Get Harvard sentences as separate lists

output_dir = "/Users/joregan/Playing/spoken-sentence-transformers/harvard"

URL = "https://www.cs.columbia.edu/%7Ehgs/audio/harvard.html"

import requests
from bs4 import BeautifulSoup

req = requests.get(URL)
soup = BeautifulSoup(req.text, "html.parser")

lists = []
for list in soup.find_all("ol"):
    current = []
    for item in list.find_all("li"):
        current.append(item.text)
    lists.append(current)

from pathlib import Path

BASE = Path(output_dir)
for i, sentences in enumerate(lists, start=1):
    with open(BASE / f"harvard-{i}.txt", "w") as f:
        for sentence in sentences:
            f.write(sentence + "\n")