Google-friendly sitemaps for multilingual Wagtail sites

mixins.py

from wagtail.models import Page
from translation.utils import get_translated_sitemap_urls

class ExtendedPage(Page):
    class Meta:
        abstract = True

    def get_sitemap_urls(self, request):
        page = self.localized
        default_data = [{
            'location': page.full_url,
            'lastmod': (page.last_published_at or page.latest_revision_created_at),
        }]
        return get_translated_sitemap_urls(page, request, default_data)

sitemap.xml

<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:xhtml="http://www.w3.org/1999/xhtml">
{% spaceless %}
    {% for url in urlset %}
        <url>
            <loc>{{ url.location }}</loc>
            {% if url.lastmod %}
                <lastmod>{{ url.lastmod|date:'Y-m-d' }}</lastmod>
            {% endif %}
            {% for item in url.alternates %}
                <xhtml:link rel="alternate" hreflang="{{ item.locale.language_code }}" href="{{ item.url }}"/>
            {% endfor %}
        </url>
    {% endfor %}
{% endspaceless %}
</urlset>

utils.py

# Amend these to the domains your translated site uses
TRANSLATED_DOMAINS = {
    'en': 'www.girlsnotbrides.org',
    'fr': 'www.fillespasepouses.org',
    'es': 'www.girlsnotbrides.es',
}

def get_translatable_page_siblings(instance, only_live=True, include_self=False):

    translations = instance.get_translations(inclusive=include_self)

    if only_live:
        translations = translations.live()

    return translations

def get_translated_sitemap_urls(page, request, default_data):

    domains = TRANSLATED_DOMAINS
    host = request.get_host()
    domain = None
    lang = None

    for k, v in domains.items():
        if v == host:
            domain = v
            lang = k

    if domain and lang:

        # return empty array if this page isn't the current language
        if page.locale.language_code != lang:
            return []

        # get default sitemap data for page, return if no data
        data = next(iter(default_data))
        if not data:
            return []

        # get self and siblings, add to data and return
        siblings = get_translatable_page_siblings(page, only_live=True, include_self=True).select_related('locale')
        data['alternates'] = siblings

        return [data]

    # return an empty array if none of the above
    return []

To implement:

• sitemap.xml should be placed in the root of any included templates folder, e.g templates/sitemap.xml
• ExtendedPage should be used as an inherited mixin to all of your Wagtail pages
• utils.py can be placed anywhere, e.g. translation/utils.py