使用Python和NLTK从文本中高效提取名词的实用教程

pip install nltk

import nltk

try:
    nltk.data.find('tokenizers/punkt')
except nltk.downloader.DownloadError:
    nltk.download('punkt')

try:
    nltk.data.find('taggers/averaged_perceptron_tagger')
except nltk.downloader.DownloadError:
    nltk.download('averaged_perceptron_tagger')

try:
    nltk.data.find('corpora/stopwords')
except nltk.downloader.DownloadError:
    nltk.download('stopwords')

print("NLTK及其所需数据已准备就绪。")

import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize, sent_tokenize

def extract_nouns(text):
    """
    从给定文本中提取名词。

    参数:
        text (str): 待处理的输入文本。

    返回:
        list: 包含所有提取到的名词的列表。
    """
    # 1. 获取英文停用词列表
    stop_words = set(stopwords.words('english'))

    # 2. 分句 (可选，对于较短文本可直接分词)
    sentences = sent_tokenize(text)

    all_nouns = []
    for sentence in sentences:
        # 3. 分词
        words = word_tokenize(sentence)

        # 4. 去除停用词并转换为小写 (可选，根据需求决定是否去除停用词)
        filtered_words = [word.lower() for word in words if word.isalnum() and word.lower() not in stop_words]

        # 5. 词性标注
        tagged_words = nltk.pos_tag(filtered_words)

        # 6. 筛选名词
        # 常见的名词标签包括:
        # NN: 单数名词 (e.g., table)
        # NNS: 复数名词 (e.g., tables)
        # NNP: 专有名词单数 (e.g., John)
        # NNPS: 专有名词复数 (e.g., Americans)
        nouns = [word for word, tag in tagged_words if tag.startswith('NN')]
        all_nouns.extend(nouns)

    return list(set(all_nouns)) # 使用set去重并转回list

# 示例用法
sample_response = """
The quick brown fox jumps over the lazy dog. Dogs are loyal animals. 
New York is a big city with many famous landmarks. John and Mary visited the Empire State Building.
"""

extracted_nouns = extract_nouns(sample_response)
print(f"原始文本:\n{sample_response}\n")
print(f"提取到的名词:\n{extracted_nouns}")

# 另一个示例
message_response = "I have a task that involves extracting nouns from a variable called message: response. I want to display the extracted nouns in the console or print them on the screen. How can I accomplish this task using Python? I have tried using some libraries like NLTK and TextBlob, but I am not sure how to use them correctly. I have also asked GitHub Copilot for help, but it did not generate any useful code. It just showed me some random output that did not work. Can anyone please help me with this problem?"
extracted_nouns_from_message = extract_nouns(message_response)
print(f"\n从'message: response'中提取到的名词:\n{extracted_nouns_from_message}")