compare_two_files.py

import hashlib # works for all type of data


# check if files are different
def compare_files(f1, f2):

    with open(f1, 'rb') as t1, open(f2, 'rb') as t2:

        fileA_hash = hashlib.sha256(t1.read()).digest()
        fileB_hash = hashlib.sha256(t2.read()).digest()
        if fileA_hash == fileB_hash:
            print("Files are the same: no new data")
            return True
        else:
            print("Files are not the same: new data to process")
            return False
            
            """with open(f1, 'r') as t1, open(f2, 'r') as t2: # open again to read data not binary
                fileA = t1.readlines()
                fileB = t2.readlines()

            with open(out_path+'update.csv', 'w') as outFile:
                
                for line in fileB:
                    if line not in fileA:
                        print("different line detected")
                        outFile.write(line)"""