#!/usr/bin/env python3
"""
诊断脚本：验证图片 URL 和 Word 文档 URL 是否可访问
"""

import urllib.request
import requests
import sys
from typing import Dict, List, Tuple


def check_url(url: str, headers: Dict[str, str] = None, timeout: int = 10) -> Tuple[bool, str, int]:
    """
    检查 URL 是否可访问
    
    Args:
        url: 要检查的 URL
        headers: HTTP 头
        timeout: 超时时间（秒）
    
    Returns:
        (is_valid, error_message, status_code)
    """
    if headers is None:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
            'Accept': '*/*',
        }
    
    try:
        req = urllib.request.Request(url, headers=headers)
        with urllib.request.urlopen(req, timeout=timeout) as response:
            status_code = response.getcode()
            content_type = response.headers.get('Content-Type', '')
            
            # 读取前 100 字节检查
            preview = response.read(100)
            
            # 检查是否为 HTML 错误页面
            if b'<html' in preview.lower() or b'<!doctype' in preview.lower():
                error_msg = f"返回 HTML 页面（状态码: {status_code}）"
                if b'404' in preview.lower():
                    error_msg = "返回 404 错误页面"
                elif b'403' in preview.lower():
                    error_msg = "返回 403 禁止访问页面"
                return (False, error_msg, status_code)
            
            # 检查内容类型
            if 'image' in content_type:
                return (True, f"图片 - {content_type}", status_code)
            elif 'application/vnd.openxmlformats-officedocument.wordprocessingml.document' in content_type or 'application/msword' in content_type:
                return (True, f"Word 文档 - {content_type}", status_code)
            else:
                return (True, f"其他类型 - {content_type}", status_code)
                
    except urllib.error.HTTPError as e:
        status_code = e.code
        error_msg = f"HTTP 错误 {status_code}"
        if status_code == 404:
            error_msg = "404 Not Found - 资源不存在"
        elif status_code == 403:
            error_msg = "403 Forbidden - 禁止访问"
        elif status_code == 401:
            error_msg = "401 Unauthorized - 需要认证"
        return (False, error_msg, status_code)
    except urllib.error.URLError as e:
        return (False, f"网络错误: {str(e)[:100]}", 0)
    except Exception as e:
        return (False, f"未知错误: {str(e)[:100]}", 0)


def main():
    # 测试 URL 列表
    image_urls = [
        "https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/18/69baa4f5-4826-4901-00e1-c6e66f02947f.jpg?x-oss-process=image/resize,w_1000",
        "https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6ff235a12b2.jpg?x-oss-process=image/resize,w_1000",
        "https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c7055a396422.jpg?x-oss-process=image/resize,w_1000",
        "https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6fe7f9c07ef.jpg?x-oss-process=image/resize,w_1000",
        "https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c70052d895e3.jpg?x-oss-process=image/resize,w_1000",
        "https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6fc6ca7c4bf.png?x-oss-process=image/resize,w_1000",
        "https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c33f31-4826-4901-00e1-c6fb50697e06.png?x-oss-process=image/resize,w_1000",
        "https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/23/69c1029b-4826-4901-00e1-c6f614bc06d9.jpg?x-oss-process=image/resize,w_1000",
        "https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6fd479e0a0e.jpg?x-oss-process=image/resize,w_1000",
        "https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/23/69c1029b-4826-4901-00e1-c6f569b31a14.jpeg?x-oss-process=image/resize,w_1000",
    ]
    
    doc_url = "https://dpc-oss.23544.com/umsupload/2026/03/25/69c353d0-4826-4901-00e1-c7081bcab988.docx"
    
    print("=" * 80)
    print("图片 URL 诊断")
    print("=" * 80)
    
    valid_count = 0
    invalid_count = 0
    
    for i, url in enumerate(image_urls, 1):
        is_valid, msg, status_code = check_url(url)
        status = "✅ 有效" if is_valid else "❌ 无效"
        print(f"{i}. {status} - {msg}")
        print(f"   URL: {url}")
        print(f"   状态码: {status_code}")
        print()
        
        if is_valid:
            valid_count += 1
        else:
            invalid_count += 1
    
    print("=" * 80)
    print(f"汇总: {valid_count} 个有效，{invalid_count} 个无效")
    print("=" * 80)
    print()
    
    print("=" * 80)
    print("Word 文档 URL 诊断")
    print("=" * 80)
    
    is_valid, msg, status_code = check_url(doc_url)
    status = "✅ 有效" if is_valid else "❌ 无效"
    print(f"{status} - {msg}")
    print(f"URL: {doc_url}")
    print(f"状态码: {status_code}")
    print()
    
    if invalid_count > 0:
        print("=" * 80)
        print("⚠️  警告：部分 URL 无法访问")
        print("=" * 80)
        print("可能的原因：")
        print("1. URL 已过期（阿里云 OSS 签名 URL 有时效性）")
        print("2. 访问权限不足（需要认证或 IP 白名单）")
        print("3. 网络连接问题（Docker 容器网络配置）")
        print("4. 文件已被删除或移动")
        print()
        print("建议：")
        print("- 检查这些 URL 是否在浏览器中可以访问")
        print("- 如果使用签名 URL，确保 URL 未过期")
        print("- 检查 Docker 容器的网络配置和 DNS 设置")
        print("- 考虑使用公开可访问的 URL 或配置 OSS 访问权限")
        sys.exit(1)
    else:
        print("✅ 所有 URL 均可访问")
        sys.exit(0)


if __name__ == "__main__":
    main()