def dehtmlify(body):
"""
Try to dehtmlify a text
:param str body: The html content
:rtype: str
:return: The dehtmlified content
"""
html = html2text.HTML2Text()
html.body_width = 0
body = html.handle(body.replace('\r\n', '<br/>'))
body = re.sub(r'^(\s*\n){2,}', '\n', body, flags=re.MULTILINE)
return body
评论列表
文章目录