Initial commit: 招标信息爬虫与分析系统

test_attachment_processing.py

@@ -0,0 +1,60 @@
+# -*- coding: utf-8 -*-
+"""
+测试附件下载和解析功能
+"""
+import logging
+from processors.content_fetcher import ContentFetcher
+
+# 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"开始测试附件处理: {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"获取到总内容长度: {len(content)} 字符")
+    
+    # 检查是否包含附件内容
+    if "=== 附件:" in content:
+        logger.info("内容中包含附件")
+        
+        # 提取附件部分
+        attachment_parts = content.split("=== 附件:")
+        for i, part in enumerate(attachment_parts[1:], 1):
+            attachment_name = part.split("===")[0].strip()
+            attachment_content = part.split("===")[1].strip() if len(part.split("===")) > 1 else ""
+            logger.info(f"\n附件 {i}: {attachment_name}")
+            logger.info(f"附件内容长度: {len(attachment_content)} 字符")
+            
+            # 检查附件中是否包含资质要求和业绩要求
+            if "资质要求" in attachment_content:
+                logger.info("✓ 附件中包含资质要求")
+            if "业绩要求" in attachment_content:
+                logger.info("✓ 附件中包含业绩要求")
+            if "投标人须知前附表" in attachment_content:
+                logger.info("✓ 附件中包含投标人须知前附表")
+    else:
+        logger.warning("内容中不包含附件")
+    
+    # 保存完整内容到文件，以便分析
+    with open("full_content.txt", "w", encoding="utf-8") as f:
+        f.write(content)
+    logger.info("\n完整内容已保存到 full_content.txt")
+
+if __name__ == "__main__":
+    main()