智能seo系统源码

import nltk
from sklearn.feature_extraction.text import TfidfVectorizer

def extract_keywords(text):
    tokens = nltk.word_tokenize(text)
    keywords = [word for word in tokens if len(word) > 3]
    return keywords

def optimize_content(original_content):
    vectorizer = TfidfVectorizer()
    tfidf_matrix = vectorizer.fit_transform([original_content])
    feature_names = vectorizer.get_feature_names_out()
    tfidf_scores = tfidf_matrix.toarray()[0]
    
    optimized_keywords = sorted(zip(feature_names, tfidf_scores), key=lambda x: x[1], reverse=True)[:10]
    optimized_content = original_content + " " + " ".join([kw[0] for kw in optimized_keywords])
    
    return optimized_content

# 示例使用
original_text = "这是一个关于智能SEO系统的介绍。"
optimized_text = optimize_content(original_text)
print("优化后的内容:", optimized_text)