# -*- coding: utf-8 -*-
"""
使用原始config.py测试提取功能
"""
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__)))

# 导入原始配置
from config import REGION_CONFIGS
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/d2f95295-6cb0-40c9-8023-cdbbf7e660ae.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"
    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__":
    main()