#!/usr/bin/env python3
"""
Fetch a web page with proper headers and error handling.

Usage:
    python fetch_page.py https://example.com
    python fetch_page.py https://example.com --output page.html
"""

import argparse
import sys

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

try:
    from lib.safe_http import DEFAULT_HEADERS, normalize_url, safe_get
except ImportError:
    from scripts.lib.safe_http import DEFAULT_HEADERS, normalize_url, safe_get


def fetch_page(
    url: str,
    timeout: int = 30,
    follow_redirects: bool = True,
    max_redirects: int = 5,
) -> dict:
    """
    Fetch a web page and return response details.

    Args:
        url: The URL to fetch
        timeout: Request timeout in seconds
        follow_redirects: Whether to follow redirects
        max_redirects: Maximum number of redirects to follow

    Returns:
        Dictionary with:
            - url: Final URL after redirects
            - status_code: HTTP status code
            - content: Response body
            - headers: Response headers
            - redirect_chain: List of redirect URLs
            - error: Error message if failed
    """
    result = {
        "url": url,
        "status_code": None,
        "content": None,
        "headers": {},
        "redirect_chain": [],
        "error": None,
    }

    try:
        url = normalize_url(url)

        response = safe_get(
            url,
            headers=DEFAULT_HEADERS,
            timeout=timeout,
            allow_redirects=follow_redirects,
            max_redirects=max_redirects,
        )

        result["url"] = response.url
        result["status_code"] = response.status_code
        result["content"] = response.text
        result["headers"] = dict(response.headers)

        # Track redirect chain
        if response.history:
            result["redirect_chain"] = [r.url for r in response.history]

    except requests.exceptions.Timeout:
        result["error"] = f"Request timed out after {timeout} seconds"
    except requests.exceptions.TooManyRedirects:
        result["error"] = f"Too many redirects (max {max_redirects})"
    except requests.exceptions.SSLError as e:
        result["error"] = f"SSL error: {e}"
    except requests.exceptions.ConnectionError as e:
        result["error"] = f"Connection error: {e}"
    except requests.exceptions.RequestException as e:
        result["error"] = f"Request failed: {e}"

    return result


def main():
    parser = argparse.ArgumentParser(description="Fetch a web page for SEO analysis")
    parser.add_argument("url", help="URL to fetch")
    parser.add_argument("--output", "-o", help="Output file path")
    parser.add_argument("--timeout", "-t", type=int, default=30, help="Timeout in seconds")
    parser.add_argument("--no-redirects", action="store_true", help="Don't follow redirects")

    args = parser.parse_args()

    result = fetch_page(
        args.url,
        timeout=args.timeout,
        follow_redirects=not args.no_redirects,
    )

    if result["error"]:
        print(f"Error: {result['error']}", file=sys.stderr)
        sys.exit(1)

    if args.output:
        with open(args.output, "w", encoding="utf-8") as f:
            f.write(result["content"])
        print(f"Saved to {args.output}")
    else:
        print(result["content"])

    # Print metadata to stderr
    print(f"\nURL: {result['url']}", file=sys.stderr)
    print(f"Status: {result['status_code']}", file=sys.stderr)
    if result["redirect_chain"]:
        print(f"Redirects: {' -> '.join(result['redirect_chain'])}", file=sys.stderr)


if __name__ == "__main__":
    main()