duplicate_files_stage3

import sys
import os
import pathlib
import hashlib


class DuplicateFileHandler:

    def __init__(self):
        self.file_dict = {}
        self._format = ''
        self.option = ''
        self.sorted_file_dict = {}

    def get_dict(self):
        if len(sys.argv) < 2:
            print('Directory is not specified')
            sys.exit()
        else:
            # print(sys.argv)
            for (root, dirs, files) in os.walk(sys.argv[1], topdown=True):
                # print(root,dirs, files)
                for name in files:
                    # path = os.path.abspath(os.path.join(root, name))
                    path = os.path.join(root, name)
                    size = os.path.getsize(path)
                    with open(path, 'rb') as f:
                        # print(path)
                        _bytes = f.read()
                        _hash = hashlib.md5(_bytes).hexdigest()
                        # print(_hash)
                    try:
                        temp = self.file_dict[size][_hash]
                    except:
                        self.file_dict.update({size: {_hash: [path]}})
                    else:
                        temp.append(path)
                        self.file_dict.update({size: {_hash: temp}})
                # _dict.update({size: {_hash: []}})
                # _dict.setdefault(size[_hash], []).append(path)
                # _dict[size][_hash].append(path)
                # print('name', name)

    def sort_dict(self, _reverse=True):
        for i in sorted(self.file_dict, reverse=_reverse):
            for j in self.file_dict[i]:
                for z in self.file_dict[i][j]:
                    if len(self.file_dict[i][j]) > 1:
                        # self.sorted_file_dict[i][j] = z
                        if pathlib.Path(z).suffix[1:] == self._format or self._format == '':
                            self.sorted_file_dict[i] = self.file_dict[i]
                            # print(i, 'bytes')
                            # for x in _dict[i]:
                            # print(x)
                            print(f'{i} bytes', *self.file_dict[i][j], sep='\n', end='\n\n')
                            break
        self.check_dup()

    def check_dup(self='Descending'):
        while True:
            print('Check for duplicates?')
            dup_choice = input()
            if dup_choice == 'yes':
                print()
                n = 0
                for x in self.sorted_file_dict:  # need to sort here
                    for y in self.sorted_file_dict[x]:
                        if len(self.sorted_file_dict[x][y]) > 1:
                            print(f'{x} bytes', f'Hash: {y}', sep='\n')
                            for _z in self.sorted_file_dict[x][y]:
                                n += 1
                                # print(y, z)
                                print(f'{n}.', _z)

                    print('\n')
                break

            elif dup_choice == 'no':
                break
            else:
                print('Wrong option\n')

    def operate(self):
        self.get_dict()
        # print(self.file_dict)
        self._format = input('Enter file format:')
        print('''
Size sorting options:
1. Descending
2. Ascending
                    ''')
        while True:
            print('Enter a sorting option:')
            self.option = input()
            if self.option in ['1', '2']:
                print()
                self.option = int(self.option)
                if self.option == 1:
                    self.sort_dict()
                elif self.option == 2:
                    self.sort_dict(_reverse=False)
                break
            else:
                print('Wrong option\n')


handler = DuplicateFileHandler()
handler.operate()