Parse and dump a sitemap (using Python)

gistfile1.py

#! /usr/bin/env python
# -*- coding: utf-8 -*-

"""
Inspired by Craig Addyman (http://www.craigaddyman.com/parse-an-xml-sitemap-with-python/)
Enhanced by Viktor Petersson (http://viktorpetersson.com) / @vpetersson
"""

from bs4 import BeautifulSoup
import requests


def get_sitemap(url):
    get_url = requests.get(url)

    if get_url.status_code == 200:
        return get_url.text
    else:
        print 'Unable to fetch sitemap: %s.' % url


def process_sitemap(s):
    soup = BeautifulSoup(s)
    result = []

    for loc in soup.findAll('loc'):
        result.append(loc.text)

    return result


def is_sub_sitemap(s):
    if s.endswith('.xml') and 'sitemap' in s:
        return True
    else:
        return False


def parse_sitemap(s):
    sitemap = process_sitemap(s)
    result = []

    while sitemap:
        candidate = sitemap.pop()

        if is_sub_sitemap(candidate):
            sub_sitemap = get_sitemap(candidate)
            for i in process_sitemap(sub_sitemap):
                sitemap.append(i)
        else:
            result.append(candidate)

    return result


def main():
    sitemap = get_sitemap('https://www.cloudsigma.com/sitemap.xml')
    print '\n'.join(parse_sitemap(sitemap))


if __name__ == '__main__':
    main()