搜索关键字爬虫

schoolNewsCrawler/crawler/RmrbHotPoint.py

@@ -25,20 +25,27 @@ def main():
         epilog="""
 示例:
   python RmrbHotPoint.py
+  python RmrbHotPoint.py --output "output/hotpoint.json"
         """
     )
 
+    # 添加输出文件参数
+    parser.add_argument(
+        '--output', '-o',
+        type=str,
+        help='输出文件路径'
+    )
+
     args = parser.parse_args()
 
+    output_file = args.output
+    logger.info("使用直接参数模式")
+
     try:
-        # 创建爬虫实例
         logger.info("开始获取人民日报热点排行")
         crawler = RmrbCrawler()
-
-        # 执行获取热点排行
         result = crawler.hotPointRank()
 
-        # 输出JSON结果
         output = {
             "code": result.code,
             "message": result.message,
@@ -47,12 +54,15 @@ def main():
             "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)
 
     except Exception as e:
@@ -67,7 +77,6 @@ def main():
         print(json.dumps(error_output, ensure_ascii=False, indent=2))
         sys.exit(1)
 
-" "
+
 if __name__ == "__main__":
-    main()
-    
+    main()