schoolNews/schoolNewsCrawler/crawler/rmrb/RmrbTrending.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
人民日报热点新闻爬虫命令行工具
用法:
  python RmrbTrending.py --date 20250110
  python RmrbTrending.py --start-date 20250101 --end-date 20250110
"""

import argparse
import json
import sys
from datetime import datetime, timedelta
from pathlib import Path

# Add parent directory to path to import crawler
sys.path.insert(0, str(Path(__file__).parent.parent))

from crawler.rmrb.RmrbCrawler import RmrbCrawler
from loguru import logger
from core.ResultDomain import ResultDomain

def parse_date(date_str) -> datetime:
    """
    解析日期字符串或数字为datetime对象 (格式: YYYYMMDD)

    Args:
        date_str: 可为字符串或整数，如 "20250110" 或 20250110

    Returns:
        datetime对象

    Raises:
        ValueError: 格式错误
    """
    # 统一转为字符串并清理
    if date_str is None:
        raise ValueError("日期不能为空")
    date_str = str(date_str).strip()
    if len(date_str) != 8 or not date_str.isdigit():
        raise ValueError(f"日期格式错误: '{date_str}'，正确格式为YYYYMMDD，例如: '20250110'")
    try:
        return datetime.strptime(date_str, "%Y%m%d")
    except ValueError:
        raise ValueError(f"日期格式错误: '{date_str}'，正确格式为YYYYMMDD，例如: '20250110'")


def main():
    """主函数"""
    parser = argparse.ArgumentParser(
        description='人民日报热点新闻获取工具',
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
示例:
  # 获取单日热点新闻
  python RmrbTrending.py --date 20250110
  python RmrbTrending.py -d 20250110

  # 获取日期范围内的热点新闻
  python RmrbTrending.py --start-date 20250101 --end-date 20250110
  python RmrbTrending.py -s 20250101 -e 20250110

  # 不指定日期则根据 isYesterday 决定（默认昨日）
  python RmrbTrending.py
        """
    )

    parser.add_argument('--startDate', '-s', type=str, help='开始日期 (需与--end-date一起使用)')
    parser.add_argument('--endDate', '-e', type=str, help='结束日期 (需与--start-date一起使用)')
    parser.add_argument('--yesterday', '-y', action='store_true', help='查询昨日 (默认行为)')
    parser.add_argument('--output', '-o', type=str, help='输出文件路径')

    args = parser.parse_args()

    # 初始化变量
    output_file = args.output
    start_date = args.startDate
    end_date = args.endDate
    is_yesterday = args.yesterday if args.yesterday else True  # 默认查昨日

    logger.info("使用直接参数模式")

    # 辅助函数：清理空字符串
    def clean(s):
        return s.strip() if s and isinstance(s, str) and s.strip() else None

    start_date = clean(start_date)
    end_date = clean(end_date)

    try:
        crawler = RmrbCrawler()

        if is_yesterday:
            target_date = datetime.now() - timedelta(days=1)
            date_str = target_date.strftime('%Y%m%d')
            logger.info(f"获取昨日热点新闻: {target_date.strftime('%Y-%m-%d')} (参数格式: {date_str})")
            result = crawler.getOneDayTrendingNews(target_date)
        # 日期范围模式
        elif start_date and end_date:
            start_dt = parse_date(start_date)
            end_dt = parse_date(end_date)
            if start_dt > end_dt:
                raise ValueError("开始日期不能晚于结束日期")
            logger.info(f"获取日期范围热点新闻: {start_dt.strftime('%Y-%m-%d')} 至 {end_dt.strftime('%Y-%m-%d')}")
            result = crawler.getDaysTrendingNews(start_dt, end_dt)

        # 只给一个边界
        elif start_date or end_date:
            raise ValueError("--startDate 和 --endDate 必须同时指定")
        else:
            result = ResultDomain(code=0, message="参数错误", success=False, data=None, dataList=None)

        # 构造输出
        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 []
        }

        # 保存到文件
        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))
        crawler.close()
        sys.exit(0 if result.success else 1)

    except ValueError as e:
        logger.error(f"参数错误: {str(e)}")
        error_output = {
            "code": 400,
            "message": f"参数错误: {str(e)}",
            "success": False,
            "data": None,
            "dataList": []
        }
        print(json.dumps(error_output, ensure_ascii=False, indent=2))
        sys.exit(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()