main.py

import argparse
import sys
from src.crawler import Crawler
from src.analyzer import ImageAnalyzer
from src.reporter import generate_json_report, generate_html_report

def main():
    parser = argparse.ArgumentParser(description="Web Image Alt Text Checker (Whole Domain)")
    parser.add_argument("url", help="The Start URL of the domain to crawl (e.g. https://example.com)")
    parser.add_argument("--output", choices=['json', 'html', 'both'], default='html', help="Report output format")
    parser.add_argument("--limit", type=int, default=100, help="Max pages to crawl (default 100)")
    args = parser.parse_args()

    # Crawl
    print(f"Starting domain crawl from: {args.url}")
    crawler = Crawler()
    site_data, total_discovered, blocked_reason = crawler.crawl_domain(args.url, max_pages=args.limit)
    
    if not site_data and blocked_reason:
        print(f"\n[!] CRAWL BLOCKED: {blocked_reason}")
        # Proceed to generate report even if empty to show the block status
    elif not site_data:
        print("No data crawled. Please check the URL and try again.")
        sys.exit(1)

    print(f"Crawl complete. Scanned {len(site_data)} pages.")

    # Analyze
    print("Analyzing images for missing alt text...")
    analyzer = ImageAnalyzer()
    results = analyzer.analyze_site(site_data)
    
    # Add discovery stats to summary
    results['summary']['total_pages_discovered'] = total_discovered
    results['summary']['blocked_reason'] = blocked_reason
    results['summary']['crawl_blocked'] = bool(blocked_reason)

    # Report
    print("Generating reports...")
    if args.output in ['json', 'both']:
        generate_json_report(results, "seo_report.json")
    if args.output in ['html', 'both']:
        generate_html_report(results, "seo_report.html")

    summary = results['summary']
    print("\n--- Summary ---")
    if summary.get('crawl_blocked'):
        print(f"STATUS: BLOCKED ({summary['blocked_reason']})")
        print("Results are likely incomplete.")
        
    print(f"Total Pages Discovered: {summary['total_pages_discovered']}")
    print(f"Pages Scanned: {summary['total_pages_scanned']}")
    print(f"Total Images: {summary['total_images_found']}")
    print(f"Images Missing Alt: {summary['total_images_missing_alt']}")
    
    if summary['total_images_missing_alt'] > 0:
        print("Please check the generated report for details.")
    elif not summary.get('crawl_blocked'):
        print("All images have alt text! Great job.")

if __name__ == "__main__":
    main()