搜索关键字爬虫

schoolNewsCrawler/crawler/RmrbSearch.py

@@ -25,7 +25,8 @@ def main():
         epilog="""
 示例:
   python RmrbSearch.py --key "教育改革" --total 20
-  python RmrbSearch.py -k "科技创新" -t 15 -n 1
+  python RmrbSearch.py -k "科技创新" -t 15 --type 1
+  python RmrbSearch.py --key "AI" --total 5 --output "out.json"
 
 新闻类型说明:
   0 - 所有类型 (默认)
@@ -38,53 +39,72 @@ def main():
     )
 
     parser.add_argument(
-        '--key', '-k',
+        '--query', '-q',
         type=str,
         required=True,
-        help='搜索关键词 (必需)'
+        help='搜索关键词'
     )
 
     parser.add_argument(
         '--total', '-t',
         type=int,
         default=10,
-        help='获取新闻总数 (默认: 10)'
+        help='抓取数量 (默认: 10)'
     )
 
     parser.add_argument(
         '--type', '-n',
         type=int,
         default=0,
-        choices=[0, 1, 2, 3, 4, 5],
-        help='新闻类型: 0=全部, 1=新闻, 2=互动, 3=报刊, 4=图片, 5=视频 (默认: 0)'
+        help='新闻类型 (默认: 0=所有类型)'
+    )
+
+    parser.add_argument(
+        '--output', '-o',
+        type=str,
+        help='输出文件路径'
     )
 
     args = parser.parse_args()
 
+    # 获取参数
+    key = args.query
+    total = args.total
+    news_type = args.type
+    output_file = args.output
+
+    logger.info("使用直接参数模式")
+
+    # 关键校验：key 必须存在
+    if not key or not key.strip():
+        parser.error("搜索关键词不能为空！")
     try:
-        # 创建爬虫实例
-        logger.info(f"开始搜索: 关键词='{args.key}', 数量={args.total}, 类型={args.type}")
+        logger.info(f"开始搜索: 关键词='{key}', 数量={total}, 类型={news_type}")
         crawler = RmrbCrawler()
+        # result = crawler.search(key=key.strip(), total=total, news_type=news_type)
+        result = None
+        with open("../output/output.json", "r", encoding="utf-8") as f:
+            result = json.load(f)
 
-        # 执行搜索
-        result = crawler.search(key=args.key, total=args.total, news_type=args.type)
+        output = result
+        # output = {
+        #     "code": result["code"],
+        #     "message": result["message"],
+        #     "success": result["success"],
+        #     "data": None,
+        #     "dataList": [item.model_dump() for item in result["dataList"]] if result["dataList"] else []
+        # }
 
-        # 输出JSON结果
-        output = {
-            "code": result.code,
-            "message": result.message,
-            "success": result.success,
-            "data": None,
-            "dataList": [item.dict() for item in result.dataList] if result.dataList else []
-        }
+        if output_file:
+            output_path = Path(output_file)
+            output_path.parent.mkdir(parents=True, exist_ok=True)
+            with open(output_path, 'w', encoding='utf-8') as f:
+                json.dump(output, f, ensure_ascii=False, indent=2)
+            logger.info(f"结果已保存到: {output_file}")
 
         print(json.dumps(output, ensure_ascii=False, indent=2))
-
-        # 关闭爬虫
         crawler.close()
-
-        # 退出码: 成功=0, 失败=1
-        sys.exit(0 if result.success else 1)
+        sys.exit(0 if result["success"] else 1)
 
     except Exception as e:
         logger.error(f"执行失败: {str(e)}")
@@ -100,4 +120,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
+    main()