stress_test_all.py

"""
PRUEBA DE ESTRES COMPLETA - 998 URLs
"""
import csv
import time
import json
from datetime import datetime
from oreillyauto_scraper import OReillyAutoScraper

def main():
    # Leer URLs del CSV
    urls = []
    with open("orreily - Sheet1.csv", "r") as f:
        reader = csv.DictReader(f)
        for row in reader:
            urls.append(row["url"])

    print("=" * 70)
    print(f"PRUEBA DE ESTRES - {len(urls)} URLs")
    print(f"Inicio: {datetime.now().strftime('%H:%M:%S')}")
    print("=" * 70)

    results = {
        "success": 0,
        "fail": 0,
        "errors": []
    }

    start_time = time.time()

    for i, url in enumerate(urls):
        scraper = OReillyAutoScraper()
        html = scraper.scrape(url)

        if html and len(html) > 1000:
            results["success"] += 1
            status = "OK"
            info = scraper.extract_product_info(html)
            title = info.get("title", "")[:30] if info else ""
        else:
            results["fail"] += 1
            status = "FAIL"
            title = ""
            results["errors"].append(url)

        # Mostrar progreso cada 10 URLs
        if (i + 1) % 10 == 0 or i == 0:
            elapsed = time.time() - start_time
            rate = (i + 1) / elapsed if elapsed > 0 else 0
            eta = (len(urls) - i - 1) / rate if rate > 0 else 0
            print(f"[{i+1:4}/{len(urls)}] {status:4} | {results['success']:3} OK | {results['fail']:3} FAIL | {rate:.1f}/s | ETA: {eta:.0f}s | {title}")

        time.sleep(0.5)  # 0.5s entre requests

    elapsed = time.time() - start_time

    print("\n" + "=" * 70)
    print("RESUMEN FINAL")
    print("=" * 70)
    print(f"Total URLs: {len(urls)}")
    print(f"Exitosos:   {results['success']} ({results['success']*100/len(urls):.1f}%)")
    print(f"Fallidos:   {results['fail']} ({results['fail']*100/len(urls):.1f}%)")
    print(f"Tiempo:     {elapsed:.1f}s ({elapsed/60:.1f} min)")
    print(f"Velocidad:  {len(urls)/elapsed:.2f} URLs/segundo")

    # Guardar resultados
    with open("captures/stress_test_results.json", "w") as f:
        json.dump(results, f, indent=2)

    print(f"\nResultados guardados en captures/stress_test_results.json")


if __name__ == "__main__":
    main()