import requests
from bs4 import BeautifulSoup
import string

def fetch_article_text(url: str):

    r = requests.get(url)
    soup = BeautifulSoup(r.text, "html.parser")
    results = soup.find_all(["h1", "p"])
    text = [result.text for result in results]
    ARTICLE = " ".join(text)
    ARTICLE = ARTICLE.replace(".", ".<eos>")
    ARTICLE = ARTICLE.replace("!", "!<eos>")
    ARTICLE = ARTICLE.replace("?", "?<eos>")
    sentences = ARTICLE.split("<eos>")
    current_chunk = 0
    chunks = []
    for sentence in sentences:
        if len(chunks) == current_chunk + 1:
            if len(chunks[current_chunk]) + len(sentence.split(" ")) <= 500:
                chunks[current_chunk].extend(sentence.split(" "))
            else:
                current_chunk += 1
                chunks.append(sentence.split(" "))
        else:
            print(current_chunk)
            chunks.append(sentence.split(" "))

    for chunk_id in range(len(chunks)):
        chunks[chunk_id] = " ".join(chunks[chunk_id])

    return ARTICLE, chunks

def count_tokens(text: str):
    return len(text.split(" "))