Parses and reorganise exported credentials from Bitwarden

Bitwarden Export Parser

 ## Bitwarden Export Parser
 
 Parses and reorganise exported credentials from Bitwarden
 

cred_parser.py

import csv
import typing as t

import tldextract

from collections import OrderedDict
from urllib.parse import urlparse


T_data = t.OrderedDict[str, str]
T_htable = t.Dict[str, t.Union[t.List[T_data], T_data]]


def main(in_csv_path: str, out_csv_path: str, duplicate_csv_path: str):
    htable: T_htable = OrderedDict()
    dup_htable = []
    invalid_bucket = []
    notes_bucket = []
    with open(in_csv_path) as f_in:
        in_csv = csv.DictReader(f_in)
        field_names = in_csv.fieldnames
        for r in in_csv:
            if r['type'] == 'note':
                notes_bucket.append(r)
                continue

            try:
                key, data = parse_row(r)
            except IndexError:
                invalid_bucket.append(r)

            # Check duplicates & multi-values
            if key in htable and handle_duplicate(htable, key, data):
                dup_htable.append(data)
            else:
                htable[key] = data

    write_csv(out_csv_path, [*htable.values(), *notes_bucket], field_names)
    write_csv(duplicate_csv_path, dup_htable, field_names)


def write_csv(file_name: str, rows, field_names: t.Sequence[str]):
    with open(file_name, 'w') as f:
        out_csv = csv.DictWriter(f, field_names)
        out_csv.writeheader()
        out_csv.writerows(rows)


def parse_row(data: T_data) -> t.Tuple[str, T_data]:
    if data['login_uri'].startswith('http://android://'):
        key = data['login_uri'].split('==@')[-1].rstrip('/').split('.')
        key_len = len(key)
        if key_len == 2:
            key = key[1]
        elif key_len == 3:
            key = ' '.join(key[1:])
        else:
            key = ' '.join(key[1:4])
    else:
        key = tldextract.extract(data['login_uri']).domain
        # key = urlparse(data['login_uri']).netloc.split('.')[-2]
    data['name'] = key.title()
    data['type'] = data['type'] or 'login'
    data['favorite'] = ''
    return key.title(), data


def handle_duplicate(htable: T_htable, key: str,
                     data: T_data, check_values=None) -> bool:
    """Returns true if duplicate value"""
    def do_compare(old, new):
        old_loc = urlparse(old['login_uri']).netloc
        new_loc = urlparse(new['login_uri']).netloc
        if old_loc == new_loc:
            return True
        return all([old[k] == new[k] for k in check_values])

    check_values = check_values or ['type', 'notes', 'fields',
                                    'login_username', 'login_password',
                                    'folder']

    _t = type(htable[key]).__name__
    if _t == 'list':
        for d in htable[key]:
            if do_compare(d, data):
                return True
            htable[key].append(data)
            return False

    if _t in ('OrderedDict', 'dict'):
        if do_compare(htable[key], data):
            return True
        htable[key] = [htable[key], data]
        return False

    raise ValueError(f"Unexpected type found: {_t}\nData: {htable[key]}")


if __name__ == '__main__':
    in_csv_path = "./bitwarden_export_20210704104034.csv"
    out_csv_path = "./bitwarden_export_20210704104034_processed.csv"
    duplicate_csv_path = "./bitwarden_export_20210704104034_duplicates.csv"
    main(in_csv_path, out_csv_path, duplicate_csv_path)

requirements.txt

tldextract