1def findDup(parentFolder):
2 # Dups in format {hash:[names]}
3 dups = {}
4 for dirName, subdirs, fileList in os.walk(parentFolder):
5 print('Scanning %s...' % dirName)
6 for filename in fileList:
7 # Get the path to the file
8 path = os.path.join(dirName, filename)
9 # Calculate hash
10 file_hash = hashfile(path)
11 # Add or append the file path
12 if file_hash in dups:
13 dups[file_hash].append(path)
14 else:
15 dups[file_hash] = [path]
16 return dups
17