from collections import defaultdict
from urllib import urlopen

#ilo = urlopen('http://www.loaddoc.com/files/db/GaKoHvnpVkxI26756/GaKoHvnpVkxI26756.txt').read()
latin = open('seneca.txt').read()
words = latin.split()

wl = set(words)

d = defaultdict(list)
for i,w in enumerate(words):
  d[w].append(i)

freqs = sorted([(len(d[w]),w) for w in d])

print d