更新处理这个外观部分

app/amazon/detail_spider.py

@@ -288,7 +288,7 @@ class SpiderTask:
         print(f"[{timestamp}] [PriceTask] [{level}] {message}")
 
     @staticmethod
-    def group_by_id_prefix(data):
+    def group_by_id_prefix(data):
         """
         根据每条数据的 id 字段进行分组：
         - 如果 id 为 "2_1"，则取 "_" 前面的 "2" 作为分组 key
@@ -304,10 +304,35 @@ class SpiderTask:
             item_id = str(item.get("id", ""))
             group_key = item_id.split("_")[0]
             grouped[group_key].append(item)
-
-        return list(grouped.values())
-
-    def process_task(self, task_data: dict):
+
+        return list(grouped.values())
+
+    @staticmethod
+    def normalize_groups(data):
+        groups = data.get("groups")
+        if isinstance(groups, list) and len(groups) > 0:
+            return groups
+
+        rows = data.get("rows") or data.get("items") or []
+        if not isinstance(rows, list) or len(rows) == 0:
+            return []
+
+        normalized = []
+        for items in SpiderTask.group_by_id_prefix(rows):
+            first = items[0] if items else {}
+            item_id = str(first.get("id") or first.get("displayId") or "")
+            base_id = item_id.split("_")[0] if item_id else ""
+            normalized.append({
+                "sourceFileKey": first.get("sourceFileKey", ""),
+                "sourceFilename": first.get("sourceFilename", ""),
+                "groupKey": first.get("groupKey") or base_id,
+                "baseId": first.get("baseId") or base_id,
+                "displayId": first.get("displayId") or item_id,
+                "items": items,
+            })
+        return normalized
+
+    def process_task(self, task_data: dict):
         """处理审批任务主入口
 
         Args:
@@ -316,7 +341,7 @@ class SpiderTask:
         try:
             data = task_data.get("data", {})
             task_id = data.get("taskId")
-            groups = data.get("groups")
+            groups = self.normalize_groups(data)
 
             # 用于测试
             limit = data.get("limit", None)
@@ -328,7 +353,11 @@ class SpiderTask:
 
             self.log(f"开始处理爬取任务 {task_id}，{len(groups)} 个任务")
 
-            from config import runing_task
+            if not groups:
+                self.log("appearance-patent groups/rows is empty, skip", "WARNING")
+                return
+
+            from config import runing_task
             runing_task[task_id] = {
                 "status": "running",
                 "start_time": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
@@ -354,11 +383,12 @@ class SpiderTask:
             try:
                 # 数据整理
                 # new_items = self.group_by_id_prefix(items)
-                result = []
-                for gp_index,gp in enumerate(groups):
-                    items = gp.get("items", [])
-
-                    for index,value in enumerate(items):
+                result = []
+                for gp_index,gp in enumerate(groups):
+                    items = gp.get("items", [])
+                    return_data = {}
+
+                    for index,value in enumerate(items):
 
                         return_data = {
                             'image_url': "",
@@ -369,13 +399,15 @@ class SpiderTask:
                         return_data = None
                         for _ in range(max_retry):
                             try:
-                                return_data = chrome.run(country, asin)
+                                return_data = chrome.run(country, asin) or {}
                                 self.log(f"抓取结果->{return_data}")
                                 break
                             except Exception as e:
                                 if "与页面的连接已断开" in str(e):
                                     chrome = ChromeAmzone()
-                        if return_data.get("image_url"):
+                        if not isinstance(return_data, dict):
+                            return_data = {}
+                        if return_data.get("image_url"):
                             break
 
                     group_item = [
@@ -8381,4 +8413,4 @@ if __name__ == '__main__':
 ]
     # spide.process_task(task_data)
     res = SpiderTask.group_by_id_prefix(task_data)
-    print(res)
+    print(res)