csv2json.py

import json
import csv
import sys
import codecs
import argparse

class UTF8Recoder:
    """
    Iterator that reads an encoded stream and reencodes the input to UTF-8
    """
    def __init__(self, f, encoding):
        self.reader = codecs.getreader(encoding)(f)

    def __iter__(self):
        return self

    def next(self):
        return self.reader.next().encode("utf-8")

class UnicodeReader:
    """
    A CSV reader which will iterate over lines in the CSV file "f",
    which is encoded in the given encoding.
    """

    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        f = UTF8Recoder(f, encoding)
        self.reader = csv.reader(f, dialect=dialect, **kwds)

    def next(self):
        row = self.reader.next()
        return [unicode(s, "utf-8") for s in row]

    def __iter__(self):
        return self


def to_json(input_file, output_file, encoding):
    rows = UnicodeReader(input_file, encoding=encoding)
    header = rows.next()
    l = []
    for row in rows:
        l.append(dict(zip(header, row)))
    return json.dump(l, output_file, indent=2)




def main(argv):
    parser = argparse.ArgumentParser(description='converts csv to json', prog=argv[0])
    parser.add_argument('input_file', help='path to csv input file')
    parser.add_argument('--output', help='path to json output file [%(default)s]', default='-')
    parser.add_argument('--encoding', help='character encoding of csv [%(default)s]', default='latin-1')
    args = parser.parse_args(argv[1:])

    with open(args.input_file, 'rU') as input_file:
        encoding = args.encoding 

        if args.output == '-':
            output_file = sys.stdout
        else:
            output_file = open(args.output, 'w')

        to_json(input_file, output_file, encoding)


if __name__ == '__main__':
    main(sys.argv)