Decompress FlateDecode Objects in PDF

pdf_flatedecode.py

#!/usr/bin/env python3

import re
import sys
import zlib

def main(filename:str):
    """This script will find each FlateDecode stream in the given PDF document using a regular expression, unzip it, and print out the unzipped data."""

    with open(filename, 'rb') as pdf_file:
        pdf_stream = re.compile(rb'.*?FlateDecode.*?stream(.*?)endstream', re.S)

        for s in pdf_stream.findall(pdf_file.read()):
            s = s.strip(b'\r\n')
            try:
                print(zlib.decompress(s))
                print('-'*64)
            except:
                print('Error: Could not decompress pdf stream using zlib:', s, file=sys.stderr)

if __name__ == '__main__':
    if len(sys.argv) != 2:
        print('Provide the filename of the pdf as commandline argument.', file=sys.stderr)
        exit(1)

    main(filename=sys.argv[1])