import xml.etree.ElementTree as ET


def get_tree(url):
    with open(url) as f:
        root = ET.fromstring(f.read())
    return root[1]

def with_paragraf(data):
    table = []
    for p in data:
        paragraf = []
        for sentence in p:
            sentence_string = ''
            for word in sentence:
                if word[0].tail is not None:
                    merge = word[0].tail + word.tail.replace('\n', '')
                    print(merge)
                    sentence_string += merge + ' '
            paragraf.append(sentence_string)
        table.append(paragraf)
    return table

data = get_tree('itartass4.html')
bits_list = with_paragraf(data)