Get some statistics from bible

set_in_test.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Created on Sun Jun 16 05:19:49 2013
# Danilo de Jesus da Silva Bellini
""" Get some statistics from bible """

from __future__ import print_function, unicode_literals
import os, zipfile, random
try: # Python 2
  from urllib2 import urlopen
  from string import letters as ascii_letters
except ImportError: # Python 3
  from urllib.request import urlopen
  from string import ascii_letters

bible_link = "http://printkjv.ifbweb.com/"
zip_name = "AV_txt.zip"

class DownloadError(Exception):
  pass

def download_file(url, output_filename):
  data = urlopen(url)
  code = data.getcode()
  if code != 200:
    raise DownloadError("Error {}".format(code))
  with open(output_filename, "wb") as f:
    f.write(data.read())

def get_bible_data():
  if not os.path.exists(zip_name) or not zipfile.is_zipfile(zip_name):
    download_file(bible_link + zip_name, zip_name)
  with zipfile.ZipFile(zip_name) as zf:
    return zf.read(zf.namelist()[0]).decode("utf-8")

def new_random_word():
  msg = list(ascii_letters)
  size = random.randrange(3, len(msg))
  random.shuffle(msg)
  return "".join(msg[:size])

if __name__ == "__main__":
  words = get_bible_data().split()
  set_words = set(words)
  print("Total whitespace-separated items:", len(words))
  print("Unique (case sensitive):", len(set_words))

  # Comparison for Junior Polegato
  print()
  nw = [words[5], words[37], words[458]]
  nw.extend(new_random_word() for _ in range(17))
  print("New words:", nw)
  print()
  print("Repeated:", len([x for x in nw if x in words]))
  print("Repeated in set:", len([x for x in nw if x in set_words]))
  final = words + [x for x in nw if x in words]
  print("Final size, appending the new words:", len(final))
  print("Final size, adding to set:", len(set(final)))