Python 如何高效地从 HTML 中提取纯文本、处理实体和不需要的内容？

from urllib.request import urlopen
from bs4 import BeautifulSoup

url = "http://news.bbc.co.uk/2/hi/health/2284783.stm"
html = urlopen(url).read()
soup = BeautifulSoup(html, features="html.parser")

# Remove unwanted elements like scripts and styles
for script in soup(["script", "style"]):
    script.extract()

# Extract the text content
text = soup.get_text()

# Preprocess the text for improved readability
lines = (line.strip() for line in text.splitlines())
chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
text = '\n'.join(chunk for chunk in chunks if chunk)

print(text)