python实现的简单html文本转纯text

一个python实现的简单转html转纯text的函数

import re
from html import unescapedef html_to_plain_text(html):text = re.sub('<head.*?>.*?</head>', '', html, flags=re.M | re.S | re.I)text = re.sub('<a\s.*?>', ' HYPERLINK ', text, flags=re.M | re.S | re.I)text = re.sub('<.*?>', '', text, flags=re.M | re.S)text = re.sub(r'(\s*\n)+', '\n', text, flags=re.M | re.S)return unescape(text)

例如有一段html文本

<HTML><HEAD><TITLE></TITLE><META http-equiv="Content-Type" content="text/html; charset=windows-1252"><STYLE>A:link {TEX-DECORATION: none}A:active {TEXT-DECORATION: none}A:visited {TEXT-DECORATION: none}A:hover {COLOR: #0033ff; TEXT-DECORATION: underline}</STYLE><MET