Files
schoolNews/schoolNewsCrawler/crawler/xhw/XhwHotPoint.py

88 lines
2.3 KiB
Python
Raw Normal View History

2025-11-20 15:22:26 +08:00
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
新华网热点爬虫命令行工具
用法: python XhwHotPoint.py --output "输出文件路径"
2025-11-20 15:22:26 +08:00
"""
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='新华网热点爬虫工具',
2025-11-20 15:22:26 +08:00
formatter_class=argparse.RawDescriptionHelpFormatter,
epilog="""
"""
)
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:
crawler = XhwCrawler()
time.sleep(5)
result = crawler.hot_point()
# 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()