104 lines
2.5 KiB
Python
104 lines
2.5 KiB
Python
|
#!/usr/bin/env python
|
||
|
|
# -*- coding: utf-8 -*-
|
||
|
|
"""
|
||
|
|
人民日报搜索爬虫命令行工具
|
||
|
|
用法: python RmrbSearch.py --key "关键词" --total 10 --type 0
|
||
|
|
"""
|
||
|
|
|
||
|
|
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='人民日报新闻搜索工具',
|
||
|
|
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||
|
|
epilog="""
|
||
|
|
示例:
|
||
|
|
python RmrbSearch.py --key "教育改革" --total 20
|
||
|
|
python RmrbSearch.py -k "科技创新" -t 15 -n 1
|
||
|
|
|
||
|
|
新闻类型说明:
|
||
|
|
0 - 所有类型 (默认)
|
||
|
|
1 - 新闻
|
||
|
|
2 - 互动
|
||
|
|
3 - 报刊
|
||
|
|
4 - 图片
|
||
|
|
5 - 视频
|
||
|
|
"""
|
||
|
|
)
|
||
|
|
|
||
|
|
parser.add_argument(
|
||
|
|
'--key', '-k',
|
||
|
|
type=str,
|
||
|
|
required=True,
|
||
|
|
help='搜索关键词 (必需)'
|
||
|
|
)
|
||
|
|
|
||
|
|
parser.add_argument(
|
||
|
|
'--total', '-t',
|
||
|
|
type=int,
|
||
|
|
default=10,
|
||
|
|
help='获取新闻总数 (默认: 10)'
|
||
|
|
)
|
||
|
|
|
||
|
|
parser.add_argument(
|
||
|
|
'--type', '-n',
|
||
|
|
type=int,
|
||
|
|
default=0,
|
||
|
|
choices=[0, 1, 2, 3, 4, 5],
|
||
|
|
help='新闻类型: 0=全部, 1=新闻, 2=互动, 3=报刊, 4=图片, 5=视频 (默认: 0)'
|
||
|
|
)
|
||
|
|
|
||
|
|
args = parser.parse_args()
|
||
|
|
|
||
|
|
try:
|
||
|
|
# 创建爬虫实例
|
||
|
|
logger.info(f"开始搜索: 关键词='{args.key}', 数量={args.total}, 类型={args.type}")
|
||
|
|
crawler = RmrbCrawler()
|
||
|
|
|
||
|
|
# 执行搜索
|
||
|
|
result = crawler.search(key=args.key, total=args.total, news_type=args.type)
|
||
|
|
|
||
|
|
# 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()
|