#!/usr/bin/python

from html5lib import parse
from os import listdir, path
from sys import argv

directory = argv[1]

for filename in listdir(directory):
    with open(path.join(directory, filename)) as f:
        tree = parse(f, treebuilder='etree')
        for element in tree.iter():
            try:
                print element.attrib['id']
            except KeyError:
                pass

