refactor(app): 重构 SPA报表下载功能

- 修改 __get_report_table_html 函数，增加重试逻辑，优化异常处理- 重命名 __get_report_table_html 为 __get_report_table_links，提高代码可读性
- 优化日志记录，增加更多详细信息
- 移除 tool_gui.py 中的 cleanup_resources 函数调用

app/vc/spa.py

@@ -32,8 +32,13 @@ class Spa(AutoInterface):
         full_url = host + url
         self.page.get(full_url, timeout=10)
 
-    def __get_report_table_html(self, invoice_id):
+    def __get_report_table_links(self, invoice_id):
+        retry_count = 0
         while True:
+            if retry_count > 5:
+                self.logger.warning(f"{invoice_id} 获取报表链接重试次数超过{retry_count}次,请检查发票号")
+                return None
+
             try:
                 self.__page_get(f"hz/vendor/members/coop?searchText={invoice_id}")
                 # 点击选项卡
@@ -42,16 +47,25 @@ class Spa(AutoInterface):
                 # 点击下载报表选项
                 # self.page.ele(f"#invoiceDownloads-{invoice_id}_2").click()
                 self.page.ele('xpath://li[a[contains(text(), "Backup report")]]/a').click()
-                self.page.wait(1)
+                self.page.wait(2)
+
                 # 获取报表表单内容
                 report_table_html = self.page.ele("#backup-report-table").html
                 if report_table_html is None or report_table_html == "":
                     self.logger.warning("表单内容为空,刷新网页")
                     self.page.refresh()
                     continue
-                return report_table_html
+
+                tree = etree.HTML(report_table_html)
+                links = tree.xpath('//table[@id="backup-report-table"]//a/@href')
+                if len(links) == 0:
+                    self.logger.warning(f"{invoice_id} 未获取到下载连接，开始重试...")
+                    retry_count += 1
+                    continue
+
+                return links
             except ElementNotFoundError:
-                self.logger.warning("元素未找到,刷新网页")
+                self.logger.warning(f"{invoice_id} 元素未找到,刷新网页")
                 self.page.refresh()
 
     def __export_item_read_data(self, invoice_id):
@@ -60,14 +74,12 @@ class Spa(AutoInterface):
             df = pd.read_excel(file_name, sheet_name=None)
             return df
 
-        # 获取报表表单内容
-        report_table_html = self.__get_report_table_html(invoice_id)
-        tree = etree.HTML(report_table_html)
-        # 提取所有链接
-        links = tree.xpath('//table[@id="backup-report-table"]//a/@href')
+        # 获取报表表单所有链接
+        links = self.__get_report_table_links(invoice_id)
         if len(links) == 0:
             # data_list = get_report_agreement_text(invoice_id)
             # return {"Accrual For Current Period": pd.DataFrame(data_list)}
+            self.logger.warning(f"{invoice_id} 没有下载连接")
             return None
 
         for link in links:
@@ -90,6 +102,7 @@ class Spa(AutoInterface):
                 header_is_normal = any(column in headers for column in column_names_to_check)
                 if not header_is_normal:
                     os.remove(report_file)
+                    self.logger.warning(f"{invoice_id} 文件格式不满足要求")
                     continue
 
                 save_report_file = os.path.join(os.getcwd(), "spa", str(invoice_id), "BackupReport.xls")
@@ -103,8 +116,8 @@ class Spa(AutoInterface):
                     data = df[df['Asin'].notna()]
                     excel.save_xls(data, file_name, sheet_name)
                 return pd.read_excel(file_name, sheet_name=None)
-            except ValueError as e:
-                self.logger.warning(f"{invoice_id} 文件格式错误: {e}")
+            except ValueError:
+                self.logger.warning(f"{invoice_id} 文件格式错误")
 
         return None
 

tool_gui.py

@@ -238,8 +238,6 @@ class VCManagerGUI(ttk.Window):
         except Exception as e:
             self.log(f"发生错误：{str(e)}")
             self.log(traceback.format_exc())
-        finally:
-            self.cleanup_resources()
 
     def init_browser(self):
         """初始化浏览器配置"""