refactor: 重构目录结构 - 简化层级

backend/app/subgraphs/news_analysis/api_client.py

@@ -0,0 +1,196 @@
+"""
+资讯子图API调用工具
+News Analysis API Client
+支持 async 和真实数据库缓存
+"""
+
+from typing import Dict, Any, Optional, List
+import random
+from datetime import datetime
+from dataclasses import dataclass
+
+
+@dataclass
+class NewsAPIClient:
+    """
+    资讯API客户端 - 可扩展支持多种API和数据库缓存
+    """
+    
+    # 可以配置多个API（如 NewsAPI, 今日头条, 百度新闻等）
+    newsapi_key: Optional[str] = None
+    
+    # 数据库 Repository（可选，用于缓存新闻）
+    news_repository: Optional[Any] = None
+    
+    async def query_news_db(self, user_id: str, keyword: str) -> Optional[List[Dict[str, Any]]]:
+        """从数据库缓存查询新闻"""
+        if not self.news_repository:
+            return None
+        try:
+            entities = await self.news_repository.search_by_keywords(user_id, keyword)
+            if entities:
+                return [
+                    {
+                        "title": e.title,
+                        "source": e.source,
+                        "summary": e.content,
+                        "keywords": e.keywords.split(",") if e.keywords else [],
+                        "author": "",
+                        "published_at": e.created_at
+                    }
+                    for e in entities
+                ]
+        except Exception as e:
+            print(f"从数据库查询新闻失败：{e}")
+        return None
+    
+    async def cache_news_db(self, user_id: str, news: Dict[str, Any]):
+        """把新闻缓存到数据库"""
+        if not self.news_repository:
+            return
+        try:
+            from ...db.models import NewsEntity
+            entity = NewsEntity(
+                user_id=user_id,
+                title=news.get("title", ""),
+                content=news.get("summary", ""),
+                url=news.get("url", ""),
+                source=news.get("source", ""),
+                keywords=",".join(news.get("keywords", []))
+            )
+            await self.news_repository.insert(entity)
+        except Exception as e:
+            print(f"缓存新闻到数据库失败：{e}")
+    
+    def query_news_mock(self, query: str) -> List[Dict[str, Any]]:
+        """
+        模拟查询资讯 - 目前用于演示
+        """
+        # 模拟资讯数据库
+        mock_news = [
+            {
+                "title": "OpenAI发布GPT-5：智能再升级",
+                "source": "Tech News",
+                "summary": "最新消息，OpenAI刚刚发布了GPT-5模型，智能水平再次取得重大突破...",
+                "keywords": ["AI", "GPT-5", "OpenAI"],
+                "author": "AI Team",
+                "published_at": datetime.now().isoformat()
+            },
+            {
+                "title": "大模型在医疗领域的应用",
+                "source": "Health Tech",
+                "summary": "大模型AI技术正在医疗领域展现巨大潜力，从辅助诊断到药物研发...",
+                "keywords": ["医疗", "大模型", "应用"],
+                "author": "Medical Team",
+                "published_at": datetime.now().isoformat()
+            },
+            {
+                "title": "2026年AI行业发展趋势报告",
+                "source": "Business Daily",
+                "summary": "最新行业报告显示，AI行业将继续保持高速增长，企业数字化转型加速...",
+                "keywords": ["趋势", "AI", "商业"],
+                "author": "Business Team",
+                "published_at": datetime.now().isoformat()
+            }
+        ]
+        
+        # 根据查询词简单过滤
+        results = []
+        query_lower = query.lower()
+        
+        for news in mock_news:
+            if (query_lower in news["title"].lower() or 
+                query_lower in news["summary"].lower() or 
+                any(keyword.lower() in query_lower for keyword in news["keywords"])):
+                results.append(news)
+        
+        # 如果没有匹配到，返回前两条
+        if not results:
+            results = mock_news[:2]
+        
+        return results
+    
+    def analyze_url_mock(self, url: str) -> Dict[str, Any]:
+        """
+        模拟URL分析 - 目前用于演示
+        """
+        return {
+            "title": f"分析结果：{url}",
+            "source": "URL Analyzer",
+            "summary": "已完成对该URL的内容分析，包含文章摘要和情感倾向判断...",
+            "keywords": ["News", "Analysis", url.split("/")[-1] if url else "unknown"]
+        }
+    
+    def extract_keywords_mock(self, text: str) -> List[str]:
+        """
+        模拟关键词提取 - 目前用于演示
+        """
+        # 简单的关键词提取模拟
+        common_keywords = ["AI", "大模型", "应用场景", "行业趋势", "创新", "技术"]
+        result = []
+        
+        for keyword in common_keywords:
+            if keyword.lower() in text.lower():
+                result.append(keyword)
+        
+        # 如果没找到，返回默认关键词
+        if not result:
+            result = ["AI", "大模型", "应用场景", "行业趋势"]
+        
+        return result
+    
+    def generate_report_mock(self, query: str) -> str:
+        """
+        模拟报告生成 - 目前用于演示
+        """
+        report = f"""═══════════════════════════════════════════
+📊 资讯分析报告
+═══════════════════════════════════════════
+
+主题：{query}
+
+📋 摘要：
+这是一份关于 {query} 的资讯分析综合报告，包含最新行业动态和趋势分析。
+
+🔍 主要发现：
+1. AI技术持续快速发展
+2. 大模型应用场景不断拓展
+3. 行业数字化转型加速
+
+🏷️ 关键词：
+- AI
+- 大模型
+- 数字化转型
+- 创新
+
+═══════════════════════════════════════════
+💡 建议：继续关注行业动态，把握发展机遇！
+"""
+        return report
+    
+    # ========== 统一入口（优先查缓存） ==========
+    async def query_news(self, user_id: str = "default", query: str = "", use_cache: bool = True) -> List[Dict[str, Any]]:
+        """查询新闻（统一入口，优先查数据库缓存）"""
+        # 1. 先查数据库缓存
+        if use_cache:
+            cached = await self.query_news_db(user_id, query)
+            if cached:
+                return cached
+        
+        # 2. 查第三方 API（暂未实现）
+        # api_result = await self.query_news_api(query)
+        # if api_result:
+        #     for news in api_result:
+        #         await self.cache_news_db(user_id, news)
+        #     return api_result
+        
+        # 3. 用模拟数据（兜底）
+        mock_result = self.query_news_mock(query)
+        if use_cache:
+            for news in mock_result:
+                await self.cache_news_db(user_id, news)
+        return mock_result
+
+
+# 单例实例（模拟模式，保持向后兼容）
+news_api = NewsAPIClient()