commit

2026-01-06 19:36:42 +08:00
parent 15b579d64a
commit 19942144fb
261 changed files with 24034 additions and 5477 deletions
--- a/backend/test_cookie_format_fix.py
+++ b/backend/test_cookie_format_fix.py
@@ -0,0 +1,313 @@
+"""
+测试Cookie格式处理修复
+验证scheduler.py中的_format_cookies方法能正确处理各种Cookie格式
+"""
+import json
+from typing import List, Dict
+
+
+def _format_cookies(cookies) -> List[Dict]:
+    """
+    格式化Cookie，只处理非标准格式的Cookie
+    对于Playwright原生格式的Cookie，直接返回，不做任何修改
+    
+    这是scheduler.py中_format_cookies方法的副本，用于独立测试
+    
+    Args:
+        cookies: Cookie数据，支持list[dict]或dict格式
+    
+    Returns:
+        格式化后的Cookie列表
+    """
+    # 如果是字典格式(键值对)，转换为列表格式
+    if isinstance(cookies, dict):
+        cookies = [
+            {
+                "name": name,
+                "value": str(value) if not isinstance(value, str) else value,
+                "domain": ".xiaohongshu.com",
+                "path": "/"
+            }
+            for name, value in cookies.items()
+        ]
+    
+    # 验证是否为列表
+    if not isinstance(cookies, list):
+        raise ValueError(f"Cookie必须是列表或字典格式，当前类型: {type(cookies).__name__}")
+    
+    # 检查是否是Playwright原生格式（包含name和value字段）
+    if cookies and isinstance(cookies[0], dict) and 'name' in cookies[0] and 'value' in cookies[0]:
+        # 已经是Playwright格式，直接返回，不做任何修改
+        return cookies
+    
+    # 其他格式，进行基础验证
+    formatted_cookies = []
+    for cookie in cookies:
+        if not isinstance(cookie, dict):
+            raise ValueError(f"Cookie元素必须是字典格式，当前类型: {type(cookie).__name__}")
+        
+        # 确保有基本字段
+        if 'domain' not in cookie and 'url' not in cookie:
+            cookie = cookie.copy()
+            cookie['domain'] = '.xiaohongshu.com'
+        if 'path' not in cookie and 'url' not in cookie:
+            if 'domain' in cookie or 'url' not in cookie:
+                cookie = cookie.copy() if cookie is cookies[cookies.index(cookie)] else cookie
+                cookie['path'] = '/'
+        
+        formatted_cookies.append(cookie)
+    
+    return formatted_cookies
+
+
+def test_format_cookies():
+    """测试_format_cookies方法"""
+    
+    print("="*60)
+    print("测试 Cookie 格式处理")
+    print("="*60)
+    
+    # 测试1: 字典格式(键值对)
+    print("\n测试 1: 字典格式(键值对)")
+    cookies_dict = {
+        "a1": "xxx",
+        "webId": "yyy",
+        "web_session": "zzz"
+    }
+    try:
+        result = _format_cookies(cookies_dict)
+        print(f"✅ 成功处理字典格式")
+        print(f"   输入: {type(cookies_dict).__name__} with {len(cookies_dict)} items")
+        print(f"   输出: {type(result).__name__} with {len(result)} items")
+        print(f"   第一个Cookie: {result[0]}")
+        assert isinstance(result, list)
+        assert len(result) == 3
+        assert all('name' in c and 'value' in c and 'domain' in c for c in result)
+    except Exception as e:
+        print(f"❌ 失败: {str(e)}")
+    
+    # 测试2: 列表格式(完整格式，已有domain和path)
+    print("\n测试 2: 列表格式(完整格式)")
+    cookies_list_full = [
+        {
+            "name": "a1",
+            "value": "xxx",
+            "domain": ".xiaohongshu.com",
+            "path": "/",
+            "expires": -1,
+            "httpOnly": False,
+            "secure": False,
+            "sameSite": "Lax"
+        }
+    ]
+    try:
+        result = _format_cookies(cookies_list_full)
+        print(f"✅ 成功处理完整列表格式")
+        print(f"   输入: {type(cookies_list_full).__name__} with {len(cookies_list_full)} items")
+        print(f"   输出: {type(result).__name__} with {len(result)} items")
+        # 验证Playwright原生格式被完整保留
+        print(f"   保留的字段: {list(result[0].keys())}")
+        assert result == cookies_list_full, "Playwright原生格式应该被完整保留，不做任何修改"
+        assert 'expires' in result[0], "expires字段应该被保留"
+        assert result[0]['expires'] == -1, "expires=-1应该被保留"
+        assert isinstance(result, list)
+        assert len(result) == 1
+    except Exception as e:
+        print(f"❌ 失败: {str(e)}")
+    
+    # 测试3: 非Playwright格式（缺少name字段，需要补充domain和path）
+    print("\n测试 3: 非Playwright格式（缺少字段，需要补充）")
+    cookies_list_partial = [
+        {
+            "cookie_name": "a1",  # 没有name字段，不是Playwright格式
+            "cookie_value": "xxx"
+        }
+    ]
+    try:
+        result = _format_cookies(cookies_list_partial)
+        print(f"✅ 成功处理非Playwright格式")
+        print(f"   输入: {type(cookies_list_partial).__name__} with {len(cookies_list_partial)} items")
+        print(f"   输出: {type(result).__name__} with {len(result)} items")
+        print(f"   自动添加的字段: domain={result[0].get('domain')}, path={result[0].get('path')}")
+        assert isinstance(result, list)
+        # 应该自动添加domain和path
+        assert result[0]['domain'] == '.xiaohongshu.com'
+        assert result[0]['path'] == '/'
+    except Exception as e:
+        print(f"❌ 失败: {str(e)}")
+    
+    # 测试4: 双重JSON编码(模拟数据库存储场景)
+    print("\n测试 4: 双重JSON编码字符串")
+    cookies_dict = {"a1": "xxx", "webId": "yyy"}
+    # 第一次JSON编码
+    cookies_json_1 = json.dumps(cookies_dict)
+    # 第二次JSON编码
+    cookies_json_2 = json.dumps(cookies_json_1)
+    
+    print(f"   原始字典: {cookies_dict}")
+    print(f"   第一次编码: {cookies_json_1}")
+    print(f"   第二次编码: {cookies_json_2}")
+    
+    # 模拟从数据库读取并解析
+    try:
+        # 第一次解析
+        cookies_parsed_1 = json.loads(cookies_json_2)
+        print(f"   第一次解析后类型: {type(cookies_parsed_1).__name__}")
+        
+        # 处理双重编码
+        if isinstance(cookies_parsed_1, str):
+            cookies_parsed_2 = json.loads(cookies_parsed_1)
+            print(f"   第二次解析后类型: {type(cookies_parsed_2).__name__}")
+            cookies = cookies_parsed_2
+        else:
+            cookies = cookies_parsed_1
+        
+        # 格式化
+        result = _format_cookies(cookies)
+        print(f"✅ 成功处理双重JSON编码")
+        print(f"   最终输出: {type(result).__name__} with {len(result)} items")
+        assert isinstance(result, list)
+    except Exception as e:
+        print(f"❌ 失败: {str(e)}")
+    
+    # 测试5: 错误格式 - 字符串(不是JSON)
+    print("\n测试 5: 错误格式 - 普通字符串")
+    try:
+        result = _format_cookies("invalid_string")
+        print(f"❌ 应该抛出异常但没有")
+    except ValueError as e:
+        print(f"✅ 正确抛出ValueError异常")
+        print(f"   错误信息: {str(e)}")
+    except Exception as e:
+        print(f"❌ 抛出了非预期的异常: {str(e)}")
+    
+    # 测试6: 错误格式 - 列表中包含非字典元素
+    print("\n测试 6: 错误格式 - 列表中包含非字典元素")
+    try:
+        result = _format_cookies(["string_item", 123])
+        print(f"❌ 应该抛出异常但没有")
+    except ValueError as e:
+        print(f"✅ 正确抛出ValueError异常")
+        print(f"   错误信息: {str(e)}")
+    except Exception as e:
+        print(f"❌ 抛出了非预期的异常: {str(e)}")
+    
+    # 测试7: Playwright原生格式中value为对象（保持原样）
+    print("\n测试 7: Playwright原生格式中value为对象（应保持原样）")
+    cookies_with_object_value = [
+        {
+            "name": "test_cookie",
+            "value": {"nested": "object"},  # value是对象
+            "domain": ".xiaohongshu.com",
+            "path": "/"
+        }
+    ]
+    try:
+        result = _format_cookies(cookies_with_object_value)
+        print(f"✅ Playwright原生格式被完整保留")
+        print(f"   输入value类型: {type(cookies_with_object_value[0]['value']).__name__}")
+        print(f"   输出value类型: {type(result[0]['value']).__name__}")
+        print(f"   输出value内容: {result[0]['value']}")
+        # Playwright原生格式不做任何修改，包括uvalue
+        assert result == cookies_with_object_value, "Playwright原生格式应完整保留"
+    except Exception as e:
+        print(f"❌ 失败: {str(e)}")
+    
+    # 测试8: 字典格式中value为数字
+    print("\n测试 8: 字典格式中value为数字（应自动转换为字符串）")
+    cookies_dict_with_number = {
+        "a1": "xxx",
+        "user_id": 12345,  # value是数字
+        "is_login": True   # value是布尔值
+    }
+    try:
+        result = _format_cookies(cookies_dict_with_number)
+        print(f"✅ 成功处理数字/布尔value")
+        print(f"   输入: {cookies_dict_with_number}")
+        print(f"   user_id value类型: {type(result[1]['value']).__name__}, 值: {result[1]['value']}")
+        print(f"   is_login value类型: {type(result[2]['value']).__name__}, 值: {result[2]['value']}")
+        # 验证不再包含expires等字段
+        print(f"   字段: {list(result[0].keys())}")
+        assert all(isinstance(c['value'], str) for c in result), "所有value应该都是字符串类型"
+        assert 'expires' not in result[0], "不应该包含expires字段"
+    except Exception as e:
+        print(f"❌ 失败: {str(e)}")
+    
+    # 测试9: Playwright原生格式中expires=-1（应被保留）
+    print("\n测试 9: Playwright原生格式中expires=-1（应被保留）")
+    cookies_with_invalid_expires = [
+        {
+            "name": "test_cookie",
+            "value": "test_value",
+            "domain": ".xiaohongshu.com",
+            "path": "/",
+            "expires": -1  # Playwright原生格式
+        }
+    ]
+    try:
+        result = _format_cookies(cookies_with_invalid_expires)
+        print(f"✅ Playwright原生格式被完整保留")
+        print(f"   原始字段: {list(cookies_with_invalid_expires[0].keys())}")
+        print(f"   处理后字段: {list(result[0].keys())}")
+        assert result == cookies_with_invalid_expires, "Playwright原生格式应被完整保留"
+        assert 'expires' in result[0] and result[0]['expires'] == -1, "expires=-1应该被保留"
+    except Exception as e:
+        print(f"❌ 失败: {str(e)}")
+    
+    # 测试10: Playwright原生格式中expires为浮点数（应被保留）
+    print("\n测试 10: Playwright原生格式中expires为浮点数（应被保留）")
+    cookies_with_float_expires = [
+        {
+            "name": "test_cookie",
+            "value": "test_value",
+            "domain": ".xiaohongshu.com",
+            "path": "/",
+            "expires": 1797066497.112584  # Playwright原生格式常常有浮点数
+        }
+    ]
+    try:
+        result = _format_cookies(cookies_with_float_expires)
+        print(f"✅ Playwright原生格式被完整保留")
+        print(f"   原始expires: {cookies_with_float_expires[0]['expires']} (类型: {type(cookies_with_float_expires[0]['expires']).__name__})")
+        print(f"   处理后expires: {result[0]['expires']} (类型: {type(result[0]['expires']).__name__})")
+        assert result == cookies_with_float_expires, "Playwright原生格式应被完整保留"
+        assert isinstance(result[0]['expires'], float), "expires浮点数应该被保留"
+    except Exception as e:
+        print(f"❌ 失败: {str(e)}")
+    
+    # 测试11: Playwright原生格式中sameSite大小写（应被保留）
+    print("\n测试 11: Playwright原生格式中sameSite（应被完整保留）")
+    cookies_with_samesite = [
+        {
+            "name": "test_cookie1",
+            "value": "test_value1",
+            "domain": ".xiaohongshu.com",
+            "path": "/",
+            "sameSite": "Lax"  # Playwright原生格式
+        },
+        {
+            "name": "test_cookie2",
+            "value": "test_value2",
+            "domain": ".xiaohongshu.com",
+            "path": "/",
+            "sameSite": "Strict"
+        }
+    ]
+    try:
+        result = _format_cookies(cookies_with_samesite)
+        print(f"✅ Playwright原生格式被完整保留")
+        print(f"   cookie1 sameSite: {result[0]['sameSite']}")
+        print(f"   cookie2 sameSite: {result[1]['sameSite']}")
+        assert result == cookies_with_samesite, "Playwright原生格式应被完整保留"
+        assert result[0]['sameSite'] == 'Lax'
+        assert result[1]['sameSite'] == 'Strict'
+    except Exception as e:
+        print(f"❌ 失败: {str(e)}")
+    
+    print("\n" + "="*60)
+    print("测试完成")
+    print("="*60)
+
+
+if __name__ == "__main__":
+    test_format_cookies()