Dehashed-API Cleanup

This file takes a dehashed-API output file and cleans it up to have an output of username:password in a case-insensitive, de-duped list:

import os
import datetime

# Prompt user for input file
input_file = input("Enter the name of the input file (e.g., companycreds.txt): ").strip()

# Check if the file exists
if not os.path.isfile(input_file):
    print(f"Error: File '{input_file}' not found.")
    exit()

# Generate a timestamped output file name
timestamp = datetime.datetime.now().strftime('%Y-%m-%d-%H%M')
base_name, ext = os.path.splitext(input_file)
output_file = f"{base_name}_{timestamp}-clean{ext}"

# Read the file and process lines
with open(input_file, 'r') as file:
    lines = file.readlines()

# Extract email and password, and store in a dictionary to handle deduplication
entries = {}
for line in lines:
    parts = line.split(',')
    email_part = parts[0].split('email:')[-1].strip()
    password_part = parts[1].split('password:')[-1].strip()
    entries[email_part] = password_part

# Sort the dictionary by email (case-insensitive)
sorted_entries = sorted(entries.items(), key=lambda x: x[0].lower())

# Write the sorted entries to the output file
with open(output_file, 'w') as file:
    for email, password in sorted_entries:
        file.write(f'{email}:{password}\n')

print(f"Processed entries saved to {output_file}.")