import argparse
import requests
import csv
import time

def get_parser():
    """Parse command-line arguments."""
    parser = argparse.ArgumentParser(description='URL Health Checker')
    parser.add_argument('--input', default='urls.txt', help='Input file with URLs')
    parser.add_argument('--output', default='results.csv', help='Output CSV file')
    parser.add_argument('--timeout', type=int, default=5, help='Request timeout in seconds')
    parser.add_argument('--retries', type=int, default=3, help='Number of retries')
    return parser

def read_urls(file_path):
    """Read URLs from a file, ignoring empty lines and comments."""
    urls = []
    with open(file_path, 'r') as f:
        for line in f:
            line = line.strip()
            if not line or line.startswith('#'):
                continue
            urls.append(line)
    return urls

def check_url(url, timeout, retries):
    """Check a single URL with retries and return result."""
    result = {
        'url': url,
        'status_code': None,
        'response_time_ms': None,
        'success': False
    }
    
    for attempt in range(retries + 1):  # +1 to include the initial attempt
        try:
            start_time = time.time()
            response = requests.get(url, timeout=timeout)
            elapsed = (time.time() - start_time) * 1000
            
            if 200 <= response.status_code < 300:
                result['status_code'] = response.status_code
                result['response_time_ms'] = elapsed
                result['success'] = True
                break  # Success, exit loop
            else:
                # Non-2xx response; retry if not last attempt
                if attempt < retries:
                    continue
                else:
                    # Last attempt, record failure
                    result['status_code'] = response.status_code
                    result['response_time_ms'] = elapsed
                    result['success'] = False
                    break
        except requests.exceptions.RequestException as e:
            # Network error (e.g., connection timeout, DNS issue)
            elapsed = (time.time() - start_time) * 1000
            result['status_code'] = 0  # Indicate exception occurred
            result['response_time_ms'] = elapsed
            result['success'] = False
            if attempt < retries:
                continue
            else:
                break  # No more retries, record failure
    
    return result

def main():
    parser = get_parser()
    args = parser.parse_args()
    
    urls = read_urls(args.input)
    results = []
    
    for url in urls:
        result = check_url(url, args.timeout, args.retries)
        results.append(result)
    
    # Write results to CSV
    with open(args.output, mode='w', newline='') as file:
        fieldnames = ['url', 'status_code', 'response_time_ms', 'success']
        writer = csv.DictWriter(file, fieldnames=fieldnames)
        writer.writeheader()
        for row in results:
            writer.writerow(row)
    
    # Summary statistics
    total = len(results)
    successful = sum(1 for r in results if r['success'])
    failed = total - successful
    total_response_time = sum(r['response_time_ms'] for r in results)
    average = total_response_time / total if total else 0
    
    print("\nSummary:")
    print(f"Total URLs checked: {total}")
    print(f"Successful requests: {successful}")
    print(f"Failed requests: {failed}")
    print(f"Average response time: {average:.2f} ms")

if __name__ == '__main__':
    main()