SHOW:
|
|
- or go back to the newest paste.
| 1 | #!/usr/bin/env python3 | |
| 2 | ||
| 3 | # dedup.py | |
| 4 | # Removes duplicates from Bitwarden export .csv | |
| 5 | # 2019-02-09 5erif | |
| 6 | ||
| 7 | import sys | |
| 8 | import hashlib | |
| 9 | from urllib.parse import urlparse | |
| 10 | ||
| 11 | # Field ordinals in Bitwarden CSV | |
| 12 | FOLDER = 0 | |
| 13 | FAVORITE = 1 | |
| 14 | TYPE = 2 | |
| 15 | NAME = 3 | |
| 16 | NOTES = 4 | |
| 17 | FIELDS = 5 | |
| 18 | URI = 6 | |
| 19 | USERNAME = 7 | |
| 20 | PASSWORD = 8 | |
| 21 | TOTP = 9 | |
| 22 | ||
| 23 | def main(argv): | |
| 24 | ||
| 25 | if len(argv) < 1: | |
| 26 | print('Missing input file path')
| |
| 27 | sys.exit(1) | |
| 28 | ||
| 29 | in_file_path = argv[0] | |
| 30 | out_file_path = in_file_path[0:(len(in_file_path)-4)]+'_out.csv' | |
| 31 | rem_file_path = in_file_path[0:(len(in_file_path)-4)]+'_rem.csv' | |
| 32 | completed_lines_hash = set() | |
| 33 | line_number = -1 | |
| 34 | write_count = 0 | |
| 35 | cache = '' | |
| 36 | ||
| 37 | out_file = open(out_file_path, 'w', encoding = 'utf8') | |
| 38 | rem_file = open(rem_file_path, 'w', encoding = 'utf8') | |
| 39 | for line in open(in_file_path, 'r', encoding = 'utf8'): | |
| 40 | line_number += 1 | |
| 41 | fields = line.split(',')
| |
| 42 | if len(fields) < 10: | |
| 43 | # Add previous line if short | |
| 44 | line = cache.strip('\n') + line
| |
| 45 | cache = line | |
| 46 | fields = line.split(',')
| |
| 47 | if len(fields) > 9: | |
| 48 | print(f'Recovered with line {line_number}:\n{line}')
| |
| 49 | cache = '' | |
| 50 | else: | |
| 51 | print(f'Missing fields in line {line_number}:\n{line}')
| |
| 52 | rem_file.write(line) | |
| 53 | continue | |
| 54 | else: | |
| 55 | cache = '' | |
| 56 | if line_number != 0: | |
| 57 | domain = urlparse(fields[URI]).netloc | |
| 58 | if len(domain) > 0: | |
| 59 | fields[URI] = domain | |
| 60 | token = fields[URI] + fields[USERNAME] + fields[PASSWORD] | |
| 61 | hashValue = hashlib.md5(token.rstrip().encode('utf-8')).hexdigest()
| |
| 62 | if hashValue not in completed_lines_hash: | |
| 63 | out_file.write(line) | |
| 64 | completed_lines_hash.add(hashValue) | |
| 65 | write_count += 1 | |
| 66 | else: | |
| 67 | rem_file.write(line) | |
| 68 | # Uncomment for verbose mode | |
| 69 | # print(f'Skipping duplicate on line {line_number}:\n{line}')
| |
| 70 | out_file.close() | |
| 71 | rem_file.close() | |
| 72 | ||
| 73 | dup_count = line_number - write_count | |
| 74 | print(f'\nOutput file: {out_file_path}\n{write_count} unique entries saved')
| |
| 75 | print(f'\n{dup_count} duplicates saved to {rem_file_path}')
| |
| 76 | ||
| 77 | if __name__ == "__main__": | |
| 78 | main(sys.argv[1:]) |
