爬虫

schoolNewsCrawler/crawler/RmrbHotPoint.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+人民日报热点排行爬虫命令行工具
+用法: python RmrbHotPoint.py
+"""
+
+import argparse
+import json
+import sys
+from pathlib import Path
+
+# Add parent directory to path to import crawler
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from crawler.RmrbCrawler import RmrbCrawler
+from loguru import logger
+
+
+def main():
+    """主函数"""
+    parser = argparse.ArgumentParser(
+        description='人民日报热点排行获取工具',
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+示例:
+  python RmrbHotPoint.py
+        """
+    )
+
+    args = parser.parse_args()
+
+    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,
+            "success": result.success,
+            "data": None,
+            "dataList": [item.dict() for item in result.dataList] if result.dataList else []
+        }
+
+        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:
+        logger.error(f"执行失败: {str(e)}")
+        error_output = {
+            "code": 500,
+            "message": f"执行失败: {str(e)}",
+            "success": False,
+            "data": None,
+            "dataList": []
+        }
+        print(json.dumps(error_output, ensure_ascii=False, indent=2))
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()