This python script compares files in two directories on their md5 hash. lists the files which have same md5, and the ones which don't. I use this to verify my file backups. The directory structures are different hence a direct folder comparison with tools like beyond compare (compare on contents) wont work.

DirectoryCompareConsole.py

# This is a Python script.
#This python script compares files in two directories
# on their md5 hash. lists the files which have same md5,
# and the ones which don't. I use this to verify my file backups.
# The directory structures are different hence a direct folder
# comparison with tools like beyond compare (compare on contents) wont work.

import glob
import os
import hashlib
from datetime import datetime

dir1Path = "D:/"
dir2Path = "E:/LighroomLibrary"

# Press the green button in the gutter to run the script.
def ProcessPath(dirPath):
    cwd = os.getcwd()
    os.chdir(dirPath)
    fileHashMap = {}
    fileList = glob.glob("**", recursive=True)
    for file in fileList:
        if os.path.isfile(file):
            fhandle = open(file, 'rb')
            md5hash = hashlib.md5(fhandle.read()).hexdigest()
            fhandle.close()
            if md5hash in fileHashMap.keys():
                #print("duplicate", fileHashMap[md5hash], file)
                fileHashMap[md5hash].append(file)
            else:
                fileHashMap[md5hash] = [file]
    #print(fileHashMap)
    os.chdir(cwd)
    return fileHashMap

startTime = datetime.now()
print("startTime", startTime)
dir1hashMap = ProcessPath(dir1Path)
print("path1 processed", datetime.now() - startTime)
dir2hashMap = ProcessPath(dir2Path)
print("path2 processed", datetime.now() - startTime)

sameFiles = {}
dir1ExtraFiles = {}
dir2ExtraFiles = {}

for key in dir1hashMap:
    if key in dir2hashMap.keys():
        sameFiles[key] = [] + dir1hashMap[key] + dir2hashMap[key]
    else:
        dir1ExtraFiles[key] = dir1hashMap[key]

for key in dir2hashMap:
    if key in dir1hashMap.keys():
        pass
    else:
        dir2ExtraFiles[key] = dir2hashMap[key]

print("same files")

for key in sameFiles:
    print(key, sameFiles[key])

print("Dir1 extra files")

for key in dir1ExtraFiles:
    print(key, dir1ExtraFiles[key])

print("Dir2 extra files")

for key in dir2ExtraFiles:
    print(key, dir2ExtraFiles[key])

print("runTime", datetime.now() - startTime)
# See PyCharm help at https://www.jetbrains.com/help/pycharm/