Email Segmentation - Python Script .py

#!/usr/bin/env python3

import csv
import sys
import re

#######################
## Configurations    ##
#######################

# Source Csv File
source = 'source.csv'

# Segmented Email List
destination = 'processed.csv'

# Unsegmented Email List 
unidentified = 'unprocessed.csv'

# Coulumns taken for the segmented list, the column name should match the columns in the source csv
fieldnames = ['Name', 'Email', 'Category']

# Categories to search for
categories = {'flower', 'doctor', 'dr.', 'clinic', 'pharmacy', 'hospital', 'hotel', 'spa', 'saloon', 'gym', 'trading', 'account', 'lawyer', 'laser'}

# each of the categories specified in the `categories` will be matched against this column
columnToMatch = 'FirstName'

# this column will be taken as the email id
emailColumn   = 'Email'
#######################
## End Configuration ##
#######################


with open(source,'r') as csvSource, open(destination,'w') as csvDest, open(unidentified,'w') as csvUnprocessed:
    reader = csv.DictReader(csvSource)
    writer = csv.DictWriter(csvDest, fieldnames=fieldnames)
    unprocessed = csv.DictWriter(csvUnprocessed, fieldnames=reader.fieldnames)
    writer.writeheader()
    unprocessed.writeheader()

    print("Script Started")

    for row in reader:
        found = False

        for c in categories:
            if re.search(c,  row[columnToMatch], flags=re.IGNORECASE):
                writer.writerow({'Name': row[columnToMatch], 'Email': row[emailColumn], 'Category': c})
                found = True
                break

        if not found:
            unprocessed.writerow(row)
            found = False

print("\nSegmentation completed\n")
print("\n -- Segmented Emails - ", destination)
print("\n -- Unprocessed Emails - ", unidentified)