parser.py 文件源码

def main():
    """Command line entry point."""
    import argparse
    import sys

    parser = argparse.ArgumentParser(
        description=sys.modules[__name__].__doc__)
    parser.add_argument(
        'article_file', metavar='ARTICLE', type=argparse.FileType(),
        help='path to Wiktionary article file')
    parser.add_argument(
        '-z', '--zim-file', action='store_true',
        help='treat the article file as a ZIM archive, instead of HTML '
             'source')
    parser.add_argument(
        '-d', '--debug', action='store_true',
        help='enable debugging output')
    args = parser.parse_args()

    logging.basicConfig(
        level=logging.DEBUG if args.debug else logging.INFO)

    if args.zim_file:
        article_tuples = ZimFile(args.article_file).article_tuples()
    else:
        article_tuples = [(None, None, args.article_file.read())]

    for article_tuple in article_tuples:
        context = {'edition': article_tuple[0], 'pagename': article_tuple[1]}
        doc = html.fromstring(article_tuple[2])
        for translation in parse_document(doc):
            translation.update(context)
            print json.dumps(translation)