import requests
from bs4 import BeautifulSoup
import re

def extract_text_from_url(url:str) -> dict:
    # Step 1: Fetch the webpage content
    response = requests.get(url)
    if response.status_code != 200:
        return {
            "statusCode" : response.status_code,
            "url" : url
            }

    # Step 2: Parse the HTML content
    soup = BeautifulSoup(response.text, 'html.parser')

    # Step 3: Extract text from the entire document
    text = soup.get_text(separator='\n')
    
    return {
            "statusCode" : response.status_code,
            "url" : url,
            "content" : re.sub(r'\s+', ' ', text.replace('\n', ' '))
            }