You can use the Path.glob function from the pathlib standard library module.

For example:

from pathlib import Path

def get_soup(html_file_path):  # added argument
    f = html_file_path.open()
    return BeautifulSoup(f, "lxml")

def get_all_tables(soup):
    return soup.find_all("table")

def get_all_html_files(root_path):
    return Path(root_path).glob("**/*.html")

if __name__ == "__main__":
    html_root = Path("./html_files/")  # This is the folder with the html files

    for html_file in get_all_html_files(html_root):
        soup = get_soup(html_file)
        tables = get_all_tables(soup)

I am still new to coding. I needed to write a code to iterate through a data folder of many html files and execute a predefined function (Extracting specific tables from HTML document). I used bs4 to parse the html file. The proposed solution below allowed to retrieve the files and extract the tables from each html file.

from bs4 import BeautifulSoup
import glob

def get_soup(html_file_path):  
    f = html_file_path.open()
    return BeautifulSoup(f, "lxml")

def get_all_tables(soup):
    return soup.find_all("table")

def get_all_html_files(root_path):
    return Path(root_path).glob("**/*.html")

if __name__ == "__main__":
    html_root = Path("data_file_pathname/")

    soup = get_soup(html_file)

    tables = get_all_tables(soup)
    print(f"[+] Found a total of {len(tables)} tables.")

Thanks