73 lines
1.7 KiB
Python
73 lines
1.7 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.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
|
|
"""
|
|
)
|
|
|
|
args = parser.parse_args()
|
|
|
|
try:
|
|
# 创建爬虫实例
|
|
logger.info("开始获取人民日报热点排行")
|
|
crawler = RmrbCrawler()
|
|
|
|
# 执行获取热点排行
|
|
result = crawler.hotPointRank()
|
|
|
|
# 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 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()
|