优化项目结构,添加注释

core/gether.py

@@ -3,24 +3,19 @@ import traceback
 import concurrent.futures
 from utils import files, messages, clash, formats
 import lib
-from core import Config, types
+from core import Config, types, goods
-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):
+    # if os.path.exists(category_urls_path):
-        return
+    #     return
-    
     category_urls = lib.Server.get_category_urls()
-    for urls in category_urls:
+    files.save_list(category_urls_path, category_urls)
-        if 'http' not in urls:
-            continue
-        files.save_line(category_urls_path, urls)
 
-def get_goods_urls(categorys_len: int = 3):
+def get_goods_urls(categorys_len: int = 3, home_mode: bool = False):
     goods_urls_path = f"{lib.Server.__urls_folder__}/goods.txt"
     category_urls_path = f"{lib.Server.__urls_folder__}/categorys.txt"
-    if Config.home_mode:
+    if home_mode:
         goods_urls_path = goods_urls_path.replace('.txt', '(home).txt')
         category_urls_path = category_urls_path.replace('.txt', '(home).txt')
 
@@ -42,7 +37,7 @@ def get_goods_urls(categorys_len: int = 3):
         index += 1
         if 'https' not in category_url:
             continue
-        if Config.skip_category and Config.home_mode == False and len(category.split('/')) < categorys_len:
+        if Config.skip_category and home_mode == False and len(category.split('/')) < categorys_len:
             continue
         if category in category_index:
             continue
@@ -58,7 +53,7 @@ def get_goods_urls(categorys_len: int = 3):
             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:
+    if home_mode == False:
         formats.de_repeat_urls(goods_urls_path)
 
 def get_goods_info():

lib/__init__.py

@@ -1,3 +1,3 @@
-from lib.module import example
+from lib import example
 
 Server: example.SpiderModule

lib/example.py

@@ -7,19 +7,45 @@ class SpiderModule(spiders.Spiders):
     def __init__(self):
         super().__init__(
             self.project_name,
-            bitch = 10,
+            bitch = 10, # 运行批次大小
-            worker_num = 1,
+            worker_num = 1, # 线程数
             switch_clash = False,
             reflush_browser = False
         )
 
+    # 获取导航入口
     def get_category_urls(self) -> list[str]:
         category_urls = []
 
-        pass
+        self.tab.get('')
+        # 一级分类
+        one_menu_eles = self.tab.eles('')
+        for one_menu_ele in one_menu_eles:
+            one_link_ele = one_menu_ele.ele('')
+            one_url = one_link_ele.attr('href')
+            one_name = one_link_ele.text.replace('/', '-').replace(',', ' ')
+            category_urls.append(f"{one_url}#{one_name}")
+            messages.sendInfo(one_name)
+
+            # 二级分类
+            two_menu_eles = one_menu_ele.eles('')
+            for two_menu_ele in two_menu_eles:
+                two_link_ele = two_menu_ele.ele('')
+                two_url = two_link_ele.attr('href')
+                two_name = two_link_ele.text.replace('/', '-').replace(',', ' ')
+                category_urls.append(f"{two_url}#{one_name}/{two_name}")
+
+                # 三级分类
+                three_menu_eles = two_menu_ele.eles('')
+                for three_menu_ele in three_menu_eles:
+                    three_link_ele = three_menu_ele.ele('')
+                    three_url = three_link_ele.attr('href')
+                    three_name = three_link_ele.text.replace('/', '-').replace(',', ' ')
+                    category_urls.append(f"{three_url}#{one_name}/{two_name}/{three_name}")
 
         return category_urls
 
+    # 获取商品链接入口
     def get_goods_urls(self, category_url: str) -> list[str]:
         self.tab.get(f"{category_url}")
         goods_urls = []
@@ -28,6 +54,7 @@ class SpiderModule(spiders.Spiders):
         
         return goods_urls
 
+    # 获取商品详情入口
     def get_goods_info(self, url) -> types.GoodsInfo:
         def get_image_urls():
             image_urls = []

main.py

@@ -1,45 +1,23 @@
 import lib
-from lib import gether, shopyy
+from core import shopyy, gether, goods
-from lib.model import goods
 from utils import formats, files, wpdata
 
 if __name__ == '__main__':
-    from lib.module import example
+    from lib import example
 
     Server:example.SpiderModule
 
     Server = example.SpiderModule()
     lib.Server = Server
 
-    # category_urls = Server.get_category_urls()
+    # gether.get_category_urls() # 网站导航
-    # files.save_list(f"{Server.__urls_folder__}/categorys.txt", category_urls)
+    # gether.get_goods_urls(3, False) # 商品链接
-    # Server.get_home()
+    # gether.get_goods_info() # 商品详情
-    # gether.get_goods_urls(2)
-    # formats.de_repeat_urls(r'data\bricomarche\urls\goods(home).txt')
-    # gether.get_goods_info()
 
     GoodsModel = goods.GoodsModel(Server.__database_path__)
-    # GoodsModel.to_shopyy_xlsx(f"{Server.__excels_folder__}/goods.xlsx")
+    # GoodsModel.to_shopyy_xlsx(f"{Server.__excels_folder__}/goods.xlsx") # 导出shopyy表格
-    # GoodsModel.to_woo_csv(r'data\fs\urls\goods_2026-01-23.txt_old.txt', f"data/fs/goods.csv")
-    # shopyy.Shopyy(Server.__data_path__).generate_album(
-    #     f"{Server.__urls_folder__}/goods.txt_old.txt"
-    # )
-    # shopyy.Shopyy(Server.__data_path__).generate_navigation(
-    #     f"{Server.__urls_folder__}/categorys.txt"
-    # )
-    # shopyy.Shopyy(Server.__data_path__).generate_album(
-    #     f"{Server.__urls_folder__}/goods(home).txt"
-    # ).generate_navigation(
-    #     f"{Server.__urls_folder__}/categorys(home).txt"
-    # )
 
-    # wpdata.Wpdata(
+    # Verify = shopyy.ShopyyVerify('https://takeokikuchi001.zenshop.cn')
-    #     'data/condom69',
-    #     r'data\condom69\excels\goods_1.xlsx',
-    #     r'data\condom69\urls\goods.txt_old.txt',
-    # ).run()
-
-    # Verify = shopyy.ShopyyVerify('https://ssfshop.zenshop.cn')
     # Verify.get_zero_collections(True)
     # Verify.get_error_images(True)