some ugly little snippet to find toc from isbn13

crawl_isbn.py

#!/usr/bin/env python3

from aiohttp import ClientSession as Session
from asyncio import run
from bs4 import BeautifulSoup as Soup
from pprint import pprint
from sys import argv

yes24 = "http://www.yes24.com"


async def query(session: Session, url: str) -> Soup:
    async with session.get(url) as res:
        html = await res.text()
        return Soup(html, "html.parser")

async def main(isbn: int):
    querystr = f"{yes24}/product/search?query={isbn}"
    async with Session() as ses:
        soup = await query(ses, querystr)
        books = soup.find("div", class_="itemUnit")
        anchor = books.find("a", class_="gd_name")
        product = f"{yes24}/{anchor['href']}"

        book = await query(ses, product)
        toc_html = book.find("div", id="infoset_toc")
        
        # TODO: fix here
        toc_text = toc_html.find("textarea", class_="txtContentText").text
        pprint(toc_text.split("__"))

if __name__ == "__main__":
    run(main(argv[1]))