Decodes and re-encodes PDBs to UTF-8

decode_pdb.py

from glob import glob

def decode_encode_pdb(input_file, output_file):
    with open(input_file, 'r', encoding='utf-8') as file:
        lines = file.readlines()
    
    decoded_lines = [line.encode('utf-8').decode('utf-8', 'replace') for line in lines]

    with open(output_file, 'w', encoding='utf-8') as file:
        file.writelines(decoded_lines)

    print(f"Decoding and encoding complete. New PDB file saved as {output_file}")

if __name__ == "__main__":
    pdbs = glob("*.pdb")
    
    for pdb in pdbs:
        decode_encode_pdb(pdb, pdb.split(".")[0] + "_utf.pdb")