# __main__.py
import sys
import pandas as pd
import time
from crawler.scraper import fetch_and_parse
from crawler.utils import log


def main():
    if len(sys.argv) < 3:
        print("Usage: python -m crawler <urls.txt> <output.xlsx>")
        sys.exit(1)

    url_file = sys.argv[1]
    output_file = sys.argv[2]

    log.info(f"Lade URL-Liste aus {url_file}")

    with open(url_file, "r", encoding="utf-8") as f:
        urls = [line.strip() for line in f if line.strip()]

    results = []

    for url in urls:
        try:
            data = fetch_and_parse(url)
            results.append(data)
        except Exception as e:
            log.error(f"Fehler bei {url}: {e}")
        time.sleep(1)

    df = pd.DataFrame(results)
    df.to_excel(output_file, index=False)

    log.info(f"Fertig! Datei gespeichert: {output_file}")

if __name__ == "__main__":
    main()