解析博客文章

import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from collections import Counter

# 下载必要的NLTK数据
nltk.download('punkt')
nltk.download('stopwords')

def extract_keywords(text, num_keywords=10):
    # 分词
    tokens = word_tokenize(text)
    
    # 去除停用词
    stop_words = set(stopwords.words('english'))
    filtered_tokens = [word for word in tokens if word.isalnum() and word.lower() not in stop_words]
    
    # 计算词频
    word_counts = Counter(filtered_tokens)
    
    # 提取关键词
    keywords = word_counts.most_common(num_keywords)
    
    return keywords

# 示例文本
text = """
Natural Language Processing (NLP) is a subfield of linguistics, computer science, and artificial intelligence concerned with the interactions between computers and human language, in particular how to program computers to process and analyze large amounts of natural language data.
"""

# 提取关键词
keywords = extract_keywords(text)
print(keywords)