python gutenberg古腾堡语料库

import nltk
from nltk.corpus import gutenberg
a = gutenberg.fileids()
print(a)
emma = gutenberg.words("shakespeare-macbeth.txt")
print(emma[1030 :1037])
for fileid in gutenberg.fileids():
    num_chars = len(gutenberg.raw(fileid))
    num_words = len(gutenberg.words(fileid))
    num_sents = len(gutenberg.sents(fileid))
    print(num_chars , num_words, num_sents , fileid)