清理已删除的测试文件，准备云端部署

spiders/zhejiang.py

@@ -7,6 +7,7 @@ import logging
 import os
 import re
 from datetime import datetime, timedelta
+from bs4 import BeautifulSoup
 from .base import BaseSpider
 from utils.attachment import AttachmentHandler
 
@@ -95,8 +96,7 @@ class ZhejiangSpider(BaseSpider):
 
     # ---------- 解析记录 ----------
 
-    @staticmethod
-    def _parse_record(record: dict, source: str) -> dict:
+    def _parse_record(self, record: dict, source: str) -> dict:
         """将 API 原始记录转换为结果字典"""
         title = record.get("title", "").strip()
         link = record.get("linkurl", "")
@@ -115,36 +115,8 @@ class ZhejiangSpider(BaseSpider):
             "来源": source,
         }
 
-        # 解析特定格式的标题：[招标文件]项目名称[批准文号]
-        import re
-        # 改进的正则表达式，确保正确匹配标题格式
-        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()
-            # 删除结尾的"招标文件公示"、"招标文件预公示"等后缀
-            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()
-            item["项目名称"] = project_name
-            item["项目批准文号"] = match.group(2).strip()
-        else:
-            # 如果正则匹配失败，直接使用标题作为项目名称
-            project_name = title
-            # 删除结尾的"招标文件公示"、"招标文件预公示"等后缀
-            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()
-            # 尝试从标题中提取批准文号
-            number_pattern = r"\[([A-Z0-9]+)\]\s*$"
-            match = re.search(number_pattern, project_name)
-            if match:
-                item["项目批准文号"] = match.group(1).strip()
-                # 从项目名称中删除批准文号部分
-                project_name = project_name[:match.start()].strip()
-            item["项目名称"] = project_name
+        # 解析标题：提取项目名称和批准文号（统一规则）
+        item.update(self._parse_title(title))
 
         return item
 
@@ -176,6 +148,65 @@ class ZhejiangSpider(BaseSpider):
 
         return fields
 
+    # ---------- 详情页补充 ----------
+
+    def parse_detail(self, url: str) -> dict:
+        """访问详情页，提取项目名称和批准文号等结构化字段"""
+        resp = self.fetch(url)
+        if resp is None:
+            return {}
+
+        detail = {}
+        soup = BeautifulSoup(resp.text, "html.parser")
+
+        # 解析表格字段
+        field_map = {
+            "项目名称": "项目名称",
+            "项目批准文件及文号": "项目批准文号",
+            "项目批准文号": "项目批准文号",
+            "批准文号": "项目批准文号",
+            "建设单位(招标人)": "招标人",
+            "建设单位（招标人）": "招标人",
+            "招标人": "招标人",
+            "项目类型": "项目类型",
+            "招标方式": "招标方式",
+            "联系人": "联系人",
+            "联系方式": "联系方式",
+        }
+
+        for row in soup.select("table tr"):
+            cells = row.select("td")
+            if len(cells) >= 2:
+                key = cells[0].get_text(strip=True)
+                value = cells[1].get_text(strip=True)
+                if key in field_map and value:
+                    detail[field_map[key]] = value
+            if len(cells) >= 4:
+                key2 = cells[2].get_text(strip=True)
+                value2 = cells[3].get_text(strip=True)
+                if key2 in field_map and value2:
+                    detail[field_map[key2]] = value2
+
+        # 招标项目表（计划招标时间 / 预估合同金额）
+        for table in soup.select("table"):
+            headers = [th.get_text(strip=True) for th in table.select("th")]
+            if "计划招标时间" in headers:
+                data_rows = table.select("tbody tr") or [
+                    r for r in table.select("tr") if r.select("td")
+                ]
+                if data_rows:
+                    cells = data_rows[0].select("td")
+                    for i, h in enumerate(headers):
+                        if i < len(cells):
+                            val = cells[i].get_text(strip=True)
+                            if h == "计划招标时间" and val:
+                                detail["计划招标时间"] = val
+                            elif "预估合同金额" in h and val:
+                                detail["预估合同金额(万元)"] = val
+                break
+
+        return detail
+
     # ---------- 附件 ----------
 
     def _extract_attachments_from_detail(self, url: str) -> list:
@@ -275,9 +306,16 @@ class ZhejiangSpider(BaseSpider):
                 detail = self._parse_content_fields(rec.get("content", ""))
                 item.update(detail)
 
+                # 详情页补充：提取项目名称和批准文号等
+                self.detail_delay()
+                page_detail = self.parse_detail(link)
+                # 详情页字段仅补充，不覆盖已有值
+                for k, v in page_detail.items():
+                    if not item.get(k):
+                        item[k] = v
+
                 # 附件
                 if download_attachment and attachment_handler:
-                    self.detail_delay()
                     atts = self._extract_attachments_from_detail(link)
                     if atts:
                         item["附件数量"] = len(atts)