清理已删除的测试文件，准备云端部署

spiders/base.py

@@ -6,6 +6,7 @@ import csv
 import logging
 import os
 import random
+import re
 import signal
 import sys
 import time
@@ -181,6 +182,37 @@ class BaseSpider(ABC):
         logger.info(f"[统计] 总请求: {self._total_requests}, "
                     f"耗时: {elapsed:.0f}s, 速率: {rpm:.1f}次/分钟")
 
+    # ---------- 标题解析（统一规则） ----------
+
+    @staticmethod
+    def _parse_title(title: str) -> dict:
+        """从标题中提取项目名称和批准文号（统一规则）"""
+        result = {}
+
+        # 统一正则：前缀可选，贪婪匹配项目名称，提取尾部批准文号
+        title_pattern = r"(?:\[(?:招标文件|招标公告)\])?\s*(.*)\s*\[([A-Z0-9]+)\]\s*$"
+        match = re.search(title_pattern, title)
+        if match:
+            project_name = match.group(1).strip()
+            result["项目批准文号"] = match.group(2).strip()
+        else:
+            project_name = title
+            # 尝试从标题尾部提取批准文号
+            number_pattern = r"\[([A-Z0-9]+)\]\s*$"
+            match = re.search(number_pattern, project_name)
+            if match:
+                result["项目批准文号"] = match.group(1).strip()
+                project_name = project_name[:match.start()].strip()
+
+        # 清理项目名称后缀
+        suffixes = ["招标文件公示", "招标文件预公示", "招标公告", "招标预公告"]
+        for suffix in suffixes:
+            if project_name.endswith(suffix):
+                project_name = project_name[:-len(suffix)].strip()
+
+        result["项目名称"] = project_name
+        return result
+
     # ---------- 去重 ----------
 
     def is_duplicate(self, url: str) -> bool: