NeuCube form submission XML parser

kedri_form_submission_parser.py

import xmltodict
import pandas as pd
import dateutil.parser


def format_date(dt):
    """
    Formats DateTTime to D-M-Y.

    Parameters
    ----------
    dt: str
        String of date and time.

    Returns
    -------
    dt: str
        Formatted date.
    """
    date = dateutil.parser.parse(dt)
    dt = '{}-{}-{}'.format(date.day, date.month, date.year)
    return dt


def parse(path, file_name):
    """
    Parses the KEDRI download submission form to relevant data and writes it to CSV file.

    Parameters
    ----------
    path: str
        Absolute path of the XML file.
    file_name: str
        File name to bes saved as csv.
    """
    file = open(path)

    main_content = {'Date': [], 'Name': [], 'Company/Institute': [], 'Email': [], 'Phone': []}

    content = xmltodict.parse(file.read())
    for submission in dict(dict(content)['submissions'])['submission']:
        main_content['Date'].append(format_date(dict(submission)['@time']))
        for text_q in dict(submission)['text_q']:
            if dict(text_q)['@name'] == 'Name':
                if '#text' in dict(text_q):
                    main_content['Name'].append(dict(text_q)['#text'])
                else:
                    main_content['Name'].append(None)
            elif dict(text_q)['@name'] == 'Company/Institute':
                if '#text' in dict(text_q):
                    main_content['Company/Institute'].append(dict(text_q)['#text'])
                else:
                    main_content['Company/Institute'].append(None)
            elif dict(text_q)['@name'] == 'Email':
                if '#text' in dict(text_q):
                    main_content['Email'].append(dict(text_q)['#text'])
                else:
                    main_content['Email'].append(None)
            elif dict(text_q)['@name'] == 'Phone':
                if '#text' in dict(text_q):
                    main_content['Phone'].append(dict(text_q)['#text'])
                else:
                    main_content['Phone'].append(None)

    df = pd.DataFrame(main_content)
    df = df[['Date', 'Name', 'Company/Institute', 'Phone', 'Email']]
    df = df.drop_duplicates(subset=['Name'])
    df.index += 1
    df.to_csv(file_name)

    file.close()


if __name__ == '__main__':
    parse('submission_log.xml', 'Kedri.csv')