict[file] = filepath
# use strict = False to ignore PdfReadError: Illegal character error
merger = PdfFileMerger(strict=False)

for k, v in file_dict.items():
    print(k, v)
    merger.append(v)

merger.write("combined_result.pdf")

You can use PdfFileMerger from the PyPDF2 module.

For example, to merge multiple PDF files from a list of paths you can use the following function:

from PyPDF2 import PdfFileMerger

# pass the path of the output final file.pdf and the list of paths
def merge_pdf(out_path: str, extracted_files: list [str]):
    merger   = PdfFileMerger()
    
    for pdf in extracted_files:
        merger.append(pdf)

    merger.write(out_path)
    merger.close()

merge_pdf('./final.pdf', extracted_files)

And this function to get all the files recursively from a parent folder:

import os

# pass the path of the parent_folder
def fetch_all_files(parent_folder: str):
    target_files = []
    for path, subdirs, files in os.walk(parent_folder):
        for name in files:
            target_files.append(os.path.join(path, name))
    return target_files 

# get a list of all the paths of the pdf
extracted_files = fetch_all_files('./parent_folder')

Finally, you use the two functions declaring.a parent_folder_path that can contain multiple documents, and an output_pdf_path for the destination of the merged PDF:

# get a list of all the paths of the pdf
parent_folder_path = './parent_folder'
outup_pdf_path     = './final.pdf'

extracted_files = fetch_all_files(parent_folder_path)
merge_pdf(outup_pdf_path, extracted_files)

You can get the full code from here (Source): How to merge PDF documents using Python

I used pdf unite on the linux terminal by leveraging subprocess (assumes one.pdf and two.pdf exist on the directory) and the aim is to merge them to three.pdf

 import subprocess
 subprocess.call(['pdfunite one.pdf two.pdf three.pdf'],shell=True)

The answer from Giovanni G. PY in an easily usable way (at least for me):

import os
from PyPDF2 import PdfFileMerger

def merge_pdfs(export_dir, input_dir, folder):
    current_dir = os.path.join(input_dir, folder)
    pdfs = os.listdir(current_dir)
    
    merger = PdfFileMerger()
    for pdf in pdfs:
        merger.append(open(os.path.join(current_dir, pdf), 'rb'))

    with open(os.path.join(export_dir, folder + ".pdf"), "wb") as fout:
        merger.write(fout)

export_dir = r"E:\Output"
input_dir = r"E:\Input"
folders = os.listdir(input_dir)
[merge_pdfs(export_dir, input_dir, folder) for folder in folders];

Here's a time comparison for the most common answers for my specific use case: combining a list of 5 large single-page pdf files. I ran each test twice.

(Disclaimer: I ran this function within Flask, your mileage may vary)

TL;DR

pdfrw is the fastest library for combining pdfs out of the 3 I tested.

PyPDF2

start = time.time()
merger = PdfFileMerger()
for pdf in all_pdf_obj:
    merger.append(
        os.path.join(
            os.getcwd(), pdf.filename # full path
                )
            )
formatted_name = f'Summary_Invoice_{date.today()}.pdf'
merge_file = os.path.join(os.getcwd(), formatted_name)
merger.write(merge_file)
merger.close()
end = time.time()
print(end - start) #1 66.50084733963013 #2 68.2995400428772

PyMuPDF

start = time.time()
result = fitz.open()

for pdf in all_pdf_obj:
    with fitz.open(os.path.join(os.getcwd(), pdf.filename)) as mfile:
        result.insertPDF(mfile)
formatted_name = f'Summary_Invoice_{date.today()}.pdf'

result.save(formatted_name)
end = time.time()
print(end - start) #1 2.7166640758514404 #2 1.694727897644043

pdfrw

start = time.time()
result = fitz.open()

writer = PdfWriter()
for pdf in all_pdf_obj:
    writer.addpages(PdfReader(os.path.join(os.getcwd(), pdf.filename)).pages)

formatted_name = f'Summary_Invoice_{date.today()}.pdf'
writer.write(formatted_name)
end = time.time()
print(end - start) #1 0.6040127277374268 #2 0.9576816558837891

def pdf_merger(path): """Merge the pdfs into one pdf"""

import logging
logging.basicConfig(filename = 'output.log', level = logging.DEBUG, format = '%(asctime)s %(levelname)s %(message)s' )

try:
    import glob, os
    import PyPDF2
    
    os.chdir(path)
    
    pdfs = []
    
    for file in glob.glob("*.pdf"):
        pdfs.append(file)
        
    if len(pdfs) == 0:
        logging.info("No pdf in the given directory")
        
    else:
        merger = PyPDF2.PdfFileMerger()
        
        for pdf in pdfs:
            merger.append(pdf)
            
        merger.write('result.pdf')
        merger.close()
        
except Exception as e:
    logging.error('Error has happened')
    logging.exception('Exception occured' + str(e))