Clean Title

clean_title.py

import regex

def clean_title(raw_title):
    NON_ENGLISH_CHARS = "\u3040-\u30ff\u3400-\u4dbf\u4e00-\u9fff\uf900-\ufaff\uff66-\uff9f\u0400-\u04ff"
    RUSSIAN_CAST_REGEX = regex.compile(r"\([^)]*[\u0400-\u04ff][^)]*\)$|(?<=\/.*)\(.*\)$")
    ALT_TITLES_REGEX = regex.compile(rf"[^/|(]*[{NON_ENGLISH_CHARS}][^/|]*[/|]|[/|][^/|(]*[{NON_ENGLISH_CHARS}][^/|]*")
    NOT_ONLY_NON_ENGLISH_REGEX = regex.compile(rf"(?<=[a-zA-Z][^{NON_ENGLISH_CHARS}]+)[{NON_ENGLISH_CHARS}].*[{NON_ENGLISH_CHARS}]|[{NON_ENGLISH_CHARS}].*[{NON_ENGLISH_CHARS}](?=[^{NON_ENGLISH_CHARS}]+[a-zA-Z])")
    NOT_ALLOWED_SYMBOLS_AT_START_AND_END = regex.compile(rf"^[^\w{NON_ENGLISH_CHARS}#[【★]+|[ \-:/\\[|{{(#$&^]+$")
    REMAINING_NOT_ALLOWED_SYMBOLS_AT_START_AND_END = regex.compile(rf"^[^\w{NON_ENGLISH_CHARS}#]+|]$")

    cleaned_title = raw_title

    cleaned_title = regex.sub(r"_", " ", raw_title, flags=regex.MULTILINE)
    cleaned_title = regex.sub(r"\[(movie)\]", "", cleaned_title, flags=regex.IGNORECASE)
    cleaned_title = regex.sub(NOT_ALLOWED_SYMBOLS_AT_START_AND_END, "", cleaned_title)
    cleaned_title = regex.sub(RUSSIAN_CAST_REGEX, "", cleaned_title)
    cleaned_title = regex.sub(ALT_TITLES_REGEX, "", cleaned_title)
    cleaned_title = regex.sub(NOT_ONLY_NON_ENGLISH_REGEX, "", cleaned_title)
    cleaned_title = regex.sub(REMAINING_NOT_ALLOWED_SYMBOLS_AT_START_AND_END, "", cleaned_title)
    cleaned_title = cleaned_title.strip()

    return cleaned_title