add_est_column.py

#!/usr/bin/env python
import sys
import csv
from datetime import datetime
from dateutil import tz


def get_est(date):
    from_zone = tz.gettz('UTC')
    to_zone = tz.gettz('EST')

    utc = datetime.strptime(date, '%Y%m%d_%H%M%S')
    # Tell the datetime object that it's in UTC time zone since 
    # datetime objects are 'naive' by default
    utc = utc.replace(tzinfo=from_zone)
    est = utc.astimezone(to_zone)
    est_date = est.strftime('%Y%m%d_%H%M%S')
    return est_date


if __name__ == '__main__':
    input_file = csv.DictReader(open(sys.argv[-1]))
    output_file = '{}-est.csv'.format(sys.argv[-1].split('/')[-1].replace('.csv', ''))

    with open(output_file, 'wb') as fp:
        # IA_Philly_Media_Watch_IDENTIFIED_ADS_v1.0.csv
        #fields = [
        #    'ad identifier (state, year, race, sponsor, candidate, seconds pro, seconds con)',
        #    'url',
        #    'candidate',
        #    'sponsor',
        #    'network',
        #    'date_time (UTC)',
        #    'date_time (EST)',
        #    'seconds\r\ninto program',
        #    'identifier',
        #]

        # IA_Philly_Media_Watch_PROGRAMS_v1.0.csv
        fields = [
            '# ads /\r\nprogram',
            'program title',
            'network',
            'date_time (UTC)',
            'date_time (EST)',
            'program identifier',
            'length of program\r\n/seconds',
            'length of program\r\n/minutes',
        ]

        w = csv.DictWriter(fp, fields)
        w.writeheader()

        for row in input_file:
            try:
                est = get_est(row['date_time (UTC)'])
            except:
                est = None
            row['date_time (EST)'] = est
            w.writerow(row)