Dictionary of most used language by country based on https://stackoverflow.com/a/22202770/2962940

get_langs.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import xml.etree.ElementTree as etree
import urllib
import pprint


def get_most_used_language_by_territory():
    langxml = urllib.urlopen('http://unicode.org/repos/cldr/trunk/common/supplemental/supplementalData.xml')
    langtree = etree.XML(langxml.read())
    langs = {}
    for t in langtree.find('territoryInfo').findall('territory'):
        code = t.get('type')
        # Seems like the languages are conveniently ordered by population percent, so the first one
        # on the list will be the most used.
        # We don't even need to look at the 'official' status, just get what is better for the user
        lang_pop = t.findall('languagePopulation')
        langs[code] = (lang_pop[0] if len(lang_pop) > 0 else {}).get('type', 'en')
    return langs


def main():
    langs = get_most_used_language_by_territory()
    pp = pprint.PrettyPrinter(indent=4)
    pp.pprint(langs)


if __name__ == "__main__":
    main()