Remove unwanted attributes from tags in HTML snippets with BeautifulSoup (3.21 - might work with BS4)

clean_attrs.py

from BeautifulSoup import BeautifulSoup

def clean(html):
    whitelist = ['backColor', 'backcolor', 'bgcolor',
                 'color', 'fg', 'fontName', 'fontSize',
                 'fontname', 'fontsize', 'href', 'name',
                 'textColor', 'textcolor']
    html.attrs = None
    for e in html.findAll(True):
        for attribute in e.attrs:
            if attribute[0] not in whitelist:
                del e[attribute[0]]
    return html

test = """
A full view of the location of the Ben Shahn mural shown in the previous image.
The mural is a fresco And is located  at the entrance to the school gym. Below it  are a group of photographs by several well known photographers ((including Dorothea Lange and Arthur Rothstein, documenti
ng the early days of the community.
<a href="http://music.columbia.edu/roosevelt/pop_mural_video.html"
    rel="nofollow">music.columbia.edu/roosevelt/pop_mural_video.html</a>

<a href="http://music.columbia.edu/roosevelt/pop_mural.html" rel="no
follow">music.columbia.edu/roosevelt/pop_mural.html</a>.
"""

soup = BeautifulSoup(test)
clean(soup)

print soup

# output
"""
A full view of the location of the Ben Shahn mural shown in the previous image.
The mural is a fresco And is located  at the entrance to the school gym. Below it  are a group of photographs by several well known photographers ((including Dorothea Lange and Arthur Rothstein, documenti
ng the early days of the community.
<a href="http://music.columbia.edu/roosevelt/pop_mural_video.html">music.columbia.edu/roosevelt/pop_mural_video.html</a>
<a href="http://music.columbia.edu/roosevelt/pop_mural.html">music.columbia.edu/roosevelt/pop_mural.html</a>.
"""