python-ciso8601.py

import datetime
import gzip
import csv
from glob import glob

import ciso8601

cutoff = datetime.datetime.utcnow().replace(
    tzinfo=datetime.timezone.utc
) - datetime.timedelta(days=6 * 30)


def count(fn):
    count = total = 0
    with gzip.open(fn, 'rt') as f:
        reader = csv.reader(f)
        for line in reader:
            lastmodified = ciso8601.parse_datetime(line[3])
            if lastmodified > cutoff:
                count += 1
            total += 1

    return total, count


def run():
    total = recent = 0
    # for fn in glob('*.csv.gz'):
    for i, fn in enumerate(glob('*.csv.gz')):
        if len(fn) == 39:
            print(i + 1, fn)
            t, c = count(fn)
            total += t
            recent += c

    print(total)
    print(recent)
    print('{:.1f}%'.format(100 * recent / total))


run()