ztb/test_with_fixed_config.py

# -*- coding: utf-8 -*-
"""
使用修复后的配置文件测试提取功能
"""
import logging
import sys
import os
import requests
from bs4 import BeautifulSoup
import json
import re

# 添加当前目录到模块搜索路径
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))

# 导入修复后的配置
from config_fixed import REGION_CONFIGS, DEEPSEEK_PROMPTS

# 简化的ContentFetcher类
class ContentFetcher:
    def __init__(self, temp_dir="temp_files"):
        self.temp_dir = temp_dir
        if not os.path.exists(temp_dir):
            os.makedirs(temp_dir)
    
    def get_full_content(self, url):
        try:
            response = requests.get(url, timeout=30)
            response.encoding = 'utf-8'
            soup = BeautifulSoup(response.text, 'html.parser')
            
            # 提取主要内容
            content = []
            
            # 查找标题
            title = soup.find('h1')
            if title:
                content.append(title.get_text(strip=True))
            
            # 查找正文内容
            content_div = soup.find('div', class_='ewb-article')
            if content_div:
                for p in content_div.find_all('p'):
                    text = p.get_text(strip=True)
                    if text:
                        content.append(text)
            
            # 查找附件
            attachments = soup.find_all('a', href=re.compile(r'\.(pdf|doc|docx)$'))
            if attachments:
                content.append("\n附件：")
                for attachment in attachments:
                    content.append(f"- {attachment.get_text(strip=True)}: {attachment['href']}")
            
            return "\n".join(content)
        except Exception as e:
            logging.error(f"获取内容失败: {e}")
            return None

# 简化的DeepSeekProcessor类
class DeepSeekProcessor:
    def __init__(self):
        pass
    
    def extract_fields(self, content, fields, region_name):
        results = {}
        for field in fields:
            if field in DEEPSEEK_PROMPTS:
                # 这里我们只是模拟提取，实际项目中会调用DeepSeek API
                prompt = DEEPSEEK_PROMPTS[field]
                # 简单模拟：如果内容包含关键词，返回模拟结果
                if field == "资质要求" and any(keyword in content for keyword in ["资质", "资格"]):
                    results[field] = "建筑工程施工总承包三级及以上"
                elif field == "业绩要求" and any(keyword in content for keyword in ["业绩", "经验"]):
                    results[field] = "近3年类似工程业绩不少于2项"
                else:
                    results[field] = "文档未提及"
            else:
                results[field] = "文档未提及"
        return results

# 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"
    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()