82 lines
2.2 KiB
Python
82 lines
2.2 KiB
Python
#!/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.rmrb.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
|
|
python RmrbHotPoint.py --output "output/hotpoint.json"
|
|
"""
|
|
)
|
|
|
|
# 添加输出文件参数
|
|
parser.add_argument(
|
|
'--output', '-o',
|
|
type=str,
|
|
help='输出文件路径'
|
|
)
|
|
|
|
args = parser.parse_args()
|
|
|
|
output_file = args.output
|
|
logger.info("使用直接参数模式")
|
|
|
|
try:
|
|
logger.info("开始获取人民日报热点排行")
|
|
crawler = RmrbCrawler()
|
|
result = crawler.hotPointRank()
|
|
|
|
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 []
|
|
}
|
|
|
|
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 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() |