parsexml.py

# -*- coding: utf-8 -*-
import os
import argparse

from lxml import etree


ELEM_TAG = 'tmk:MarkSignificantVerbalElementText'
ELEM_NAMESPACE = {'tmk': 'http://www.wipo.int/standards/XMLSchema/Trademark/1'}


def isfile(f):
    if not os.path.exists(f):
        raise argparse.ArgumentTypeError("%s does not exist" % f)
    return f


def cmdline_args():
    desc = 'Extract text inside %s elements' % ELEM_TAG
    parser = argparse.ArgumentParser(description=desc)
    parser.add_argument('infile', type=isfile, help='Input XML-file')
    return parser.parse_args()


def parse_xml(infile, outfile):
    tree = etree.parse(open(infile))
    with open(outfile, 'w') as f:
        elems = tree.findall('//' + ELEM_TAG, ELEM_NAMESPACE)
        f.write('\n'.join(e.text.encode('utf8') for e in elems))


def get_filename_without_extension(path):
    filename = os.path.basename(path)
    return os.path.splitext(filename)[0]


if __name__ == '__main__':
    args = cmdline_args()
    outfile = 'results_%s.txt' % get_filename_without_extension(args.infile)
    parse_xml(args.infile, outfile)

test_parsexml.py

# -*- coding: utf-8 -*-

from parsexml import get_filename_without_extension


def test_get_filename_without_extension():
    assert get_filename_without_extension('/tmp/a.py') == 'a'
    assert get_filename_without_extension('a.py') == 'a'