Simple Function to remove English Languages stopwords without using NLTK

demo.py

from stopwords import remove_stopwords

dummy_string = ("""Mr. and Mrs. Dursley, of number four, Privet Drive, were """
                """proud to say that they were perfectly normal, thank you """
                """very much. They were the last people you'd expect to be """
                """involved in anything strange or mysterious, because they """
                """just didn't hold with such nonsense.""")

# Simple Word tokenizer
dummy_list = dummy_string.replace(",", " ").replace(".", " ").split(" ")

# Remove Stop Words
non_stop_words = remove_stopwords(dummy_list)

# Display texts
print "Original:", dummy_string
print "Non-Stopwords:", non_stop_words

stopwords.py

stop_words = ['all', 'over', 'with', 'had', 'to', 'has', 'do', 'very', 'not',
              'this', 'some', 'are', 'out', 'for', 'be', 'we', 'by', 'on',
              'about', 'of', 'or', 'your', 'from', 'there', 'been', 'was',
              'that', 'but', 'he', 'me', 'will', 'my', 'and', 'is', 'it', 'an',
              'as', 'at', 'have', 'in', 'no', 'which', 'you', 'a', 'i', 'the',
              '', 'just', 'being', 'both', 'through', 'during', 'its',
              'before', ' ', 'how', 'should', 'only', 'under', 'ours', 'them',
              'his', 'get', 'stop', 'they', 'yourselves', 'now', 'him', 'nor',
              'did', 'she', 'each', 'further', 'where', 'few', 'because',
              'doing', 'theirs', 'up', 'our', 'ourselves', 'what', 'below',
              'does', 'above', 'between', 't', 'after', 'here', 'hers', 'her',
              'against', 's', 'own', 'into', 'yourself', 'down', 'would', '&',
              'their', 'too', 'then', 'themselves', 'until', 'more', 'himself',
              'bus', 'don', 'herself', 'than', 'those', 'myself', 'these', 'whom',
              'while', 'can', 'were', 'give', 'am', 'itself', 'any', 'if',
              'again', 'when', 'same', 'also', 'other', 'take', 'may', 'who',
              'most', 'such', 'why', 'off', 'having', 'so', 'yours', 'once']


def remove_stopwords(raw_words_list):
    no_stopwords_list = [
        word for word in raw_words_list if word.lower() not in stop_words]
    return no_stopwords_list


if __name__ == '__main__':
    dummy_string = ("""Mr. and Mrs. Dursley, of number four, Privet Drive, """
    	"""were proud to say that they were perfectly normal, thank you """
    	"""very much. They were the last people you'd expect to be """
    	"""involved in anything strange or mysterious, because they """
    	"""just didn't hold with such nonsense.""")
    # Simple Word tokenizer
    dummy_list = dummy_string.replace(","," ").replace("."," ").split(" ")
    # Remove Stop Words
    non_stop_words = remove_stopwords(dummy_list)
    # Display texts
    print "Original text:", dummy_string
    print "Words which are not stop words:", non_stop_words