This code parses a RTF content from your clipboard to a simple LaTeX syntax

pyrtf2latex.py

'''
pyrtf2latex.py
==============

    This  script  was created to copy   rich  text  from  an  office suite
    application and adapt it  for transferring text  formatting, including
    bold,  italic,  subscript,   and superscript content. Additionally, it
    highlights any text enclosed in  parentheses (but maybe you won't need
    this, feel free to modify). You are welcome  to adapt this  script for
    your   own   needs,  but  please  note  that  it  is  designed to work
    exclusively on Linux distributions, as it relies on the xclip tool. In
    this implementation, I opted to convert RTF (Rich Text Format) to HTML
    first   to  facilitate  parsing.   Parsing  HTML  proved to    be more
    straightforward for me, as I  didn't   have  sufficient time  to delve
    deeply  into the complexities of RTF syntax. Feel free  to use, modify
    and redistribute the script as you see fit!
'''
import re
import pyperclip
import subprocess
from pynput import keyboard

CMD1=['xclip', '-selection', 'clipboard']
CMD2=['xclip', '-selection', 'clipboard', '-o', '-t', 'text/html']

def get_clipboard_as_html() -> str:
    try:
        print('copying from clipboard')
        subprocess.run(CMD1, stdout=subprocess.DEVNULL)
        result = subprocess.run(CMD2,
            capture_output=True,
            text=True,
            check=True,
            encoding='utf-8'
        )
        return result.stdout
    except subprocess.CalledProcessError as e:
        print(f'Err: something went wrong during copy: {str(e)}')
        return None

def html_parser(content:str) -> str:
    print('parsing')
    # bold
    content = re.sub(r'<\s*(b|strong)\s*>(.*?)<\s*/\s*(b|strong)\s*>', r'\\textbf{\2}', content, flags=re.DOTALL | re.IGNORECASE)
    # italic
    content = re.sub(r'<\s*(i|em)\s*>(.*?)<\s*/\s*(i|em)\s*>', r'\\textit{\2}', content, flags=re.DOTALL | re.IGNORECASE)
    # subscript
    content = re.sub(r'<\s*sub\s*>(.*?)<\s*/\s*sub\s*>', r'\\textsubscript{\1}', content, flags=re.DOTALL | re.IGNORECASE)
    # superscript
    content = re.sub(r'<\s*sup\s*>(.*?)<\s*/\s*sup\s*>', r'\\textsubscript{\1}', content, flags=re.DOTALL | re.IGNORECASE)
    # paragraphs
    content = re.sub(r'<\s*p\s*>', r'\n', content, flags=re.IGNORECASE) # opening paragraph
    content = re.sub(r'<\s*/\s*p\s*>', r'\n', content, flags=re.IGNORECASE) # closing paragraph
    # i'm highlighting parentesis cases, just for my personal use, you can comment the line below to avoid this
    content = re.sub(r'\((.*?)\)', r'(\\hl{\1})', content)   
    # ignoring the rest
    content = re.sub(r'<[^>]+>', '', content)
    return content

def on_press(key):
    # change here the hotkey for parsing
    if(hasattr(key, 'f9') and key == key.f9):
        cboard = get_clipboard_as_html()
        if cboard:
            pyperclip.copy(test:=html_parser(cboard.replace('\n', ' ')))
            print('ready to paste')
        else:
            print('Something went wrong')
            pyperclip.copy('<<Error on copying check log>>')

def main():
    global listener
    listener = keyboard.Listener(
        on_press=on_press
    )
    listener.start()
    listener.join()

if __name__ == '__main__':
    try:
        print('You need to perform 3 steps:\
               \n  1) Copy content.\
               \n  2) Press F9 to parse from RTF to LaTeX.\
               \n  3) Paste it.\
               \n<This will keep running until you press Ctrl+C, to stop>\n')
        main()
    except KeyboardInterrupt:
        listener.stop()
        print('\nLeaving...')

Requirements:

1. Install xclip tool

2. Create a file named requirements.txt with the content below:

evdev==1.7.1
pynput==1.7.7
pyperclip==1.9.0
python-xlib==0.33
six==1.16.0

3. Run pip install -r requirements.txt, preferable from a virtual environment to avoid messing up your global settings