from natasha import (
    Segmenter,

    NewsEmbedding,
    NewsMorphTagger,
    NewsSyntaxParser,
    MorphVocab,
    Doc
)
segmenter = Segmenter()
emb = NewsEmbedding()
morph_tagger = NewsMorphTagger(emb)
syntax_parser = NewsSyntaxParser(emb)

import re



def get_standart_text(text):
    text = text.lower()
    text = ' '.join(re.findall('[а-яё0-9a-z]+', text))
    doc = Doc(text)
    doc.segment(segmenter)
    doc.tag_morph(morph_tagger)
    doc.parse_syntax(syntax_parser)

    morph_vocab = MorphVocab()
    for token in doc.tokens:
        token.lemmatize(morph_vocab)
    d = [i.lemma for i in doc.tokens]

    return " ".join(d)