对外py编写

2025-11-21 15:41:28 +08:00
parent 3a44a2ddc4
commit 7eab82c6af
5 changed files with 240 additions and 186 deletions
--- a/schoolNewsCrawler/crawler/xxqg/XxqgColumn.py
+++ b/schoolNewsCrawler/crawler/xxqg/XxqgColumn.py
@@ -0,0 +1,130 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+学习强国栏目爬虫命令行工具
+用法: python RmrbSearch.py --key "关键词" --total 10 --type 0
+"""
+
+import argparse
+import json
+import sys
+from pathlib import Path
+import time
+# Add project root directory to path to import crawler
+sys.path.insert(0, str(Path(__file__).parent.parent.parent))
+
+from crawler.xxqg.XxqgCrawler import XxqgCrawler
+from loguru import logger
+
+
+def main():
+    """主函数"""
+    parser = argparse.ArgumentParser(
+        description='学习强国新闻栏目爬虫工具',
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+        """
+    )
+
+    parser.add_argument(
+        '--column', '-c',
+        type=str,
+        required=True,
+        help='栏目名称 important：重要新闻， xuexishiping：学习时评，zonghexinwen：综合新闻，zhongxuanbu：中宣部'
+    )
+
+    parser.add_argument(
+        '--yesterday', '-y',
+        type=str,
+        default="True",
+        help='是否抓取昨天的数据 (默认: True)'
+    )
+
+    parser.add_argument(
+        '--start', '-s',
+        type=str,
+        default=None,
+        help='开始日期 (格式: YYYY-MM-DD)'
+    )
+
+    parser.add_argument(
+        '--end', '-e',
+        type=str,
+        default=None,
+        help='结束日期 (格式: YYYY-MM-DD)'
+    )
+
+    parser.add_argument(
+        '--output', '-o',
+        type=str,
+        help='输出文件路径'
+    )
+
+    args = parser.parse_args()
+
+    # 获取参数
+    column = args.column
+    yesterday = str(args.yesterday)
+    if yesterday.upper() == "FALSE":
+        yesterday = False
+    elif yesterday.upper() == "TRUE":
+        yesterday = True
+    else:
+        parser.error("--yesterday 参数必须是 True 或 False")
+
+    start = args.start
+    end = args.end
+    output_file = args.output
+
+    logger.info("使用直接参数模式")
+
+    # column 必须存在
+    if not column or not column.strip():
+        parser.error("栏目不能为空！")
+    try:
+        logger.info(f"开始搜索: 栏目='{column}', 昨天={yesterday}, 开始日期={start}, 结束日期={end}")
+        crawler = XxqgCrawler()
+        url_config= crawler.config.urls[column]
+        time.sleep(5)
+        result = crawler.crawl_base(url_config, yesterday=yesterday, start=start, end=end)
+        # print(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 []
+        }
+        # result = None
+        # with open("F:\Project\schoolNews\schoolNewsCrawler\output\output.json", "r", encoding="utf-8") as f:
+        #     result = json.load(f)
+        # print(result)
+        # output = result
+
+        
+        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}")
+
+        crawler.close()
+        sys.exit(0 if result.success else 1)
+        # print(json.dumps(output, ensure_ascii=False, indent=2))
+        # 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()