Twitter dump duplicate joiner

twoiynk.py

import os
import re

# Directory path where the txt files are stored
folder_path = '.'

# Adjusted regular expressions to match the given line format
email_pattern = re.compile(r'Email: ([\w\.-]+@[\w\.-]+)')
screen_name_pattern = re.compile(r'ScreenName: (\S+)')

# Dictionary to store email addresses, their counts, and associated unique screen names
email_dict = {}

# Loop through each file in the directory
for filename in os.listdir(folder_path):
    if filename.endswith('.txt'):
        with open(os.path.join(folder_path, filename), 'r') as file:
            for line_number, line in enumerate(file, 1):  # Iterating over the file line by line
                email_matches = email_pattern.findall(line)
                screen_name_matches = screen_name_pattern.findall(line)

                # Assuming one email and one screen name per line
                if email_matches and screen_name_matches:
                    email = email_matches[0]
                    screen_name = screen_name_matches[0]

                    if email in email_dict:
                        email_dict[email]['screen_names'].add(screen_name)  # Using a set to prevent duplicates
                    else:
                        email_dict[email] = {'screen_names': {screen_name}}

# Write the summary to output.txt
with open('output.txt', 'w') as outfile:
    found_duplicates = False

    for email, data in email_dict.items():
        # Checking if there are multiple unique screen names for the email
        if len(data['screen_names']) > 1:
            found_duplicates = True
            outfile.write(f"Email: {email} has accounts with the following unique screen names:\n")
            for screen_name in data['screen_names']:
                outfile.write(f"- {screen_name}\n")
            outfile.write("\n")
    
    if not found_duplicates:
        outfile.write("No email addresses with multiple unique screen names found.\n")

print("Summary written to output.txt")