email-csv-extractor

import glob
import pandas as pd
import re

#This function searches for csv and extracts the 'to' column. Added support for case insensitive columns.
def import_emails():
    emails = []
    for name in glob.glob("./*.csv"):
        df = pd.read_csv(name)
        # Normalize the column names to lowercase
        df.columns = df.columns.str.lower()
        # Check if 'to' column exists, to avoid KeyError
        if 'to' in df.columns:
            emails.extend(df['to'].dropna().tolist())
    return emails

#Searches columns for email using regex.
def find_matches():
    pattern = ("([a-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[a-z0-9!#$%&'*+/=?^_`{|}~-]+)*@(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?)")
    emails = import_emails()
    matches = [re.search(pattern, email).group(0) for email in emails if re.search(pattern, email) is not None]
    return list(set(matches))  # removes duplicates

#Outputs the matches to a text file.
def write_output():
    matches = find_matches()
    txtlist = ';'.join(matches)
    with open("email-list.txt", "w") as filew:
        filew.write(txtlist)

write_output()