NLTK干txt文件存储在本地文件夹中

Question

我在本地驱动器中有大量的txt文件，我想用它们标记并阻止它们的内容。如果您只有1个要处理的文档，那么脚本可以正常工作，并且大多数在线NLTK教程都没有解释如果需要在本地文件夹中循环txt文件（即如果您有文档语料库）那么将如何进行。我确信这是一个简单的循环问题，但我无法弄清楚如何阻止我的文件。

 import nltk
 import string
 from collections import Counter

    def get_tokens():
       with open('/Users/myname/Desktop/text.txt', 'r') as shakes:
        text = shakes.read()
        lowers = text.lower()
        no_punctuation = lowers.translate(None, string.punctuation)
        tokens = nltk.word_tokenize(no_punctuation)
        return tokens

    tokens = get_tokens()
    count = Counter(tokens)
    print count.most_common(10)


    from nltk.corpus import stopwords

    tokens = get_tokens()
    filtered = [w for w in tokens if not w in stopwords.words('english')]
    count = Counter(filtered)
    print count.most_common(100)

    from nltk.stem.porter import *

    def stem_tokens(tokens, stemmer):
        stemmed = []
        for item in tokens:
            stemmed.append(stemmer.stem(item))
        return stemmed

    stemmer = PorterStemmer()
    stemmed = stem_tokens(filtered, stemmer)
    count = Counter(stemmed)
    print count.most_common(100)