main.py

#!/usr/bin/env python3
"""Main entry point for Blocket scraper."""

import argparse
import os
import sys

from config import (
    CATEGORIES,
    DEFAULT_CATEGORIES,
    OUTPUT_DIR,
    DEFAULT_CSV_FILE,
    DEFAULT_JSON_FILE,
)
from scraper import BlocketScraper


def main():
    """Main function to run the scraper."""
    parser = argparse.ArgumentParser(
        description="Scrape listings from Blocket.se marketplace",
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
Examples:
  python main.py                           # Scrape default categories (phones, electronics)
  python main.py -c phones -p 3            # Scrape phones category, 3 pages
  python main.py -c phones computers       # Scrape multiple categories
  python main.py --list-categories         # List all available categories
  python main.py -o my_results.csv         # Custom output filename
        """,
    )

    parser.add_argument(
        "-c",
        "--categories",
        nargs="+",
        default=DEFAULT_CATEGORIES,
        help=f"Categories to scrape (default: {DEFAULT_CATEGORIES})",
    )

    parser.add_argument(
        "-p",
        "--pages",
        type=int,
        default=2,
        help="Maximum pages per category (default: 2)",
    )

    parser.add_argument(
        "-d",
        "--delay",
        type=float,
        default=1.0,
        help="Delay between requests in seconds (default: 1.0)",
    )

    parser.add_argument(
        "-o",
        "--output",
        default=DEFAULT_CSV_FILE,
        help=f"Output CSV filename (default: {DEFAULT_CSV_FILE})",
    )

    parser.add_argument(
        "--json",
        action="store_true",
        help="Also export to JSON format",
    )

    parser.add_argument(
        "--list-categories",
        action="store_true",
        help="List all available categories and exit",
    )

    parser.add_argument(
        "--api-key",
        help="ScrapingAnt API key (or set SCRAPINGANT_API_KEY env var)",
    )

    args = parser.parse_args()

    # List categories if requested
    if args.list_categories:
        print("Available categories:")
        print("-" * 40)
        for key, value in sorted(CATEGORIES.items()):
            print(f"  {key:<20} ({value})")
        return 0

    # Validate categories
    invalid_categories = [c for c in args.categories if c not in CATEGORIES]
    if invalid_categories:
        print(f"Error: Unknown categories: {invalid_categories}")
        print(f"Use --list-categories to see available categories")
        return 1

    # Initialize scraper
    try:
        scraper = BlocketScraper(api_key=args.api_key)
    except ValueError as e:
        print(f"Error: {e}")
        return 1

    # Run scraper
    print(f"Scraping categories: {args.categories}")
    print(f"Max pages per category: {args.pages}")
    print("-" * 40)

    total = scraper.scrape_categories(
        categories=args.categories,
        max_pages=args.pages,
        delay=args.delay,
    )

    print("-" * 40)
    print(f"Total listings scraped: {total}")

    if total > 0:
        # Export to CSV
        csv_path = os.path.join(OUTPUT_DIR, args.output)
        scraper.export_csv(csv_path)

        # Export to JSON if requested
        if args.json:
            json_filename = args.output.replace(".csv", ".json")
            if json_filename == args.output:
                json_filename = DEFAULT_JSON_FILE
            json_path = os.path.join(OUTPUT_DIR, json_filename)
            scraper.export_json(json_path)

    return 0


if __name__ == "__main__":
    sys.exit(main())