no message

.idea/.gitignore

+# 默认忽略的文件
+/shelf/
+/workspace.xml
+# 基于编辑器的 HTTP 客户端请求
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/git_code.iml

+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="PLAIN" />
+    <option name="myDocStringFormat" value="Plain" />
+  </component>
+</module>
\ No newline at end of file

.idea/inspectionProfiles/profiles_settings.xml

+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file

.idea/misc.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file

.idea/modules.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/git_code.iml" filepath="$PROJECT_DIR$/.idea/git_code.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file

.idea/vcs.xml

+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file

hjm_spider_code/app_amazon_image_recognition/app_amazon_image_recognition.py

+import hashlib
+import time
+import uuid
+from typing import Optional, List
+from loguru import logger
+import requests
+from requests.exceptions import RequestException, ConnectionError, Timeout
+
+# 配置日志
+logger.add("amazon_search.log", rotation="10 MB", level="INFO")
+
+# 全局变量（clientDeviceId 固定，cookie 失效时更新）
+GLOBAL_CLIENT_DEVICE_ID = str(uuid.uuid4())
+logger.info(f"初始化全局 clientDeviceId: {GLOBAL_CLIENT_DEVICE_ID}")
+
+# 常量配置
+AMAZON_STYLE_SNAP_URL = "https://match-visualsearch.amazon.com/style-snap/2.0"
+AMAZON_SEARCH_BASE_URL = "https://www.amazon.com/s?rh=p_78:{bbx_asin_list}&rank=asin-scores-asc-rank&searchMethod=CameraSearch"
+SECRET = "5b6874d3a20417591bd5464a25a37bc6"
+APPLICATION = "amzn-mbl-cscan-us"
+USERNAME = "amzn-mbl-cscan-us"
+RETRY_TIMES = 5 # 重试次数
+RETRY_DELAY = 1  # 重试间隔（秒）
+
+
+def get_amazon_search_url(image_path: str, cookies: dict) -> Optional[str]:
+    """
+    调用亚马逊以图搜物接口，获取搜索结果并生成最终搜索URL
+
+    :param image_path: 图片本地路径
+    :param cookies: 亚马逊请求所需的cookies
+    :return: 拼接后的搜索URL，失败时返回None
+    """
+    for retry in range(RETRY_TIMES):
+        try:
+            logger.info(f"开始第 {retry + 1}/{RETRY_TIMES} 次请求")
+
+            # 1. 准备动态参数
+            session_id = cookies.get("session-id", "")
+            if not session_id:
+                logger.error("Cookies中缺少session-id")
+                return None
+
+            client_id = str(uuid.uuid4())  # 每次请求生成新的clientId
+            ts = str(int(time.time()))
+
+            # 2. 生成authtoken
+            combined = SECRET + USERNAME + APPLICATION + ts
+            authtoken = hashlib.sha512(combined.encode("utf-8")).hexdigest()
+            logger.debug(f"生成authtoken: {authtoken[:10]}...")  # 只打印前10位避免过长
+
+            # 3. 构建query_metadata
+            query_metadata = (
+                    '{"amznSessionId":"%s","clientVersion":"30.20.2.100","cardsVersion":"1.0",'
+                    '"clientMessageVersion":"1.0","amznDirectedCustomerId":"","clientDeviceId":"%s",'
+                    '"clientDevice":"Android - Pixel 2","deviceManufacturer":"Google","clientDeviceVersion":"10",'
+                    '"clientId":"%s","orientation":"-1","sourceType":"Photo","ingressSource":"ctp","uiMode":"stylesnap"}'
+                    % (session_id, GLOBAL_CLIENT_DEVICE_ID, client_id)
+            )
+            # logger.debug(f"构建query_metadata: {query_metadata[:50]}...")  # 只打印前50位
+
+            # 4. 读取图片文件
+            try:
+                with open(image_path, "rb") as f:
+                    image_data = f.read()
+                logger.info(f"成功读取图片: {image_path} (大小: {len(image_data)} bytes)")
+            except Exception as e:
+                logger.error(f"读取图片失败: {str(e)}", exc_info=True)
+                return None  # 图片错误无需重试
+
+            # 5. 构建请求头
+            headers = {
+                "x-amz-access-token": "",
+                "x-amz-lens-session-auth-token": cookies.get("session-token", ""),
+                "x-amz-lens-session-id": session_id,
+                "x-amz-lens-ubid": cookies.get("ubid-main", ""),
+                "accept-encoding": "gzip",
+                "user-agent": "okhttp/4.9.1"
+            }
+
+            # 6. 构建表单数据
+            files = [
+                ("application", (None, APPLICATION, "multipart/form-data; charset=utf-8")),
+                ("query_metadata", (None, query_metadata, "multipart/form-data; charset=utf-8")),
+                ("authtoken", (None, authtoken, "multipart/form-data; charset=utf-8")),
+                ("lang", (None, "en_US", "multipart/form-data; charset=utf-8")),
+                ("username", (None, USERNAME, "multipart/form-data; charset=utf-8")),
+                ("ts", (None, ts, "multipart/form-data; charset=utf-8")),
+                ("file", ("", image_data, "image/jpeg"))
+            ]
+
+            # 7. 发送请求
+            logger.info("发送POST请求到亚马逊以图搜物接口")
+            response = requests.post(
+                url=AMAZON_STYLE_SNAP_URL,
+                headers=headers,
+                files=files,
+                cookies=cookies,
+                timeout=10  # 10秒超时
+            )
+            response.raise_for_status()  # 抛出HTTP错误状态码
+            logger.info(f"请求成功，状态码: {response.status_code}")
+
+            # 8. 解析响应
+            try:
+                response_json = response.json()
+                # logger.debug(f"响应数据: {str(response_json)[:100]}...")  # 打印前100字符
+            except ValueError:
+                logger.error("响应不是有效的JSON格式", exc_info=True)
+                if retry < RETRY_TIMES - 1:
+                    logger.info(f"等待 {RETRY_DELAY} 秒后重试...")
+                    time.sleep(RETRY_DELAY)
+                    continue
+                return None
+
+            # 9. 提取bbxAsinList
+            try:
+                search_result = response_json.get("style-snap", {}).get("searchResult", [])
+                if not search_result:
+                    logger.warning("searchResult列表为空")
+                    return None
+
+                first_result = search_result[0]
+                bbx_asin_list = first_result.get("bbxAsinList", [])
+                if not bbx_asin_list:
+                    logger.warning("bbxAsinList列表为空")
+                    return None
+
+                logger.info(f"成功提取bbxAsinList，共 {len(bbx_asin_list)} 个元素,注意 实际有些不可用 打开网页数据少几个为正常现象")
+                joined_asin = "|".join(bbx_asin_list)
+                final_url = AMAZON_SEARCH_BASE_URL.format(bbx_asin_list=joined_asin)
+                logger.success(f"生成最终搜索URL: {final_url}")
+                return final_url
+
+            except (IndexError, KeyError) as e:
+                logger.error(f"解析响应结构失败: {str(e)}", exc_info=True)
+                if retry < RETRY_TIMES - 1:
+                    logger.info(f"等待 {RETRY_DELAY} 秒后重试...")
+                    time.sleep(RETRY_DELAY)
+                    continue
+                return None
+
+        except (ConnectionError, Timeout) as e:
+            logger.error(f"网络错误: {str(e)}", exc_info=True)
+        except RequestException as e:
+            # 处理HTTP错误（如401/403可能是cookie过期）
+            status_code = getattr(e.response, "status_code", None)
+            logger.error(f"请求异常 (状态码: {status_code}): {str(e)}", exc_info=True)
+
+            # 401/403 通常是认证失效，直接终止重试（需要更新cookie）
+            if status_code in (401, 403):
+                logger.warning("检测到认证失效，终止重试")
+                return None
+        except Exception as e:
+            logger.error(f"未知错误: {str(e)}", exc_info=True)
+
+        # 重试前等待
+        if retry < RETRY_TIMES - 1:
+            logger.info(f"等待 {RETRY_DELAY} 秒后重试...")
+            time.sleep(RETRY_DELAY)
+
+    logger.error(f"经过 {RETRY_TIMES} 次重试后仍失败")
+    return None
+
+
+if __name__ == "__main__":
+    sample_cookies = {"i18n-prefs": "USD", "lc-main": "en_US", "session-id": "131-0347800-4175077", "session-id-time": "2082787201l", "session-token": "Jo+AthxsQrcFH8qeii+sHhoo7puFd/cpJUEsjnWXtCLhr8ycF9TQSAv9zuyoAvFjfmXZuACFNa/D+i5et63EafMMPDK/825m8TUtNtlO88KmmEsm94fiyoPL0UakTyZsUBv/CzndcKB7h0K3NkbeFws9gZSdwYRGJFVeX+pPQ9ceN0WkE+XLwCt0plIIxG3BC+VtdFJWxPKxH+R5dlnbtxPso2S5zlrOf1FTEdGNNhNZvVq25XeydshrSp7AKG6VUOicnipgfAY0Qle3Y4bw72N1IqY9i3rXVZlkrkGePamBxew+Vel7U8ccVsEIT/vtOtLHPfsTljTgltlJU0bzk0YeoJ1LwI9S", "skin": "noskin", "ubid-main": "134-9889499-1876667"}
+
+    # 调用函数
+    result_url = get_amazon_search_url("test_image/amazon3.png", sample_cookies)
+    if result_url:
+        logger.success(f"最终搜索URL: {result_url}")
+    else:
+        logger.error("未能生成搜索URL")
\ No newline at end of file