from HTMLParser import HTMLParser

class VerbatimParser(HTMLParser):
    def __init__(self, out):
        HTMLParser.__init__(self)
        # @#%#@% HTMLParser uses old-style classes, can't use super()
        self.out = out
    def emit(self, text):
        self.out.write(text)
    def handle_starttag(self, tag, attrs):
        self.emit(self.get_starttag_text())
    def handle_endtag(self, tag):
        self.emit('</')
        self.emit(tag)
        self.emit('>')
    def handle_startendtag(self, tag, attrs):
        self.emit(self.get_starttag_text())
    def handle_data(self, data):
        self.emit(data)
    def handle_entityref(self, name):
        self.emit('&')
        self.emit(name)
        self.emit(';')
    def handle_charref(self, name):
        self.emit('&#')
        self.emit(name)
        self.emit(';')
    def handle_comment(self, data):
        self.emit('<!--')
        self.emit(data)
        self.emit('-->')
    def handle_decl(self, decl):
        self.emit('<!')
        self.emit(decl)
        self.emit('>')
    def handle_pi(self, data):
        self.emit('<?')
        self.emit(data)
        self.emit('>')
    def unknown_decl(self, data):
        self.emit('<![')
        self.emit(data)
        self.emit(']>')

def doit(infile, outfile):
    with open(outfile,'w') as fout:
        parser = VerbatimParser(fout)
        with open(infile) as f:
            parser.feed(f.read())
            parser.close()

doit('test1.html','test1b.html')