159 lines
4.5 KiB
Python
159 lines
4.5 KiB
Python
#!/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
|
||
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 parse_date(date_str: str) -> datetime:
|
||
"""
|
||
解析日期字符串为datetime对象
|
||
|
||
Args:
|
||
date_str: 日期字符串，格式为YYYYMMDD
|
||
|
||
Returns:
|
||
datetime对象
|
||
"""
|
||
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
|
||
|
||
# 不指定日期则获取今天的热点新闻
|
||
python RmrbTrending.py
|
||
"""
|
||
)
|
||
|
||
parser.add_argument(
|
||
'--date', '-d',
|
||
type=str,
|
||
help='指定日期 (格式: YYYYMMDD，例如: 20250110)'
|
||
)
|
||
|
||
parser.add_argument(
|
||
'--start-date', '-s',
|
||
type=str,
|
||
help='开始日期 (格式: YYYYMMDD，需与--end-date一起使用)'
|
||
)
|
||
|
||
parser.add_argument(
|
||
'--end-date', '-e',
|
||
type=str,
|
||
help='结束日期 (格式: YYYYMMDD，需与--start-date一起使用)'
|
||
)
|
||
|
||
args = parser.parse_args()
|
||
|
||
try:
|
||
# 创建爬虫实例
|
||
crawler = RmrbCrawler()
|
||
|
||
# 判断使用哪种模式
|
||
if args.date:
|
||
# 单日模式
|
||
if args.start_date or args.end_date:
|
||
raise ValueError("不能同时使用--date和--start-date/--end-date参数")
|
||
|
||
target_date = parse_date(args.date)
|
||
logger.info(f"获取单日热点新闻: {args.date}")
|
||
result = crawler.getOneDayTrendingNews(target_date)
|
||
|
||
elif args.start_date and args.end_date:
|
||
# 日期范围模式
|
||
start_date = parse_date(args.start_date)
|
||
end_date = parse_date(args.end_date)
|
||
|
||
if start_date > end_date:
|
||
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: {args.start_date} 至 {args.end_date}")
|
||
result = crawler.getDaysTrendingNews(start_date, end_date)
|
||
|
||
elif args.start_date or args.end_date:
|
||
# 只指定了一个日期
|
||
raise ValueError("--start-date和--end-date必须同时使用")
|
||
|
||
else:
|
||
# 默认使用今天的日期
|
||
today = datetime.now()
|
||
today_str = today.strftime("%Y%m%d")
|
||
logger.info(f"获取今日热点新闻: {today_str}")
|
||
result = crawler.getOneDayTrendingNews(today)
|
||
|
||
# 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 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()
|