using generator comprehensions in python to extract words from epub files

get-words-from-epubs.py

from glob import glob
from os.path import basename
from zipfile import ZipFile, is_zipfile
from re import findall
from nltk.corpus import words

ROOT_PATH = '/Volumes/USB20FD/downloads/*.epub'
WORDS = set(words.words())

groups = (group for group in zip(*(iter(glob(ROOT_PATH)),)*100))
zips = ((ZipFile(file) for file in group if is_zipfile(file)) for group in groups)
files = (((z.open(f.filename).read() for f in z.infolist() if '.html' in f.filename) for z in zip) for zip in zips)
texts = ((((WORDS & set(findall(r'[\w]+', t.lower()))) for t in txt) for txt in text) for text in files)

corpus = set()
for text in texts:
    for txt in text:
        for t in txt:
            corpus = (corpus | t)
    print (float(len(corpus)) / float(len(WORDS)))*100
    print "-"*75