from playwright.sync_api import sync_playwright
from dubizzle_scraper.scraper import DUBIZZLEScraper
from dubizzle_scraper.parsing.parser import VehicleParser
import json
import re

url = 'https://www.dubizzle.com/VehicleDetail/45394480~US'
out = {}
with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    page = browser.new_page()
    page.goto(url, wait_until='commit', timeout=60000)
    try:
        page.wait_for_load_state('domcontentloaded', timeout=5000)
    except Exception:
        pass
    try:
        page.wait_for_selector("#VehicleDetailViewModel, .veh-details, .vehicle-details, [data-uname='vehicleDetailPage']", timeout=1000)
    except Exception:
        pass
    html = page.content()
    try:
        dom_text = page.evaluate("() => document.body?.textContent || ''")
    except Exception:
        dom_text = ''
    title = page.title()
    js_data = {}
    try:
        js_data = page.evaluate(DUBIZZLEScraper._JS_EXTRACT) or {}
    except Exception:
        js_data = {'eval_error': True}
    hints = VehicleParser._dom_hints(dom_text)
    out = {
        'final_url': page.url,
        'title': title,
        'html_len': len(html),
        'dom_text_len': len(dom_text),
        'selector_present': any(token in html for token in ['VehicleDetailViewModel', 'veh-details', 'vehicle-details', 'vehicleDetailPage']),
        'js_ok': bool(js_data.get('ok')),
        'js_keys': sorted(list(js_data.keys()))[:20],
        'dom_hints': hints,
        'dom_text_preview': re.sub(r'\s+', ' ', dom_text)[:1500],
        'html_preview': re.sub(r'\s+', ' ', html)[:2000],
    }
    browser.close()
print(json.dumps(out, ensure_ascii=False))