Decrypt password-protected PDF in Python.

decrypt_pdf.py

# Decrypt password-protected PDF in Python.
# cleaned-up version of http://stackoverflow.com/a/26537710/329263
# 
# Requirements:
# pip install PyPDF2
#
# Usage: decrypt_pdf('encrypted.pdf', 'decrypted.pdf', 'secret_password')

from PyPDF2 import PdfFileReader, PdfFileWriter

def decrypt_pdf(input_path, output_path, password):
  with open(input_path, 'rb') as input_file, \
    open(output_path, 'wb') as output_file:
    reader = PdfFileReader(input_file)
    reader.decrypt(password)

    writer = PdfFileWriter()

    for i in range(reader.getNumPages()):
      writer.addPage(reader.getPage(i))

    writer.write(output_file)

if __name__ == '__main__':
  # example usage:
  decrypt_pdf('encrypted.pdf', 'decrypted.pdf', 'secret_password')

decryptpdfv3.py

#!/usr/bin/python3

# pylint: disable=missing-function-docstring

""" Convert PDF with password to a standard PDF
"""

import sys
import os.path
from PyPDF2 import PdfReader, PdfWriter


def usage():
    myfile = os.path.realpath(__file__)
    print(f"""{myfile} [-p|--pass XYZ] file1 [file2] [...]

Decrypts PDF inputs (file1, ...) using password XYZ,
and writes into file which is the name, with a suffix:
	_decrypt.pdf

Note that this is a simplification, the password should be stored somewhere safe!
""")
    return 0


def main():
    """ Process file(s).
    """
    do_script(sys.argv[1:])

def do_script(args):
    param = args
    a_pass = ""
    while param and param[0].startswith("-"):
        if param[0].startswith(("-h", "--help")):
            return usage()
        if param[0].startswith(("-p", "--pass")):
            a_pass = param[1]
            del param[:2]
            continue
        print("Bogus option:", param[0])
        return usage()
    run_script(
        param,
        (a_pass,),
    )
    return 0

def run_script(param, opt_tup):
    a_pass = opt_tup[0]
    for fname in param:
        base = os.path.splitext(fname)[0]
        if "decrypt" in base.lower():
            print("Skipped:", fname)
            continue
        outname = base + "_decrypt.pdf"
        print("Input:", base)
        n_pages = decrypt_pdf(fname, outname, a_pass)
        if a_pass:
            print(f"Decrypted to: {outname}, {n_pages} page(s)")
    return 0


def decrypt_pdf(input_path, output_path, password=""):
    """ Reads PDF that may have a password,
    writes another PDF without password (decrypted),
    and returns the number of pages processed.
    """
    assert isinstance(password, str), "Password is a string"
    idx = -1
    with open(input_path, 'rb') as input_file:
        reader = PdfReader(input_file)
        if password:
            reader.decrypt(password)
        writer = PdfWriter()
        for idx, a_page in enumerate(reader.pages):
            writer.add_page(a_page)
        if password:
            with open(output_path, 'wb') as fdout:
                #print("# Overwritten:", output_path)
                writer.write(fdout)
        return idx + 1
    return idx


if __name__ == "__main__":
    main()

requirements.txt

PyPDF2>=3.1.0