remove all HTML attributes with BeautifulSoup except some tags(<a> <img>...)

remove_attrs.py

from bs4 import BeautifulSoup

# remove all attributes
def _remove_all_attrs(soup):
    for tag in soup.find_all(True): 
        tag.attrs = {}
    return soup

# remove all attributes except some tags
def _remove_all_attrs_except(soup):
    whitelist = ['a','img']
    for tag in soup.find_all(True):
        if tag.name not in whitelist:
            tag.attrs = {}
    return soup

# remove all attributes except some tags(only saving ['href','src'] attr)
def _remove_all_attrs_except_saving(soup):
    whitelist = ['a','img']
    for tag in soup.find_all(True):
        if tag.name not in whitelist:
            tag.attrs = {}
        else:
            attrs = dict(tag.attrs)
            for attr in attrs:
                if attr not in ['src','href']:
                    del tag.attrs[attr]
    return soup

some useful issues reference from : BeautifulSoup删除html文档中所有属性

is working with nested tags? because in my test soup.find_all(True) will return only parents elements.

Instead of removing HTML tags for the whole soup, how is this done for a specific BS4 tag?

Example:

• I have the soup: feed = BeautifulSoup(response, 'xml')
• I parse a specific tag using item = feed.select_one('item')
• If the resulting item contains <a>, <p>, and <img> tags that I want to remove, how is this accomplished?