Example: Extract emails from a text file

gistfile1.txt

import re
from validate_email import validate_email
from collections import OrderedDict
from fuzzywuzzy import fuzz

# Open the input file in read mode
with open("input.txt", "r") as input_file:
    # Read the contents of the file
    data = input_file.read()

# Use a regular expression to find emails in the text
email_regex = r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b'
emails = re.findall(email_regex, data)

# Create an ordered dictionary to store the emails
email_dict = OrderedDict()

# Iterate through the emails
for email in emails:
    # Check if the email is valid
    if validate_email(email):
        # Iterate through the keys in the dictionary
        for key in email_dict.keys():
            # Check if the email is similar to a key in the dictionary
            if fuzz.token_set_ratio(email, key) > 90:
                # If it is, don't add it to the dictionary
                break
        else:
            # If it isn't similar to any key, add it to the dictionary
            email_dict[email] = None

# Open the output file in write mode
with open("output.txt", "w") as output_file:
    # Write the emails to the output file
    for email in email_dict.keys():
        output_file.write(email + "\n")