Python で正規表現を用いて日付表現を抽出する

extract_date.py

#!/usr/bin/env python
import re

def extract_date(s):
    date_pattern = re.compile('(\d{4})/(\d{1,2})/(\d{1,2})')
    result = date_pattern.search(s)
    if result:
        y, m, d = result.groups()
        return {'year': y, 'month': m, 'day': d}
    else:
        return None


if __name__ == '__main__':
    import sys

    filename = sys.argv[1]
    f = open(filename)
    text = f.read()
    f.close()

    for line in text.splitlines():
        result = extract_date(line)
        if result:
            print result
            print line