爬取新闻数据并文本聚类分析代码

以下是一个简单的 Python 代码示例，用于爬取新闻数据并进行文本聚类分析：

import requests
from bs4 import BeautifulSoup
import jieba
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt

# 爬取新闻数据
def get_news(url):
    res = requests.get(url)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text, 'html.parser')
    news = soup.select('h2 > a')
    content = []
    for n in news:
        href = n['href']
        title = n.text
        news_res = requests.get(href)
        news_res.encoding = 'utf-8'
        news_soup = BeautifulSoup(news_res.text, 'html.parser')
        article = news_soup.select('.article-content-inner > p')
        content.append(title)
        for p in article:
            content.append(p.text)
    return content

# 文本预处理
def preprocess(content):
    stopwords = [line.strip() for line in open('stopwords.txt', 'r', encoding='utf-8').readlines()]
    corpus = []
    for c in content:
        words = jieba.cut(c)
        words = [w for w in words if w not in stopwords and len(w) > 1]
        corpus.append(' '.join(words))
    return corpus

# 文本聚类分析
def cluster_analysis(corpus):
    vectorizer = TfidfVectorizer()
    X = vectorizer.fit_transform(corpus)
    kmeans = KMeans(n_clusters=5)
    kmeans.fit(X)
    labels = kmeans.labels_
    return labels

# 可视化展示
def visualization(corpus, labels):
    plt.rcParams['font.sans-serif'] = ['SimHei']
    plt.rcParams['axes.unicode_minus'] = False
    plt.scatter(labels, range(len(corpus)))
    plt.show()

# 主函数
if __name__ == '__main__':
    url = 'http://news.sina.com.cn/china/'
    content = get_news(url)
    corpus = preprocess(content)
    labels = cluster_analysis(corpus)
    visualization(corpus, labels)

需要注意的是，以上代码仅供参考，实际应用中需要根据具体需求进行修改和完善。同时，需要注意文本预处理和文本聚类算法的参数设置等细节问题。