Merge branch 'master' of https://gitee.com/TeaCodeNice/crawler-plugin

app/.env

@@ -1,3 +1,4 @@
+base_url=http://8.136.19.173:15124
 workflow_id=7608812635877900322
 mysql_host=8.136.19.173
 mysql_user=aiimage

app/amazon/approve.py

@@ -352,6 +352,8 @@ class AmzoneApprove(AmamzonBase):
                     print(f"没有获取到 ASIN 商品,重试{retry_num}/{max_retry_num}")
                     self.tab.refresh()
                     self.tab.wait.doc_loaded(raise_err=False, timeout=120)
+                    if retry_num == max_retry_num:
+                        raise RuntimeError(f"与页面的连接已断开，没有获取到 ASIN 商品,重试{retry_num}/{max_retry_num}")
                     continue
                 # for sku_ele in sku_ls[0:2]:
                 for sku_ele in sku_ls:

app/amazon/chrome_base.py

@@ -52,6 +52,7 @@ class ChromeAmzoneBase:
         print("正在启动chromium浏览器...")
         # 配置浏览器选项
         co = ChromiumOptions()
+        co.no_imgs(True)
         user_data_path = os.path.join(base_dir, "user_data", "chrome_data")
         if not os.path.exists(user_data_path):
             os.makedirs(user_data_path, exist_ok=True)
@@ -80,6 +81,11 @@ class ChromeAmzoneBase:
         关闭所有的初始化弹窗
         """
         self.tab.wait.doc_loaded(timeout=60, raise_err=True)
+        continue_shipping = self.tab.eles('xpath://button[@alt="Continue shopping"]',timeout=3)
+        if len(continue_shipping) > 0:
+            continue_shipping[0].click()
+            time.sleep(0.5)
+            self.tab.wait.doc_loaded(timeout=60, raise_err=True)
         footbar = self.tab.eles('xpath://footer[@class="el-dialog__footer"]', timeout=5)
         if len(footbar) > 0:
             do_not_remind = footbar[0].eles('xpath:.//input[@class="el-checkbox__original"]')

app/amazon/detail_spider.py

@@ -111,15 +111,10 @@ class ChromeAmzone(ChromeAmzoneBase):
 
 
 
-class SpiderTask(TaskBase):
-    task_name = "亚马逊采集"
-    mark_name = "亚马逊采集"
-
-    def __init__(self, user_info: dict = None):
-        super().__init__(user_info)
-        self.result_api_module = "appearance-patent"
-
-    @staticmethod
+class SpiderTask(TaskBase):
+    task_name = "亚马逊采集"
+
+    @staticmethod
     def group_by_id_prefix(data):
         """
         根据每条数据的 id 字段进行分组：
@@ -164,20 +159,18 @@ class SpiderTask(TaskBase):
             })
         return normalized
 
-    def process_task(self, task_data: dict):
-        """处理审批任务主入口
-
-        Args:
-            task_data: 任务数据
-        """
-        task_id = None
-        try:
-            data = task_data.get("data", {})
-            task_id = data.get("taskId")
-            groups = self.normalize_groups(data)
-            self.result_api_module = "similar-asin" if task_data.get("type") == "similar-asin-run" else "appearance-patent"
-
-            # 用于测试
+    def process_task(self, task_data: dict):
+        """处理审批任务主入口
+
+        Args:
+            task_data: 任务数据
+        """
+        try:
+            data = task_data.get("data", {})
+            task_id = data.get("taskId")
+            groups = self.normalize_groups(data)
+
+            # 用于测试
             limit = data.get("limit", None)
 
             if not task_id:
@@ -308,22 +301,22 @@ class SpiderTask(TaskBase):
                     runing_task[task_id]["status"] = "failed"
                     runing_task[task_id]["error"] = str(e)
 
-    def post_result(self, task_id: int, chunkIndex:int,chunkTotal: int, asin: str, error:str="",
-                    item_data=None,
-                    is_done: bool = False):
-        """回传处理结果到API
-        """
+    def post_result(self, task_id: int, chunkIndex:int,chunkTotal: int, asin: str, error:str="",
+                    item_data:dict={},
+                    is_done: bool = False):
+        """回传处理结果到API
+        """
 
-        url = f"{DELETE_BRAND_API_BASE}/api/{self.result_api_module}/tasks/{task_id}/result"
+        url = f"{DELETE_BRAND_API_BASE}/api/appearance-patent/tasks/{task_id}/result"
 
-        payload ={
-          "submissionId": f"{task_id}",
-          "chunkIndex": chunkIndex,
-          "chunkTotal": chunkTotal,
-          "error": error,
-          "groups": item_data or [],
-          "done": is_done
-        }
+        payload ={
+          "submissionId": f"{task_id}",
+          "chunkIndex": chunkIndex,
+          "chunkTotal": chunkTotal,
+          "error": error,
+          "groups": item_data,
+          "done": is_done
+        }
 
         max_retries = 3
         for retry in range(max_retries):
@@ -333,13 +326,13 @@ class SpiderTask(TaskBase):
                 self.log(f"尝试回传结果 (第 {retry + 1}/{max_retries} 次)")
                 self.log(f"回传URL: {url}")
                 self.log(f"回传数据: {payload}")
-                response = requests.post(
-                    url,
-                    data=json.dumps(payload, ensure_ascii=False).encode("utf-8"),
-                    headers={"Content-Type": "application/json; charset=utf-8"},
-                    timeout=request_timeout,
-                    verify=False
-                )
+                response = requests.post(
+                    url,
+                    json=payload,
+                    headers={"Content-Type": "application/json"},
+                    timeout=request_timeout,
+                    verify=False
+                )
                 self.log(f"回传结果: {response.text}")
                 data = response.json() if response.text else {}
                 if response.status_code == 200 and isinstance(data, dict) and data.get("success"):

app/amazon/main.py

@@ -12,7 +12,7 @@ from amazon.price_match import PriceTask
 from amazon.asin_status import StatusTask
 from amazon.patrol_delete import PatrolDeleteTask
 from amazon.detail_spider import SpiderTask
-
+from amazon.similar_asin import SimilarAsinTask
 from amazon.amazon_base import kill_process
 
 
@@ -62,11 +62,11 @@ class TaskMonitor:
             "product-risk-resolve-run" : "产品风险审批",
             "shop-match-run" : "匹配价格",
             "price-track-run" : "跟价",
-            "query-asin-run" : "状态查询",
-            "patrol-delete-run" : "巡店删除",
-            "appearance-patent-run" : "亚马逊采集",
-            "similar-asin-run" : "亚马逊采集",
-        }
+            "query-asin-run" : "状态查询",
+            "patrol-delete-run" : "巡店删除",
+            "appearance-patent-run" : "亚马逊采集",
+            "similar-asin-run" : "相似ASIN"
+        }
         try:
             while self.running:
                 try:
@@ -140,6 +140,7 @@ class TaskMonitor:
                 "状态查询" : StatusTask,
                 "巡店删除" : PatrolDeleteTask,
                 "亚马逊采集" : SpiderTask,
+                "相似ASIN" : SimilarAsinTask
             }
             self.log(f"线程 {id(task_data)} 开始处理产品风险审批任务...")
             # 创建ApproveTask实例并处理任务

app/amazon/price_match.py

@@ -37,7 +37,7 @@ class RepricingLogic:
             # 0.8 到 10.5 之间全部是在减1
             return rank1_price - (diff + 1.0)
         else:
-            return None  # 相差10.5以上，跳过
+            return rank1_price - 10.5  # 相差10.5以上，跳过
 
     @staticmethod
     def situation_2_own_buybox(my_price, rank2_price):
@@ -582,6 +582,8 @@ class AmzonePriceMatch(AmamzonBase):
                     self.log(f"没有获取到 ASIN 商品,重试{retry_num}/{max_retry_num}")
                     self.tab.refresh()
                     self.tab.wait.doc_loaded(raise_err=False, timeout=120)
+                    if retry_num == max_retry_num:
+                        raise RuntimeError(f"与页面的连接已断开，没有获取到 ASIN 商品,重试{retry_num}/{max_retry_num}")
                     continue
 
                 # for sku_ele in sku_ls[0:2]:
@@ -977,7 +979,7 @@ class PriceTask(TaskBase):
         country_name = self.country_info.get(country_code, country_code)
         info_mes = f"开始处理国家: {country_name} ({country_code}),需要跳过的asin {skip_asin}"
         self.log(info_mes)
-        show_notification(info_mes, "info")
+        show_notification(f"开始处理国家:{country_name}", "info")
 
         # 更新当前处理的国家
         if task_id in runing_task:
@@ -1216,7 +1218,7 @@ class PriceTask(TaskBase):
             max_retries = 3
             for retry in range(max_retries):
                 try:
-                    print("================【跟价】=====================")
+                    self.log("================【跟价】=====================")
                     self.log(f"尝试回传结果 (第 {retry + 1}/{max_retries} 次)")
                     self.log(f"回传URL: {url}")
                     self.log(f"回传数据: {payload}")
@@ -1234,11 +1236,11 @@ class PriceTask(TaskBase):
                         return
                     else:
                         self.log(f"结果回传失败，状态码: {response.status_code}", "WARNING")
-                    print("=====================================")
+                    self.log("=====================================")
 
                 except Exception as e:
                     self.log(f"调用API异常: {str(e)}", "ERROR")
-                    print("=====================================")
+                    self.log("=====================================")
 
                 # 如果还有重试机会，等待后继续
                 if retry < max_retries - 1:

app/amazon/similar_asin.py

@@ -1,3 +1,5 @@
+# encoding utf-8
+
 import json
 from pathlib import Path
 import base64
@@ -20,6 +22,17 @@ from amazon.chrome_base import ChromeAmzoneBase
 
 from config import runing_task, runing_shop,base_dir,DELETE_BRAND_API_BASE
 
+try:
+    from config import proxy_url as CONFIG_PROXY_URL, proxy_mode as CONFIG_PROXY_MODE
+except ImportError:
+    CONFIG_PROXY_URL = None
+    CONFIG_PROXY_MODE = 1
+
+# Forbidden 后 3 分钟内统一使用代理：记录代理生效截止时间与当前代理
+_FORBIDDEN_PROXY_UNTIL = 0.0
+_FORBIDDEN_PROXY_DICT = None
+_FORBIDDEN_PROXY_MINUTES = 0.5
+
 
 class ChromeAmzone(ChromeAmzoneBase):
     mark_name = "亚马逊相似ASIN"
@@ -81,6 +94,8 @@ class ChromeAmzone(ChromeAmzoneBase):
         标题 :
         
         """
+        global _FORBIDDEN_PROXY_UNTIL, _FORBIDDEN_PROXY_DICT
+        
         headers = {
             "accept": "application/json, text/plain, */*",
             "accept-language": "zh-CN,zh;q=0.9,en;q=0.8",
@@ -126,11 +141,93 @@ class ChromeAmzone(ChromeAmzoneBase):
         data = {
             "imageBase64" : imageBase64
         }
-        response = requests.post(url, headers=headers, params=params, json=data, impersonate="chrome101",
-                                 cookies=cookie)
-        response.encoding = "utf-8"
-        data = response.json()
-        return data
+        
+        proxies = None
+        
+        # 若 3 分钟内曾出现 Forbidden，则直接使用当时保存的代理
+        now = time.time()
+        if now < _FORBIDDEN_PROXY_UNTIL and _FORBIDDEN_PROXY_DICT:
+            proxies = _FORBIDDEN_PROXY_DICT
+            print("处于 Forbidden 代理窗口内，直接使用代理", proxies)
+        
+        # 发送第一次请求
+        try:
+            response = requests_frp.post(url, headers=headers, params=params, json=data, impersonate="chrome101",
+                                     cookies=cookie, proxies=proxies)
+            response.encoding = "utf-8"
+            
+            # 检查响应状态码和数据有效性
+            need_retry = False
+            if response.status_code != 200:
+                print(f"请求失败，状态码: {response.status_code}")
+                need_retry = True
+            else:
+                try:
+                    result_data = response.json()
+                    # 检查是否获取到有效数据
+                    if not result_data or not isinstance(result_data, dict):
+                        print("返回数据为空或格式不正确")
+                        need_retry = True
+                    elif "Forbidden" in response.text or "Too Many Requests" in response.text:
+                        print("返回Forbidden或Too Many Requests")
+                        need_retry = True
+                except Exception as e:
+                    print(f"解析响应JSON失败: {e}")
+                    need_retry = True
+            
+            # 如果需要重试且配置了代理URL
+            if need_retry and CONFIG_PROXY_URL and not proxies:
+                try:
+                    proxy_resp = requests.get(CONFIG_PROXY_URL, timeout=10)
+                    print("代理请求结果->：", proxy_resp.text)
+                    
+                    # 模式 2：账号密码代理，接口返回 JSON
+                    if CONFIG_PROXY_MODE == 2:
+                        resp_json = proxy_resp.json()
+                        proxy_list = resp_json.get("data", {}).get("list") or []
+                        first_item = proxy_list[0] if proxy_list else None
+                        if first_item:
+                            ip = first_item.get("ip")
+                            port = first_item.get("port")
+                            account = first_item.get("account")
+                            password = first_item.get("password")
+                            if ip and port and account and password:
+                                auth_proxy = f"{account}:{password}@{ip}:{port}"
+                                print("获取到账号密码代理：", auth_proxy)
+                                proxies = {
+                                    "http": f"http://{auth_proxy}",
+                                    "https": f"http://{auth_proxy}",
+                                }
+                    # 默认模式 1：普通 IP:port 文本
+                    if CONFIG_PROXY_MODE != 2:
+                        proxy_ip = (proxy_resp.text or "").strip()
+                        if proxy_ip:
+                            proxies = {
+                                "http": f"http://{proxy_ip}",
+                                "https": f"http://{proxy_ip}",
+                            }
+                    
+                    if proxies:
+                        print("使用代理重试请求")
+                        response = requests_frp.post(url, headers=headers, params=params, json=data, 
+                                                 impersonate="chrome101", cookies=cookie, proxies=proxies)
+                        response.encoding = "utf-8"
+                        print("代理重试结果状态码:", response.status_code)
+                        
+                        # 记录 3 分钟内都使用该代理
+                        _FORBIDDEN_PROXY_UNTIL = now + _FORBIDDEN_PROXY_MINUTES * 60
+                        _FORBIDDEN_PROXY_DICT = proxies
+                        
+                except Exception as e:
+                    print("获取代理或重试失败:", e)
+            
+            # 返回最终结果
+            result_data = response.json()
+            return result_data
+            
+        except Exception as e:
+            print(f"get_aliprice_data 请求异常: {e}")
+            return {}
 
     def _scrape_data(self):
         """
@@ -276,8 +373,8 @@ class SimilarAsinTask(TaskBase):
 
         return list(grouped.values())
 
-    @staticmethod
-    def normalize_groups(data):
+    @staticmethod
+    def normalize_groups(data):
         groups = data.get("groups")
         if isinstance(groups, list) and len(groups) > 0:
             return groups
@@ -299,71 +396,71 @@ class SimilarAsinTask(TaskBase):
                 "displayId": first.get("displayId") or item_id,
                 "items": items,
             })
-        return normalized
-
-    def fetch_parsed_payload(self, task_id, user_id=1):
-        url = f"{DELETE_BRAND_API_BASE}/api/similar-asin/tasks/{task_id}/parsed-payload"
-        response = requests.get(url, params={"user_id": user_id}, timeout=300, verify=False)
-        response.raise_for_status()
-        payload = response.json() if response.text else {}
-        if isinstance(payload, dict) and payload.get("success"):
-            return payload.get("data") or {}
-        raise RuntimeError(f"获取货源查询解析载荷失败: {payload}")
+        return normalized
 
-    @staticmethod
-    def _count_payload_rows(data):
-        rows = data.get("rows") or data.get("items") or []
-        if isinstance(rows, list) and rows:
-            return len(rows)
-
-        groups = data.get("groups") or []
-        if not isinstance(groups, list):
-            return 0
-
-        total = 0
-        for group in groups:
-            if isinstance(group, dict) and isinstance(group.get("items"), list):
-                total += len(group.get("items"))
-        return total
-
-    def _merge_parsed_payload(self, data, parsed_payload):
-        payload_rows = parsed_payload.get("allItems") or parsed_payload.get("items") or []
-        merged = {
-            **data,
-            "groups": parsed_payload.get("groups") or [],
-            "rows": payload_rows,
-        }
-        if parsed_payload.get("aiPrompt"):
-            merged["prompt"] = parsed_payload.get("aiPrompt")
-        if parsed_payload.get("apiKey") and not merged.get("api_key"):
-            merged["api_key"] = parsed_payload.get("apiKey")
-        return merged
-
-    def process_task(self, task_data: dict):
+    def fetch_parsed_payload(self, task_id, user_id=1):
+        url = f"{DELETE_BRAND_API_BASE}/api/similar-asin/tasks/{task_id}/parsed-payload"
+        response = requests.get(url, params={"user_id": user_id}, timeout=300, verify=False)
+        response.raise_for_status()
+        payload = response.json() if response.text else {}
+        if isinstance(payload, dict) and payload.get("success"):
+            return payload.get("data") or {}
+        raise RuntimeError(f"获取货源查询解析载荷失败: {payload}")
+
+    @staticmethod
+    def _count_payload_rows(data):
+        rows = data.get("rows") or data.get("items") or []
+        if isinstance(rows, list) and rows:
+            return len(rows)
+
+        groups = data.get("groups") or []
+        if not isinstance(groups, list):
+            return 0
+
+        total = 0
+        for group in groups:
+            if isinstance(group, dict) and isinstance(group.get("items"), list):
+                total += len(group.get("items"))
+        return total
+
+    def _merge_parsed_payload(self, data, parsed_payload):
+        payload_rows = parsed_payload.get("allItems") or parsed_payload.get("items") or []
+        merged = {
+            **data,
+            "groups": parsed_payload.get("groups") or [],
+            "rows": payload_rows,
+        }
+        if parsed_payload.get("aiPrompt"):
+            merged["prompt"] = parsed_payload.get("aiPrompt")
+        if parsed_payload.get("apiKey") and not merged.get("api_key"):
+            merged["api_key"] = parsed_payload.get("apiKey")
+        return merged
+
+    def process_task(self, task_data: dict):
         """处理审批任务主入口
 
         Args:
             task_data: 任务数据
         """
         try:
-            data = task_data.get("data", {})
-            task_id = data.get("taskId")
-            if task_id:
-                queued_rows = self._count_payload_rows(data)
-                try:
-                    parsed_payload = self.fetch_parsed_payload(task_id, data.get("user_id") or data.get("userId") or 1)
-                    data = self._merge_parsed_payload(data, parsed_payload)
-                    self.log(
-                        f"similar asin task {task_id} loaded full parsed payload from Java, queuedRows={queued_rows}, fullRows={self._count_payload_rows(data)}"
-                    )
-                except Exception as e:
-                    if not queued_rows:
-                        raise
-                    self.log(
-                        f"similar asin task {task_id} failed to load full parsed payload, fallback to queued rows={queued_rows}: {e}",
-                        "WARNING"
-                    )
-            groups = self.normalize_groups(data)
+            data = task_data.get("data", {})
+            task_id = data.get("taskId")
+            if task_id:
+                queued_rows = self._count_payload_rows(data)
+                try:
+                    parsed_payload = self.fetch_parsed_payload(task_id, data.get("user_id") or data.get("userId") or 1)
+                    data = self._merge_parsed_payload(data, parsed_payload)
+                    self.log(
+                        f"similar asin task {task_id} loaded full parsed payload from Java, queuedRows={queued_rows}, fullRows={self._count_payload_rows(data)}"
+                    )
+                except Exception as e:
+                    if not queued_rows:
+                        raise
+                    self.log(
+                        f"similar asin task {task_id} failed to load full parsed payload, fallback to queued rows={queued_rows}: {e}",
+                        "WARNING"
+                    )
+            groups = self.normalize_groups(data)
 
             if not task_id:
                 self.log("任务ID为空，跳过", "WARNING")
@@ -439,6 +536,8 @@ class SimilarAsinTask(TaskBase):
                             "country": i.get("country"),
                             "url": return_data.get("image_url"),
                             "title": return_data.get("title"),
+                            "done": False,
+                            "urls" : [i.get("ori_picture") for i in return_data.get("similar_data")]
                         }
                          for i in items
                     ]
@@ -452,6 +551,7 @@ class SimilarAsinTask(TaskBase):
                       "displayId": gp.get("displayId"),
                       "items": group_item
                     }
+
                     print("================")
                     result.append(res)
                     print("================")
@@ -500,10 +600,10 @@ class SimilarAsinTask(TaskBase):
         """回传处理结果到API
         """
 
-        url = f"{DELETE_BRAND_API_BASE}/api/similar-asin/tasks/{task_id}/result"
+        url = f"{DELETE_BRAND_API_BASE}/api/similar-asin/tasks/{task_id}/result"
 
         payload ={
-          "submissionId": f"{int(time.time())}",
+          "submissionId": f"{task_id}",
           "chunkIndex": chunkIndex,
           "chunkTotal": chunkTotal,
           "error": error,
@@ -519,13 +619,13 @@ class SimilarAsinTask(TaskBase):
                 self.log(f"尝试回传结果 (第 {retry + 1}/{max_retries} 次)")
                 self.log(f"回传URL: {url}")
                 self.log(f"回传数据: {payload}")
-                response = requests.post(
-                    url,
-                    data=json.dumps(payload, ensure_ascii=False).encode("utf-8"),
-                    headers={"Content-Type": "application/json; charset=utf-8"},
-                    timeout=request_timeout,
-                    verify=False
-                )
+                response = requests.post(
+                    url,
+                    json=payload,
+                    headers={"Content-Type": "application/json"},
+                    timeout=request_timeout,
+                    verify=False
+                )
                 self.log(f"回传结果: {response.text}")
                 data = response.json() if response.text else {}
                 if response.status_code == 200 and isinstance(data, dict) and data.get("success"):
@@ -553,6 +653,263 @@ if __name__ == '__main__':
         country="英国", asin="B0F79LCB3X", total_page=2
     )
     print(resp)
+#     task_data = {
+#     "type": "similar-asin-run",
+#     "ts": 1778038688824,
+#     "data": {
+#         "taskId": 6850,
+#         "api_key": "sk-EMcDFg36zCeWUtCbRzKUbrRZyNeC6M4KBhY6fAVcNP7GG4xI",
+#         "groups": [
+#             {
+#                 "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                 "sourceFilename": "17(1) - 副本1.xlsx",
+#                 "groupKey": "similar-asin:6850",
+#                 "baseId": "",
+#                 "displayId": "1",
+#                 "items": [
+#                     {
+#                         "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                         "sourceFilename": "17(1) - 副本1.xlsx",
+#                         "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::2",
+#                         "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::1@2",
+#                         "id": "1",
+#                         "asin": "B0D792ND9V",
+#                         "country": "英国",
+#                         "price": "12.29",
+#                         "url": "",
+#                         "title": "",
+#                         "target_urls": []
+#                     },
+#                     {
+#                         "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                         "sourceFilename": "17(1) - 副本1.xlsx",
+#                         "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::3",
+#                         "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::2@3",
+#                         "id": "2_1",
+#                         "asin": "B0D14L34S7",
+#                         "country": "英国",
+#                         "price": "14.88",
+#                         "url": "",
+#                         "title": "",
+#                         "target_urls": []
+#                     },
+#                     {
+#                         "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                         "sourceFilename": "17(1) - 副本1.xlsx",
+#                         "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::4",
+#                         "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::2@3",
+#                         "id": "2_2",
+#                         "asin": "B0D14N8FJY",
+#                         "country": "英国",
+#                         "price": "15.36",
+#                         "url": "",
+#                         "title": "",
+#                         "target_urls": []
+#                     },
+#                     {
+#                         "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                         "sourceFilename": "17(1) - 副本1.xlsx",
+#                         "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::5",
+#                         "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::2@3",
+#                         "id": "2_3",
+#                         "asin": "B0D14NBL5D",
+#                         "country": "英国",
+#                         "price": "14.87",
+#                         "url": "",
+#                         "title": "",
+#                         "target_urls": []
+#                     },
+#                     {
+#                         "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                         "sourceFilename": "17(1) - 副本1.xlsx",
+#                         "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::6",
+#                         "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::2@3",
+#                         "id": "2_4",
+#                         "asin": "B0D14M5X4J",
+#                         "country": "英国",
+#                         "price": "14.41",
+#                         "url": "",
+#                         "title": "",
+#                         "target_urls": []
+#                     },
+#                     {
+#                         "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                         "sourceFilename": "17(1) - 副本1.xlsx",
+#                         "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::7",
+#                         "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::3@7",
+#                         "id": "3_1",
+#                         "asin": "B0CWQFZMGY",
+#                         "country": "英国",
+#                         "price": "17.05",
+#                         "url": "",
+#                         "title": "",
+#                         "target_urls": []
+#                     },
+#                     {
+#                         "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                         "sourceFilename": "17(1) - 副本1.xlsx",
+#                         "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::8",
+#                         "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::3@7",
+#                         "id": "3_2",
+#                         "asin": "B0CX8D68L3",
+#                         "country": "英国",
+#                         "price": "16.46",
+#                         "url": "",
+#                         "title": "",
+#                         "target_urls": []
+#                     },
+#                     {
+#                         "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                         "sourceFilename": "17(1) - 副本1.xlsx",
+#                         "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::9",
+#                         "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::4@9",
+#                         "id": "4_1",
+#                         "asin": "B0CX87XXWJ",
+#                         "country": "英国",
+#                         "price": "17.54",
+#                         "url": "",
+#                         "title": "",
+#                         "target_urls": []
+#                     },
+#                     {
+#                         "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                         "sourceFilename": "17(1) - 副本1.xlsx",
+#                         "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::10",
+#                         "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::5@10",
+#                         "id": "5_1",
+#                         "asin": "B0CR3PMR8L",
+#                         "country": "英国",
+#                         "price": "16.74",
+#                         "url": "",
+#                         "title": "",
+#                         "target_urls": []
+#                     }
+#                 ]
+#             }
+#         ],
+#         "rows": [
+#             {
+#                 "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                 "sourceFilename": "17(1) - 副本1.xlsx",
+#                 "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::2",
+#                 "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::1@2",
+#                 "id": "1",
+#                 "asin": "B0D792ND9V",
+#                 "country": "英国",
+#                 "price": "12.29",
+#                 "url": "",
+#                 "title": "",
+#                 "target_urls": []
+#             },
+#             {
+#                 "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                 "sourceFilename": "17(1) - 副本1.xlsx",
+#                 "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::3",
+#                 "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::2@3",
+#                 "id": "2_1",
+#                 "asin": "B0D14L34S7",
+#                 "country": "英国",
+#                 "price": "14.88",
+#                 "url": "",
+#                 "title": "",
+#                 "target_urls": []
+#             },
+#             {
+#                 "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                 "sourceFilename": "17(1) - 副本1.xlsx",
+#                 "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::4",
+#                 "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::2@3",
+#                 "id": "2_2",
+#                 "asin": "B0D14N8FJY",
+#                 "country": "英国",
+#                 "price": "15.36",
+#                 "url": "",
+#                 "title": "",
+#                 "target_urls": []
+#             },
+#             {
+#                 "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                 "sourceFilename": "17(1) - 副本1.xlsx",
+#                 "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::5",
+#                 "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::2@3",
+#                 "id": "2_3",
+#                 "asin": "B0D14NBL5D",
+#                 "country": "英国",
+#                 "price": "14.87",
+#                 "url": "",
+#                 "title": "",
+#                 "target_urls": []
+#             },
+#             {
+#                 "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                 "sourceFilename": "17(1) - 副本1.xlsx",
+#                 "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::6",
+#                 "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::2@3",
+#                 "id": "2_4",
+#                 "asin": "B0D14M5X4J",
+#                 "country": "英国",
+#                 "price": "14.41",
+#                 "url": "",
+#                 "title": "",
+#                 "target_urls": []
+#             },
+#             {
+#                 "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                 "sourceFilename": "17(1) - 副本1.xlsx",
+#                 "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::7",
+#                 "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::3@7",
+#                 "id": "3_1",
+#                 "asin": "B0CWQFZMGY",
+#                 "country": "英国",
+#                 "price": "17.05",
+#                 "url": "",
+#                 "title": "",
+#                 "target_urls": []
+#             },
+#             {
+#                 "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                 "sourceFilename": "17(1) - 副本1.xlsx",
+#                 "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::8",
+#                 "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::3@7",
+#                 "id": "3_2",
+#                 "asin": "B0CX8D68L3",
+#                 "country": "英国",
+#                 "price": "16.46",
+#                 "url": "",
+#                 "title": "",
+#                 "target_urls": []
+#             },
+#             {
+#                 "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                 "sourceFilename": "17(1) - 副本1.xlsx",
+#                 "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::9",
+#                 "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::4@9",
+#                 "id": "4_1",
+#                 "asin": "B0CX87XXWJ",
+#                 "country": "英国",
+#                 "price": "17.54",
+#                 "url": "",
+#                 "title": "",
+#                 "target_urls": []
+#             },
+#             {
+#                 "sourceFileKey": "cdfa437df62b40a0bde5682a05c1f6a3",
+#                 "sourceFilename": "17(1) - 副本1.xlsx",
+#                 "rowToken": "cdfa437df62b40a0bde5682a05c1f6a3::row::10",
+#                 "groupKey": "cdfa437df62b40a0bde5682a05c1f6a3::5@10",
+#                 "id": "5_1",
+#                 "asin": "B0CR3PMR8L",
+#                 "country": "英国",
+#                 "price": "16.74",
+#                 "url": "",
+#                 "title": "",
+#                 "target_urls": []
+#             }
+#         ]
+#     }
+# }
+#     sim_asin = SimilarAsinTask({})
+#     sim_asin.process_task(task_data)
 
 
 

app/amazon/tool.py

@@ -124,7 +124,6 @@ def remove_special_characters(text: str) -> str:
     return cleaned
 
 
-
 def split_currency_values(currency_str: str) -> tuple[float, float]:
     """
     将包含两个货币值的字符串拆分成两个浮点数。

app/amazon/user_data/chrome_data/Default/BookmarkMergedSurfaceOrdering

@@ -0,0 +1,2 @@
+{
+}

app/amazon/user_data/chrome_data/Default/BrowsingTopicsState

@@ -0,0 +1,12 @@
+{
+   "epochs": [ {
+      "calculation_time": "13422512990906273",
+      "config_version": 0,
+      "model_version": "0",
+      "padded_top_topics_start_index": 0,
+      "taxonomy_version": 0,
+      "top_topics_and_observing_domains": [  ]
+   } ],
+   "hex_encoded_hmac_key": "57AA4C4DDB252DC6FA3F442115CBE555E87CBF826CA55E9705992FE3B34B6B58",
+   "next_scheduled_calculation_time": "13423117790906516"
+}