#!/usr/bin/env python3
"""Extract CNES hospital table from DATASUS."""

import csv
import sys
import requests
from bs4 import BeautifulSoup

URL = "https://cnes2.datasus.gov.br/Mod_Ind_Unidade_Listar.asp?VTipo=05&VListar=1&VEstado=31&VMun=&VSubUni=&VComp=201412"
OUTPUT = "cnes_hospitais.csv"


def fetch(url: str) -> BeautifulSoup:
    headers = {
        "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36"
    }
    r = requests.get(url, headers=headers, timeout=30)
    r.encoding = "iso-8859-1"
    return BeautifulSoup(r.text, "html.parser")


def extract_table(soup: BeautifulSoup) -> tuple[list[str], list[list[str]]]:
    # Target the bordered data table (not layout tables)
    table = soup.find("table", {"border": "1"})
    if not table:
        raise ValueError("Tabela não encontrada na página.")

    rows = table.find_all("tr")
    if not rows:
        raise ValueError("Nenhuma linha encontrada na tabela.")

    headers = [th.get_text(strip=True) for th in rows[0].find_all("td")]
    data = []
    for row in rows[1:]:
        cells = [td.get_text(strip=True) for td in row.find_all("td")]
        if cells:
            data.append(cells)

    return headers, data


def save_csv(headers: list[str], data: list[list[str]], path: str) -> None:
    with open(path, "w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f)
        writer.writerow(headers)
        writer.writerows(data)


def main() -> None:
    print(f"Buscando: {URL}")
    soup = fetch(URL)

    headers, data = extract_table(soup)
    print(f"Colunas: {headers}")
    print(f"Linhas: {len(data)}")

    save_csv(headers, data, OUTPUT)
    print(f"Salvo em: {OUTPUT}")


if __name__ == "__main__":
    try:
        main()
    except Exception as e:
        print(f"Erro: {e}", file=sys.stderr)
        sys.exit(1)