初始化

lib/__init__.py

@@ -0,0 +1,4 @@
+from core import browsers
+from lib.module import example
+
+Server: example.SpiderModule

lib/gether.py

@@ -0,0 +1,131 @@
+import os
+import traceback
+import concurrent.futures
+from utils import files, messages, clash, formats
+import lib
+from core import Config, types
+from lib.model import goods
+
+def get_category_urls():
+    category_urls_path = f"{lib.Server.__urls_folder__}/categorys.txt"
+    if os.path.exists(category_urls_path):
+        return
+    
+    category_urls = lib.Server.get_category_urls()
+    for urls in category_urls:
+        if 'http' not in urls:
+            continue
+        files.save_line(category_urls_path, urls)
+
+def get_goods_urls(categorys_len: int = 3):
+    goods_urls_path = f"{lib.Server.__urls_folder__}/goods.txt"
+    category_urls_path = f"{lib.Server.__urls_folder__}/categorys.txt"
+    if Config.home_mode:
+        goods_urls_path = goods_urls_path.replace('.txt', '(home).txt')
+        category_urls_path = category_urls_path.replace('.txt', '(home).txt')
+
+    category_index = {}
+    category_urls = files.load_lines(category_urls_path)
+
+    if os.path.exists(goods_urls_path):
+        old_goods_urls = files.load_lines(goods_urls_path)
+        for old_goods_url in old_goods_urls:
+            category = old_goods_url.split('#')[-1]
+            category_index[category] = None
+
+    index = 0
+    max_len = len(category_urls)
+    for category_url in category_urls:
+        category = category_url.split('#')[-1]
+        category_url = '#'.join(category_url.split('#')[:-1])
+
+        index += 1
+        if 'https' not in category_url:
+            continue
+        if Config.skip_category and Config.home_mode == False and len(category.split('/')) < categorys_len:
+            continue
+        if category in category_index:
+            continue
+
+        try:
+            goods_urls = lib.Server.get_goods_urls(category_url)
+            goods_category_urls = []
+            for goods_url in goods_urls:
+                goods_category_urls.append(f"{goods_url}#{category}")
+
+            files.add_list(goods_urls_path, goods_category_urls)
+        except Exception as e:
+            files.add_text(f"{lib.Server.__errors_folder__}/category_errors.log", f"{category_url}:\n[{e}] {traceback.format_exc()}")
+            messages.sendError(str(e))
+        messages.sendInfo(f"{index}/{max_len} {len(goods_urls)}条")
+    if Config.home_mode == False:
+        formats.de_repeat_urls(goods_urls_path)
+
+def get_goods_info():
+    p_urls = {}
+    def workers(goods_urls, index):
+        with concurrent.futures.ThreadPoolExecutor(max_workers=lib.Server.worker_num) as executor:
+            futures = []
+            for goods_url in goods_urls:
+                if goods_url in p_urls:
+                    continue
+                future = executor.submit(lib.Server.get_goods_info, goods_url)
+                futures.append(future)
+
+            results: list[types.GoodsInfo] = []
+            for future_index, future in enumerate(futures):
+                index += 1
+                try:
+                    result = future.result()  # 阻塞直到该任务完成
+                except Exception as e:
+                    try:
+                        files.add_text(f"{lib.Server.__errors_folder__}/goods_errors.log", f"{goods_urls[future_index]}:\n[{e}] {traceback.format_exc()}")
+                    except:
+                        pass
+                    messages.sendWarn(f"{goods_urls[future_index]} 出错")
+                    continue
+
+                results.append(result)
+                messages.sendInfo(f"{index}/{max_len}")
+
+            for goods_info in results:
+                try:
+                    GoodsModel.add_goods(*goods_info.to_db_data())
+                    for p_url in goods_info.p_urls:
+                        p_urls[p_url] = None
+                except Exception as e:
+                    messages.sendWarn(f"{e}")
+
+        return index
+
+    goods_urls = files.load_lines(f"{lib.Server.__urls_folder__}/goods.txt")
+    messages.sendInfo('读取url完成')
+
+    messages.sendInfo('读取上次存档')
+    GoodsModel = goods.GoodsModel(lib.Server.__database_path__)
+    excel_index = GoodsModel.select_goods_to_dict()
+    messages.sendInfo('读取完成')
+
+    de_save_url = []
+    for goods_url in goods_urls:
+        if goods_url in excel_index:
+            continue
+        if 'http' not in goods_url:
+            continue
+        de_save_url.append(goods_url)
+    goods_urls = de_save_url
+    del excel_index
+
+    max_len = len(goods_urls)
+    index = 1
+    for i in range(0, len(goods_urls), lib.Server.bitch):
+        index = workers(goods_urls=goods_urls[i:i+lib.Server.bitch], index=index)
+        if lib.Server.switch_clash:
+            try:
+                clash.change_proxy()
+            except:
+                pass
+        if lib.Server.reflush_browsers:
+            if lib.Server.worker_num > 1:
+                lib.Server.reflush_browser()
+        messages.sendInfo("已保存")

lib/model/goods.py

@@ -0,0 +1,417 @@
+#############################################################################
+
+# Author: Cerys
+# Update: 2026-02-06
+
+#############################################################################
+
+import os
+import orjson
+from core import excels, types
+from utils import db, messages, files, formats
+
+class GoodsModel:
+    def __init__(self, db_path: str):
+        """
+        商品模型
+
+        :param db_path: 数据库文件路径(不存在则自动创建并初始化表)
+
+        """
+        self.__source_folder__ = "sources"
+
+        create_table = False
+        if os.path.exists(db_path) == False:
+            create_table = True
+
+        self.Db = db.Db(db_path)
+        if create_table:
+            self.__create_table__()
+
+    def __create_table__(self):
+        table_sql = '''
+            PRAGMA foreign_keys = false;
+
+            DROP TABLE IF EXISTS "goods";
+            CREATE TABLE "goods" (
+            "spu" TEXT NOT NULL,
+            "title" TEXT NOT NULL,
+            "brand" TEXT,
+            "attr" TEXT NOT NULL,
+            "desc" TEXT,
+            "item1" TEXT,
+            "item2" TEXT,
+            "item3" TEXT,
+            "price" NUMBER NOT NULL,
+            "old_price" NUMBER NOT NULL,
+            "images" blob NOT NULL,
+            "url" TEXT NOT NULL,
+            "other_data" blob DEFAULT "{}",
+            PRIMARY KEY ("spu")
+            );
+
+            DROP TABLE IF EXISTS "goods_son";
+            CREATE TABLE "goods_son" (
+            "spu" TEXT NOT NULL,
+            "item1" TEXT,
+            "item2" TEXT,
+            "item3" TEXT,
+            "price" NUMBER NOT NULL,
+            "old_price" NUMBER NOT NULL,
+            "images" blob NOT NULL,
+            "url" TEXT,
+            "other_data" blob DEFAULT "{}"
+            );
+
+            CREATE INDEX "search_spu"
+            ON "goods_son" (
+            "spu" ASC
+            );
+
+            PRAGMA foreign_keys = true;
+        '''
+        self.Db.execute_script(table_sql)
+
+    def add_goods(self, main_info: dict, son_infos: list = []):
+        """
+        添加商品
+
+        :param main_info: 主表信息
+        :param son_infos: 变体信息列表
+        
+        """
+        if main_info['attr'] == 'M' and len(son_infos) == 0:
+            raise Exception(f"变体丢失 {main_info}")
+        if len(main_info['images']) == 0:
+            raise Exception('无图片')
+
+        self.Db.table('goods').insert(main_info, True)
+        self.Db.table('goods_son').insert_all(son_infos)
+
+    def is_repeat(self, url):
+        """
+        判断是否需要合并
+        
+        :param url: 商品链接
+
+        """
+        count = self.Db.table('goods_son').where('url', url).count()
+        if count > 1:
+            return True
+        return False
+
+    def select_goods_to_lists(self) -> list[dict]:
+        """获取商品列表（包含变体）"""
+        messages.sendInfo('开始查询')
+        db_data = self.Db.table('goods').join('goods_son', 'goods.spu = goods_son.spu').select(
+            '''
+                goods.spu,
+                goods.title,
+                goods.brand,
+                goods.attr,
+                goods.desc,
+                goods.item1 as main_item1,
+                goods.item2 as main_item2,
+                goods.item3 as main_item3,
+                goods.price,
+                goods.old_price,
+                goods.images,
+                goods.url,
+                goods.other_data,
+                goods_son.item1 as son_item1,
+                goods_son.item2 as son_item2,
+                goods_son.item3 as son_item3,
+                goods_son.price as son_price,
+                goods_son.old_price as son_old_price,
+                goods_son.images as son_images,
+                goods_son.url as son_url,
+                goods_son.other_data as son_other_data
+            '''
+        )
+        messages.sendInfo('查询完成')
+        return db_data
+
+    def select_goods_to_dict(self, key: str = 'url') -> dict:
+        """
+        获取商品列表并转换为字典格式
+
+        :param key: 字典的键
+
+        """
+        db_data = self.select_goods_to_lists()
+        dict_data = {}
+        for item in db_data:
+            if item[key] in dict_data:
+                dict_data[item[key]]['son_lists'].append({
+                    'attr_items': [item['son_item1'], item['son_item2'], item['son_item3']],
+                    'price': item['son_price'],
+                    'old_price': item['son_old_price'],
+                    'images': orjson.loads(item['son_images']),
+                    'url': item['son_url'],
+                    'son_other_data': orjson.loads(item['son_other_data'])
+                })
+            else:
+                dict_data[item[key]] = {
+                    'spu': item['spu'],
+                    'title': item['title'],
+                    'brand': item['brand'],
+                    'desc': item['desc'],
+                    'attr': item['attr'],
+                    'attr_items': [item['main_item1'], item['main_item2'], item['main_item3']],
+                    'price': item['price'],
+                    'old_price': item['old_price'],
+                    'images': orjson.loads(item['images']),
+                    'url': item['url'],
+                    'other_data': orjson.loads(item['other_data'])
+                }
+                if item['attr'] == 'M':
+                    if item['son_price'] == None:
+                        continue
+                    dict_data[item[key]]['son_lists'] = [
+                        {
+                            'attr_items': [item['son_item1'], item['son_item2'], item['son_item3']],
+                            'price': item['son_price'],
+                            'old_price': item['son_old_price'],
+                            'images': orjson.loads(item['son_images']),
+                            'url': item['son_url'],
+                            'son_other_data': orjson.loads(item['son_other_data'])
+                        }
+                    ]
+        return dict_data
+
+    def select_goods_to_goodsinfo(self) -> list[types.GoodsInfo]:
+        """获取商品列表并转换为GoodsInfo对象列表"""
+        db_data = self.select_goods_to_lists()
+        index_data = {}
+        for item in db_data:
+            if item['spu'] in index_data:
+                index_data[item['spu']].p_lists.append(
+                    types.GoodsInfo.GoodsInfoP(
+                        attr_items = [item['son_item1'], item['son_item2'], item['son_item3']],
+                        price = item['son_price'],
+                        old_price = item['son_old_price'],
+                        images = orjson.loads(item['son_images']),
+                        url = item['son_url'],
+                        other_data = orjson.loads(item['son_other_data'])
+                    )
+                )
+            else:
+                try:
+                    index_data[item['spu']] = types.GoodsInfo(
+                        spu = item['spu'],
+                        title = item['title'],
+                        brand = item['brand'],
+                        attr = item['attr'],
+                        desc = item['desc'],
+                        attr_items = [item['main_item1'], item['main_item2'], item['main_item3']],
+                        price = item['price'],
+                        old_price = item['old_price'],
+                        images = orjson.loads(item['images']),
+                        url = item['url'],
+                        other_data = orjson.loads(item['other_data'])
+                    )
+                    if item['attr'] == 'M':
+                        index_data[item['spu']].p_lists.append(
+                            types.GoodsInfo.GoodsInfoP(
+                                attr_items = [item['son_item1'], item['son_item2'], item['son_item3']],
+                                price = item['son_price'],
+                                old_price = item['son_old_price'],
+                                images = orjson.loads(item['son_images']),
+                                url = item['son_url'],
+                                other_data = orjson.loads(item['son_other_data'])
+                            )
+                        )
+                except Exception as e:
+                    messages.sendError(e)
+        return list(index_data.values())
+
+    def to_amazon_xlsx(self, goods_url_path: str, save_path: str):
+        """
+        整数据库导出为亚马逊导入表格
+
+        :param save_path: 保存路径
+        :param goods_url_path: 未去重商品链接路径
+
+        """
+        goods_data = self.select_goods_to_dict()
+        goods_urls = files.load_lines(goods_url_path)
+        WookBook = excels.WorkBook(
+            f'{self.__source_folder__}/amazon商品模板.xlsx',
+            save_path
+        )
+
+        for goods_url in goods_urls:
+            key = '#'.join(goods_url.split('#')[:-1])
+            if key not in goods_data:
+                continue
+
+            spu = formats.url_to_spu(key)
+            category = goods_url.split('#')[-1]
+
+            WookBook.add_row_of_list([
+                goods_data[key]['title'],
+                spu,
+                goods_data[key]['other_data']['popover'],
+                goods_data[key]['other_data']['popover_num'],
+                0,
+                goods_data[key]['price'],
+                goods_data[key]['old_price'],
+                orjson.dumps(goods_data[key]['images']),
+                goods_data[key]['url'],
+                category
+            ])
+
+        # for goods_info in goods_info_data:
+        #     WookBook.add_row_of_list([
+        #         goods_info.title,
+        #         goods_info.price,
+        #         goods_info.images[0],
+        #         goods_info.other_data['popover'],
+        #         goods_info.other_data['popover_num'],
+        #         goods_info.url,
+        #         orjson.dumps(goods_info.images)
+        #     ])
+        
+        WookBook.save()
+        WookBook.close()
+    
+    def to_shopyy_xlsx(self, save_path: str, save_bitch: int = 150000, shift_urls_path: str = ''):
+        """
+        整数据库导出为Shopyy导入表格
+
+        :param save_path: 保存路径
+        :param repeat: 是否合并商品
+        :param save_bitch: 超过多少行时自动分割
+
+        """
+        def get_wookbook(bitch_index: int):
+            return excels.WorkBook(
+                f'{self.__source_folder__}/shopyy商品模板.xlsx',
+                save_path.replace('.xlsx', f'_{bitch_index}.xlsx')
+            )
+
+        def get_shift_url():
+            shift_urls = {}
+            if shift_urls_path:
+                urls = files.load_lines(shift_urls_path)
+                for url in urls:
+                    if url == '':
+                        continue
+                    shift_urls[url] = None
+            return shift_urls
+
+        goods_info_data = self.select_goods_to_goodsinfo()
+        bitch = 1
+        shift_urls = get_shift_url()
+        WookBook = get_wookbook(bitch)
+
+        count = len(goods_info_data)
+        for index, goods_info in enumerate(goods_info_data):
+            messages.sendInfo(f"{index}/{count}")
+            if shift_urls_path and goods_info.url not in shift_urls:
+                continue
+
+            rows_data = goods_info.to_shopyy_row_data()
+            for row_data in rows_data:
+                WookBook.add_row_of_list(row_data)
+            if WookBook.start_row > save_bitch:
+                WookBook.save()
+                WookBook.close()
+                bitch += 1
+                WookBook = get_wookbook(bitch)
+
+        WookBook.save()
+        WookBook.close()
+
+    def to_woo_csv(self, goods_url_path: str, save_path: str):
+        """
+        整数据库导出为woo商品CSV表格
+
+        :param goods_url_path: 未去重链接txt路径
+        :param save_path: 保存路径
+
+        """
+        goods_urls = files.load_lines(goods_url_path)
+        category_data = {}
+        for goods_url in goods_urls:
+            category_name = goods_url.split('#')[-1].replace('/', '>')
+            goods_url = '#'.join(goods_url.split('#')[:-1])
+            category_data[goods_url] = category_name
+        goods_info_data = self.select_goods_to_goodsinfo()
+
+        bitch = 0
+        save_data = []
+        for goods_info in goods_info_data:
+            rows_data = goods_info.to_woo_row_data(category_data[goods_info.url])
+            save_data += rows_data
+            if len(save_data) > 10000:
+                excels.save_lists_to_csv(save_data, save_path.replace('.csv', f"{bitch}.csv"), r'sources\woo商品模板.csv')
+                save_data = []
+                bitch += 1
+        excels.save_lists_to_csv(save_data, save_path.replace('.csv', f"{bitch}.csv"), r'sources\woo商品模板.csv')
+
+    def import_shopyy_xlsx(self, excel_path: str):
+        """
+        导入shopyy表格为数据库数据
+
+        :param excel_path: 表格路径
+        """
+        shopyy_data = excels.read_excel_to_dict(excel_path)
+        for url, main_goods_info in shopyy_data.items():
+            main_info = {
+                'spu': main_goods_info.spu,
+                'title': main_goods_info.title,
+                'brand': main_goods_info.category_name,
+                'attr': main_goods_info.attribute,
+                'desc': main_goods_info.desc,
+                'price': main_goods_info.price,
+                'old_price': main_goods_info.old_price,
+                'images': orjson.dumps(main_goods_info.images),
+                'url': main_goods_info.url,
+                'other_data': orjson.dumps({})
+            }
+            for index, item_name in enumerate(main_goods_info.attribute_items):
+                if item_name:
+                    main_info[f"item{index+1}"] = item_name
+
+            son_infos = []
+            for p_info in main_goods_info.p_lists:
+                item = {
+                    'spu': p_info.spu,
+                    'price': p_info.price,
+                    'old_price': p_info.old_price,
+                    'images': orjson.dumps(p_info.images),
+                    'url': p_info.url,
+                    'other_data': orjson.dumps({}),
+                    'item1': None,
+                    'item2': None,
+                    'item3': None
+                }
+                for index, item_name in enumerate(p_info.attribute_items):
+                    if item_name:
+                        item[f"item{index+1}"] = item_name
+                son_infos.append(item)
+
+            self.add_goods(main_info, son_infos)
+
+    def splice_db(self, db_folder: str):
+        """
+        拼接指定文件夹下所有数据库文件
+
+        :param db_folder: 数据库文件夹路径
+
+        """
+        db_lists = os.listdir(db_folder)
+        db_index = self.select_goods_to_dict()
+        for db_name in db_lists:
+            splice_db = GoodsModel(f"{db_folder}/{db_name}")
+            goods_lists = splice_db.select_goods_to_goodsinfo()
+            for goods_info in goods_lists:
+                if goods_info.url in db_index:
+                    continue
+                try:
+                    self.add_goods(*goods_info.to_db_data())
+                except Exception as e:
+                    messages.sendError(f"{e} {goods_info.spu}")
+                db_index[goods_info.url] = None
+            messages.sendInfo(db_name)

lib/module/agatameble.py

@@ -0,0 +1,176 @@
+from core import spiders, types
+from utils import formats, messages
+
+class SpiderModule(spiders.Spiders):
+    project_name = "agatameble"
+
+    def __init__(self):
+        super().__init__(
+            self.project_name,
+            bitch = 30,
+            worker_num = 1,
+            switch_clash = False,
+            reflush_browser = False
+        )
+
+    def get_category_urls(self) -> list[str]:
+        category_urls = []
+
+        self.tab.get('https://www.agatameble.pl/')
+        one_menu_eles = self.tab.eles('xpath=//*[@id="root"]/main/div[5]/div[3]/nav/div')
+        for one_menu_ele in one_menu_eles:
+            one_link_ele = one_menu_ele.ele('@tag()=a')
+            one_url = one_link_ele.attr('href')
+            one_name = one_link_ele.text.replace('/', '-')
+            category_urls.append(f"{one_url}#{one_name}")
+            messages.sendInfo(one_name)
+
+            two_menu_eles = one_menu_ele.eles('xpath=div/div[1]/div')
+            for two_menu_ele in two_menu_eles:
+                two_link_ele = two_menu_ele.ele('@tag()=a')
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-')
+                category_urls.append(f"{two_url}#{one_name}/{two_name}")
+            
+                three_menu_eles = two_menu_ele.eles('xpath=ul/li')
+                for three_menu_ele in three_menu_eles:
+                    three_link_ele = three_menu_ele.ele('@tag()=a')
+                    three_url = three_link_ele.attr('href')
+                    three_name = three_link_ele.text.replace('/', '-')
+                    category_urls.append(f"{three_url}#{one_name}/{two_name}/{three_name}")
+
+        return category_urls
+
+    def get_goods_urls(self, category_url: str) -> list[str]:
+        self.tab.get(f"{category_url}")
+        goods_urls = []
+        
+        while True:
+            try:
+                self.tab.scroll.to_bottom()
+                self.tab.ele('xpath=//*[@id="contentContainer"]/div/article/div[2]/div[2]/div/div/a').click()
+            except:
+                break
+        
+        goods_eles = self.tab.eles('xpath=//*[@id="contentContainer"]/div/article/div[2]/div[2]/section/div/div/div')
+        for goods_ele in goods_eles:
+            goods_link_ele = goods_ele.ele('xpath=a')
+            goods_urls.append(goods_link_ele.attr('href'))
+
+        return goods_urls
+
+    def get_goods_info(self, url) -> types.GoodsInfo:
+        def get_image_urls():
+            image_urls = []
+
+            tab.ele('xpath=//*[@id="contentContainer"]/form/div[1]/section/div/div[2]/button[1]').click()
+            image_eles = tab.eles('xpath=//*[@id="root"]/div/section/div[2]/div/aside/div[2]/div/div/div/div[1]/div/div/div/div')
+            for image_ele in image_eles:
+                image_link_ele = image_ele.ele('xpath=div/img[2]')
+                image_urls.append(image_link_ele.attr('src').replace('width=', '').replace('height=', ''))
+
+            return image_urls
+
+        tab = self.browser.new_tab(url)
+        tab.set.window.max()
+        spu = formats.url_to_spu(url)
+
+        try:
+            brand = ''
+            try:
+                brand = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[1]/h1/div[1]', timeout=10).text
+            except:
+                pass
+            if brand == '':
+                title = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[1]/h1').text
+            else:
+                title = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[1]/h1/div[2]').text
+
+            desc = ""
+            desc_eles = tab.eles('xpath=//*[@id="contentContainer"]/form/div[1]/div/div')[:3]
+            for desc_ele in desc_eles:
+                desc += formats.clean_html(desc_ele.html)
+            
+            price = float(f"{tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/section[2]/div[1]/div[2]/span[1]').text}.{tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/section[2]/div[1]/div[2]/span[3]').text}")
+            old_price = price
+
+            main_images = get_image_urls()
+
+            goods_info = types.GoodsInfo(
+                title=title,
+                desc=desc,
+                brand=brand,
+                url=url,
+                spu=spu,
+                price=price,
+                old_price=old_price,
+            )
+
+            m_data = []
+            attr_items = []
+            color_urls = [url]
+            color_eles = tab.eles('xpath=//*[@id="contentContainer"]/form/div[2]/div[2]/div/ul/li')
+            for color_ele in color_eles[1:]:
+                color_link_ele = color_ele.ele('xpath=a')
+                color_urls.append(color_link_ele.attr('href'))
+            if len(color_urls) > 1:
+                m_data = ["Color"]
+            
+            if len(color_urls) > 1:
+                for color_url in color_urls:
+                    color_images = main_images
+                    if color_url != url:
+                        tab.get(color_url)
+                        if brand == '':
+                            title = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[1]/h1').text
+                        else:
+                            title = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[1]/h1/div[2]').text
+                        color_images = get_image_urls()
+
+                    price = float(f"{tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/section[2]/div[1]/div[2]/span[1]').text}.{tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/section[2]/div[1]/div[2]/span[3]').text}")
+                    old_price = price
+
+                    try:
+                        item_name = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[2]/div/ul/li[1]/div[2]/p').text
+                    except:
+                        continue
+                    attr_items.append({
+                        'url': color_url,
+                        'items': [item_name],
+                        'price': price,
+                        'old_price': old_price,
+                        'images': color_images
+                    })
+
+            if len(attr_items) == 0:
+                goods_info.attr = 'S'
+                goods_info.attr_items = []
+                goods_info.images = main_images
+                goods_info.p_lists = []
+            else:
+                goods_info.attr = 'M'
+                goods_info.attr_items = m_data
+                for attr_item in attr_items:
+                    goods_info.p_lists.append(types.GoodsInfo.GoodsInfoP(
+                        url=attr_item['url'],
+                        attr_items=attr_item['items'],
+                        price=attr_item['price'],
+                        old_price=attr_item['old_price'],
+                        images=attr_item['images'],
+                    ))
+                    for image_url in attr_item['images']:
+                        if image_url not in main_images:
+                            main_images.append(image_url)
+                goods_info.images = main_images
+                goods_info.p_urls = color_urls
+        except Exception as e:
+            try:
+                tab.close()
+            except:
+                pass
+            raise Exception(e)
+        try:
+            tab.close()
+        except:
+            pass
+        return goods_info

lib/module/ancientnutrition.py

@@ -0,0 +1,325 @@
+from core import spiders, types
+from utils import formats, messages
+
+class SpiderModule(spiders.Spiders):
+    project_name = "ancientnutrition"
+
+    def __init__(self):
+        super().__init__(
+            self.project_name,
+            bitch = 30,
+            worker_num = 1,
+            switch_clash = False,
+            reflush_browser = False
+        )
+
+    def get_category_urls(self) -> list[str]:
+        category_urls = []
+
+        self.tab.get('https://ancientnutrition.com/')
+        one_menu_eles = self.tab.eles('xpath=//*[@id="__next"]/div[4]/div[1]/div[1]/div')
+        for index, one_menu_ele in enumerate(one_menu_eles[1:]):
+            one_link_ele = one_menu_ele.ele('xpath=div/a')
+            one_url = one_link_ele.attr('href')
+            one_name = one_link_ele.text.replace('/', '-')
+            category_urls.append(f"{one_url}#{one_name}")
+            messages.sendInfo(one_name)
+
+            print(index+2)
+            two_menu_eles = self.tab.eles(f'xpath=//*[@id="__next"]/div[4]/div[{index+2}]/div/div/div[2]/div/a')
+            for two_menu_ele in two_menu_eles:
+                two_link_ele = two_menu_ele
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-')
+                category_urls.append(f"{two_url}#{one_name}/{two_name}")
+            
+                # three_menu_eles = two_menu_ele.eles('xpath=ul/li')
+                # for three_menu_ele in three_menu_eles:
+                #     three_link_ele = three_menu_ele.ele('@tag()=a')
+                #     three_url = three_link_ele.attr('href')
+                #     three_name = three_link_ele.text.replace('/', '-')
+                #     category_urls.append(f"{three_url}#{one_name}/{two_name}/{three_name}")
+
+        return category_urls
+
+    def get_goods_urls(self, category_url: str) -> list[str]:
+        self.tab.get(f"{category_url}")
+        goods_urls = []
+
+        while True:
+            try:
+                self.tab.scroll.to_bottom()
+                self.tab.ele('text=Load More').click()
+            except:
+                break
+
+        goods_eles = self.tab.eles('xpath=//*[@id="__next"]/div[9]/div/div[2]/div[2]/div')
+        for goods_ele in goods_eles:
+            try:
+                goods_link_ele = goods_ele.ele('@tag()=a')
+            except Exception as e:
+                continue
+            goods_urls.append(goods_link_ele.attr('href'))
+
+        return goods_urls
+
+    def get_goods_info(self, url) -> types.GoodsInfo:
+        def get_image_urls():
+            image_urls = []
+
+            image_eles = tab.eles('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[1]/div/div[2]/div/div[1]/div')
+            for image_ele in image_eles:
+                image_link_ele = image_ele.ele('xpath=div/span/img')
+                image_urls.append(image_link_ele.attr('src').replace('_150x150', '_1450x1450'))
+
+            return image_urls
+
+        tab = self.browser.new_tab(url)
+        tab.set.window.max()
+        spu = formats.url_to_spu(url)
+
+        try:
+            brand = ''
+            # try:
+            #     brand = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[1]/h1/div[1]', timeout=10).text
+            # except:
+            #     pass
+            # if brand == '':
+            #     title = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[1]/h1').text
+            # else:
+            title = tab.ele('@tag()=h1').text
+
+            desc = formats.clean_html(tab.ele('#productDescription').html)
+            
+            price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[1]').text.replace('$', ''))
+            old_price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[2]/span[1]').text.replace('$', ''))
+
+            main_images = get_image_urls()
+
+            goods_info = types.GoodsInfo(
+                title=title,
+                desc=desc,
+                brand=brand,
+                url=url,
+                spu=spu,
+                price=price,
+                old_price=old_price,
+            )
+
+            m_data = []
+            attr_items = []
+            try:
+                tab.ele('text=Select Flavor').click()
+                m_data.append('Flavor')
+            except:
+                pass
+            try:
+                tab.ele('text=Select Size').click()
+                m_data.append('Size')
+            except:
+                pass
+            try:
+                tab.ele('text=Select Quantity').click()
+                m_data.append('Quantity')
+            except:
+                pass
+
+            if 'Flavor' in m_data:
+                tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[3]/div/div').click()
+                color_eles = tab.eles('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[3]/div/div[2]/div')
+                color_xpaths = []
+                for color_ele in color_eles:
+                    color_xpaths.append(color_ele.xpath)
+                
+                for color_xpath in color_xpaths:
+                    while True:
+                        tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[3]/div/div').click()
+                        try:
+                            color_ele = tab.ele(f"xpath={color_xpath}")
+                            color_name = color_ele.text
+                            break
+                        except:
+                            tab.get(url)
+                    color_ele.click()
+                    tab.wait(3)
+                    color_images = get_image_urls()
+                    if 'Size' in m_data:
+                        try:
+                            size_eles = tab.eles(f"xpath={tab.ele('text=Select Size').xpath.replace('/span[1]', '/div/div')}")
+                        except:
+                            size_name = 'Default'
+                            if 'Quantity' in m_data:
+                                quantity_eles = tab.eles(f"xpath={tab.ele('text=Select Quantity').xpath.replace('/span[1]', '/div/div')}")
+                                for quantity_index, quantity_ele in enumerate(quantity_eles):
+                                    try:
+                                        quantity_ele = tab.ele(f"xpath={tab.ele('text=Select Quantity').xpath.replace('/span[1]', f'/div/div[{quantity_index+1}]')}")
+                                        quantity_name =  quantity_ele.text
+                                    except:
+                                        continue
+                                    quantity_ele.click()
+                                    tab.wait(2)
+                                    price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[1]').text.replace('$', ''))
+                                    old_price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[2]/span[1]').text.replace('$', ''))
+                                    attr_items.append({
+                                        'url': tab.url,
+                                        'items': [color_name, size_name, quantity_name],
+                                        'price': price,
+                                        'old_price': old_price,
+                                        'images': color_images
+                                    })
+                            else:
+                                price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[1]').text.replace('$', ''))
+                                old_price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[2]/span[1]').text.replace('$', ''))
+                                attr_items.append({
+                                    'url': tab.url,
+                                    'items': [color_name, size_name],
+                                    'price': price,
+                                    'old_price': old_price,
+                                    'images': color_images
+                                })
+                        size_xpaths = []
+                        for size_ele in size_eles:
+                            try:
+                                size_xpaths.append(size_ele.xpath)
+                            except:
+                                continue
+                        
+                        for size_xpath in size_xpaths:
+                            try:
+                                size_ele = tab.ele(f"xpath={size_xpath}")
+                                size_name = size_ele.text
+                            except:
+                                continue
+                            size_ele.click()
+                            tab.wait(3)
+                            color_images = get_image_urls()
+                            if 'Quantity' in m_data:
+                                quantity_eles = tab.eles(f"xpath={tab.ele('text=Select Quantity').xpath.replace('/span[1]', '/div/div')}")
+                                for quantity_index, quantity_ele in enumerate(quantity_eles):
+                                    try:
+                                        quantity_ele = tab.ele(f"xpath={tab.ele('text=Select Quantity').xpath.replace('/span[1]', f'/div/div[{quantity_index+1}]')}")
+                                        quantity_name =  quantity_ele.text
+                                    except:
+                                        continue
+                                    quantity_ele.click()
+                                    tab.wait(2)
+                                    price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[1]').text.replace('$', ''))
+                                    old_price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[2]/span[1]').text.replace('$', ''))
+                                    attr_items.append({
+                                        'url': tab.url,
+                                        'items': [color_name, size_name, quantity_name],
+                                        'price': price,
+                                        'old_price': old_price,
+                                        'images': color_images
+                                    })
+                            else:
+                                price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[1]').text.replace('$', ''))
+                                old_price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[2]/span[1]').text.replace('$', ''))
+                                attr_items.append({
+                                    'url': tab.url,
+                                    'items': [color_name, size_name],
+                                    'price': price,
+                                    'old_price': old_price,
+                                    'images': color_images
+                                })
+                    else:
+                        price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[1]').text.replace('$', ''))
+                        old_price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[2]/span[1]').text.replace('$', ''))
+                        attr_items.append({
+                            'url': tab.url,
+                            'items': [color_name],
+                            'price': price,
+                            'old_price': old_price,
+                            'images': color_images
+                        })
+            else:
+                color_images = []
+                if 'Size' in m_data:
+                    size_eles = tab.eles(f"xpath={tab.ele('text=Select Size').xpath.replace('/span[1]', '/div/div')}")
+                    size_xpaths = []
+                    for size_ele in size_eles:
+                        try:
+                            size_xpaths.append(size_ele.xpath)
+                        except:
+                            continue
+                        
+                    for size_xpath in size_xpaths:
+                        try:
+                            size_ele = tab.ele(f"xpath={size_xpath}")
+                            size_name = size_ele.text
+                        except:
+                            continue
+                        size_ele.click()
+                        tab.wait(2)
+                        color_images = get_image_urls()
+                        if 'Quantity' in m_data:
+                            quantity_eles = tab.eles(f"xpath={tab.ele('text=Select Quantity').xpath.replace('/span[1]', '/div/div')}")
+                            for quantity_index, quantity_ele in enumerate(quantity_eles):
+                                try:
+                                    quantity_ele = tab.ele(f"xpath={tab.ele('text=Select Quantity').xpath.replace('/span[1]', f'/div/div[{quantity_index+1}]')}")
+                                    quantity_name =  quantity_ele.text
+                                except:
+                                    continue
+                                quantity_ele.click()
+                                tab.wait(2)
+                                price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[1]').text.replace('$', ''))
+                                old_price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[2]/span[1]').text.replace('$', ''))
+                                attr_items.append({
+                                    'url': tab.url,
+                                    'items': [size_name, quantity_name],
+                                    'price': price,
+                                    'old_price': old_price,
+                                    'images': color_images
+                                })
+                else:
+                    if 'Quantity' in m_data:
+                        quantity_eles = tab.eles(f"xpath={tab.ele('text=Select Quantity').xpath.replace('/span[1]', '/div/div')}")
+                        for quantity_index, quantity_ele in enumerate(quantity_eles):
+                            try:
+                                quantity_ele = tab.ele(f"xpath={tab.ele('text=Select Quantity').xpath.replace('/span[1]', f'/div/div[{quantity_index+1}]')}")
+                                quantity_name =  quantity_ele.text
+                            except:
+                                continue
+                            quantity_ele.click()
+                            tab.wait(2)
+                            price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[1]').text.replace('$', ''))
+                            old_price = float(tab.ele('xpath=//*[@id="__next"]/div[8]/div[1]/div/div[2]/div[2]/div/div[1]/div/span/span[2]/span[1]').text.replace('$', ''))
+                            attr_items.append({
+                                'url': tab.url,
+                                'items': [quantity_name],
+                                'price': price,
+                                'old_price': old_price,
+                                'images': color_images
+                            })
+
+            if len(attr_items) == 0:
+                goods_info.attr = 'S'
+                goods_info.attr_items = []
+                goods_info.images = main_images
+                goods_info.p_lists = []
+            else:
+                goods_info.attr = 'M'
+                goods_info.attr_items = m_data
+                for attr_item in attr_items:
+                    goods_info.p_lists.append(types.GoodsInfo.GoodsInfoP(
+                        url=attr_item['url'],
+                        attr_items=attr_item['items'],
+                        price=attr_item['price'],
+                        old_price=attr_item['old_price'],
+                        images=attr_item['images'],
+                    ))
+                    for image_url in attr_item['images']:
+                        if image_url not in main_images:
+                            main_images.append(image_url)
+                goods_info.images = main_images
+        except Exception as e:
+            try:
+                tab.close()
+            except:
+                pass
+            raise Exception(e)
+        try:
+            tab.close()
+        except:
+            pass
+        return goods_info

lib/module/bricomarche.py

@@ -0,0 +1,201 @@
+from core import spiders, types
+from utils import formats, messages
+from DrissionPage.common import Keys
+
+class SpiderModule(spiders.Spiders):
+    project_name = "bricomarche"
+
+    def __init__(self):
+        super().__init__(
+            self.project_name,
+            bitch = 5,
+            worker_num = 1,
+            switch_clash = False,
+            reflush_browser = False
+        )
+        self.tab.get('https://www.bricomarche.pl/')
+        # input('wait:')
+
+    def get_category_urls(self) -> list[str]:
+        category_urls = []
+
+        self.tab.get('https://www.bricomarche.pl/')
+        one_menu_eles = self.tab.eles('xpath=//*[@id="root"]/main/div[5]/div[3]/nav/div')
+        for one_menu_ele in one_menu_eles:
+            one_link_ele = one_menu_ele.ele('@tag()=a')
+            one_url = one_link_ele.attr('href')
+            one_name = one_link_ele.text.replace('/', '-')
+            category_urls.append(f"{one_url}#{one_name}")
+            messages.sendInfo(one_name)
+
+            two_menu_eles = one_menu_ele.eles('xpath=div/div[1]/div')
+            for two_menu_ele in two_menu_eles:
+                two_link_ele = two_menu_ele.ele('@tag()=a')
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-')
+                category_urls.append(f"{two_url}#{one_name}/{two_name}")
+            
+                three_menu_eles = two_menu_ele.eles('xpath=ul/li')
+                for three_menu_ele in three_menu_eles:
+                    three_link_ele = three_menu_ele.ele('@tag()=a')
+                    three_url = three_link_ele.attr('href')
+                    three_name = three_link_ele.text.replace('/', '-')
+                    category_urls.append(f"{three_url}#{one_name}/{two_name}/{three_name}")
+
+        return category_urls
+
+    def get_goods_urls(self, category_url: str) -> list[str]:
+        page = 1
+        limit = 100
+        self.tab.get(f"{category_url}?page={page}&limit={limit}")
+        if self.tab.ele('@tag()=h2').text == '执行安全验证':
+            self.tab.wait(10)
+            self.tab.actions.type((Keys.TAB, Keys.SPACE))
+        goods_urls = []
+        
+        while True:
+            try:
+                self.tab.scroll.to_bottom()
+                goods_eles = self.tab.eles('xpath=//*[@id="spark"]/div[2]/div/section/div/div/main/div[2]/section/div')
+                for goods_ele in goods_eles:
+                    goods_link_ele = goods_ele.ele('@tag()=a')
+                    goods_urls.append(goods_link_ele.attr('href'))
+                if len(goods_eles) == 0:
+                    break
+            except:
+                break
+            page += 1
+            self.tab.get(f"{category_url}?page={page}&limit={limit}")
+            if self.tab.ele('@tag()=h2').text == '执行安全验证':
+                self.tab.wait(10)
+                self.tab.actions.type((Keys.TAB, Keys.SPACE))
+
+        return goods_urls
+
+    def get_goods_info(self, url) -> types.GoodsInfo:
+        def get_image_urls():
+            image_urls = []
+
+            image_eles = tab.eles('xpath=//*[@id="spark"]/div[2]/div/main/div/div[2]/section[1]/div/div[1]/div/div/div/div/div')
+            for image_ele in image_eles:
+                image_link_ele = image_ele.ele('xpath=button/div/img')
+                image_urls.append(image_link_ele.attr('src').replace('gallery_100_91', 'gallery'))
+
+            return image_urls
+
+        tab = self.browser.new_tab(url)
+        while True:
+            try:
+                if tab.ele('@tag()=h2').text == '执行安全验证':
+                    tab.wait(10)
+                    tab.actions.type((Keys.TAB, Keys.SPACE))
+                    tab.wait(5)
+                else:
+                    break
+            except:
+                break
+        tab.set.window.max()
+        spu = formats.url_to_spu(url)
+
+        try:
+            brand = ''
+            # try:
+            #     brand = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[1]/h1/div[1]', timeout=10).text
+            # except:
+            #     pass
+
+            title = tab.ele('@tag()=h1', timeout=10).text
+
+            desc = ""
+            try:
+                desc = formats.clean_html(tab.ele('.attributes').html)
+            except:
+                pass
+            
+            # try:
+            price_ele = tab.ele('.main-price')
+            price = float(f"{price_ele.ele('.whole').text}{price_ele.ele('.cents').text.replace(' zł', '')}")
+            # except:
+            #     price = 0.0
+            old_price = price
+
+            main_images = get_image_urls()
+
+            goods_info = types.GoodsInfo(
+                title=title,
+                desc=desc,
+                brand=brand,
+                url=url,
+                spu=spu,
+                price=price,
+                old_price=old_price,
+            )
+
+            m_data = []
+            attr_items = []
+            # color_urls = [url]
+            # color_eles = tab.eles('xpath=//*[@id="contentContainer"]/form/div[2]/div[2]/div/ul/li')
+            # for color_ele in color_eles[1:]:
+            #     color_link_ele = color_ele.ele('xpath=a')
+            #     color_urls.append(color_link_ele.attr('href'))
+            # if len(color_urls) > 1:
+            #     m_data = ["Color"]
+            
+            # if len(color_urls) > 1:
+            #     for color_url in color_urls:
+            #         color_images = main_images
+            #         if color_url != url:
+            #             tab.get(color_url)
+            #             if brand == '':
+            #                 title = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[1]/h1').text
+            #             else:
+            #                 title = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[1]/h1/div[2]').text
+            #             color_images = get_image_urls()
+
+            #         price = float(f"{tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/section[2]/div[1]/div[2]/span[1]').text}.{tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/section[2]/div[1]/div[2]/span[3]').text}")
+            #         old_price = price
+
+            #         try:
+            #             item_name = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[2]/div/ul/li[1]/div[2]/p').text
+            #         except:
+            #             continue
+            #         attr_items.append({
+            #             'url': color_url,
+            #             'items': [item_name],
+            #             'price': price,
+            #             'old_price': old_price,
+            #             'images': color_images
+            #         })
+
+            if len(attr_items) == 0:
+                goods_info.attr = 'S'
+                goods_info.attr_items = []
+                goods_info.images = main_images
+                goods_info.p_lists = []
+            else:
+                goods_info.attr = 'M'
+                goods_info.attr_items = m_data
+                for attr_item in attr_items:
+                    goods_info.p_lists.append(types.GoodsInfo.GoodsInfoP(
+                        url=attr_item['url'],
+                        attr_items=attr_item['items'],
+                        price=attr_item['price'],
+                        old_price=attr_item['old_price'],
+                        images=attr_item['images'],
+                    ))
+                    for image_url in attr_item['images']:
+                        if image_url not in main_images:
+                            main_images.append(image_url)
+                goods_info.images = main_images
+                # goods_info.p_urls = color_urls
+        except Exception as e:
+            try:
+                tab.close()
+            except:
+                pass
+            raise Exception(e)
+        try:
+            tab.close()
+        except:
+            pass
+        return goods_info

lib/module/condom69.py

@@ -0,0 +1,136 @@
+from core import spiders, types
+from utils import formats, messages
+
+class SpiderModule(spiders.Spiders):
+    project_name = "condom69"
+
+    def __init__(self):
+        super().__init__(
+            self.project_name,
+            bitch = 30,
+            worker_num = 5,
+            switch_clash = False,
+            reflush_browser = False
+        )
+        self.tab.get('https://www.condom69.net/')
+        # input('wait:')
+
+    def get_category_urls(self) -> list[str]:
+        category_urls = []
+        
+        one_menu_eles = self.tab.eles('xpath=//*[@id="nav-one"]/li')
+        for one_menu_ele in one_menu_eles[:-1]:
+            one_link_ele = one_menu_ele.ele('xpath=a')
+            one_url = one_link_ele.attr('href')
+            one_name = one_link_ele.text.replace('/', '-')
+            category_urls.append(f"{one_url}#{one_name}")
+            messages.sendInfo(one_name)
+
+            two_menu_eles = one_menu_ele.eles('xpath=div/ul/li', timeout=1)
+            for two_index, two_menu_ele in enumerate(two_menu_eles):
+                two_link_ele = two_menu_ele.ele('xpath=div/a')
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-').replace(',', '，').replace('#', ' ')
+                category_urls.append(f"{two_url}#{one_name}/{two_name}")
+            
+                # try:
+                #     three_menu_eles = self.tab.ele(f'xpath=//*[@id="__next"]/div[1]/header/div/div[2]/nav/div[{two_index+1}]/div/div[1]').eles('@tag()=li')
+                # except:
+                #     continue
+                # for three_menu_ele in three_menu_eles:
+                #     three_link_ele = three_menu_ele.ele('@tag()=a')
+                #     three_url = three_link_ele.attr('href')
+                #     three_name = three_link_ele.text.replace('/', '-')
+                #     category_urls.append(f"{three_url}#{one_name}/{two_name}/{three_name}")
+
+        return category_urls
+
+    def get_goods_urls(self, category_url: str) -> list[str]:
+        page = 1
+        self.tab.get(f"{category_url}&pg={page}")
+
+        #####获取页数####
+
+        #################
+
+        goods_urls = []
+        url_index = {}
+        while True:
+            self.tab.scroll.to_bottom()
+            goods_eles = self.tab.eles('.divProdItemImg2Inner')
+            page_urls = []
+            for goods_ele in goods_eles:
+                goods_url = f"{goods_ele.ele('xpath=a').attr('href')}"
+                if goods_url not in url_index:
+                    page_urls.append(goods_url)
+                    url_index[goods_url] = None
+            if len(page_urls) > 0:
+                goods_urls += page_urls
+            else:
+                break
+            page += 1
+            self.tab.get(f"{category_url}&pg={page}")
+
+        messages.sendInfo(f"{len(goods_urls)} 个")
+
+        return goods_urls
+
+    def get_goods_info(self, url) -> types.GoodsInfo:
+        def get_image_urls():
+            image_urls = []
+            image_eles = tab.eles('xpath=/html/body/form/div[3]/div[2]/div/div[2]/div/div/div[2]/div[2]/div[3]/div/div[2]/div/div/div[1]/div[1]/div[2]/div')
+
+            for image_ele in image_eles:
+                image_url = image_ele.ele('xpath=div/div/a/img').attr('src')
+                image_urls.append(image_url)
+            return image_urls
+
+        tab = self.browser.new_tab(url)
+        tab.set.window.max()
+        spu = formats.url_to_spu(url)
+
+        try:
+            h1_ele = tab.ele('xpath=/html/body/form/div[3]/div[2]/div/div[2]/div/div/div[2]/div[2]/div[3]/div/div[2]/div/div/div[1]/div[2]/div/div[1]')
+            brand = ''
+            try:
+                brand = tab.ele('xpath=/html/body/form/div[3]/div[2]/div/div[2]/div/div/div[2]/div[2]/div[3]/div/div[2]/div/div/div[1]/div[2]/div/div[2]/div[1]/table/tbody/tr/td[3]/a').text
+            except:
+                pass
+            title = h1_ele.text
+
+            desc = ""
+            try:
+                desc = formats.clean_html(tab.ele('.ctl00_cphContent_ucUsrIndProduct_pnlIndProdDesc').html)
+            except:
+                pass
+
+            price = tab.ele('xpath=/html/body/form/div[3]/div[2]/div/div[2]/div/div/div[2]/div[2]/div[3]/div/div[2]/div/div/div[1]/div[2]/div/div[2]/div[3]/div[1]/div[2]/span').text.replace(',', '')
+            old_price = price
+
+            main_images = get_image_urls()
+
+            goods_info = types.GoodsInfo(
+                title=title,
+                desc=desc,
+                brand=brand,
+                url=url,
+                spu=spu,
+                price=price,
+                old_price=old_price,
+            )
+
+            goods_info.attr = 'S'
+            goods_info.attr_items = []
+            goods_info.images = main_images
+            goods_info.p_lists = []
+        except Exception as e:
+            try:
+                tab.close()
+            except:
+                pass
+            raise Exception(e)
+        try:
+            tab.close()
+        except:
+            pass
+        return goods_info

lib/module/dk_one.py

@@ -0,0 +1,210 @@
+from core import spiders, types
+from utils import formats, messages
+
+class SpiderModule(spiders.Spiders):
+    project_name = "dk_one"
+
+    def __init__(self):
+        super().__init__(
+            self.project_name,
+            bitch = 30,
+            worker_num = 1,
+            switch_clash = False,
+            reflush_browser = False
+        )
+
+    def get_category_urls(self) -> list[str]:
+        category_urls = []
+
+        self.tab.get('https://www.dk_one.com/')
+        one_menu_eles = self.tab.eles('xpath=/html/body/div[5]/header/div[2]/div[2]/div/div[1]/div[1]/ul/li')
+        for one_menu_ele in one_menu_eles:
+            one_link_ele = one_menu_ele.ele('@tag()=a')
+            one_url = one_link_ele.attr('href')
+            one_name = one_link_ele.text.replace('/', '-')
+            if one_name == '라이프':
+                continue
+            category_urls.append(f"{one_url}#{one_name}")
+            messages.sendInfo(one_name)
+
+            two_menu_eles = one_menu_ele.eles('xpath=div/div/div[1]/ul/li')
+            for two_menu_ele in two_menu_eles:
+                two_link_ele = two_menu_ele.ele('@tag()=a')
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-')
+                if two_name == '메인':
+                    continue
+                category_urls.append(f"{two_url}#{one_name}/{two_name}")
+            two_menu_eles = one_menu_ele.eles('xpath=div/div/div[2]/ul/li')
+            for two_menu_ele in two_menu_eles:
+                two_link_ele = two_menu_ele.ele('@tag()=a')
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-')
+                if two_name == '메인':
+                    continue
+                category_urls.append(f"{two_url}#{one_name}/Top Brand/{two_name}")
+            
+                # three_menu_eles = two_menu_ele.eles('xpath=ul/li')
+                # for three_menu_ele in three_menu_eles:
+                #     three_link_ele = three_menu_ele.ele('@tag()=a')
+                #     three_url = three_link_ele.attr('href')
+                #     three_name = three_link_ele.text.replace('/', '-')
+                #     category_urls.append(f"{three_url}#{one_name}/{two_name}/{three_name}")
+
+        return category_urls
+
+    def get_goods_urls(self, category_url: str) -> list[str]:
+        self.tab.get(category_url)
+        goods_urls = []
+        goods_eles = self.tab.eles('xpath=//*[@id="prodList"]/div')
+        for goods_ele in goods_eles:
+            goods_link_ele = goods_ele.ele('.prod-link')
+            goods_urls.append(goods_link_ele.attr('href'))
+
+        return goods_urls
+
+    def get_goods_info(self, url) -> types.GoodsInfo:
+        def get_image_urls(tab):
+            image_urls = []
+            image_eles = tab.ele('#prod-img').eles('@tag()=img')
+            for image_ele in image_eles:
+                image_urls.append(image_ele.attr('src'))
+            return image_urls
+
+        tab = self.browser.new_tab(url)
+        tab.set.window.max()
+        spu = formats.url_to_spu(url)
+
+        try:
+            brand = ''
+            # try:
+            #     brand = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[1]/h1/div[1]', timeout=10).text
+            # except:
+            #     pass
+            # if brand == '':
+            #     title = tab.ele('xpath=//*[@id="contentContainer"]/form/div[2]/div[1]/h1').text
+            # else:
+            title = tab.ele('.page-title').text
+
+            try:
+                desc = formats.clean_html(tab.ele('@@class=tab-content@@id=tabContent0202').html)
+            except:
+                desc = ''
+            
+            price = float(tab.ele('.price-group').ele('.val').text.replace(',', ''))
+            try:
+                old_price = float(tab.ele('.price-group origin').text.replace(',', ''))
+            except:
+                old_price = price
+
+            main_images = get_image_urls(tab)
+
+            goods_info = types.GoodsInfo(
+                title=title,
+                desc=desc,
+                brand=brand,
+                url=url,
+                spu=spu,
+                price=price,
+                old_price=old_price,
+                images=main_images
+            )
+
+            m_data = []
+            color_data = {}
+            color_eles = []
+            # 颜色
+            tab.ele('.opt-color')
+            m_data.append('컬러')
+            color_eles = tab.ele('.color-list-wrap').eles('.prod-color-rdo')
+
+            m_data.append('사이즈')
+
+            for color_ele in color_eles:
+                color_input_onclick = color_ele.ele('@tag()=input').attr('onclick')
+                have_url = False
+                if 'location.href=' in color_input_onclick:
+                    color_url = 'https://dk-on.com' + formats.re_search(color_input_onclick, r"location\.href\s*=\s*'([^']*)'")
+                    color_name = color_url.split('/')[-1]
+                    have_url = True
+                elif 'fnColorClicked' in color_input_onclick:
+                    color_url = goods_info.url
+                    color_name = color_ele.ele('@tag()=input').attr('value')
+                    color_ele.click()
+                else:
+                    color_url = goods_info.url
+                    color_name = goods_info.title.split(' / ')[-1]
+
+                color_data[color_name] = {'url': color_url, 'have_url': have_url, 'ele': color_ele}
+                goods_info.p_urls.append(color_url)
+            
+            real_color_data = {}
+            
+
+            for color_name, color_item in color_data.items():
+                color_tab = tab
+                if color_item['have_url']:
+                    color_tab = self.browser.new_tab()
+
+                size_data = []
+                if color_item['have_url']:
+                    color_tab.get(color_item['url'])
+                else:
+                    color_item['ele'].click()
+                color_tab.wait(1)
+                color_item['price'] = str(color_tab.ele('.price-group').ele('.val').text.replace(',', ''))
+                try:
+                    color_item['old_price'] = str(color_tab.ele('.price-group origin').text.replace(',', ''))
+                except:
+                    color_item['old_price'] = color_item['price']
+
+                # 颜色对应商品图
+                color_item['images'] = get_image_urls(tab = color_tab)
+
+                # 颜色对应尺码
+                radio_eles = color_tab.ele('.prod-size-list').eles('.prod-size')
+                for radio_ele in radio_eles:
+                    value = radio_ele.ele('@tag()=label').text
+                    if value == None:
+                        continue
+                    size_data.append(value)
+                color_item['size'] = size_data
+
+                real_color_data[color_tab.ele('.page-title').text.split(' / ')[-1]] = color_item
+            color_data = real_color_data
+
+            goods_info.attr = 'M'
+            goods_info.title = goods_info.title.split(' / ')[0]
+            goods_info.attr_items = m_data
+            for color_name, color_item in color_data.items():
+                for color_image in color_item['images']:
+                    if color_image in goods_info.images:
+                        continue
+                    goods_info.images.append(color_image)
+
+            # if color_data:
+            item_data = []
+            for color_name, color_item in color_data.items():
+                for size in color_item['size']:
+                    item_data.append([color_name, size])
+            for attribute_items in item_data:
+                goods_info.p_lists.append(types.GoodsInfo.GoodsInfoP(
+                    attr_items=attribute_items,
+                    price=color_data[attribute_items[0]]['price'],
+                    old_price=color_data[attribute_items[0]]['price'],
+                    images=color_data[attribute_items[0]]['images'],
+                ))
+
+        except Exception as e:
+            try:
+                tab.close()
+                color_tab.close()
+            except:
+                pass
+            raise Exception(e)
+        try:
+            tab.close()
+            color_tab.close()
+        except:
+            pass
+        return goods_info

lib/module/example.py

@@ -0,0 +1,86 @@
+from core import spiders, types
+from utils import formats, messages
+
+class SpiderModule(spiders.Spiders):
+    project_name = "example"
+
+    def __init__(self):
+        super().__init__(
+            self.project_name,
+            bitch = 10,
+            worker_num = 1,
+            switch_clash = False,
+            reflush_browser = False
+        )
+
+    def get_category_urls(self) -> list[str]:
+        category_urls = []
+
+        pass
+
+        return category_urls
+
+    def get_goods_urls(self, category_url: str) -> list[str]:
+        self.tab.get(f"{category_url}")
+        goods_urls = []
+        
+        pass
+        
+        return goods_urls
+
+    def get_goods_info(self, url) -> types.GoodsInfo:
+        def get_image_urls():
+            image_urls = []
+            pass
+            return image_urls
+
+        tab = self.browser.new_tab(url)
+        tab.set.window.max()
+        spu = formats.url_to_spu(url)
+
+        desc = "简介"
+        brand = "品牌"
+        title = "标题"
+        price = 0.00
+        old_price = price
+
+        main_images = get_image_urls()
+
+        goods_info = types.GoodsInfo(
+            title=title,
+            desc=desc,
+            brand=brand,
+            url=url,
+            spu=spu,
+            price=price,
+            old_price=old_price,
+        )
+
+        m_data = []
+        attr_items = []
+
+        if len(attr_items) == 0:
+            goods_info.attr = 'S'
+            goods_info.attr_items = []
+            goods_info.images = main_images
+            goods_info.p_lists = []
+        else:
+            goods_info.attr = 'M'
+            goods_info.attr_items = m_data
+            for attr_item in attr_items:
+                goods_info.p_lists.append(types.GoodsInfo.GoodsInfoP(
+                    attr_items=attr_item['items'],
+                    price=attr_item['price'],
+                    old_price=attr_item['old_price'],
+                    images=attr_item['images']
+                ))
+                for image_url in attr_item['images']:
+                    if image_url not in main_images:
+                        main_images.append(image_url)
+            goods_info.images = main_images
+
+        try:
+            tab.close()
+        except:
+            pass
+        return goods_info

lib/module/friskybusiness.py

@@ -0,0 +1,141 @@
+from core import spiders, types
+from utils import formats, messages
+
+class SpiderModule(spiders.Spiders):
+    project_name = "friskybusiness"
+
+    def __init__(self):
+        super().__init__(
+            self.project_name,
+            bitch = 30,
+            worker_num = 5,
+            switch_clash = False,
+            reflush_browser = False
+        )
+        self.tab.get('https://friskybusiness.sg/')
+        # input('wait:')
+
+    def get_category_urls(self) -> list[str]:
+        category_urls = []
+        
+        one_menu_eles = self.tab.eles('xpath=/html/body/header/height-observer/x-header/nav[2]/ul/li')
+        for one_index, one_menu_ele in enumerate(one_menu_eles[:-1]):
+            
+            one_link_ele = one_menu_ele.ele('@tag()=summary')
+            one_url = one_link_ele.attr('data-follow-link')
+            one_name = one_link_ele.text.replace('/', '-')
+            category_urls.append(f"{one_url}#{one_name}")
+            messages.sendInfo(one_name)
+
+            if one_index == 0 or one_index == 6:
+                two_menu_eles = one_menu_ele.eles('xpath=mega-menu-disclosure/details/div/div/a')
+            else:
+                two_menu_eles = one_menu_ele.eles('xpath=mega-menu-disclosure/details/div/ul/li', timeout=1)
+            for two_index, two_menu_ele in enumerate(two_menu_eles):
+                if one_index == 0 or one_index == 6:
+                    two_link_ele = two_menu_ele
+                else:
+                    two_link_ele = two_menu_ele.ele('@tag()=a')
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-').replace(',', '，').replace('#', ' ')
+                category_urls.append(f"{two_url}#{one_name}/{two_name}")
+            
+                try:
+                    three_menu_eles = two_menu_ele.eles(f'xpath=div/ul/li')
+                except:
+                    continue
+                for three_menu_ele in three_menu_eles:
+                    three_link_ele = three_menu_ele.ele('@tag()=a')
+                    three_url = three_link_ele.attr('href')
+                    three_name = three_link_ele.text.replace('/', '-').replace(',', '，').replace('#', ' ')
+                    category_urls.append(f"{three_url}#{one_name}/{two_name}/{three_name}")
+
+        return category_urls
+
+    def get_goods_urls(self, category_url: str) -> list[str]:
+        page = 1
+        self.tab.get(f"{category_url}?page={page}")
+        goods_urls = []
+        
+        #####获取页数####
+
+        #################
+
+        goods_urls = []
+        while True:
+            self.tab.scroll.to_bottom()
+            try:
+                goods_eles = self.tab.eles('#:snize-product-', timeout=5)
+                for goods_ele in goods_eles:
+                    goods_url = f"{goods_ele.ele('@tag()=a').attr('href')}"
+                    goods_urls.append(goods_url)
+                if len(goods_eles) == 0:
+                    break
+            except:
+                break
+            page += 1
+            self.tab.get(f"{category_url}?page={page}")
+
+        messages.sendInfo(f"{len(goods_urls)} 个")
+
+        return goods_urls
+
+    def get_goods_info(self, url) -> types.GoodsInfo:
+        def get_image_urls():
+            image_urls = []
+            image_eles = tab.eles('xpath=/html/body/main/section[1]/div/div/product-rerender/div/product-gallery/safe-sticky/product-gallery-navigation/button')
+
+            for image_ele in image_eles[-1:]:
+                image_url = image_ele.ele('xpath=img').attr('src')
+                image_urls.append(image_url)
+            return image_urls
+
+        tab = self.browser.new_tab(url)
+        tab.set.window.max()
+        spu = formats.url_to_spu(url)
+
+        try:
+            h1_ele = tab.ele('@tag()=h1')
+            brand = ''
+            title = h1_ele.text
+
+            desc = ""
+            try:
+                desc = formats.clean_html(tab.ele('.liquid').html)
+            except:
+                pass
+
+            price_list = tab.ele('.price-list price-list--product')
+            price = price_list.ele('@tag()=sale-price').ele('.money').text.replace('$', '').replace(',', '')
+            try:
+                old_price = price_list.ele('@tag()=compare-at-price').ele('.money').text.replace('$', '').replace(',', '')
+            except:
+                old_price = price
+
+            main_images = get_image_urls()
+
+            goods_info = types.GoodsInfo(
+                title=title,
+                desc=desc,
+                brand=brand,
+                url=url,
+                spu=spu,
+                price=price,
+                old_price=old_price,
+            )
+
+            goods_info.attr = 'S'
+            goods_info.attr_items = []
+            goods_info.images = main_images
+            goods_info.p_lists = []
+        except Exception as e:
+            try:
+                tab.close()
+            except:
+                pass
+            raise Exception(e)
+        try:
+            tab.close()
+        except:
+            pass
+        return goods_info

lib/module/peek_cloppenburg.py

@@ -0,0 +1,217 @@
+from core import spiders, types
+from utils import formats, messages
+
+class SpiderModule(spiders.Spiders):
+    project_name = "peek-cloppenburg"
+
+    def __init__(self):
+        super().__init__(
+            self.project_name,
+            bitch = 30,
+            worker_num = 5,
+            switch_clash = False,
+            reflush_browser = False
+        )
+
+    def get_category_urls(self) -> list[str]:
+        category_urls = []
+
+        self.tab.get('https://www.peek-cloppenburg.at/')
+        one_menu_eles = self.tab.ele('@data-testid=header-links').eles('@tag()=a')
+        for one_menu_ele in one_menu_eles:
+            one_link_ele = one_menu_ele
+            one_url = one_link_ele.attr('href')
+            one_name = one_link_ele.text.replace('/', '-')
+            category_urls.append(f"{one_url}#{one_name}")
+            messages.sendInfo(one_name)
+            one_link_ele.click()
+            self.tab.wait(3)
+
+            two_menu_eles = self.tab.eles('xpath=//*[@id="__next"]/div[1]/header/div[2]/div[2]/nav/a', timeout=1)
+            for two_index, two_menu_ele in enumerate(two_menu_eles):
+                two_link_ele = two_menu_ele
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-')
+                category_urls.append(f"{two_url}#{one_name}/{two_name}")
+            
+                try:
+                    three_menu_eles = self.tab.ele(f'xpath=//*[@id="__next"]/div[1]/header/div[2]/div[2]/nav/div[{two_index+1}]/div/div[1]').eles('@tag()=li')
+                except:
+                    continue
+                for three_menu_ele in three_menu_eles:
+                    three_link_ele = three_menu_ele.ele('@tag()=a')
+                    three_url = three_link_ele.attr('href')
+                    three_name = three_link_ele.text.replace('/', '-')
+                    category_urls.append(f"{three_url}#{one_name}/{two_name}/{three_name}")
+
+        return category_urls
+
+    def get_goods_urls(self, category_url: str) -> list[str]:
+        self.tab.get(f"{category_url}?page=1")
+        goods_urls = []
+        
+        max_page = 1
+        #####获取页数####
+        try:
+            max_page = int(self.tab.eles('@data-testid=pagination-item')[-1].text)
+        except:
+            pass
+        #################
+
+        goods_urls = []
+        if max_page > 1:
+            for page in range(1, max_page+1):
+                if page > 1:
+                    self.tab.get(f"{category_url}?page={page}&userId=123456")
+
+                goods_eles = self.tab.eles('xpath=//*[@id="__next"]/div[2]/div/section/div/div[2]/div[5]/div/section[1]/section/div/div')
+                for goods_ele in goods_eles:
+                    goods_url = f"{goods_ele.ele('@tag()=a').attr('href')}"
+                    goods_urls.append(goods_url)
+                messages.sendInfo(f"{page}/{max_page}")
+        else:
+            goods_eles = self.tab.eles('xpath=//*[@id="__next"]/div[2]/div/section/div/div[2]/div[5]/div/section[1]/section/div/div')
+            for goods_ele in goods_eles:
+                goods_url = f"{goods_ele.ele('@tag()=a').attr('href')}"
+                goods_urls.append(goods_url)
+
+        return goods_urls
+
+    def get_goods_info(self, url) -> types.GoodsInfo:
+        def get_image_urls():
+            image_urls = []
+            image_eles = tab.ele('#photoswipe-gallery').eles('@tag()=a')
+
+            for image_ele in image_eles:
+                image_url = image_ele.attr('href')
+                image_urls.append(image_url)
+            return image_urls
+
+        def get_size_eles():
+            try: 
+                eles = tab.ele('.option-picker mt-2 ').eles('@tag()=li')
+            except:
+                pass
+            try: 
+                eles = tab.ele('.option-picker mt-2 long-label ').eles('@tag()=li')
+            except:
+                pass
+            try:
+                eles = tab.ele('.option-picker mt-2 out-of-stock').eles('@tag()=li')
+            except:
+                pass
+            try:
+                eles = tab.ele('.option-picker mt-2 long-label out-of-stock').eles('@tag()=li')
+            except:
+                pass
+            return eles
+
+        tab = self.browser.new_tab(url)
+        tab.set.window.max()
+        spu = formats.url_to_spu(url)
+
+        try:
+            h1_eles = tab.ele('@tag()=h1', timeout=10).eles('@tag()=span')
+            brand = ''
+            try:
+                brand = h1_eles[0].text
+                title = h1_eles[1].text
+            except:
+                title = tab.ele('@tag()=h1').text
+
+            desc = ""
+            try:
+                desc = formats.clean_html(f"{tab.ele('#accordion-panel-material-care').html}{tab.ele('#accordion-panel-details').html}")
+            except:
+                pass
+
+            price = tab.ele('.:text-pdp-price-primary-xs font-bold').text.split(' ')[0].replace(',', '.')
+            try:
+                old_price = tab.ele('.line-through').text.split(' ')[0].replace(',', '.')
+            except:
+                old_price = price
+
+            main_images = get_image_urls()
+
+            goods_info = types.GoodsInfo(
+                title=title,
+                desc=desc,
+                brand=brand,
+                url=url,
+                spu=spu,
+                price=price,
+                old_price=old_price,
+            )
+
+            m_data = []
+            attr_items = []
+            color_urls = []
+            try:
+                color_eles = tab.ele('.pt-6 xl:pt-8 -mr-6 md:mr-0').eles('@tag()=li')
+                m_data.append('Farbe')
+                for color_ele in color_eles:
+                    color_url = color_ele.ele('@tag()=a').attr('href')
+                    color_urls.append(color_url)
+            except:
+                pass
+            m_data.append('Größe')
+            
+            if len(color_urls) > 0:
+                for color_url in color_urls:
+                    color_images = main_images
+                    if color_url != url:
+                        tab.get(color_url)
+                        color_images = get_image_urls()
+
+                    price = tab.ele('.:text-pdp-price-primary-xs font-bold').text.split(' ')[0].replace(',', '')
+                    try:
+                        old_price = tab.ele('.line-through').text.split(' ')[0].replace(',', '')
+                    except:
+                        old_price = price
+
+                    color_name = tab.ele('.text-cp-md font-bold').ele('xpath=text()[3]')
+
+                    size_eles = get_size_eles()
+                    for size_ele in size_eles:
+                        size_name = size_ele.ele('.text-cp-md truncate').text
+                        
+                        attr_items.append({
+                            'url': color_url,
+                            'items': [color_name, size_name],
+                            'price': price,
+                            'old_price': old_price,
+                            'images': color_images
+                        })
+
+            if len(attr_items) == 0:
+                goods_info.attr = 'S'
+                goods_info.attr_items = []
+                goods_info.images = main_images
+                goods_info.p_lists = []
+            else:
+                goods_info.attr = 'M'
+                goods_info.attr_items = m_data
+                for attr_item in attr_items:
+                    goods_info.p_lists.append(types.GoodsInfo.GoodsInfoP(
+                        url=attr_item['url'],
+                        attr_items=attr_item['items'],
+                        price=attr_item['price'],
+                        old_price=attr_item['old_price'],
+                        images=attr_item['images'],
+                    ))
+                    for image_url in attr_item['images']:
+                        if image_url not in main_images:
+                            main_images.append(image_url)
+                goods_info.images = main_images
+                goods_info.p_urls = color_urls
+        except Exception as e:
+            try:
+                tab.close()
+            except:
+                pass
+            raise Exception(e)
+        try:
+            tab.close()
+        except:
+            pass
+        return goods_info

lib/module/peek_cloppenburg_nl.py

@@ -0,0 +1,213 @@
+from core import spiders, types
+from utils import formats, messages
+
+class SpiderModule(spiders.Spiders):
+    project_name = "peek-cloppenburg-nl"
+
+    def __init__(self):
+        super().__init__(
+            self.project_name,
+            bitch = 30,
+            worker_num = 5,
+            switch_clash = False,
+            reflush_browser = False
+        )
+
+    def get_category_urls(self) -> list[str]:
+        category_urls = []
+
+        self.tab.get('https://www.peek-cloppenburg.nl/')
+        one_menu_eles = self.tab.ele('@data-testid=header-links').eles('@tag()=a')
+        for one_menu_ele in one_menu_eles:
+            one_link_ele = one_menu_ele
+            one_url = one_link_ele.attr('href')
+            one_name = one_link_ele.text.replace('/', '-')
+            category_urls.append(f"{one_url}#{one_name}")
+            messages.sendInfo(one_name)
+            one_link_ele.click()
+            self.tab.wait(3)
+
+            two_menu_eles = self.tab.eles('xpath=//*[@id="__next"]/div[1]/header/div/div[2]/nav/a', timeout=1)
+            for two_index, two_menu_ele in enumerate(two_menu_eles):
+                two_link_ele = two_menu_ele
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-')
+                category_urls.append(f"{two_url}#{one_name}/{two_name}")
+            
+                try:
+                    three_menu_eles = self.tab.ele(f'xpath=//*[@id="__next"]/div[1]/header/div/div[2]/nav/div[{two_index+1}]/div/div[1]').eles('@tag()=li')
+                except:
+                    continue
+                for three_menu_ele in three_menu_eles:
+                    three_link_ele = three_menu_ele.ele('@tag()=a')
+                    three_url = three_link_ele.attr('href')
+                    three_name = three_link_ele.text.replace('/', '-')
+                    category_urls.append(f"{three_url}#{one_name}/{two_name}/{three_name}")
+
+        return category_urls
+
+    def get_goods_urls(self, category_url: str) -> list[str]:
+        self.tab.get(f"{category_url}?page=1")
+        goods_urls = []
+        
+        max_page = 1
+        #####获取页数####
+        try:
+            max_page = int(self.tab.eles('@data-testid=pagination-item')[-1].text)
+        except:
+            pass
+        #################
+
+        goods_urls = []
+        if max_page > 1:
+            for page in range(1, max_page+1):
+                if page > 1:
+                    self.tab.get(f"{category_url}?page={page}&userId=123456")
+
+                goods_eles = self.tab.eles('xpath=//*[@id="__next"]/div[2]/div/section/div/div[2]/div[5]/div/section[1]/section/div/div')
+                for goods_ele in goods_eles:
+                    goods_url = f"{goods_ele.ele('@tag()=a').attr('href')}"
+                    goods_urls.append(goods_url)
+                messages.sendInfo(f"{page}/{max_page}")
+        else:
+            goods_eles = self.tab.eles('xpath=//*[@id="__next"]/div[2]/div/section/div/div[2]/div[5]/div/section[1]/section/div/div')
+            for goods_ele in goods_eles:
+                goods_url = f"{goods_ele.ele('@tag()=a').attr('href')}"
+                goods_urls.append(goods_url)
+
+        return goods_urls
+
+    def get_goods_info(self, url) -> types.GoodsInfo:
+        def get_image_urls():
+            image_urls = []
+            image_eles = tab.ele('#photoswipe-gallery').eles('@tag()=a')
+
+            for image_ele in image_eles:
+                image_url = image_ele.attr('href')
+                image_urls.append(image_url)
+            return image_urls
+
+        def get_size_eles():
+            try: 
+                eles = tab.ele('.option-picker mt-2 ').eles('@tag()=li')
+            except:
+                pass
+            try: 
+                eles = tab.ele('.option-picker mt-2 long-label ').eles('@tag()=li')
+            except:
+                pass
+            try:
+                eles = tab.ele('.option-picker mt-2 out-of-stock').eles('@tag()=li')
+            except:
+                pass
+            try:
+                eles = tab.ele('.option-picker mt-2 long-label out-of-stock').eles('@tag()=li')
+            except:
+                pass
+            return eles
+
+        tab = self.browser.new_tab(url)
+        tab.set.window.max()
+        spu = formats.url_to_spu(url)
+
+        try:
+            h1_eles = tab.ele('@tag()=h1').eles('@tag()=span')
+            brand = h1_eles[0].text
+            title = h1_eles[1].text
+
+            desc = ""
+            try:
+                desc = formats.clean_html(f"{tab.ele('#accordion-panel-material-care').html}{tab.ele('#accordion-panel-details').html}")
+            except:
+                pass
+
+            price = tab.ele('.:text-pdp-price-primary-xs font-bold').text.split(' ')[1].replace(',', '.')
+            try:
+                old_price = tab.ele('.line-through').text.split(' ')[1].replace(',', '.')
+            except:
+                old_price = price
+
+            main_images = get_image_urls()
+
+            goods_info = types.GoodsInfo(
+                title=title,
+                desc=desc,
+                brand=brand,
+                url=url,
+                spu=spu,
+                price=price,
+                old_price=old_price,
+            )
+
+            m_data = []
+            attr_items = []
+            color_urls = []
+            try:
+                color_eles = tab.ele('.pt-6 xl:pt-8 -mr-6 md:mr-0').eles('@tag()=li')
+                m_data.append('Kleur')
+                for color_ele in color_eles:
+                    color_url = color_ele.ele('@tag()=a').attr('href')
+                    color_urls.append(color_url)
+            except:
+                pass
+            m_data.append('Maat')
+            
+            if len(color_urls) > 0:
+                for color_url in color_urls:
+                    color_images = main_images
+                    if color_url != url:
+                        tab.get(color_url)
+                        color_images = get_image_urls()
+
+                    price = tab.ele('.:text-pdp-price-primary-xs font-bold').text.split(' ')[1].replace(',', '.')
+                    try:
+                        old_price = tab.ele('.line-through').text.split(' ')[1].replace(',', '.')
+                    except:
+                        old_price = price
+
+                    color_name = tab.ele('.text-cp-md font-bold').ele('xpath=text()[3]')
+
+                    size_eles = get_size_eles()
+                    for size_ele in size_eles:
+                        size_name = size_ele.ele('.text-cp-md truncate').text
+                        
+                        attr_items.append({
+                            'url': color_url,
+                            'items': [color_name, size_name],
+                            'price': price,
+                            'old_price': old_price,
+                            'images': color_images
+                        })
+
+            if len(attr_items) == 0:
+                goods_info.attr = 'S'
+                goods_info.attr_items = []
+                goods_info.images = main_images
+                goods_info.p_lists = []
+            else:
+                goods_info.attr = 'M'
+                goods_info.attr_items = m_data
+                for attr_item in attr_items:
+                    goods_info.p_lists.append(types.GoodsInfo.GoodsInfoP(
+                        url=attr_item['url'],
+                        attr_items=attr_item['items'],
+                        price=attr_item['price'],
+                        old_price=attr_item['old_price'],
+                        images=attr_item['images'],
+                    ))
+                    for image_url in attr_item['images']:
+                        if image_url not in main_images:
+                            main_images.append(image_url)
+                goods_info.images = main_images
+                goods_info.p_urls = color_urls
+        except Exception as e:
+            try:
+                tab.close()
+            except:
+                pass
+            raise Exception(e)
+        try:
+            tab.close()
+        except:
+            pass
+        return goods_info

lib/module/ssfshop.py

@@ -0,0 +1,371 @@
+from core import spiders, types
+from utils import formats, messages, files
+import requests
+
+class SpiderModule(spiders.Spiders):
+    project_name = "ssfshop"
+
+    def __init__(self):
+        super().__init__(
+            self.project_name,
+            bitch = 300,
+            worker_num = 24,
+            switch_clash = False,
+            reflush_browser = False
+        )
+
+    def get_category_urls(self) -> list[str]:
+        category_urls = []
+
+        self.tab.get('https://www.ssfshop.com/')
+        one_menu_eles = self.tab.eles('xpath=/html/body/div[5]/header/div[2]/div[2]/div/div[1]/div[1]/ul/li')
+        for one_menu_ele in one_menu_eles:
+            one_link_ele = one_menu_ele.ele('@tag()=a')
+            one_url = one_link_ele.attr('href')
+            one_name = one_link_ele.text.replace('/', '-')
+            if one_name == '라이프':
+                continue
+            category_urls.append(f"{one_url}#{one_name}")
+            messages.sendInfo(one_name)
+
+            two_menu_eles = one_menu_ele.eles('xpath=div/div/div[1]/ul/li')
+            for two_menu_ele in two_menu_eles:
+                two_link_ele = two_menu_ele.ele('@tag()=a')
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-')
+                if two_name == '메인':
+                    continue
+                category_urls.append(f"{two_url}#{one_name}/{two_name}")
+            two_menu_eles = one_menu_ele.eles('xpath=div/div/div[2]/ul/li')
+            for two_menu_ele in two_menu_eles:
+                two_link_ele = two_menu_ele.ele('@tag()=a')
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-')
+                if two_name == '메인':
+                    continue
+                category_urls.append(f"{two_url}#{one_name}/Top Brand/{two_name}")
+            
+                # three_menu_eles = two_menu_ele.eles('xpath=ul/li')
+                # for three_menu_ele in three_menu_eles:
+                #     three_link_ele = three_menu_ele.ele('@tag()=a')
+                #     three_url = three_link_ele.attr('href')
+                #     three_name = three_link_ele.text.replace('/', '-')
+                #     category_urls.append(f"{three_url}#{one_name}/{two_name}/{three_name}")
+
+        return category_urls
+
+    def get_goods_urls(self, category_url: str) -> list[str]:
+        page = 1
+        self.tab.get(f"{category_url}&currentPage={page}&sortColumn=SALE_QTY_SEQ&serviceType=DSP&ctgrySectCd=GNRL_CTGRY&fitPsbYn=N")
+        goods_urls = []
+
+        url_index = {}
+        while True:
+            self.tab.scroll.to_bottom()
+            page_urls = []
+            goods_eles = self.tab.eles('.god-item')
+            for goods_ele in goods_eles:
+                goods_link_ele = goods_ele.ele('xpath=a')
+                if goods_link_ele.attr('href') in url_index:
+                    continue
+                page_urls.append(goods_link_ele.attr('href'))
+                url_index[goods_link_ele.attr('href')] = None
+
+            if len(page_urls) == 0:
+                break
+            if len(goods_urls) > 5000:
+                break
+            goods_urls += page_urls
+            page += 1
+            self.tab.get(f"{category_url}&currentPage={page}&sortColumn=SALE_QTY_SEQ&serviceType=DSP&ctgrySectCd=GNRL_CTGRY&fitPsbYn=N")
+            self.tab.wait(1)
+
+        return goods_urls
+
+    def get_goods_info(self, url: str) -> types.GoodsInfo:
+        def get_image_urls():
+            image_urls = []
+
+            for _ in range(10):
+                image_eles = tab.eles('xpath=//*[@id="godImgThumb"]/div')
+                if len(image_eles) > 0:
+                    break
+                tab.wait(3)
+            for image_ele in image_eles:
+                image_link_ele = image_ele
+                image_urls.append('https://img.ssfshop.com'+image_link_ele.attr('data'))
+
+            return image_urls
+
+        def get_options(godNo, optValCd1, optValCd2 = ''):
+            headers = {
+                'Accept': 'application/json, text/javascript, */*; q=0.01',
+                'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
+                'Connection': 'keep-alive',
+                'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+                'Origin': 'https://www.ssfshop.com',
+                'Referer': url,
+                'Sec-Fetch-Dest': 'empty',
+                'Sec-Fetch-Mode': 'cors',
+                'Sec-Fetch-Site': 'same-origin',
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36 Edg/146.0.0.0',
+                'X-CSRF-TOKEN': 'e8e4bcd2-b976-4ca3-89b0-c85de0d1f3b0',
+                'X-Requested-With': 'XMLHttpRequest',
+                'sec-ch-ua': '"Chromium";v="146", "Not-A.Brand";v="24", "Microsoft Edge";v="146"',
+                'sec-ch-ua-mobile': '?0',
+                'sec-ch-ua-platform': '"Windows"',
+                # 'Cookie': 'PCID=17748347492661999807244; UTID=17748347492661999807244; MAI="eyJsb2dpbiI6Ik4ifQ=="; WMONID=mUUUMLseCyQ; AWSALBAPP-1=_remove_; AWSALBAPP-2=_remove_; AWSALBAPP-3=_remove_; visid_incap_2173964=lpNXES71Q5iAc3f2rzl/jTzUyWkAAAAAQUIPAAAAAABeBQZ8XijRe/SDlNUYlcCm; nlbi_2173964_3216183=TbQ1Ku6HAX5AN79F2g4AdQAAAADFBJVdMHKyRlRjq5BE8+sZ; storedUrl=Y; visid_incap_2794548=/x/uA+w/Rna/+lXitrmX20DUyWkAAAAAQUIPAAAAAACOgO5Lt68U4l70FJ35r3uf; incap_ses_725_2173964=A1WxV+agRSxFFqDq6bcPCtPnyWkAAAAAl1pNcoghbBUv0Idr250rQA==; visid_incap_2898463=WYviBGzFSwWHcJFJUGirBdXnyWkAAAAAQUIPAAAAAAAtfVuBlsqIe97ZjwN6QI2j; nlbi_2898463=wXQSYet0xyoFwAnd4MbCSgAAAAArzXmJlyqxxSh3+i0S9GbO; incap_ses_725_2898463=s8pzSCxlllS0GaDq6bcPCtXnyWkAAAAAu3cfqwOGa86YepyhOT6TvQ==; nth_pcid=3d5ffbba-60dd-a49a-6747-a542beef7538-1774839765504; incap_ses_725_2794548=D/rjK2Wq+zSjGqDq6bcPCtXnyWkAAAAAwfdIptRC0JfZMv8gf0dFHw==; incap_ses_724_2173964=dLR3AfGiVBRg7b2bbSoMCuEsymkAAAAAo4viBM5iG3asWiau6QX32w==; incap_ses_724_2898463=/V2oJwzj6BLV8L2bbSoMCuMsymkAAAAA9Ybn1njwVQ3r7KT6QLCZcg==; incap_ses_724_2794548=3i9aHRkHkTdh872bbSoMCugsymkAAAAAt9AH6HTki4ssrvCcPmSpIA==; AWSALBTG=AIb2slX0AEp+Mv3KJalsspDk7579UU9Jv2/3kjqEGNWjsIrDM+27+/1Ke7bKfPJDQPkvjZ2Sxz50ZoGgs7wax+6xPQZc22NzAPVhfCwSibc44xWGCNEUT9ixCDWhVrmeHJTF4AGiXACsmVs+73qXWgynz4bNZxFvwGcomdcZ09QX; AWSALB=1Lc2nZgyDqlHzKH2Ht9zUCbVzO3nmyjbvR6L8TbjmEzgIJXLWPHd2TKRrA4NweRQ4J3aqEC0O7/FVTTgdHmYYm6M1K3NeLkZbyrFTXyTGk7GFDh5nYLYl/aBRLKe; AWSALBCORS=1Lc2nZgyDqlHzKH2Ht9zUCbVzO3nmyjbvR6L8TbjmEzgIJXLWPHd2TKRrA4NweRQ4J3aqEC0O7/FVTTgdHmYYm6M1K3NeLkZbyrFTXyTGk7GFDh5nYLYl/aBRLKe; AWSALBAPP-0=AAAAAAAAAACeq+TZG7CFWkFz6UEyoFzfgzCso6p2one/fqTkDd1D8aJwmBMDcXt1z/4SFXLjp7cnG/VXtUeFI5VsG2vzUNb7CeolT4ZG4OzG2MYZTDISyFXF0Ftu3Y5EnlA+ClLy5QvoVKs=; nlbi_2173964_2029297=AebNbzFaqQMN0dyi2g4AdQAAAADw44LnFE5aKd0nWF3BiMTo; STID=1774941024138741600844420260331161024; INFLOW_SN=99993; N_INFLOW_SN=Y; PC_JSESSIONID=054FCD4B9E7ABB3B015CF732C022A41B; incap_ses_138_2173964=rIZHCDf5DCYIKM99lkbqAV9zy2kAAAAAhshd7O+yiHEnrcRAybEDaw==; incap_ses_138_2898463=zRn2E3KmY3qUMM99lkbqAWBzy2kAAAAAT0zfogyh0Cs4exDxqH0C5w==; nlbi_2794548=gojpVZcccHOhC/svvoS1vwAAAAB8htUpn549dG0/xu4xckFq; incap_ses_138_2794548=A1yKCZEQdFLyMc99lkbqAWBzy2kAAAAAcNViNS39K56YSoYGpK3p0A==; _TODAYALLLIST="[{\\"todayGodSectCd\\":\\"GOD\\",\\"godNo\\":\\"GM0026011527285\\",\\"regDt\\":\\"1774840170633\\"},{\\"todayGodSectCd\\":\\"GOD\\",\\"godNo\\":\\"GQ3A26021060165\\",\\"regDt\\":\\"1774920131600\\"},{\\"todayGodSectCd\\":\\"GOD\\",\\"godNo\\":\\"GM0025122296270\\",\\"regDt\\":\\"1774920840210\\"},{\\"todayGodSectCd\\":\\"GOD\\",\\"godNo\\":\\"GQJ924040149659\\",\\"regDt\\":\\"1774921134062\\"},{\\"todayGodSectCd\\":\\"GOD\\",\\"godNo\\":\\"GR4H25042395931\\",\\"regDt\\":\\"1774921515277\\"},{\\"todayGodSectCd\\":\\"GOD\\",\\"godNo\\":\\"GQZG26012945089\\",\\"regDt\\":\\"1774921868451\\"},{\\"todayGodSectCd\\":\\"GOD\\",\\"godNo\\":\\"GQZG26012945090\\",\\"regDt\\":\\"1774921870125\\"},{\\"todayGodSectCd\\":\\"GOD\\",\\"godNo\\":\\"GQZG26012945092\\",\\"regDt\\":\\"1774921872189\\"},{\\"todayGodSectCd\\":\\"GOD\\",\\"godNo\\":\\"GRRI26030602949\\",\\"regDt\\":\\"1774941024251\\"},{\\"todayGodSectCd\\":\\"GOD\\",\\"godNo\\":\\"GRRI26030602950\\",\\"regDt\\":1774941046056}]"; godClickInfo=GQY026032636412||GM0026011527285||GQ3A26021060165||GM0025122296270||GR4H25042395931||GR4H25042395931||GQJ924040149659||GR4H25042395931||GR4H25042395931||GQZG26012945092||GQZG26012945089||GQZG26012945090||GQZG26012945092||GQZG26012945089||GQZG26012945090||GQZG26012945092||GRRI26030602949||GRRI26030602950',
+            }
+
+            data = {
+                'optValCd1': optValCd1,
+                'optValCd2': optValCd2,
+                'optValCd3': '',
+                'godNo': godNo,
+            }
+
+            response = requests.post('https://www.ssfshop.com/public/goods/selectGodDetailOpt', headers=headers, data=data, proxies={'http': 'http://127.0.0.1:7890','https': 'http://127.0.0.1:7890'})
+            json_data = response.json()
+
+            options = {}
+            if 'opt' not in json_data:
+                return options
+
+            for option in json_data['opt']:
+                for i in range(1, 6):
+                    key = f"optValNm{i}"
+                    if option[key]:
+                        options[option[key]] = {}
+                        break
+            return options
+
+        tab = self.browser.new_tab(url)
+        tab.set.window.max()
+        spu = formats.url_to_spu(url)
+
+        try:
+            brand = url.split('/')[3]
+            godNo = url.split('/')[4]
+
+            title = tab.ele('#goodDtlTitle').text
+
+            desc = ""
+            try:
+                desc = tab.ele('#godsTabView').html
+            except:
+                pass
+            
+            price = float(tab.ele('xpath=//*[@id="content"]/section/div[2]/div[2]/div[3]/span').ele('.price').text.replace(',', ''))
+            try:
+                old_price = float(tab.ele('xpath=//*[@id="content"]/section/div[2]/div[2]/div[3]/span/span[1]/del').text.replace(',', ''))
+            except:
+                old_price = price
+
+            main_images = get_image_urls()
+
+            goods_info = types.GoodsInfo(
+                title=title,
+                desc=desc,
+                brand=brand,
+                url=url,
+                spu=spu,
+                price=price,
+                old_price=old_price,
+            )
+
+            m_data = []
+            attr_items = []
+            color_urls = []
+            try:
+                tab.ele('.gods-option').ele('text=색상').click()
+                color_eles = tab.eles('xpath=//*[@id="content"]/section/div[2]/div[2]/div[6]/div[1]/div/span/label')
+                for color_ele in color_eles:
+                    color_url = color_ele.attr('onclick')
+                    if color_url:
+                        color_url = color_url.split("'")[1]
+                    else:
+                        color_url = url
+                    if 'https://' not in color_url:
+                        color_url = 'https://www.ssfshop.com'+color_url
+                    color_urls.append(color_url)
+            except:
+                pass
+            
+            if len(color_urls) > 1:
+                m_data = ["색상"]
+
+            try:
+                option_eles = tab.ele('#prdInfoOptionArea').eles('#:optSelectPartmalDiv')
+            except:
+                option_eles = []
+            for option_ele in option_eles:
+                m_data.append(option_ele.ele('@tag()=input').attr('opt-nm'))
+            m_data = m_data[:3]
+
+            option_data = {}
+            if len(option_eles) > 0:
+                try:
+                    option_eles[0].click()
+                except:
+                    goods_info.attr = 'S'
+                    goods_info.attr_items = []
+                    goods_info.images = main_images
+                    goods_info.p_lists = []
+                    try:
+                        tab.close()
+                    except:
+                        pass
+                    return goods_info
+                tab.wait(0.5)
+                option1_eles = option_eles[0].eles('@tag()=li')
+                for option1_ele in option1_eles:
+                    option_data[option1_ele.text] = get_options(godNo, option1_ele.text)
+                    for option2_name, items in option_data[option1_ele.text].items():
+                        option_data[option1_ele.text][option2_name] = get_options(godNo, option1_ele.text, option2_name)
+
+            if len(color_urls) > 1:
+                for color_url in color_urls:
+                    color_images = main_images
+                    if color_url != url:
+                        tab.get(color_url)
+                        title = tab.ele('#goodDtlTitle').text
+                        color_images = get_image_urls()
+
+                        godNo = color_url.split('/')[4]
+                        try:
+                            option_eles = tab.ele('#prdInfoOptionArea', timeout=5).eles('.select lg unapplied')
+                        except:
+                            option_eles = []
+                        option_data = {}
+                        if len(option_eles) > 0:
+                            option1_eles = option_eles[0].eles('xpath=div/ul/li')
+                            for option1_ele in option1_eles:
+                                option_data[option1_ele.text] = get_options(godNo, option1_ele.text)
+                                for option2_name, items in option_data[option1_ele.text].items():
+                                    option_data[option1_ele.text][option2_name] = get_options(godNo, option1_ele.text, option2_name)
+                    
+                    try:
+                        color_name = title.split('-')[1]
+                    except:
+                        color_name = tab.ele('.buy-txts').text
+
+                    price = float(tab.ele('xpath=//*[@id="content"]/section/div[2]/div[2]/div[3]/span').ele('.price').text.replace(',', ''))
+                    try:
+                        old_price = float(tab.ele('xpath=//*[@id="content"]/section/div[2]/div[2]/div[3]/span/span[1]/del').text.replace(',', ''))
+                    except:
+                        old_price = price
+                    
+                    if len(option_data) > 0:
+                        for option1_name, items1 in option_data.items():
+                            if len(items1) > 0:
+                                for option2_name, items2 in items1.items():
+                                    attr_items.append({
+                                        'url': color_url,
+                                        'items': [color_name, option1_name, option2_name],
+                                        'price': price,
+                                        'old_price': old_price,
+                                        'images': color_images
+                                    })
+                            else:
+                                attr_items.append({
+                                    'url': color_url,
+                                    'items': [color_name, option1_name],
+                                    'price': price,
+                                    'old_price': old_price,
+                                    'images': color_images
+                                })
+                    else:
+                        attr_items.append({
+                            'url': color_url,
+                            'items': [color_name],
+                            'price': price,
+                            'old_price': old_price,
+                            'images': color_images
+                        })
+            else:
+                for option1_name, items1 in option_data.items():
+                    if len(items1) > 0:
+                        for option2_name, items2 in items1.items():
+                            if len(items2) > 0:
+                                for option3_name, items3 in items2.items():
+                                    attr_items.append({
+                                        'url': url,
+                                        'items': [option1_name, option2_name, option3_name],
+                                        'price': price,
+                                        'old_price': old_price,
+                                        'images': []
+                                    })
+                            else:
+                                attr_items.append({
+                                    'url': url,
+                                    'items': [option1_name, option2_name],
+                                    'price': price,
+                                    'old_price': old_price,
+                                    'images': []
+                                })
+                    else:
+                        attr_items.append({
+                            'url': url,
+                            'items': [option1_name],
+                            'price': price,
+                            'old_price': old_price,
+                            'images': []
+                        })
+
+            if len(attr_items) == 0:
+                try:
+                    tab.ele('.gods-option').ele('text=사이즈').click()
+                    size_eles = tab.eles('xpath=/html/body/div[5]/main/section/div[2]/div[2]/div[6]/div[1]/div/ul/li')
+                    goods_info.attr = 'M'
+                    goods_info.attr_items = ['사이즈']
+                    goods_info.images = main_images
+                    for size_ele in size_eles:
+                        goods_info.p_lists.append(types.GoodsInfo.GoodsInfoP(
+                            attr_items=[size_ele.text],
+                            price=price,
+                            old_price=old_price,
+                            images=[],
+                        ))
+                except:
+                    goods_info.attr = 'S'
+                    goods_info.attr_items = []
+                    goods_info.images = main_images
+                    goods_info.p_lists = []
+            else:
+                goods_info.attr = 'M'
+                goods_info.attr_items = m_data
+                for attr_item in attr_items:
+                    if len(attr_item['items']) != len(m_data):
+                        attr_item['items'] += m_data[len(attr_item['items']):]
+                    goods_info.p_lists.append(types.GoodsInfo.GoodsInfoP(
+                        url=attr_item['url'],
+                        attr_items=attr_item['items'],
+                        price=attr_item['price'],
+                        old_price=attr_item['old_price'],
+                        images=attr_item['images'],
+                    ))
+                    for image_url in attr_item['images']:
+                        if image_url not in main_images:
+                            main_images.append(image_url)
+                goods_info.images = main_images
+                goods_info.p_urls = color_urls
+        except Exception as e:
+            try:
+                tab.close()
+            except:
+                pass
+            raise Exception(e)
+        try:
+            tab.close()
+        except:
+            pass
+        return goods_info
+
+    def get_home(self):
+        self.tab.get('https://www.ssfshop.com/main')
+        li_eles = self.tab.ele('xpath=/html/body/div[5]/main/div[2]/section[2]/div/div[1]').eles('@tag()=li')
+        categorys = []
+        for li_ele in li_eles:
+            a_ele = li_ele.ele('@tag()=a')
+            categorys.append(f"{a_ele.attr('href')}#{a_ele.text}")
+        files.save_list(f"{self.__data_path__}/categorys(home).txt", categorys)

lib/module/taketoys.py

@@ -0,0 +1,131 @@
+from core import spiders, types
+from utils import formats, messages
+
+class SpiderModule(spiders.Spiders):
+    project_name = "taketoys"
+
+    def __init__(self):
+        super().__init__(
+            self.project_name,
+            bitch = 30,
+            worker_num = 5,
+            switch_clash = False,
+            reflush_browser = False
+        )
+        self.tab.get('https://taketoys.sg/')
+        # input('wait:')
+
+    def get_category_urls(self) -> list[str]:
+        category_urls = []
+        
+        one_menu_eles = self.tab.eles('xpath=/html/body/header/div[2]/div/nav/ul/li')
+        for one_menu_ele in one_menu_eles[1:-1]:
+            one_link_ele = one_menu_ele.ele('xpath=a')
+            one_url = one_link_ele.attr('href')
+            one_name = one_link_ele.text.replace('/', '-')
+            category_urls.append(f"{one_url}#{one_name}")
+            messages.sendInfo(one_name)
+
+            two_menu_eles = one_menu_ele.eles('xpath=ul/li', timeout=1)
+            for two_index, two_menu_ele in enumerate(two_menu_eles):
+                two_link_ele = two_menu_ele.ele('xpath=a')
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-').replace(',', '，').replace('#', ' ')
+                category_urls.append(f"{two_url}#{one_name}/{two_name}")
+            
+                # try:
+                #     three_menu_eles = self.tab.ele(f'xpath=//*[@id="__next"]/div[1]/header/div/div[2]/nav/div[{two_index+1}]/div/div[1]').eles('@tag()=li')
+                # except:
+                #     continue
+                # for three_menu_ele in three_menu_eles:
+                #     three_link_ele = three_menu_ele.ele('@tag()=a')
+                #     three_url = three_link_ele.attr('href')
+                #     three_name = three_link_ele.text.replace('/', '-')
+                #     category_urls.append(f"{three_url}#{one_name}/{two_name}/{three_name}")
+
+        return category_urls
+
+    def get_goods_urls(self, category_url: str) -> list[str]:
+        self.tab.get(f"{category_url}?page=1")
+        goods_urls = []
+        
+        #####获取页数####
+
+        #################
+
+        goods_urls = []
+        while True:
+            self.tab.scroll.to_bottom()
+            try:
+                self.tab.ele('text=Show more', timeout=5).click()
+                self.tab.wait(1)
+            except:
+                break
+
+        goods_eles = self.tab.eles('.col-xs-6 col-sm-4 col-lg-3 item-wrapper')
+        for goods_ele in goods_eles:
+            goods_url = f"{goods_ele.ele('@tag()=a').attr('href')}"
+            goods_urls.append(goods_url)
+        messages.sendInfo(f"{len(goods_urls)} 个")
+
+        return goods_urls
+
+    def get_goods_info(self, url) -> types.GoodsInfo:
+        def get_image_urls():
+            image_urls = []
+            image_eles = tab.eles('xpath=/html/body/main/div[2]/div[2]/div[2]/div[2]/div/div/div[3]/div[2]/div/div')
+
+            for image_ele in image_eles:
+                image_url = image_ele.ele('xpath=img').attr('src')
+                image_urls.append(image_url)
+            return image_urls
+
+        tab = self.browser.new_tab(url)
+        tab.set.window.max()
+        spu = formats.url_to_spu(url)
+
+        try:
+            h1_ele = tab.ele('@tag()=h1')
+            brand = ''
+            try:
+                brand = h1_ele.ele('@tag()=strong').text
+            except:
+                pass
+            title = h1_ele.ele('@tag()=span').text
+
+            desc = ""
+            try:
+                desc = formats.clean_html(tab.ele('#product-info-tab').html)
+            except:
+                pass
+
+            price = tab.ele('.price').attr('title').replace('SGD', '').replace(',', '')
+            old_price = price
+
+            main_images = get_image_urls()
+
+            goods_info = types.GoodsInfo(
+                title=title,
+                desc=desc,
+                brand=brand,
+                url=url,
+                spu=spu,
+                price=price,
+                old_price=old_price,
+            )
+
+            goods_info.attr = 'S'
+            goods_info.attr_items = []
+            goods_info.images = main_images
+            goods_info.p_lists = []
+        except Exception as e:
+            try:
+                tab.close()
+            except:
+                pass
+            raise Exception(e)
+        try:
+            tab.close()
+        except:
+            pass
+        return goods_info

lib/module/tfashion.py

@@ -0,0 +1,140 @@
+from core import spiders, types
+from utils import formats, messages
+
+class SpiderModule(spiders.Spiders):
+    project_name = "t-fashion"
+
+    def __init__(self):
+        super().__init__(
+            self.project_name,
+            bitch = 300,
+            worker_num = 24,
+            switch_clash = False,
+            reflush_browser = False
+        )
+
+    def get_category_urls(self) -> list[str]:
+        category_urls = []
+
+        self.tab.get('https://www.t-fashion.jp/')
+        one_menu_eles = self.tab.ele('.m-aside-menu-body').eles('.js-collest-li')
+        for one_menu_ele in one_menu_eles:
+            one_link_ele = one_menu_ele.ele('@tag()=a')
+            # one_url = one_link_ele.attr('href')
+            one_name = one_link_ele.text.replace('/', '-')
+            # category_urls.append(f"{one_url}#{one_name}")
+            messages.sendInfo(one_name)
+
+            two_menu_eles = one_menu_ele.eles('xpath=div/ul/li')
+            for two_menu_ele in two_menu_eles[1:]:
+                two_link_ele = two_menu_ele.ele('@tag()=a')
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-')
+                category_urls.append(f"{two_url}#{one_name}/{two_name}")
+            
+                # three_menu_eles = two_menu_ele.eles('xpath=ul/li')
+                # for three_menu_ele in three_menu_eles:
+                #     three_link_ele = three_menu_ele.ele('@tag()=a')
+                #     three_url = three_link_ele.attr('href')
+                #     three_name = three_link_ele.text.replace('/', '-')
+                #     category_urls.append(f"{three_url}#{one_name}/{two_name}/{three_name}")
+
+        return category_urls
+
+    def get_goods_urls(self, category_url: str) -> list[str]:
+        page = 1
+        self.tab.get(f"{category_url}?page={page}")
+        goods_urls = []
+        
+        while True:
+            try:
+                goods_eles = self.tab.eles('xpath=/html/body/div[1]/div[3]/div/section[1]/div/div[1]/div[1]/div[3]/ol/li')
+                for goods_ele in goods_eles:
+                    goods_link_ele = goods_ele.ele('xpath=a')
+                    goods_urls.append(goods_link_ele.attr('href'))
+                if len(goods_eles) == 0:
+                    break
+            except:
+                break
+            page += 1
+            self.tab.get(f"{category_url}?page={page}")
+
+        return goods_urls
+
+    def get_goods_info(self, url) -> types.GoodsInfo:
+        def get_image_urls():
+            image_urls = []
+
+            image_eles = tab.eles('xpath=//*[@id="item-gallery-parent"]/li')
+            for image_ele in image_eles:
+                image_link_ele = image_ele.ele('xpath=div/img')
+                image_urls.append(image_link_ele.attr('src'))
+
+            return image_urls
+
+        tab = self.browser.new_tab(url)
+        tab.set.window.max()
+        spu = formats.url_to_spu(url)
+
+        try:
+            brand = ''
+            try:
+                brand = tab.ele('xpath=//*[@id="current-tgoods-section"]/div/div[2]/div/div[1]/a[2]', timeout=10).text
+            except:
+                pass
+
+            title = tab.ele('@tag()=h1').text
+
+            desc = ""
+            try:
+                desc = formats.clean_html(tab.ele('xpath=//*[@id="slide-down-contents-parent"]'))
+            except:
+                pass
+
+            try:
+                price = float(tab.ele('.is-fz28-36f is-fw-b ').text.replace(',', '').replace('¥', '').replace('（税込）', ''))
+            except:
+                price = float(tab.ele('.is-fz28-36f is-fw-b is-color-notice').text.replace(',', '').replace('¥', '').replace('（税込）', ''))
+            old_price = price
+
+            main_images = get_image_urls()
+
+            goods_info = types.GoodsInfo(
+                title=title,
+                desc=desc,
+                brand=brand,
+                url=url,
+                spu=spu,
+                price=price,
+                old_price=old_price,
+            )
+
+            m_data = []
+            attr_items = []
+            goods_info.attr = 'M'
+            goods_info.attr_items = ['Color', 'Size']
+            goods_info.images = main_images
+            color_eles = tab.eles('xpath=//*[@id="sku-list-box"]/div')
+            for color_ele in color_eles:
+                color_image = color_ele.ele('xpath=div/a').attr('href')
+                color_name = color_ele.ele('xpath=div/a/span').text
+                size_eles = color_ele.eles('xpath=ol/li')
+                for size_ele in size_eles:
+                    size_name = size_ele.ele('xpath=div[1]/text()')
+                    goods_info.p_lists.append(types.GoodsInfo.GoodsInfoP(
+                        attr_items=[color_name, size_name],
+                        price=price,
+                        old_price=old_price,
+                        images=[color_image]
+                    ))
+        except Exception as e:
+            try:
+                tab.close()
+            except:
+                pass
+            raise Exception(e)
+        try:
+            tab.close()
+        except:
+            pass
+        return goods_info

lib/shopyy.py

@@ -0,0 +1,371 @@
+import requests
+import lib
+from core import excels, browsers
+from utils import files, formats
+
+class Shopyy:
+    def __init__(self, save_folder):
+        self.save_folder = save_folder
+
+        self.__album_template_path__ = 'sources/专辑模板.xlsx'
+        self.__navigation_template_path__ = 'sources/导航模板.xlsx'
+
+    # 导航
+    def generate_navigation(self, category_path):
+        index = {}
+        category_urls = files.load_lines(category_path)
+
+        WorkBook = excels.WorkBook(
+            template=self.__navigation_template_path__,
+            save_path=f"{self.save_folder}/导航表格.xlsx"
+        )
+        for category_url in category_urls:
+            category = category_url.split('#')[-1]
+            if category in index:
+                continue
+            category_lists = category.split('/')
+            category_lists += ['', '']
+            row_data = [
+                '顶部导航菜单',
+                category_lists[0],
+                category_lists[1],
+                category_lists[2],
+                'collection',
+                category
+            ]
+            WorkBook.add_row_of_list(row_data)
+            index[category] = None
+        WorkBook.save()
+
+        return self
+
+    # 专辑
+    def generate_album(self, goods_url_path):
+        def open_workbook(bitch_index) -> excels.WorkBook:
+            WorkBook = excels.WorkBook(
+                template=self.__album_template_path__,
+                save_path=f"{self.save_folder}/专辑表格({bitch_index}).xlsx"
+            )
+            return WorkBook
+
+        album_data = {}
+        count = 0
+        bitch_index = 1
+        WorkBook = open_workbook(bitch_index)
+
+        goods_urls = files.load_lines(goods_url_path)
+        for goods_url in goods_urls:
+            if goods_url == '':
+                continue
+            goods_url_split = goods_url.split('#')
+            goods_categorys = goods_url_split[-1].split('/')
+            goods_url = '#'.join(goods_url_split[:-1])
+            goods_url = goods_url.split('?')[0]
+
+            for category_index, goods_category in enumerate(goods_categorys):
+                goods_category = '/'.join(goods_categorys[:category_index + 1])
+
+                if goods_category in album_data:
+                    mode = ''
+                    sort = ''
+                else:
+                    mode = 'add'
+                    sort = 'collections_position'
+                    album_data[goods_category] = []
+
+                row_data = [
+                    '',
+                    goods_category,
+                    mode,
+                    sort,
+                    '',
+                    formats.url_to_spu(goods_url)
+                ]
+                album_data[goods_category].append(row_data)
+                count += 1
+
+        save_bitch = count/3+1
+        for goods_category, row_datas in album_data.items():
+            for row_data in row_datas:
+                WorkBook.add_row_of_list(row_data)
+
+                if WorkBook.start_row > save_bitch and bitch_index <= 2:
+                    WorkBook.save()
+                    WorkBook.close()
+
+                    bitch_index += 1
+                    WorkBook = open_workbook(bitch_index)
+        WorkBook.save()
+        WorkBook.close()
+
+        return self
+
+class ShopyyVerify:
+    def __init__(self, url):
+        self.url = url
+        browser = browsers.getBrowsers()
+        self.tab = browser.get_tab(0)
+        self.login()
+
+    def login(self):
+        self.tab.get(f"{self.url}/admin/login")
+        print('等待登录')
+        while True:
+            token = self.tab.local_storage('CARDADMIN_TOKEN')
+            if token:
+                print('登录成功')
+                self.token = token.replace('"', '')
+                break
+            self.tab.wait(1)
+
+    def get_zero_collections(self, delete: bool = False):
+        def get_collections(page):
+            headers = {
+                'accept': 'application/json, text/plain, */*',
+                'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
+                'priority': 'u=1, i',
+                # 'referer': 'https://cisalfasport.zenshop.cn/admin/collections?page=1&pagesize=50',
+                'sec-ch-ua': '"Not(A:Brand";v="8", "Chromium";v="144", "Microsoft Edge";v="144"',
+                'sec-ch-ua-mobile': '?0',
+                'sec-ch-ua-platform': '"Windows"',
+                'sec-fetch-dest': 'empty',
+                'sec-fetch-mode': 'cors',
+                'sec-fetch-site': 'same-origin',
+                'token': self.token,
+                'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/144.0.0.0 Safari/537.36 Edg/144.0.0.0',
+                # 'cookie': '__stripe_mid=89b6ec3f-bbac-483d-b8ab-9938859a0b340b72d8; _aiihbe_vid=18FC7E3E-1CA7-FDC2-C52D-37A4BB0E1DF0; _aiihbe_cvid=75CFD325-E408-2C25-C126-07A349ED46C5; utm_source=direct; utm_medium=default; order_utm_history=%5B%7B%22utm_source%22%3A%22direct%22%2C%22utm_medium%22%3A%22default%22%2C%22utm_term%22%3A%22%22%2C%22utm_campaign%22%3A%22%22%2C%22utm_content%22%3A%22%22%2C%22source_device%22%3A%22computer%22%2C%22create_time%22%3A1770185710%2C%22expire_time%22%3A1772777710%7D%5D; landing_page=aHR0cHM6Ly9jaXNhbGZhc3BvcnQuemVuc2hvcC5jbi9wcm9kdWN0cy90b3VyLWRlLWZyYW5jZS1qcj9wcmV2aWV3PTE%3D; first_http_referer=https%3A%2F%2Fcisalfasport.zenshop.cn%2Fadmin%2Fproducts; first_visit_time=1770185710; PHPSESSID=6329e9a44018771ce40064bc50fbe189; _aiihbe_vs=36B35E5C-874E-4D6C-8945-F5CF6F323F99; theme_id=411278; _AIIHBE_ua=Mozilla%252F5.0%2520(Windows%2520NT%252010.0%253B%2520Win64%253B%2520x64)%2520AppleWebKit%252F537.36%2520(KHTML%252C%2520like%2520Gecko)%2520Chrome%252F144.0.0.0%2520Safari%252F537.36%2520Edg%252F144.0.0.0; _AIIHBE_pu=https%253A%252F%252Fcisalfasport.zenshop.cn%252Fadmin%252Ftheme; _AIIHBE_tz=Etc%2FGMT-8; _AIIHBE_ss=1920X1080; _AIIHBE_lang=zh-CN; _AIIHBE_vs=1874X930; _AIIHBE_dt=2026-02-06%2016%3A30%3A44; acw_tc=a3b54ee217704477374193466e23fb58e387e54f5b84504527a4beab6b; cdn_sec_tc=a3b54ee217704477374193466e23fb58e387e54f5b84504527a4beab6b; __stripe_sid=49bcd8c1-4ae4-46ba-8e95-a29205606cb2980c18; visit_token=4be69765c90de228978e9738878367fbkj083fsy; _aiihbe_ka=A298A3E1-379E-4DA0-2B28-A5961B741FA9; is_theme_edit=1',
+            }
+
+            params = {
+                'page': str(page),
+                'pagesize': '600',
+            }
+
+            response = requests.get(f'{self.url}/api/collections', params=params, headers=headers)
+            response_data = response.json()
+            if response_data['code'] != 0:
+                raise Exception(response_data['msg'])
+            return response_data['data']
+        
+        def delete_collections(ids: list):
+            headers = {
+                'accept': 'application/json, text/plain, */*',
+                'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
+                'cache-control': 'no-cache',
+                'content-type': 'application/json',
+                'origin': 'https://peekcloppenburgat.zenshop.cn',
+                'pragma': 'no-cache',
+                'priority': 'u=1, i',
+                # 'referer': 'https://peekcloppenburgat.zenshop.cn/admin/collections?page=1&pagesize=600',
+                'sec-ch-ua': '"Not:A-Brand";v="99", "Microsoft Edge";v="145", "Chromium";v="145"',
+                'sec-ch-ua-mobile': '?0',
+                'sec-ch-ua-platform': '"Windows"',
+                'sec-fetch-dest': 'empty',
+                'sec-fetch-mode': 'cors',
+                'sec-fetch-site': 'same-origin',
+                'token': self.token,
+                'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/145.0.0.0 Safari/537.36 Edg/145.0.0.0',
+                # 'cookie': '__stripe_mid=49d8f368-8d82-4b14-9c42-63e0d33542ef6372ca; _bzcece_vid=E823CDA9-7EDE-3617-71BB-80F879AD878E; _bzcece_cvid=36F627EC-095F-9323-5047-43325149C808; utm_source=direct; utm_medium=default; order_utm_history=%5B%7B%22utm_source%22%3A%22direct%22%2C%22utm_medium%22%3A%22default%22%2C%22utm_term%22%3A%22%22%2C%22utm_campaign%22%3A%22%22%2C%22utm_content%22%3A%22%22%2C%22source_device%22%3A%22computer%22%2C%22create_time%22%3A1773370701%2C%22expire_time%22%3A1775962701%7D%5D; landing_page=aHR0cHM6Ly9wZWVrY2xvcHBlbmJ1cmdhdC56ZW5zaG9wLmNuL3Byb2R1Y3RzL3Zlcm8tbW9kYS13aWRlLWxlZy1qZWFucy1hdXMtYmF1bXdvbGwtbWl4LW1vZGVsbC10ZXNzYS1pbi1oZWxsZ3JhdT9wcmV2aWV3PTE%3D; first_http_referer=https%3A%2F%2Fpeekcloppenburgat.zenshop.cn%2Fadmin%2Fproducts; first_visit_time=1773370701; PHPSESSID=fba65fe62a66071f174801bb432b942c; theme_id=418468; __stripe_sid=323c1341-4108-4c33-b331-ea6b782f9a2349679f; visit_token=f1d5170d234867f2ca490821f454239bmwnlrqr7; _bzcece_vs=5F572333-803E-D038-11EC-6CFCBA6F32D3; _bzcece_ka=B2503B21-4B44-A5A0-F261-71EC86D52A6E; is_theme_edit=1; acw_tc=9b66b49a17734819180038754ede11478ee763b95bb1c9acff317f521f; cdn_sec_tc=9b66b49a17734819180038754ede11478ee763b95bb1c9acff317f521f',
+            }
+
+            json_data = {
+                'ids': ids,
+            }
+
+            response = requests.post(
+                f'{self.url}/api/collections/batchdelete',
+                headers=headers,
+                json=json_data,
+            )
+            print(response.json())
+
+        print('开始检查专辑数量')
+        collection_items = []
+        data = get_collections(1)
+        page_total = data['paginate']['pageTotal']
+        collection_items += data['collections']
+        print(f"1/{page_total}")
+        
+        if page_total > 1:
+            for page in range(2, page_total+1):
+                data = get_collections(page)
+                collection_items += data['collections']
+                print(f"{page}/{page_total}")
+        
+        lost_collection = []
+        zero_ids = []
+        for collection_item in collection_items:
+            if collection_item['collection_products_count'] == 0:
+                lost_collection.append(collection_item['title'])
+                print(f"{collection_item['title']} 数量为0")
+                zero_ids.append(collection_item['id'])
+        if delete:
+            delete_collections(zero_ids)
+        
+        if len(lost_collection) > 0:
+            with open('商品数量为0专辑.txt', 'w', encoding='utf-8') as f:
+                f.write('\n'.join(lost_collection))
+        return self
+
+    def get_error_images(self, delete: bool = False):
+        def get_errors(page):
+            headers = {
+                'accept': 'application/json, text/plain, */*',
+                'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
+                'cache-control': 'no-cache',
+                'dnt': '1',
+                'pragma': 'no-cache',
+                'priority': 'u=1, i',
+                # 'referer': 'https://vanuffelenmode.zenshop.cn/admin/resources',
+                'sec-ch-ua': '"Not:A-Brand";v="99", "Microsoft Edge";v="145", "Chromium";v="145"',
+                'sec-ch-ua-mobile': '?0',
+                'sec-ch-ua-platform': '"Windows"',
+                'sec-fetch-dest': 'empty',
+                'sec-fetch-mode': 'cors',
+                'sec-fetch-site': 'same-origin',
+                'token': self.token,
+                'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/145.0.0.0 Safari/537.36 Edg/145.0.0.0',
+                # 'cookie': 'acw_tc=a3b54dab17734824723112557e921e5eb8672de1b4bf2e0bfb7de57fe1; cdn_sec_tc=a3b54dab17734824723112557e921e5eb8672de1b4bf2e0bfb7de57fe1; __stripe_mid=cc09d025-360b-466e-bef4-ba92d045fdc94448e2; __stripe_sid=511d0972-d39d-4aa1-a031-5258db651ad1d4124e; visit_token=9b8172c220d5be292045835470d38951px0lh404',
+            }
+
+            params = {
+                'file_name': '',
+                'page_type': 'fail',
+                'page': str(page),
+                'pagesize': '600',
+            }
+
+            response = requests.get(f'{self.url}/api/resources', params=params, headers=headers)
+            response_data = response.json()
+            if response_data['code'] != 0:
+                raise Exception(response_data['msg'])
+            return response_data['data']
+        
+        def post_retry(ids: list):
+            headers = {
+                'accept': 'application/json, text/plain, */*',
+                'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
+                'content-type': 'application/json',
+                # 'origin': 'https://ssfshop.zenshop.cn',
+                'priority': 'u=1, i',
+                # 'referer': 'https://ssfshop.zenshop.cn/admin/resources',
+                'sec-ch-ua': '"Chromium";v="146", "Not-A.Brand";v="24", "Microsoft Edge";v="146"',
+                'sec-ch-ua-mobile': '?0',
+                'sec-ch-ua-platform': '"Windows"',
+                'sec-fetch-dest': 'empty',
+                'sec-fetch-mode': 'cors',
+                'sec-fetch-site': 'same-origin',
+                'token': self.token,
+                'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36 Edg/146.0.0.0',
+                # 'cookie': '__stripe_mid=a8059a05-4d7e-476d-b376-9e54f222efbe3c23c7; _bzgigi_vid=85F94DA2-7BD9-525E-E4A5-8D686E51B2C6; _bzgigi_cvid=EEFE28A2-FDC4-DC54-E76A-2BC1B2929243; utm_source=direct; utm_medium=default; order_utm_history=%5B%7B%22utm_source%22%3A%22direct%22%2C%22utm_medium%22%3A%22default%22%2C%22utm_term%22%3A%22%22%2C%22utm_campaign%22%3A%22%22%2C%22utm_content%22%3A%22%22%2C%22source_device%22%3A%22computer%22%2C%22create_time%22%3A1775195861%2C%22expire_time%22%3A1777787861%7D%5D; landing_page=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%2FcHJldmlldz0x; first_http_referer=https%3A%2F%2Fssfshop.zenshop.cn%2Fadmin%2Fproducts; first_visit_time=1775195861; visit_token=41be25876fa245bb99018d68f7338d89y49l7utp; _bzgigi_vs=E5BE5924-EEF9-E277-6AFC-5F70BB548D0F; PHPSESSID=b08ff5f29b9469e1e92740efef87c09e; _BZGIGI_ua=Mozilla%252F5.0%2520(Windows%2520NT%252010.0%253B%2520Win64%253B%2520x64)%2520AppleWebKit%252F537.36%2520(KHTML%252C%2520like%2520Gecko)%2520Chrome%252F146.0.0.0%2520Safari%252F537.36%2520Edg%252F146.0.0.0; _BZGIGI_pu=https%253A%252F%252Fssfshop.zenshop.cn%252Fadmin%252Fproducts; _BZGIGI_tz=Etc%2FGMT-8; _BZGIGI_ss=2560X1440; _BZGIGI_lang=zh-CN; _BZGIGI_vs=2514X1316; _BZGIGI_dt=2026-04-07%2014%3A48%3A20; theme_id=429104; is_theme_edit=1; acw_tc=9b66b4a617756120379694001e5c7efed3faa08e9cf1c621bbfeb27c77; cdn_sec_tc=9b66b4a617756120379694001e5c7efed3faa08e9cf1c621bbfeb27c77; __stripe_sid=a0f6f277-4a95-4d43-bd6f-c38f108e17f52fc752',
+            }
+            response = requests.post(f'{self.url}/api/resources/retry', headers=headers, json={'ids':ids})
+            print(response.json())
+        
+        def delete_images(ids: list):
+            headers = {
+                'accept': 'application/json, text/plain, */*',
+                'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
+                'content-type': 'application/json',
+                # 'origin': 'https://ssfshop.zenshop.cn',
+                'priority': 'u=1, i',
+                # 'referer': 'https://ssfshop.zenshop.cn/admin/resources',
+                'sec-ch-ua': '"Chromium";v="146", "Not-A.Brand";v="24", "Microsoft Edge";v="146"',
+                'sec-ch-ua-mobile': '?0',
+                'sec-ch-ua-platform': '"Windows"',
+                'sec-fetch-dest': 'empty',
+                'sec-fetch-mode': 'cors',
+                'sec-fetch-site': 'same-origin',
+                'token': self.token,
+                'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36 Edg/146.0.0.0',
+                # 'cookie': '__stripe_mid=a8059a05-4d7e-476d-b376-9e54f222efbe3c23c7; _bzgigi_vid=85F94DA2-7BD9-525E-E4A5-8D686E51B2C6; _bzgigi_cvid=EEFE28A2-FDC4-DC54-E76A-2BC1B2929243; utm_source=direct; utm_medium=default; order_utm_history=%5B%7B%22utm_source%22%3A%22direct%22%2C%22utm_medium%22%3A%22default%22%2C%22utm_term%22%3A%22%22%2C%22utm_campaign%22%3A%22%22%2C%22utm_content%22%3A%22%22%2C%22source_device%22%3A%22computer%22%2C%22create_time%22%3A1775195861%2C%22expire_time%22%3A1777787861%7D%5D; landing_page=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%2FcHJldmlldz0x; first_http_referer=https%3A%2F%2Fssfshop.zenshop.cn%2Fadmin%2Fproducts; first_visit_time=1775195861; visit_token=41be25876fa245bb99018d68f7338d89y49l7utp; _bzgigi_vs=E5BE5924-EEF9-E277-6AFC-5F70BB548D0F; PHPSESSID=b08ff5f29b9469e1e92740efef87c09e; _BZGIGI_ua=Mozilla%252F5.0%2520(Windows%2520NT%252010.0%253B%2520Win64%253B%2520x64)%2520AppleWebKit%252F537.36%2520(KHTML%252C%2520like%2520Gecko)%2520Chrome%252F146.0.0.0%2520Safari%252F537.36%2520Edg%252F146.0.0.0; _BZGIGI_pu=https%253A%252F%252Fssfshop.zenshop.cn%252Fadmin%252Fproducts; _BZGIGI_tz=Etc%2FGMT-8; _BZGIGI_ss=2560X1440; _BZGIGI_lang=zh-CN; _BZGIGI_vs=2514X1316; _BZGIGI_dt=2026-04-07%2014%3A48%3A20; theme_id=429104; is_theme_edit=1; acw_tc=9b66b4a617756120379694001e5c7efed3faa08e9cf1c621bbfeb27c77; cdn_sec_tc=9b66b4a617756120379694001e5c7efed3faa08e9cf1c621bbfeb27c77; __stripe_sid=60ef73cf-e5ed-483a-a342-9e581a0387d64df267',
+            }
+            json_data = {
+                'ids': ids,
+                'delete_product': 0
+            }
+            response = requests.delete('https://ssfshop.zenshop.cn/api/resources/batchdelete', headers=headers, json=json_data)
+            print(response.json())
+
+        print('开始检查失败图片')
+        image_items = []
+        data = get_errors(1)
+        page_total = data['paginate']['pageTotal']
+        image_items += data['list']
+        print(f"1/{page_total}")
+        
+        if page_total > 1:
+            for page in range(2, page_total+1):
+                ids = []
+                data = get_errors(1)
+                for item in data['list']:
+                    ids.append(item['id'])
+                if delete:
+                    delete_images(ids)
+                else:
+                    post_retry(ids)
+                page_total = data['paginate']['pageTotal']
+                print(f"{page}/{page_total}")
+        
+        # lost_image_urls = []
+        # for image_item in image_items:
+        #     lost_image_urls.append(image_item['remote_url'])
+        
+        # if len(lost_image_urls) > 0:
+        #     files.save_list('采集失败图片链接.txt', lost_image_urls)
+        # print(f"共有: {len(lost_image_urls)} 条失败链接")
+    
+    def get_all_images(self):
+        def get_images(page):
+            headers = {
+                'accept': 'application/json, text/plain, */*',
+                'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
+                'cache-control': 'no-cache',
+                'dnt': '1',
+                'pragma': 'no-cache',
+                'priority': 'u=1, i',
+                # 'referer': 'https://vanuffelenmode.zenshop.cn/admin/resources',
+                'sec-ch-ua': '"Not:A-Brand";v="99", "Microsoft Edge";v="145", "Chromium";v="145"',
+                'sec-ch-ua-mobile': '?0',
+                'sec-ch-ua-platform': '"Windows"',
+                'sec-fetch-dest': 'empty',
+                'sec-fetch-mode': 'cors',
+                'sec-fetch-site': 'same-origin',
+                'token': self.token,
+                'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/145.0.0.0 Safari/537.36 Edg/145.0.0.0',
+                # 'cookie': 'acw_tc=a3b54dab17734824723112557e921e5eb8672de1b4bf2e0bfb7de57fe1; cdn_sec_tc=a3b54dab17734824723112557e921e5eb8672de1b4bf2e0bfb7de57fe1; __stripe_mid=cc09d025-360b-466e-bef4-ba92d045fdc94448e2; __stripe_sid=511d0972-d39d-4aa1-a031-5258db651ad1d4124e; visit_token=9b8172c220d5be292045835470d38951px0lh404',
+            }
+
+            params = {
+                'file_name': '',
+                'page_type': 'all',
+                'page': str(page),
+                'pagesize': '600',
+            }
+
+            response = requests.get(f'{self.url}/api/resources', params=params, headers=headers)
+            response_data = response.json()
+            if response_data['code'] != 0:
+                raise Exception(response_data['msg'])
+            return response_data['data']
+        
+        print('开始获取图片url')
+        image_items = []
+        data = get_images(1)
+        page_total = data['paginate']['pageTotal']
+        image_items += data['list']
+        print(f"1/{page_total}")
+        
+        if page_total > 1:
+            for page in range(2, page_total+1):
+                data = get_images(page)
+                image_items += data['list']
+                print(f"{page}/{page_total}")
+        
+        image_urls = []
+        for image_item in image_items:
+            image_urls.append(image_item['remote_url'])
+        
+        if len(image_urls) > 0:
+            files.save_list('图片链接.txt', image_urls)
+        print(f"共有: {len(image_urls)} 张图片")