qrpa 1.0.88__py3-none-any.whl → 1.0.90__py3-none-any.whl

qrpa/db_migrator.py

@@ -580,7 +580,7 @@ def create_default_migrator(silent: bool = False) -> DatabaseMigrator:
     )
     
     remote_config = RemoteConfig(
-        ssh_host="git@e3",
+        ssh_host="git@ecslz",
         temp_dir="/tmp/db_migration",
         database=remote_db
     )

qrpa/fun_web.py

@@ -146,6 +146,54 @@ def full_screen_shot(web_page: Page, config):
     web_page.screenshot(path=full_screenshot_image_path, full_page=True)
     return full_screenshot_image_path
 
+def fetch_get(page: Page, url: str, headers: Optional[dict] = None, config: Optional[dict] = None) -> dict:
+    """
+    发送 HTTP GET 请求，支持自定义 headers 和配置。
+    
+    :param page: Playwright 的 Page 对象
+    :param url: 请求地址
+    :param headers: 自定义 headers 字典
+    :param config: 请求配置字典，可包含 credentials, mode, referrer, referrerPolicy 等
+    :return: 服务器返回的 JSON 响应（dict）
+    """
+    if headers is not None and not isinstance(headers, dict):
+        raise ValueError("headers 参数必须是 dict 或 None")
+    if config is not None and not isinstance(config, dict):
+        raise ValueError("config 参数必须是 dict 或 None")
+
+    try:
+        page.wait_for_load_state('load')
+        response = page.evaluate("""
+            async ({ url, extraHeaders, config }) => {
+                try {
+                    const defaultHeaders = {
+                        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36',
+                    };
+
+                    const defaultConfig = {
+                        method: 'GET',
+                        credentials: 'include',
+                        mode: 'cors'
+                    };
+
+                    const headers = Object.assign({}, defaultHeaders, extraHeaders || {});
+                    const options = Object.assign({}, defaultConfig, config || {}, { headers: headers });
+
+                    const response = await fetch(url, options);
+                    if (!response.ok) {
+                        throw new Error(`HTTP ${response.status} - ${response.statusText}`);
+                    }
+                    return await response.json();
+                } catch (error) {
+                    return { "error": "fetch_failed", "message": error.message };
+                }
+            }
+        """, {"url": url, "extraHeaders": headers, "config": config})
+
+        return response
+    except Exception as e:
+        raise send_exception()
+
 def safe_goto(page, url, **kwargs):
     caller = inspect.stack()[1]
     log(f"[DEBUG] goto called from {caller.filename}:{caller.lineno} url={url}")

qrpa/shein_lib.py

@@ -1,6 +1,6 @@
 from .fun_file import read_dict_from_file, write_dict_to_file, read_dict_from_file_ex, write_dict_to_file_ex
 from .fun_base import log, send_exception, md5_string, get_safe_value, NetWorkIdleTimeout
-from .fun_web import fetch, full_screen_shot, safe_goto
+from .fun_web import fetch, fetch_get, full_screen_shot, safe_goto
 from .time_utils import TimeUtils
 from .wxwork import WxWorkBot
 
@@ -36,26 +36,37 @@ class SheinLib:
             try:
                 current_url = web_page.url
                 log(f"尝试获取页面信息 - URL: {current_url}", self.store_username, self.store_name)
-                
+
+                # 检查是否在认证页面，如果是则直接跳转到目标页面
+                if '/auth/SSLS' in current_url:
+                    log("检测到SSLS认证页面，直接跳转到首页", self.store_username, self.store_name)
+                    web_page.goto('https://sso.geiwohuo.com/#/home', wait_until='domcontentloaded', timeout=15000)
+                    web_page.wait_for_timeout(3000)
+                    current_url = web_page.url
+                    log(f"跳转后URL: {current_url}", self.store_username, self.store_name)
+
                 # 等待导航完成
-                web_page.wait_for_load_state("networkidle", timeout=8000)
-                
+                web_page.wait_for_load_state("domcontentloaded", timeout=6000)
+
                 final_url = web_page.url
                 final_title = web_page.title()
                 log(f"页面稳定 - URL: {final_url}, 标题: {final_title}", self.store_username, self.store_name)
                 break
-                
+
             except Exception as e:
-                log(f"第{attempt+1}次等待页面稳定失败: {e}", self.store_username, self.store_name)
-                if "destroyed" in str(e) or "navigation" in str(e):
+                log(f"第{attempt + 1}次等待页面稳定失败: {e}", self.store_username, self.store_name)
+                if "crashed" in str(e) or "Target" in str(e):
+                    log("页面稳定检查时崩溃，直接继续", self.store_username, self.store_name)
+                    break
+                elif "destroyed" in str(e) or "navigation" in str(e):
                     log("检测到导航中断，等待导航完成", self.store_username, self.store_name)
-                    web_page.wait_for_timeout(5000)
+                    web_page.wait_for_timeout(4000)
                     continue
                 elif attempt == 2:
                     log("页面稳定等待最终失败，继续执行", self.store_username, self.store_name)
                     break
                 web_page.wait_for_timeout(2000)
-        
+
         web_page.wait_for_timeout(2000)
 
         # 定义最大重试次数
@@ -72,13 +83,23 @@ class SheinLib:
                 retries += 1
 
                 while not web_page.locator('//div[contains(text(),"商家后台")]').nth(1).is_visible():
-                    
+
                     try:
                         current_url = web_page.url
                         current_title = web_page.title()
                         log(f"循环检查 - URL: {current_url}, 标题: {current_title}", self.store_username, self.store_name)
+
+                        # 如果在认证页面且出现问题，直接跳转
+                        if '/auth/SSLS' in current_url:
+                            log("在主循环中检测到SSLS认证页面，跳转到首页", self.store_username, self.store_name)
+                            web_page.goto('https://sso.geiwohuo.com/#/home', wait_until='domcontentloaded', timeout=15000)
+                            web_page.wait_for_timeout(3000)
+                            continue
+
                     except Exception as status_error:
                         log(f"获取页面状态失败: {status_error}", self.store_username, self.store_name)
+                        if "crashed" in str(status_error):
+                            break
 
                     if web_page.locator('xpath=//div[@id="container" and @alita-name="gmpsso"]//button[@type="button" and @id]').nth(0).is_visible():
                         if 'https://sso.geiwohuo.com/#/home' not in web_page.url:
@@ -179,13 +200,13 @@ class SheinLib:
             except Exception as e:
                 log(f"错误发生: {e}, 重试中...({self.store_username}, {self.store_name})")
                 log(traceback.format_exc())
-                
+
                 # 收集崩溃时的详细信息
                 try:
                     crash_url = web_page.url
                     crash_title = web_page.title()
                     log(f"崩溃时页面信息 - URL: {crash_url}, 标题: {crash_title}", self.store_username, self.store_name)
-                    
+
                     # 尝试截图保存崩溃现场
                     try:
                         screenshot_path = f"crash_screenshot_{self.store_username}_{int(time.time())}.png"
@@ -193,19 +214,19 @@ class SheinLib:
                         log(f"已保存崩溃截图: {screenshot_path}", self.store_username, self.store_name)
                     except:
                         log("无法截取崩溃时的页面截图", self.store_username, self.store_name)
-                        
+
                 except:
                     log("无法获取崩溃时的页面信息", self.store_username, self.store_name)
-                
+
                 # 检查特定类型的错误
                 if any(keyword in str(e).lower() for keyword in ['memory', 'out of memory', 'oom']):
                     log("检测到内存相关崩溃", self.store_username, self.store_name)
-                
+
                 if "destroyed" in str(e) or "navigation" in str(e):
                     log("检测到导航中断，等待页面稳定后重试", self.store_username, self.store_name)
                     web_page.wait_for_timeout(5000)
                     continue
-                
+
                 if 'crashed' in str(e) or 'Target' in str(e):
                     log("检测到页面或目标崩溃，直接退出当前循环", self.store_username, self.store_name)
                     raise e
@@ -220,6 +241,44 @@ class SheinLib:
         # web_page.wait_for_load_state("networkidle")
         web_page.wait_for_timeout(3000)
 
+    # 获取用户信息
+    def get_user(self, uuid=None):
+        log(f'获取用户信息:{self.store_username} {self.store_name}')
+
+        # 生成 uuid 参数，如果没有提供则使用时间戳
+        if uuid is None:
+            import time
+            uuid = str(int(time.time() * 1000))
+
+        url = f"https://sso.geiwohuo.com/sso-prefix/auth/getUser?uuid={uuid}"
+
+        # 设置请求头，根据 Chrome 请求
+        headers = {
+            "gmpsso-language": "CN",
+            "origin-url"     : "https://sso.geiwohuo.com/#/home/",
+            "x-sso-scene"    : "gmpsso"
+        }
+
+        # 特定于此请求的配置
+        fetch_config = {
+            "credentials"   : "omit",
+            "referrer"      : "https://sso.geiwohuo.com/",
+            "referrerPolicy": "strict-origin-when-cross-origin"
+        }
+
+        response_text = fetch_get(self.web_page, url, headers, fetch_config)
+        error_code = response_text.get('code')
+        if str(error_code) != '0':
+            raise send_exception(json.dumps(response_text, ensure_ascii=False))
+        info = response_text.get('info', {})
+        log(info)
+        cache_file = f'{self.config.auto_dir}/shein_user.json'
+        info['store_username'] = self.store_username
+        info['store_name'] = self.store_name
+        write_dict_to_file_ex(cache_file, {self.store_username: info}, [self.store_username])
+
+        return info
+
     # 获取质检报告pdf地址
     def get_qc_report_url(self, deliverCode, purchaseCode):
         log(f'获取质检报告:{deliverCode} {purchaseCode}')

qrpa/shein_ziniao.py

@@ -5,7 +5,7 @@
 import os
 import platform
 import shutil
-import time
+import time, datetime
 import traceback
 import uuid
 import json
@@ -74,7 +74,7 @@ class ZiniaoClient:
         """启动客户端"""
         try:
             if self.is_windows:
-                cmd = [self.client_path, '--run_type=web_driver', '--ipc_type=http', '--port=' + str(self.socket_port)]
+                cmd = [self.client_path, '--run_type=web_driver', '--show_sidb=true', '--ipc_type=http', '--port=' + str(self.socket_port)]
             elif self.is_mac:
                 cmd = ['open', '-a', self.client_path, '--args', '--run_type=web_driver', '--ipc_type=http',
                        '--port=' + str(self.socket_port)]
@@ -272,6 +272,73 @@ class ZiniaoTaskManager:
         self.browser = browser
         self.config = config
 
+    def daily_cleanup_superbrowser(self, browser_id):
+        """
+        每天删除一次SuperBrowser缓存文件夹
+
+        Args:
+            browser_id (str): 浏览器ID，如 '26986387919128'
+        """
+
+        # 获取本地AppData路径
+        local_appdata = os.getenv('LOCALAPPDATA')
+        if not local_appdata:
+            log("错误: 无法获取LOCALAPPDATA路径")
+            return False
+
+        # 构建路径
+        cache_path = os.path.join(local_appdata, 'SuperBrowser')
+        target_folder = os.path.join(cache_path, f'User Data\\Chromium_{browser_id}')
+        flag_file = os.path.join(cache_path, f'User Data\\cleanup_flag_{browser_id}.txt')
+
+        # 检查目标文件夹是否存在
+        if not os.path.exists(target_folder):
+            log(f"目标文件夹不存在: {target_folder}")
+            return False
+
+        # 获取当前日期
+        today = datetime.date.today()
+        today_str = today.strftime('%Y-%m-%d')
+
+        # 检查标志文件
+        need_cleanup = True
+
+        if os.path.exists(flag_file):
+            try:
+                # 读取标志文件中的日期
+                with open(flag_file, 'r', encoding='utf-8') as f:
+                    last_cleanup_date = f.read().strip()
+
+                # 如果是今天已经清理过，则跳过
+                if last_cleanup_date == today_str:
+                    log(f"今天({today_str})已经清理过，跳过删除操作")
+                    need_cleanup = False
+
+            except Exception as e:
+                log(f"读取标志文件时出错: {e}")
+                # 如果读取出错，继续执行清理
+
+        if need_cleanup:
+            try:
+                # 删除目标文件夹
+                log(f"正在删除文件夹: {target_folder}")
+                shutil.rmtree(target_folder)
+                log("删除成功!")
+
+                # 创建/更新标志文件
+                os.makedirs(os.path.dirname(flag_file), exist_ok=True)
+                with open(flag_file, 'w', encoding='utf-8') as f:
+                    f.write(today_str)
+
+                log(f"已创建标志文件: {flag_file}")
+                return True
+
+            except Exception as e:
+                log(f"删除文件夹时出错: {e}")
+                return False
+
+        return True
+
     def run_single_store_task(self, browser_info: Dict[str, Any],
             run_func: Callable, task_key: str,
             just_store_username: Optional[List[str]] = None,
@@ -282,6 +349,10 @@ class ZiniaoTaskManager:
         store_name = browser_info.get("browserName")
         store_username = browser_info.get("store_username")
 
+        # 删除浏览器缓存,一天一删
+        browser_id = browser_info.get("browserId")
+        self.daily_cleanup_superbrowser(browser_id)
+
         retry_count = 0
         while True:
             try:

qrpa/time_utils.py

@@ -260,20 +260,31 @@ class TimeUtils:
 
     @staticmethod
     def get_dates_from_first_of_month_to_yesterday() -> List[str]:
-        """获取从本月第一天到昨天的日期列表"""
+        """获取从本月第一天到昨天的日期列表
+        如果今天是本月第一天，则返回上个月的日期列表
+        """
         today = datetime.today()
-        first_day_of_month = today.replace(day=1)
         yesterday = today - timedelta(days=1)
 
-        date_list = []
-        current_date = first_day_of_month
+        # 如果今天是本月第一天，取上个月
+        if today.day == 1:
+            # 找到上个月最后一天
+            last_month_last_day = today - timedelta(days=1)
+            # 上个月第一天
+            first_day_of_last_month = last_month_last_day.replace(day=1)
+            start_date = first_day_of_last_month
+            end_date = last_month_last_day
+        else:
+            start_date = today.replace(day=1)
+            end_date = yesterday
 
-        while current_date <= yesterday:
+        date_list = []
+        current_date = start_date
+        while current_date <= end_date:
             date_list.append(current_date.strftime('%Y-%m-%d'))
             current_date += timedelta(days=1)
 
         return date_list
-
     # ==================== 月份相关 ====================
 
     @staticmethod

{qrpa-1.0.88.dist-info → qrpa-1.0.90.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: qrpa
-Version: 1.0.88
+Version: 1.0.90
 Summary: qsir's rpa library
 Author: QSir
 Author-email: QSir <1171725650@qq.com>

{qrpa-1.0.88.dist-info → qrpa-1.0.90.dist-info}/RECORD

@@ -1,30 +1,30 @@
 qrpa/RateLimitedSender.py,sha256=hqvb1qspDFaW4RsLuVufylOrefkMgixANKeBaGEqYb4,1421
 qrpa/__init__.py,sha256=FjyNLjEnR4Y9_0scrWy7foJmDI4oiqSNyeAohPQTQvE,1148
-qrpa/db_migrator.py,sha256=2VmhzcMsU0MKpl-mNCwKyV8tLTqyEysSpP27-S_rQZ8,21862
+qrpa/db_migrator.py,sha256=6lz1MdSQzN3Co00uwy0EwIXjWrblgL39hHJUw18sf5I,21865
 qrpa/feishu_bot_app.py,sha256=6r2YqCAMUN7y3F7onoABRmHC7S-UPOLHwbhsQnQ3IRc,9452
 qrpa/feishu_client.py,sha256=gXvyhf7r-IqeDhPjM01SfsGf17t8g1ZwUAkhymBkBeg,17544
 qrpa/feishu_logic.py,sha256=yuwb-LeZiHKGlz-W8JobinorHonVa8L-5h12WxnU7_Q,67508
 qrpa/fun_base.py,sha256=lMzqPwsbVfe968CUR2MVNImzIskIUZqPCE2tWxYqb5o,10728
 qrpa/fun_excel.py,sha256=-GFtjg0LeiiXrpTU5RtMlBUHl05mqzdHCzIxlssT59U,117385
 qrpa/fun_file.py,sha256=yzjDV16WL5vRys7J4uQcNzIFkX4D5MAlSCwxcD-mwQo,11966
-qrpa/fun_web.py,sha256=Ep2ddMwJix_KNpCiHEjSo7tWu-g55Nlu1QtOXJf6iZw,6531
+qrpa/fun_web.py,sha256=Mv0m2P5fh2-U4DzRoVivqRcXD56BJ_Svj6TZznx49YU,8645
 qrpa/fun_win.py,sha256=-LnTeocdTt72NVH6VgLdpAT9_C5oV9okeudXG6CftMA,8034
 qrpa/shein_daily_report_model.py,sha256=H8oZmIN5Pyqe306W1_xuz87lOqLQ_LI5RjXbaxDkIzE,12589
 qrpa/shein_excel.py,sha256=1F9QMMsaihDfwr0ajSSQdXksBCjuKSPwMynfP7Jlkso,124825
-qrpa/shein_lib.py,sha256=On9tT6vVeOKH56ukgYrT7eVcnqo_0bgghWFhpvr5z5c,131491
+qrpa/shein_lib.py,sha256=5rsxoS8rI8xKprjEVmEzaNRrTcCm4FU2eGcpfhf-TzE,134142
 qrpa/shein_mysql.py,sha256=Sgz6U0_3f4cT5zPf1Ht1OjvSFhrVPLkMxt91NV-ZPCM,3005
 qrpa/shein_sqlite.py,sha256=ZQwD0Gz81q9WY7tY2HMEYvSF9r3N_G_Aur3bYfST9WY,5707
-qrpa/shein_ziniao.py,sha256=hjEgK5gNWytAkvTvJQKEy3A3L-R0sArgnSBk85m41ow,18703
+qrpa/shein_ziniao.py,sha256=4CsOPZXRDEqHJvCGyb8imCPqSH5Ln5fGqPUFqLuFgCg,21276
 qrpa/temu_chrome.py,sha256=CbtFy1QPan9xJdJcNZj-EsVGhUvv3ZTEPVDEA4-im40,2803
 qrpa/temu_excel.py,sha256=2hGw76YWzkTZGyFCuuUAab4oHptYX9a6U6yjpNsL7FE,6990
 qrpa/temu_lib.py,sha256=hYB59zsLS3m3NTic_duTwPMOTSxlHyQVa8OhHnHm-1g,7199
-qrpa/time_utils.py,sha256=ef0hhbN_6b-gcnz5ETIVOoxemIMvcxGVGGIRnHnGaBo,29564
+qrpa/time_utils.py,sha256=KFXnF1pMWACAKOSy483riPqvTsMjhQtFJAIhQsZKaMk,30075
 qrpa/time_utils_example.py,sha256=shHOXKKF3QSzb0SHsNc34M61wEkkLuM30U9X1THKNS8,8053
 qrpa/wxwork.py,sha256=gIytG19DZ5g7Tsl0-W3EbjfSnpIqZw-ua24gcB78YEg,11264
 qrpa/mysql_module/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 qrpa/mysql_module/shein_product_model.py,sha256=qViI_Ik3SkXXxqJ1nXjimvfB_a5uiwW9RXL0fOreBao,18880
 qrpa/mysql_module/shein_return_order_model.py,sha256=Zt-bGOH_kCDbakW7uaTmqqo_qTT8v424yidcYSfWvWM,26562
-qrpa-1.0.88.dist-info/METADATA,sha256=-ppgc5XGhffpjLxLSBlNMLy9OKv7BGMjpS0BG7rgo-c,231
-qrpa-1.0.88.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-qrpa-1.0.88.dist-info/top_level.txt,sha256=F6T5igi0fhXDucPPUbmmSC0qFCDEsH5eVijfVF48OFU,5
-qrpa-1.0.88.dist-info/RECORD,,
+qrpa-1.0.90.dist-info/METADATA,sha256=5_HyMIZcanl7560yxaMsi9O4YjuP2nlvjtMIzsSEJXM,231
+qrpa-1.0.90.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+qrpa-1.0.90.dist-info/top_level.txt,sha256=F6T5igi0fhXDucPPUbmmSC0qFCDEsH5eVijfVF48OFU,5
+qrpa-1.0.90.dist-info/RECORD,,