如何使用Python从一个大的html文件创建一个Word Cloud？

import re
from bs4 import BeautifulSoup
from wordcloud import WordCloud
import matplotlib.pyplot as plt

with open('your_html_file.html', 'r', encoding='utf-8') as file:
    html_content = file.read()

soup = BeautifulSoup(html_content, 'html.parser')
text = soup.get_text()

cleaned_text = re.sub(r'\s+', ' ', text)  # 去除多余的空格和换行符

wordcloud = WordCloud(width=800, height=400).generate(cleaned_text)

plt.figure(figsize=(10, 5))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.show()