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()
|