125 lines
3.3 KiB
Python
125 lines
3.3 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.rmrb.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 --type 1
|
||
python RmrbSearch.py --key "AI" --total 5 --output "out.json"
|
||
|
||
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(
|
||
'--query', '-q',
|
||
type=str,
|
||
required=True,
|
||
help='搜索关键词'
|
||
)
|
||
|
||
parser.add_argument(
|
||
'--total', '-t',
|
||
type=int,
|
||
default=10,
|
||
help='抓取数量 (默认: 10)'
|
||
)
|
||
|
||
parser.add_argument(
|
||
'--type', '-n',
|
||
type=int,
|
||
default=0,
|
||
help='新闻类型 (默认: 0=所有类型)'
|
||
)
|
||
|
||
parser.add_argument(
|
||
'--output', '-o',
|
||
type=str,
|
||
help='输出文件路径'
|
||
)
|
||
|
||
args = parser.parse_args()
|
||
|
||
# 获取参数
|
||
key = args.query
|
||
total = args.total
|
||
news_type = args.type
|
||
output_file = args.output
|
||
|
||
logger.info("使用直接参数模式")
|
||
|
||
# 关键校验：key 必须存在
|
||
if not key or not key.strip():
|
||
parser.error("搜索关键词不能为空！")
|
||
try:
|
||
logger.info(f"开始搜索: 关键词='{key}', 数量={total}, 类型={news_type}")
|
||
crawler = RmrbCrawler()
|
||
result = crawler.search(key=key.strip(), total=total, news_type=news_type)
|
||
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() |