def get_word_list(file_name):
""" Reads the specified project Gutenberg book. Header comments,
punctuation, and whitespace are stripped away. The function
returns a list of the words used in the book as a list.
All words are converted to lower case.
"""
if exists(file_name):
fiel = open(file_name, 'r')
else:
with open(file_name, 'w') as fiel:
page = URL('http://www.gutenberg.org/cache/epub/' +
file_name[2:-4] + '/' + file_name)
fiel.write(page.read().strip())
fiel = open(file_name, 'r')
txt = fiel.read()
txt = txt[txt.index('*** START OF THIS PROJECT GUTENBERG EBOOK'):txt.
index('*** END OF THIS PROJECT GUTENBERG EBOOK')]
for dot in string.punctuation:
if dot is not "'":
txt = txt.replace(dot, " ")
txt = txt.lower()
wordlist = txt.split()
return wordlist
