Simple script to generate sitemap for a specified domain.

gensitemap.py

#!/usr/bin/env python3
#   encoding: utf8
#   filename: gensitemap.py
"""Simple script to generate sitemap for a specified domain. It traverse all
HTML files from a given root directory and build URLs.
"""

import logging
import xml.etree.ElementTree as etree

from argparse import ArgumentParser, Namespace
from datetime import datetime
from os import walk
from os.path import join, getmtime, getsize, realpath, relpath


NAMESPACE = 'http://www.sitemaps.org/schemas/sitemap/0.9'


parser = ArgumentParser(epilog=__doc__)
parser.add_argument('-d', '--domain',
                    default='daskol.xyz',
                    help='domain to use in urls')
parser.add_argument('rootdir',
                    help='content directory',
                    metavar='ROOT-DIRECTORY')
parser.add_argument('sitemap',
                    default='sitemap.xml',
                    help='output sitemap',
                    metavar='SITEMAP',
                    nargs='?')


def main(args: Namespace):
    logging.basicConfig(format='%(asctime)s %(levelname)s %(message)s',
                        level=logging.INFO)
    logging.info('create root element')

    urlset = etree.Element('urlset', {'xmlns': NAMESPACE})

    logging.info('walk directory %s', realpath(args.rootdir))

    for curdir, dirnames, filenames in walk(args.rootdir):
        for filename in filenames:
            if not filename.endswith('.html'):
                continue

            logging.info('processing file %s', join(curdir, filename))

            path = relpath(join(curdir, filename), args.rootdir)
            date = datetime.fromtimestamp(getmtime(path)).date()
            rank = 1 if filename == 'index.html' else 0.5

            url = etree.SubElement(urlset, 'url')
            loc = etree.SubElement(url, 'loc')
            loc.text = f'https://{args.domain}/{path}'
            lastmod = etree.SubElement(url, 'lastmod')
            lastmod.text = date.strftime('%Y-%d-%m')
            priority = etree.SubElement(url, 'priority')
            priority.text = str(rank)

    logging.info('write XML document to %s', args.sitemap)
    sitemap = etree.ElementTree(urlset)
    sitemap.write(args.sitemap, xml_declaration=True, encoding='utf-8')
    logging.info('size of sitemap file is %s bytes', getsize(args.sitemap))
    logging.info('done.')


if __name__ == '__main__':
    main(parser.parse_args())