descarga_xml_sunat/get_token_headless.py

import os
import time
import shutil
import platform
from pathlib import Path
from playwright.sync_api import sync_playwright

from get_token import (
    MENU_URL, TOKEN_FILE, SCREENSHOT_DIR,
    fill_login_form, save_token, save_screenshot,
    check_for_token, navigate_sol_menu, extract_token_from_menu,
)
from logger_manager import get_logger

logger = get_logger(__name__)
# ============================================================================
USER_AGENT = (
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:121.0) "
    "Gecko/20100101 Firefox/121.0"
)

# ============================================================================
def firefox_instalado():
    sistema = platform.system().lower()
    if sistema == "windows":
        return bool(shutil.which("firefox")) or any(
            os.path.exists(p) for p in [
                "C:\\Program Files\\Mozilla Firefox\\firefox.exe",
                "C:\\Program Files (x86)\\Mozilla Firefox\\firefox.exe",
            ]
        )
    elif sistema == "darwin":
        return os.path.exists("/Applications/Firefox.app")
    elif sistema == "linux":
        return bool(shutil.which("firefox") or shutil.which("firefox-esr"))
    return False

# ============================================================================
def get_token_headless(timeout=90000):
    with sync_playwright() as p:
        browser = p.firefox.launch(
            headless=True,
        )
        context = browser.new_context(
            viewport={"width": 1280, "height": 800},
            locale="es-PE",
            timezone_id="America/Lima",
            user_agent=USER_AGENT,
        )
        page = context.new_page()
        page.set_default_timeout(timeout)

        logger.info("1. Sesión desde SOL...")
        page.goto("https://www.sunat.gob.pe/sol.html", wait_until="domcontentloaded")

        logger.info("2. Navegando a menú directo...")
        page.goto(MENU_URL, wait_until="domcontentloaded")

        page.wait_for_load_state("networkidle")
        has_inputs = len(page.locator("input[type='password']").all()) > 0
        if has_inputs or any(k in page.url.lower() for k in ["login", "autentica", "auth"]):
            logger.info("3. Login detectado, rellenando credenciales...")
            fill_login_form(page)
            page.keyboard.press("Enter")
            try:
                page.wait_for_load_state("networkidle", timeout=30000)
            except Exception:
                pass
            page.wait_for_timeout(3000)
        else:
            logger.info("3. Sin login (sesión activa)")

        logger.info("4. Buscando token en menú...")
        page.wait_for_timeout(2000)
        token = check_for_token(page)
        if not token:
            token = navigate_sol_menu(page)
        if not token:
            token = extract_token_from_menu(page)

        context.close()
        browser.close()

        if token:
            logger.info("Token obtenido (headless)")
            save_token(token)
            return token

        logger.error("No se encontró token")
        return None

# ============================================================================
if __name__ == "__main__":
    get_token_headless()
# ============================================================================