nltk 中的 sents 和 words ，为后续处理做准备。
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from nltk.corpus import gutenberg
sents = gutenberg.sents("burgess-busterbrown.txt")
print(sents[1:20])
words = gutenberg.words("burgess-busterbrown.txt")
print(words[1:20])输出：
[['I'], ['BUSTER', 'BEAR', 'GOES', 'FISHING'], ['Buster', 'Bear', 'yawned', 'as', 'he', 'lay', 'on', 'his', 'comfortable', 'bed', 'of', 'leaves', 'and', 'watched', 'the', 'first', 'early', 'morning', 'sunbeams', 'creeping', 'through', 'the', 'Green', 'Forest', 'to', 'chase', 'out', 'the', 'Black', 'Shadows', '.'], ['Once', 'more', 'he', 'yawned', ',', 'and', 'slowly', 'got', 'to', 'his', 'feet', 'and', 'shook', 'himself', '.'], ['Then', 'he', 'walked', 'over', 'to', 'a', 'big', 'pine', '-', 'tree', ',', 'stood', 'up', 'on', 'his', 'hind', 'legs', ',', 'reached', 'as', 'high', 'up', 'on', 'the', 'trunk', 'of', 'the', 'tree', 'as', 'he', 'could', ',', 'and', 'scratched', 'the', 'bark', 'with', 'his', 'great', 'claws', '.'], ['After', 'that', 'he', 'yawned', 'until', 'it', 'seemed', 'as', 'if', 'his', 'jaws', 'would', 'crack', ',', 'and', 'then', 'sat', 'down', 'to', 'think', 'what', 'he', 'wanted', 'for', 'breakfast', '.'], ['While', 'he', 'sat', 'there', ',', 'trying', 'to', 'make', 'up', 'his', 'mind', 'what', 'would', 'taste', 'best', ',', 'he', 'was', 'listening', 'to', 'the', 'sounds', 'that', 'told', 'of', 'the', 'waking', 'of', 'all', 'the', 'little', 'people', 'who', 'live', 'in', 'the', 'Green', 'Forest', '.'], ['He', 'heard', 'Sammy', 'Jay', 'way', 'off', 'in', 'the', 'distance', 'screaming', ',', '"', 'Thief', '!'], ['Thief', '!"'], ['and', 'grinned', '.'], ['"', 'I', 'wonder', ',"', 'thought', 'Buster', ',', '"', 'if', 'some', 'one', 'has', 'stolen', 'Sammy', "'", 's', 'breakfast', ',', 'or', 'if', 'he', 'has', 'stolen', 'the', 'breakfast', 'of', 'some', 'one', 'else', '.'], ['Probably', 'he', 'is', 'the', 'thief', 'himself', '."'], ['He', 'heard', 'Chatterer', 'the', 'Red', 'Squirrel', 'scolding', 'as', 'fast', 'as', 'he', 'could', 'make', 'his', 'tongue', 'go', 'and', 'working', 'himself', 'into', 'a', 'terrible', 'rage', '.'], ['"', 'Must', 'be', 'that', 'Chatterer', 'got', 'out', 'of', 'bed', 'the', 'wrong', 'way', 'this', 'morning', ',"', 'thought', 'he', '.'], ['He', 'heard', 'Blacky', 'the', 'Crow', 'cawing', 'at', 'the', 'top', 'of', 'his', 'lungs', ',', 'and', 'he', 'knew', 'by', 'the', 'sound', 'that', 'Blacky', 'was', 'getting', 'into', 'mischief', 'of', 'some', 'kind', '.'], ['He', 'heard', 'the', 'sweet', 'voices', 'of', 'happy', 'little', 'singers', ',', 'and', 'they', 'were', 'good', 'to', 'hear', '.'], ['But', 'most', 'of', 'all', 'he', 'listened', 'to', 'a', 'merry', ',', 'low', ',', 'silvery', 'laugh', 'that', 'never', 'stopped', 'but', 'went', 'on', 'and', 'on', ',', 'until', 'he', 'just', 'felt', 'as', 'if', 'he', 'must', 'laugh', 'too', '.'], ['It', 'was', 'the', 'voice', 'of', 'the', 'Laughing', 'Brook', '.'], ['And', 'as', 'Buster', 'listened', 'it', 'suddenly', 'came', 'to', 'him', 'just', 'what', 'he', 'wanted', 'for', 'breakfast', '.']]
['The', 'Adventures', 'of', 'Buster', 'Bear', 'by', 'Thornton', 'W', '.', 'Burgess', '1920', ']', 'I', 'BUSTER', 'BEAR', 'GOES', 'FISHING', 'Buster', 'Bear']
Process finished with exit code 0