Initial commit: 招标信息爬虫与分析系统

2026-02-13 18:15:20 +08:00
commit d2fa06801f
38 changed files with 5415 additions and 0 deletions
--- a/test_real_with_fixed_config.py
+++ b/test_real_with_fixed_config.py
@@ -0,0 +1,98 @@
+# -*- 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