130 lines
3.7 KiB
Python
130 lines
3.7 KiB
Python
#!/usr/bin/env python
|
||
# -*- coding: utf-8 -*-
|
||
"""
|
||
学习强国栏目爬虫命令行工具
|
||
用法: python RmrbSearch.py --key "关键词" --total 10 --type 0
|
||
"""
|
||
|
||
import argparse
|
||
import json
|
||
import sys
|
||
from pathlib import Path
|
||
import time
|
||
# Add project root directory to path to import crawler
|
||
sys.path.insert(0, str(Path(__file__).parent.parent.parent))
|
||
|
||
from crawler.xxqg.XxqgCrawler import XxqgCrawler
|
||
from loguru import logger
|
||
|
||
|
||
def main():
|
||
"""主函数"""
|
||
parser = argparse.ArgumentParser(
|
||
description='学习强国新闻栏目爬虫工具',
|
||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||
epilog="""
|
||
"""
|
||
)
|
||
|
||
parser.add_argument(
|
||
'--column', '-c',
|
||
type=str,
|
||
required=True,
|
||
help='栏目名称 important：重要新闻， xuexishiping：学习时评，zonghexinwen：综合新闻，zhongxuanbu：中宣部'
|
||
)
|
||
|
||
parser.add_argument(
|
||
'--yesterday', '-y',
|
||
type=str,
|
||
default="True",
|
||
help='是否抓取昨天的数据 (默认: True)'
|
||
)
|
||
|
||
parser.add_argument(
|
||
'--start', '-s',
|
||
type=str,
|
||
default=None,
|
||
help='开始日期 (格式: YYYY-MM-DD)'
|
||
)
|
||
|
||
parser.add_argument(
|
||
'--end', '-e',
|
||
type=str,
|
||
default=None,
|
||
help='结束日期 (格式: YYYY-MM-DD)'
|
||
)
|
||
|
||
parser.add_argument(
|
||
'--output', '-o',
|
||
type=str,
|
||
help='输出文件路径'
|
||
)
|
||
|
||
args = parser.parse_args()
|
||
|
||
# 获取参数
|
||
column = args.column
|
||
yesterday = str(args.yesterday)
|
||
if yesterday.upper() == "FALSE":
|
||
yesterday = False
|
||
elif yesterday.upper() == "TRUE":
|
||
yesterday = True
|
||
else:
|
||
parser.error("--yesterday 参数必须是 True 或 False")
|
||
|
||
start = args.start
|
||
end = args.end
|
||
output_file = args.output
|
||
|
||
logger.info("使用直接参数模式")
|
||
|
||
# column 必须存在
|
||
if not column or not column.strip():
|
||
parser.error("栏目不能为空！")
|
||
try:
|
||
logger.info(f"开始搜索: 栏目='{column}', 昨天={yesterday}, 开始日期={start}, 结束日期={end}")
|
||
crawler = XxqgCrawler()
|
||
url_config= crawler.config.urls[column]
|
||
time.sleep(5)
|
||
result = crawler.crawl_base(url_config, yesterday=yesterday, start=start, end=end)
|
||
# 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() |