99 lines
2.6 KiB
Python
99 lines
2.6 KiB
Python
|
# -*- coding: utf-8 -*-
|
||
|
|
"""
|
||
|
|
使用修复后的配置文件测试真实提取功能
|
||
|
|
"""
|
||
|
|
import logging
|
||
|
|
import sys
|
||
|
|
import os
|
||
|
|
|
||
|
|
# 添加当前目录到模块搜索路径
|
||
|
|
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
||
|
|
|
||
|
|
# 保存原始配置导入
|
||
|
|
import importlib
|
||
|
|
|
||
|
|
# 备份原始config模块
|
||
|
|
if 'config' in sys.modules:
|
||
|
|
del sys.modules['config']
|
||
|
|
|
||
|
|
# 临时替换config模块为config_fixed
|
||
|
|
import config_fixed
|
||
|
|
import sys
|
||
|
|
|
||
|
|
# 保存原始的config模块引用
|
||
|
|
original_config = None
|
||
|
|
if 'config' in sys.modules:
|
||
|
|
original_config = sys.modules['config']
|
||
|
|
|
||
|
|
# 将config_fixed设置为config模块
|
||
|
|
sys.modules['config'] = config_fixed
|
||
|
|
|
||
|
|
# 现在导入处理器
|
||
|
|
from processors.content_fetcher import ContentFetcher
|
||
|
|
from processors.deepseek import DeepSeekProcessor
|
||
|
|
|
||
|
|
# 配置日志
|
||
|
|
logging.basicConfig(
|
||
|
|
level=logging.INFO,
|
||
|
|
format='%(asctime)s - %(levelname)s - %(message)s'
|
||
|
|
)
|
||
|
|
logger = logging.getLogger(__name__)
|
||
|
|
|
||
|
|
# 测试网址
|
||
|
|
TEST_URL = "https://ggzy.zj.gov.cn/jyxxgk/002001/002001011/20260212/9a7966d8-80f4-475b-897e-f7631bc64d0c.html"
|
||
|
|
|
||
|
|
def main():
|
||
|
|
"""主函数"""
|
||
|
|
logger.info(f"开始测试: {TEST_URL}")
|
||
|
|
|
||
|
|
# 获取内容
|
||
|
|
fetcher = ContentFetcher(temp_dir="temp_files")
|
||
|
|
content = fetcher.get_full_content(TEST_URL)
|
||
|
|
|
||
|
|
if not content:
|
||
|
|
logger.error("无法获取内容")
|
||
|
|
return
|
||
|
|
|
||
|
|
logger.info(f"获取到内容长度: {len(content)} 字符")
|
||
|
|
|
||
|
|
# 执行提取
|
||
|
|
processor = DeepSeekProcessor()
|
||
|
|
|
||
|
|
# 获取浙江招标文件公示的配置
|
||
|
|
config_key = "zhejiang:招标文件公示"
|
||
|
|
from config import REGION_CONFIGS
|
||
|
|
|
||
|
|
if config_key not in REGION_CONFIGS:
|
||
|
|
logger.error(f"未找到配置: {config_key}")
|
||
|
|
return
|
||
|
|
|
||
|
|
ai_fields = REGION_CONFIGS[config_key]["ai_fields"]
|
||
|
|
logger.info(f"需要提取的字段: {ai_fields}")
|
||
|
|
|
||
|
|
# 执行提取
|
||
|
|
extracted = processor.extract_fields(content, ai_fields, "浙江")
|
||
|
|
|
||
|
|
# 分析结果
|
||
|
|
logger.info("\n提取结果:")
|
||
|
|
for field, value in extracted.items():
|
||
|
|
logger.info(f" {field}: {value}")
|
||
|
|
|
||
|
|
# 特别关注资质要求和业绩要求
|
||
|
|
for field in ["资质要求", "业绩要求"]:
|
||
|
|
if field in extracted:
|
||
|
|
value = extracted[field]
|
||
|
|
logger.info(f"\n{field}提取结果: {value}")
|
||
|
|
|
||
|
|
if value != "文档未提及":
|
||
|
|
logger.info(f"✓ {field}提取成功！")
|
||
|
|
else:
|
||
|
|
logger.warning(f"✗ {field}未提取到")
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
try:
|
||
|
|
main()
|
||
|
|
finally:
|
||
|
|
# 恢复原始配置
|
||
|
|
if original_config:
|
||
|
|
sys.modules['config'] = original_config
|