url-checker.py

#!/usr/bin/env python3
"""
URL Checker — Check if URLs are alive by HTTP status.

Usage:
    python url-checker.py <url> [<url> ...]
    python url-checker.py --file urls.txt
    python url-checker.py --file urls.txt --timeout 10 --concurrent 20

Options:
    --file FILE         Read URLs from file (one per line)
    --timeout SEC       Request timeout in seconds (default: 10)
    --concurrent N      Number of concurrent checks (default: 10)
    --follow-redirects  Follow redirects (default: True)
    --help              Show this help message and exit
"""

import sys
import argparse
from pathlib import Path
from concurrent.futures import ThreadPoolExecutor, as_completed

try:
    import requests
except ImportError:
    print("Error: requests is required. Install with: pip install requests")
    sys.exit(1)


def check_url(url: str, timeout: int, follow: bool) -> dict:
    """Check a single URL and return status info."""
    result = {"url": url, "status": None, "error": None, "redirect": None}
    try:
        resp = requests.get(
            url,
            timeout=timeout,
            allow_redirects=follow,
            headers={"User-Agent": "URL-Checker/1.0"},
        )
        result["status"] = resp.status_code
        if resp.history:
            result["redirect"] = resp.url
    except requests.exceptions.ConnectionError:
        result["error"] = "Connection refused / unreachable"
    except requests.exceptions.Timeout:
        result["error"] = f"Timed out ({timeout}s)"
    except requests.exceptions.TooManyRedirects:
        result["error"] = "Too many redirects"
    except requests.exceptions.MissingSchema:
        result["error"] = "Invalid URL (missing scheme like http://)"
    except Exception as e:
        result["error"] = str(e)
    return result


def status_label(status: int | None) -> str:
    """Return a colored label for an HTTP status code."""
    if status is None:
        return "ERROR"
    if 200 <= status < 300:
        return "ALIVE"
    elif 300 <= status < 400:
        return "REDIR"
    elif 400 <= status < 500:
        return "CLIENT_ERROR"
    elif 500 <= status < 600:
        return "SERVER_ERROR"
    return f"UNKNOWN({status})"


def main():
    parser = argparse.ArgumentParser(
        description="Check if URLs are alive by HTTP status.",
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog=(
            "Examples:\n"
            "  python url-checker.py https://google.com https://github.com\n"
            "  python url-checker.py --file my_urls.txt\n"
            "  python url-checker.py --file urls.txt --concurrent 20 --timeout 5\n"
        ),
    )
    parser.add_argument("urls", nargs="*", help="URL(s) to check")
    parser.add_argument("--file", help="File containing URLs (one per line)")
    parser.add_argument("--timeout", type=int, default=10, help="Request timeout in seconds (default: 10)")
    parser.add_argument("--concurrent", type=int, default=10, help="Concurrent checks (default: 10)")
    parser.add_argument("--follow-redirects", action="store_true", default=True, help="Follow redirects")

    args = parser.parse_args()

    url_list: list[str] = list(args.urls)

    if args.file:
        file_path = Path(args.file)
        if not file_path.is_file():
            print(f"Error: File '{args.file}' not found.")
            sys.exit(1)
        with open(file_path, "r") as f:
            for line in f:
                line = line.strip()
                if line and not line.startswith("#"):
                    url_list.append(line)

    if not url_list:
        print("Error: No URLs provided. Pass them as arguments or with --file.")
        parser.print_help()
        sys.exit(1)

    print(f"Checking {len(url_list)} URL(s) (timeout={args.timeout}s, concurrent={args.concurrent})\n")

    results: list[dict] = []
    with ThreadPoolExecutor(max_workers=args.concurrent) as executor:
        futures = {
            executor.submit(check_url, url, args.timeout, args.follow_redirects): url
            for url in url_list
        }
        for future in as_completed(futures):
            results.append(future.result())

    # Summary
    alive = dead = redirects = errors = 0
    for r in results:
        label = status_label(r["status"])
        if label == "ALIVE":
            alive += 1
        elif label == "REDIR":
            redirects += 1
        elif "error" in r and r["error"]:
            errors += 1
        else:
            dead += 1

        msg = f"  {r['url']:50s} {label}"
        if r["status"]:
            msg += f"  [{r['status']}]"
        if r.get("redirect"):
            msg += f"  → {r['redirect']}"
        if r.get("error"):
            msg += f"  ✗ {r['error']}"
        print(msg)

    print(f"\nSummary: {alive} alive, {redirects} redirects, {dead} dead, {errors} errors "
          f"(out of {len(results)})")


if __name__ == "__main__":
    main()