py 给 html 添加适当换行，以便版本管理

format_html.py

# -*- coding: UTF-8 -*-
# vim:set shiftwidth=4 tabstop=4 expandtab textwidth=79:

import re

def format_html(html):
    '''给 html 添加适当换行，以便版本管理
    '''
    html = re.sub('\n?\ ?<(address|blockquote|center|dir|div|dl|fieldset|form|h1|h2|h3|h4|h5|h6|hr|isindex|menu|noframes|noscript|ol|p|pre|table|ul|dd|dt|frameset|li|tbody|td|tfoot|th|thead|tr)([^>]*?)>', '\n<\\1\\2>', html)
    html = re.sub('</(address|blockquote|center|dir|div|dl|fieldset|form|h1|h2|h3|h4|h5|h6|hr|isindex|menu|noframes|noscript|ol|p|pre|table|ul|dd|dt|frameset|li|tbody|td|tfoot|th|thead|tr)([^>]*?)>\ ?\n?', '</\\1\\2>\n', html)
    html = re.sub('\n?<(img|hr|br)([^>]*?)>\n?', '\n<\\1\\2>\n', html)
    return html