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, # 运行批次大小
            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 = []

        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 = []
        
        pass
        
        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 = []
            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