from html5lib._tokenizer import HTMLTokenizer
from io import StringIO

class T():
    def __init__(self, data):
        print("Object from string: " + data)
        self.src = StringIO()
        self.tokenizer = HTMLTokenizer(self.src)

        pos = self.src.tell()
        self.src.write(data)
        self.src.seek(pos)
        self.handle_tokens()
        self.src.close()

    def handle_tokens(self):
        for token in self.tokenizer:
            print(str(self.tokenizer.stream.chunkOffset))

T("klas katt")
T("klas katt<br>")