schoolNews/schoolNewsCrawler/crawler/xhw/XhwSearch.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
新华网搜索爬虫命令行工具
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.xhw.XhwCrawler import XhwCrawler
from loguru import logger


def main():
    """主函数"""
    parser = argparse.ArgumentParser(
        description='新华网新闻搜索工具',
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
        """
    )

    parser.add_argument(
        '--query', '-q',
        type=str,
        required=True,
        help='搜索关键词'
    )

    parser.add_argument(
        '--total', '-t',
        type=int,
        default=10,
        help='抓取数量 (默认: 10)'
    )

    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
    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:
        logger.info(f"开始搜索: 关键词='{key}', 数量={total}")
        crawler = XhwCrawler()
        time.sleep(5)
        result = crawler.search(key=key.strip(), total=total)
        # 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()