split a multi-page pdf file into multiple pdf files with python?

from PyPDF2 import PdfWriter, PdfReader

inputpdf = PdfReader(open("document.pdf", "rb"))

for i in range(len(inputpdf.pages)):
    output = PdfWriter()
    output.add_page(inputpdf.pages[i])
    with open("document-page%s.pdf" % i, "wb") as outputStream:
        output.write(outputStream)

etc.

I missed here a solution where you split the PDF to two parts consisting of all pages so I append my solution if somebody was looking for the same:

from PyPDF2 import PdfFileWriter, PdfFileReader

def split_pdf_to_two(filename,page_number):
    pdf_reader = PdfFileReader(open(filename, "rb"))
    try:
        assert page_number < pdf_reader.numPages
        pdf_writer1 = PdfFileWriter()
        pdf_writer2 = PdfFileWriter()

        for page in range(page_number):
            pdf_writer1.addPage(pdf_reader.getPage(page))

        for page in range(page_number,pdf_reader.getNumPages()):
            pdf_writer2.addPage(pdf_reader.getPage(page))

        with open("part1.pdf", 'wb') as file1:
            pdf_writer1.write(file1)

        with open("part2.pdf", 'wb') as file2:
            pdf_writer2.write(file2)

    except AssertionError as e:
        print("Error: The PDF you are cutting has less pages than you want to cut!")

I know that the code is not related to python, however i felt like posting this piece of R code which is simple, flexible and works amazingly. The PDFtools package in R is amazing in splitting merging PDFs at ease.

library(pdftools) #Rpackage
pdf_subset('D:\file\20.02.20\22 GT 2017.pdf',
           pages = 1:51, output = "subset.pdf")

The PyPDF2 package gives you the ability to split up a single PDF into multiple ones.

import os
from PyPDF2 import PdfFileReader, PdfFileWriter

pdf = PdfFileReader(path)
for page in range(pdf.getNumPages()):
    pdf_writer = PdfFileWriter()
    pdf_writer.addPage(pdf.getPage(page))

    output_filename = '{}_page_{}.pdf'.format(fname, page+1)

    with open(output_filename, 'wb') as out:
        pdf_writer.write(out)

    print('Created: {}'.format(output_filename))

Source: https://www.blog.pythonlibrary.org/2018/04/11/splitting-and-merging-pdfs-with-python/

import fitz

src = fitz.open("source.pdf")
for page in src:
    tar = fitz.open()  # output PDF for 1 page
    # copy over current page
    tar.insert_pdf(src, from_page=page.number, to_page=page.number)
    tar.save(f"page-{page.number}.pdf")
    tar.close()

The earlier answers with PyPDF2 for splitting pdfs are not working anymore with the latest version update. The authors recommend using pypdf instead and this version of PyPDF2==3.0.1 will be the last version of PyPDF2. The function needs to be modified as follows:

import os
from PyPDF2 import PdfReader, PdfWriter

def split_pdfs(input_file_path):
    inputpdf = PdfReader(open(input_file_path, "rb"))

    out_paths = []
    if not os.path.exists("outputs"):
        os.makedirs("outputs")

    for i, page in enumerate(inputpdf.pages):
        output = PdfWriter()
        output.add_page(page)

        out_file_path = f"outputs/{input_file_path[:-4]}_{i}.pdf"
        with open(out_file_path, "wb") as output_stream:
            output.write(output_stream)

        out_paths.append(out_file_path)
    return out_paths

Note: The same function will work with pypdf as well. Import PdfReader and PdfWriter from pypdf rather than PyPDF2.

from PyPDF2 import PdfFileReader, PdfFileWriter
import os
import sys
import glob
abspath = os.path.abspath(__file__)
dname = os.path.dirname(abspath)
os.chdir(dname)

if getattr(sys, 'frozen', False):
    _location_ = os.path.dirname(os.path.realpath(sys.executable))
elif __file__:
    _location_ = os.path.realpath(
    os.path.join(os.getcwd(), os.path.dirname(__file__)))

for file in glob.glob(__location__ + "/*.pdf"):
    if file.endswith('.pdf'):
        pdf_file = open(os.path.join(__location__, file), 'rb')
        pdf_reader = PdfFileReader(pdf_file)
        
pageNumbers = pdf_reader.getNumPages()

for i in range (pageNumbers):
    pdf_writer = PdfFileWriter()
    pdf_writer.addPage(pdf_reader.getPage(i))
    split_motive = open('Page ' + str(i+1) + '.pdf', 'wb')
    pdf_writer.write(split_motive)
    split_motive.close()

pdf_file.close()

Link to article

This is will work perfectly. Need Microsoft Visual Studio C++ 14.0 or greater.

import fitz

# specify the path of the PDF file
pdf_path = "2021.pdf"

# open the PDF
try:
    pdf = fitz.open(pdf_path)
except FileNotFoundError:
    print("File not found")

# iterate over the pages starting from the 6th page
for i, page in enumerate(pdf[6:], start=6):
    try:
        # render the page as a JPEG image
        pix = page.get_pixmap(alpha=False)
        # save the image
        pix.writeJPG(f"page_{i+1}.jpg")
    except Exception as e:
        print(e)

# close the PDF
print("Successful")
pdf.close()