BeautifulSoup自动关闭未关闭的html标记

你可以 poke through bs4 internals 并修改 html.parser 处理HTML(这适用于我的版本 bs4==4.12.2 ):

from bs4 import BeautifulSoup
from bs4.builder import builder_registry
from bs4.formatter import HTMLFormatter


class UnsortedAttributes(HTMLFormatter):
    def __init__(self):
        super().__init__(
            void_element_close_prefix=""
        )  # <-- use void_element_close_prefix="" here

    def attributes(self, tag):
        yield from tag.attrs.items()


html_text = """\
<closed_tag>
    <my_tag id="xxx">
    <my_other_tag id="zzz">
</closed_tag>"""

builder_registry.lookup("html.parser").empty_element_tags = {"my_tag", "my_other_tag"}

soup = BeautifulSoup(html_text, "html.parser")
print(soup.encode(formatter=UnsortedAttributes()).decode())

打印:

<closed_tag>
<my_tag id="xxx">
<my_other_tag id="zzz">
</closed_tag>