split a multi-page pdf file into multiple pdf files with python?
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/
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!")
from PyPDF2 import PdfFileWriter, PdfFileReader
inputpdf = PdfFileReader(open("document.pdf", "rb"))
for i in range(inputpdf.numPages):
output = PdfFileWriter()
output.addPage(inputpdf.getPage(i))
with open("document-page%s.pdf" % i, "wb") as outputStream:
output.write(outputStream)
etc.