This code is an example of how a PDF hash can be calculated while ignoring the '/ID' identifier in the trailer of the file. This '/ID' part is modified each time the file is saved even if the contents have not been modified. This leads to files with identical contents generating different hashes. The python script opens a given PDF file in binar…

pdf_hasher.py

# run using python pdf_hasher.py <pdf_file_path.pdf>
# add -v argument to print the portions of the file which
# are excluded in hash calculation. 

import hashlib
import argparse
import sys

def hash_file_exclude_id(file_path, verbose=False):
    """Hashes a file excluding the /ID entry in the PDF trailer and optionally prints excluded parts."""
    hasher = hashlib.sha256()
    with open(file_path, 'rb') as file:
        content = file.read()
        
    content_str = content.decode('latin-1', errors='ignore')
    trailer_start_index = content_str.rfind('trailer')
    id_start_index = content_str.find('/ID', trailer_start_index)
    eof_index = content_str.find(']', id_start_index) + 1
    
    if id_start_index != -1 and eof_index != -1:
        content_before_id = content[:id_start_index]
        content_after_id = content[eof_index:]
        
        if verbose:
            excluded_content = content[id_start_index:eof_index]
            print(f"Excluded from hash in '{file_path}':")
            print(excluded_content.decode('latin-1', errors='ignore'))
            
        hasher.update(content_before_id)
        hasher.update(content_after_id)
    else:
        hasher.update(content)
        if verbose:
            print(f"No /ID found to exclude in '{file_path}'. Hashing entire file.")
    
    return hasher.hexdigest()

def main():
    parser = argparse.ArgumentParser(description="Hash a PDF file excluding its /ID entry.")
    parser.add_argument("file_path", help="Path to the PDF file to be hashed.")
    parser.add_argument("-v", "--verbose", action="store_true", help="Print the parts of the file that were excluded from the hash.")
    args = parser.parse_args()

    hash_value = hash_file_exclude_id(args.file_path, verbose=args.verbose)
    print(f"{hash_value}  {args.file_path}")

if __name__ == "__main__":
    main()