This script takes a directory of NetCDF datasets and a single JSON style file and creates one ZIP archive per dataset, ready to upload to Data Basin.

netcdf_for_databasin.py

"""
This script takes a directory of NetCDF datasets and a single JSON style file and creates one ZIP archive 
per dataset, ready to upload to Data Basin.
"""

import json
import os
import sys
from zipfile import ZipFile, ZIP_DEFLATED


def main():
    if len(sys.argv) < 3:
        print('Usage: netcdf_for_databasin.py <directory> <style file>')
        sys.exit(-1)

    netcdf_path, style_path = sys.argv[1:3]

    if not os.path.isdir(netcdf_path):
        print('{0} is not a valid directory.'.format(netcdf_path))
        sys.exit(-1)

    if not os.path.isfile(style_path):
        print('{0} is not a valid file.'.format(style_path))
        sys.exit(-1)

    with open(style_path, 'r') as f:
        style_json = json.dumps(json.load(f, strict=False))

    output_path = os.path.join(netcdf_path, 'packages')

    # Find a unique directory name if 'packages' exists.
    if os.path.exists(output_path):
        i = 1
        while os.path.exists('{0}_{1}'.format(output_path, i)):
            i += 1
        output_path = '{0}_{1}'.format(output_path, i)

    os.mkdir(output_path)

    netcdf_files = (x for x in os.listdir(netcdf_path) if x.endswith('.nc'))

    for name in netcdf_files:
        path = os.path.join(netcdf_path, name)
        base_name = name[:-3]

        zip_name = '{0}.zip'.format(base_name)
        print('Packaging {0}...'.format(zip_name))

        with ZipFile(os.path.join(output_path, zip_name), 'w', ZIP_DEFLATED) as zf:
            zf.write(path, name)
            zf.writestr('{0}_style.json'.format(base_name), style_json)

    print('Done. Packages are located at: {0}'.format(output_path))


if __name__ == '__main__':
    main()