import requests
from bs4 import BeautifulSoup


def scrape_url(url: str, timeout: int = 15) -> tuple[str, str]:
    """
    Fetch a URL and return (title, plain_text).
    Raises requests.RequestException on network errors.
    """
    headers = {
        "User-Agent": (
            "Mozilla/5.0 (compatible; KIContextTool/1.0; "
            "+https://github.com/user/ki-context-tool)"
        )
    }
    resp = requests.get(url, headers=headers, timeout=timeout)
    resp.raise_for_status()

    soup = BeautifulSoup(resp.text, "html.parser")

    # Remove script/style noise
    for tag in soup(["script", "style", "nav", "footer", "header", "aside"]):
        tag.decompose()

    title = soup.title.string.strip() if soup.title and soup.title.string else url

    # Extract readable text
    text = soup.get_text(separator="\n", strip=True)
    # Collapse excessive blank lines
    lines = [line for line in text.splitlines() if line.strip()]
    return title, "\n".join(lines)