readme_to_excel.py

from openpyxl import Workbook
import os

COLUMNS = [
    'Name', 'Data Lead', 'Description', 'Date Obtained', 'Time Period of Content Date', 'Publication Date', 
    'URL', 'Contact', 'Processing Notes', 'Keywords', 'Relative Path', 'Absolute Path'
]


def parse_readme(f):
    values = {}
    key = None
    value = []

    for line in f:
        line = line.decode('Windows-1252')
        if line.strip().startswith('##'):
            if key:
                values[key] = '\n'.join(value)
        
            key = line.strip(' #\r\n').lower()
            value = []
            continue

        value.append(line.strip())

    if key:
        values[key] = '\n'.join(value)

    return values


def main():
    workbook = Workbook()
    sheet = workbook.active

    sheet.append(COLUMNS)

    for root, dirs, files in os.walk('.'):
        for name in (n for n in files if n.lower() == 'readme.txt'):
            path = os.path.join(root, name)
            f = open(path)

            if not f.read().strip().startswith('##'):  # Ignore other files called 'readme.txt'
                print ('Skipping {0}'.format(path))
            else:
                print('Processing {0}'.format(path))
            
            f.seek(0)
            values = parse_readme(f)
            values['relative path'] = os.path.dirname(path)
            values['absolute path'] = os.path.dirname(os.path.join(os.getcwd(), path))

            sheet.append([values.get(c.lower(), '') for c in COLUMNS])

    workbook.save('data.xlsx')


if __name__ == '__main__':
    main()