Final Version

util.py

import html
import re
import copy


def parse_markdown_from_update(update):
    entities = copy.deepcopy(parse_entities_from_update(update))
    text = escape_markdown(message_text_from_update(update))

    for e in entities:
        modified = None
        pos = e.offset
        length = e.length

        if e.type == "text_link":
            text = "{}[{}]({}){}".format(text[:pos], text[pos:pos + length], e.url, text[pos + length:])
            modified = 4 + len(e.url)
        elif e.type == "bold":
            text = text[:pos] + '*' + text[pos:pos + length] + '*' + text[pos + length:]
            modified = 2
        elif e.type == "italic":
            text = text[:pos] + '_' + text[pos:pos + length] + '_' + text[pos + length:]
            modified = 2
        elif e.type == "code":
            text = text[:pos] + '`' + text[pos:pos + length] + '`' + text[pos + length:]
            modified = 2
        elif e.type == "pre":
            text = text[:pos] + '```\n' + text[pos:pos + length] + '\n```' + text[pos + length:]
            modified = 6
        else:
            print("Type of entity `{}` is not supported.".format(e.type))

        # update offsets of all entities to the right
        if modified:
            for other in entities:
                if other.offset > pos:
                    other.offset += modified
    return text


def parse_html_from_update(update):
    entities = copy.deepcopy(parse_entities_from_update(update))
    text = escape_html(message_text_from_update(update))

    for e in entities:
        modified = None
        pos = e.offset
        length = e.length

        if e.type == "text_link":
            text = '{}<a href="{}">{}</a>{}'.format(text[:pos], e.url, text[pos:pos + length], text[pos + length:])
            modified = 15 + len(e.url)
        elif e.type == "bold":
            text = text[:pos] + '<b>' + text[pos:pos + length] + '</b>' + text[pos + length:]
            modified = 7
        elif e.type == "italic":
            text = text[:pos] + '<i>' + text[pos:pos + length] + '</i>' + text[pos + length:]
            modified = 7
        elif e.type == "code":
            text = text[:pos] + '<code>' + text[pos:pos + length] + '</code>' + text[pos + length:]
            modified = 13
        elif e.type == "pre":
            text = text[:pos] + '<pre>' + text[pos:pos + length] + '</pre>' + text[pos + length:]
            modified = 11
        else:
            print("Type of entity `{}` is not supported.".format(e.type))

        # update offsets of all entities to the right
        if modified:
            for other in entities:
                if other.offset > pos:
                    other.offset += modified
    return text


def escape_markdown(text):
    """Helper function to escape telegram markup symbols"""
    escape_chars = '\*_`\['
    return re.sub(r'([%s])' % escape_chars, r'\\\1', text)


def escape_html(text):
    return html.escape(text)


def parse_entities_from_update(update):
    try:
        return update.message.parse_entities()
    except (NameError, AttributeError):
        try:
            return update.callback_query.message.parse_entities()
        except (NameError, AttributeError):
            return None


def message_text_from_update(update):
    try:
        return update.message.text
    except (NameError, AttributeError):
        try:
            return update.callback_query.message.text
        except (NameError, AttributeError):
            return None