List the tags used in a (set of) HTML file(s).

taglist.py

#!/usr/bin/env python2.7

from sys import argv

from bs4 import BeautifulSoup
from bs4.element import Tag


soup = None
tags = set()

for html_file in argv[1:]:
    with open(html_file) as fin:
        soup = BeautifulSoup(fin.read())

    for child in soup.find('body').descendants:
        if isinstance(child, Tag):
            tags.add(child.name)

print '\n'.join(sorted(tags))