搜索结果

×

搜索结果将在这里显示。

🙏 https://store.dji.com/list/handheld?tab=102&sort=recommendation&page=1&category=101%3D101.202.303&from=store_homepage

import random, csv, requests, logging, time, json, re
from selenium import webdriver
from copy import deepcopy
from time import sleep
from lxml import etree
from DrissionPage import Chromium, ChromiumOptions
from DrissionPage.common import Keys

# https://store.dji.com/list/handheld?tab=102&sort=recommendation&page=1&category=101%3D101.202.303&from=store_homepage
# https://store.dji.com/list/handheld?tab=102&sort=recommendation&page=1&category=101%3D101.203.306&from=store_homepage

class Dji:
    def __init__(self):
        self.url_list = [
            'https://store.dji.com/list/handheld?tab=102&sort=recommendation&page=1&category=101%3D101.202.303&from=store_homepage',
            'https://store.dji.com/list/handheld?tab=102&sort=recommendation&page=1&category=101%3D101.203.306&from=store_homepage'
        ]
        self.interface_url_list = [
            'https://store.dji.com/api/ec-cms/pages/list/handheld/products?tab=102&sort=recommendation&page=1&category=101%3D101.202.303&country=us&language=en',
            'https://store.dji.com/api/ec-cms/pages/list/handheld/products?tab=102&sort=recommendation&page=1&category=101%3D101.203.306&country=us&language=en'
        ]
        self.headers = {
            "accept": "application/json",
            "accept-language": "zh-CN,zh;q=0.9",
            "cache-control": "no-cache",
            "content-type": "application/json",
            "country": "us",
            "language": "en",
            "pragma": "no-cache",
            "priority": "u=1, i",
            # "referer": "https://store.dji.com/list/handheld?tab=102&sort=recommendation&page=1&category=101%3D101.202.303&from=store_homepage",
            "sec-ch-ua": "\"Chromium\";v=\"136\", \"Google Chrome\";v=\"136\", \"Not.A/Brand\";v=\"99\"",
            "sec-ch-ua-mobile": "?0",
            "sec-ch-ua-platform": "\"Windows\"",
            "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/136.0.0.0 Safari/537.36"
        }

        self.id = 0  # 保存到csv文件不用id字段
        self.init_data = {
            'Handle': '',
            'Title': '',
            'Body (HTML)': '',
            'Vendor': '',
            'Type': '',
            'Tags': '',
            'Published': 'TRUE',
            'Option1 Name': '',
            'Option1 Value': '',
            'Option2 Name': '',
            'Option2 Value': '',
            'Option3 Name': '',
            'Option3 Value': '',
            'Variant SKU': '',
            'Variant Grams': '',
            'Variant Inventory Tracker': 'Shopify',
            'Variant Inventory Qty': '99999',
            'Variant Inventory Policy': '',
            'Variant Fulfillment Service': '',
            'Variant Price': '',
            'Variant Compare At Price': '',
            'Variant Requires Shipping': '',
            'Variant Taxable': '',
            'Variant Barcode': '',
            'Image Src': '',
            'Image Position': '',
            'Image Alt Text': '',
            'Gift Card': '',
            'SEO Title': '',
            'SEO Description':'',
            'Variant Image': '',
            'Status': '',
            'Collection': '',
        }
        self.empty_data = {
            'Handle': '',
            'Title': '',
            'Body (HTML)': '',
            'Vendor': '',
            'Type': '',
            'Tags': '',
            'Published': '',
            'Option1 Name': '',
            'Option1 Value': '',
            'Option2 Name': '',
            'Option2 Value': '',
            'Option3 Name': '',
            'Option3 Value': '',
            'Variant SKU': '',
            'Variant Grams': '',
            'Variant Inventory Tracker': '',
            'Variant Inventory Qty': '',
            'Variant Inventory Policy': '',
            'Variant Fulfillment Service': '',
            'Variant Price': '',
            'Variant Compare At Price': '',
            'Variant Requires Shipping': '',
            'Variant Taxable': '',
            'Variant Barcode': '',
            'Image Src': '',
            'Image Position': '',
            'Image Alt Text': '',
            'Gift Card': '',
            'SEO Title': '',
            'SEO Description': '',
            'Variant Image': '',
            'Status': '',
            'Collection': '',
        }
        self.field_names = ['Handle', 'Title', 'Body (HTML)', 'Vendor', 'Type', 'Tags', 'Published', 'Option1 Name',
                            'Option1 Value', 'Option2 Name', 'Option2 Value', 'Option3 Name', 'Option3 Value',
                            'Variant SKU', 'Variant Grams', 'Variant Inventory Tracker', 'Variant Inventory Qty',
                            'Variant Inventory Policy', 'Variant Fulfillment Service', 'Variant Price',
                            'Variant Compare At Price', 'Variant Requires Shipping', 'Variant Taxable',
                            'Variant Barcode', 'Image Src', 'Image Position', 'Image Alt Text', 'Gift Card',
                            'SEO Title', 'SEO Description', 'Variant Image', 'Status', 'Collection']
        self.file = None
        self.writer = None

        self.browser = None
        self.tab = None

        self.cnt = 0

    def simulated_smooth_scroll(self, driver, step=1000, interval=0.5, timeout=30):
        # 平滑移动到底部

        start_time = time.time()
        last_height = driver.execute_script("return document.documentElement.scrollHeight")
        current_position = 0

        while time.time() - start_time < timeout:
            # 计算剩余滚动距离
            remaining = last_height - current_position

            # 动态调整步长
            current_step = min(step, remaining) if remaining > 0 else 0

            if current_step <= 0:
                break

            # 执行分步滚动
            driver.execute_script(f"window.scrollBy(0, {current_step})")
            current_position += current_step

            # 等待滚动和内容加载
            time.sleep(interval * (current_step / step))  # 动态间隔

            # 检查新高度
            new_height = driver.execute_script(
                "return document.documentElement.scrollHeight"
            )

            # 更新高度(处理动态加载)
            if new_height > last_height:
                last_height = new_height

    def get_driver(self, url, xpath_txt=None, is_turn=False):
        options = webdriver.ChromeOptions()
        options.add_argument('--headless')
        options.add_argument('--disable-gpu')
        options.page_load_strategy = "none"

        driver = webdriver.Chrome(options=options)

        driver.implicitly_wait(10)
        driver.maximize_window()

        while True:
            try:
                print('正在获取', url, '的页面数据')
                driver.get(url)

                if is_turn:
                    sleep(1)
                    self.simulated_smooth_scroll(driver)

                if xpath_txt:
                    driver.find_element('xpath', xpath_txt)
                else:
                    self.random_sleep(5)

                break

            except:
                print(url, '没定位到,重新请求...')

        # self.writer_to_file(driver.page_source, 'w', 'utf-8')

        return driver

    def driver_continue(self, driver, url, xpath_txt=None, is_turn=False):
        flag = True
        while flag:
            flag = False
            try:
                print('正在获取', url, '的页面数据')
                driver.get(url)

                if is_turn:
                    self.random_sleep()
                    self.simulated_smooth_scroll(driver)

                driver.find_element('xpath', xpath_txt)

            except:
                flag = True
                print(url, '没定位到,重新请求...')

        # self.writer_to_file(driver.page_source, 'w', 'utf-8')

    def get_page_html(self, url, xpath_txt=None, is_turn=False):
        driver = self.get_driver(url, xpath_txt, is_turn=is_turn)

        page_source = driver.page_source

        driver.close()

        return etree.HTML(page_source)

    def writer_to_file(self, data, mode, encoding=None):
        if 'b' in encoding:
            open('./text.html', mode).write(data)
        else:
            open('./text.html', mode, encoding=encoding).write(data)

        print('写入文件成功!')

    def driver_click(self, driver, timeout=2):
        driver.click()
        self.random_sleep(timeout)

    def driver_back(self, driver, timeout=2):
        driver.back()
        self.random_sleep(timeout)

    def driver_refresh(self, driver, timeout=2):
        driver.refresh()
        self.random_sleep(timeout)

    def tab_wait(self, tab, timeout=3):
        tab.wait(timeout)
        return tab

    def tab_get(self, tab, url, xpath_txt='html', is_turn=False):
        print('正在获取', url, '的数据')

        while True:
            tab.get(url)
            self.tab_wait(tab)

            if is_turn:
                tab.scroll.to_bottom()
                self.tab_wait(tab)

            ele = tab.ele(f'x:{xpath_txt}')
            if ele:
                break

            print('没有请求到元素,重新请求中')
            tab.wait(2)

        return tab

    def get_dp_html(self, tab, url, xpath_txt='html', is_turn=False):
        tab = self.tab_get(tab, url, xpath_txt=xpath_txt, is_turn=is_turn)

        res = etree.HTML(tab.html)

        return res

    def random_sleep(self, timeout=2):
        sleep(random.random() + timeout)

    def save_csv(self, data):
        self.writer.writerow({
            'Handle': data['Handle'],
            'Title': data['Title'],
            'Body (HTML)': data['Body (HTML)'],
            'Vendor': data['Vendor'],
            'Type': data['Type'],
            'Tags': data['Tags'],
            'Published': data['Published'],
            'Option1 Name': data['Option1 Name'],
            'Option1 Value': data['Option1 Value'],
            'Option2 Name': data['Option2 Name'],
            'Option2 Value': data['Option2 Value'],
            'Option3 Name': data['Option3 Name'],
            'Option3 Value': data['Option3 Value'],
            'Variant SKU': data['Variant SKU'],
            'VariantGrams': data['Variant Grams'],
            'Variant Inventory Tracker': data['Variant Inventory Tracker'],
            'Variant Inventory Qty': data['Variant Inventory Qty'],
            'Variant Inventory Policy': data['Variant Inventory Policy'],
            'Variant Fulfillment Service': data['Variant Fulfillment Service'],
            'Variant Price': data['Variant Price'],
            'Variant Compare At Price': data['Variant Compare At Price'],
            'Variant Requires Shipping': data['Variant Requires Shipping'],
            'Variant Taxable': data['Variant Taxable'],
            'Variant Barcode': data['Variant Barcode'],
            'Image Src': data['Image Src'],
            'Image Position': data['Image Position'],
            'Image Alt Text': data['Image Alt Text'],
            'Gift Card': data['Gift Card'],
            'SEO Title': data['SEO Title'],
            'SEO Description': data['SEO Description'],
            'Variant Image': data['Variant Image'],
            'Status': data['Status'],
            'Collection': data['Collection']
        })

    def get_response(self, url):
        print('正在获取', url, '的数据')

        while True:
            try:
                response = requests.get(url, headers=self.headers)
                break
            except:
                print('没有请求到,重新请求')
                self.random_sleep()

        self.random_sleep()

        return response

    def get_html(self, url):
        response = self.get_response(url)
        return etree.HTML(response.text)

    def tab_run_js(self, tab, js_code):
        while True:
            try:
                tab.run_js(js_code)
                break
            except Exception as e:
                print('捕获tab_run_js方法的run_js:', e)
                tab.wait(1)

    def ele_click(self, tab, ele):
        while True:
            try:
                tab.actions.click(ele)
                break
            except Exception as e:
                print('捕获ele_click方法的actions.click:', e)
                tab.wait(1)

        tab.wait(2)

    def dp_click_ad(self, tab, xpath_txt):
        ad_ele = tab.ele(f'x:{xpath_txt}', timeout=2)
        if ad_ele:
            print('有广告:', ad_ele)
            self.ele_click(tab, ad_ele)
            self.tab_wait(tab, 1)

    def infinite_scroll(self, tab):
        product_url_list = []
        w_cnt = 0
        turn_cnt = 0
        is_bottom = False

        while True:
            self.dp_click_ad(tab, '//button[@class="css-2vqtum"]')
            self.dp_click_ad(tab, '//button[@class="css-71t821"]')

            if is_bottom:
                break

            tab.scroll.to_bottom()
            self.tab_wait(tab, 1)
            self.tab_run_js(self.tab, 'window.scrollBy(0, -1000)')

            turn_cnt += 1
            print(f'翻页了{turn_cnt}次')

            n_cnt = 0

            self.tab_wait(tab, 5)
            product_url_ele_list = tab.eles('x://div[@class="product-thumbnail plpv3 css-1gasjii"]//a[@class="css-avqw6d"]')

            for product_url_ele in product_url_ele_list:
                product_url = product_url_ele.attr('href')
                if 'https:' not in product_url:
                    product_url = 'https://www.coach.com' + product_url

                if product_url in product_url_list:
                    continue

                n_cnt += 1
                product_url_list.append(product_url)

            print('产品个数:', len(product_url_ele_list))
            print('获取到的产品个数', len(product_url_list))

            if n_cnt == 0:
w_cnt += 1
            else:
                w_cnt = 0

            if w_cnt >= 5:
                print('到底了')
                is_bottom = True

        return product_url_list

    def get_detail_tab(self, url, xpath_txt='html', backup_xpath_txt='html'):
        print('正在获取', url, '的数据')

        tab = self.browser.latest_tab

        while True:
            tab.get(url)
            self.tab_wait(tab)

            ele = tab.ele(f'x:{xpath_txt}')
            if ele:
                print('第1个xpath找到的')
                break
            else:
                t_ele = tab.ele(f'x:{backup_xpath_txt}')
                if t_ele:
                    print('第2个xpath找到的')
                    break

            print('没有请求到元素,重新请求中')
            tab.wait(2)

        return tab

    def get_product_img_url_list(self, tab, data):
        tab.wait(5)
        self.dp_click_ad(tab, '//button[@class="css-2vqtum"]')

        data['Option1 Value'] = tab.ele('x://p[contains(@class, "color-name")]').text

        product_color_img_url_list = []

        img_temp_ele = tab.ele('x://li[contains(@class, "is-prev")]')
        if img_temp_ele:
            product_color_img_url_cnt = int(img_temp_ele.attr('data-slide-index'))
        else:
            product_color_img_url_cnt = len(tab.eles('x://div[@class="css-1161qt5"]/div')) - 1

        print(data['Option1 Value'], '色的图片个数应为:', product_color_img_url_cnt)

        tab.wait(6)
        raw_product_color_img_ele_list = tab.eles('x://li[contains(@class, "splide__slide")]/div | //li[contains(@class, "splide__slide")]//video/source | //div[@class="css-1161qt5"]/div[@class="css-113el1s"]/div')

        for raw_product_color_img_ele in raw_product_color_img_ele_list:
            raw_product_color_img_url = raw_product_color_img_ele.attr('src')

            if not raw_product_color_img_url:
                continue

            raw_product_color_img_url = raw_product_color_img_url.split('?')[0]

            if raw_product_color_img_url in product_color_img_url_list:
                continue

            product_color_img_url_list.append(raw_product_color_img_url)

        print(data['Option1 Value'], '色获取到的图片个数为:', len(product_color_img_url_list))

        return product_color_img_url_list

    def init_tab(self):
        co = ChromiumOptions()
        co.set_browser_path(r'C:\Program Files\Google\Chrome\Application\chrome.exe')
        co.auto_port()
        # co.headless()
        # co.set_argument('--no-sandbox')

        self.browser = Chromium(co)

        self.tab = self.browser.latest_tab
        self.tab.set.window.max()

    def handle_img_url(self, raw_img_url):
        return raw_img_url

    def save_all_data(self, product_data_list):
        for product_data in product_data_list:
            self.cnt += 1
            self.save_csv(product_data)
            print('第', self.cnt, '行保存完成!')

    # 取消翻译
    def cancel_translate(self, url):
        tab = self.tab_get(self.tab, url, '//div[@class="collection_item overflow-hidden"]')
        tab.actions.move_to(tab.ele('x://div[@class="gt-translate-btn-bg"]'))
        tab.wait(2)
        tab.actions.click(tab.ele('x://div[@class="gt-translate-switch"]'))
        tab.wait(2)

    # 翻译成英文
    def translate_english(self, tab):
        self.ele_click(tab, tab.ele('x://div[contains(@class, "style-module__country-selector-wrapper")]/div/span[1]'))
        self.ele_click(tab, tab.ele('x://div[contains(@class, "Item-module__item")]/a[./span[1]/text()="United States"]'))

    def test_product(self, url, product_host_img_url, data_type):
        self.file = open('./test.csv', 'w', newline='', encoding='utf-8-sig')
        self.writer = csv.DictWriter(self.file, fieldnames=self.field_names)
        self.writer.writeheader()

        logging.captureWarnings(True)

        self.init_tab()

        tab = self.tab_get(self.tab, url, '//div[contains(@class, "style-module__country-selector-wrapper")]/div/span[2]')

        self.translate_english(tab)

        data = deepcopy(self.init_data)
        data['Type'] = data_type
        data['Collection'] = data['Type']

        product_data_list = self.product_detail_parse(url, data, product_host_img_url)

        self.save_all_data(product_data_list)

        if self.file:
            self.file.close()

        if self.browser:
            self.browser.quit()

    def product_detail_parse(self, url, data, product_host_img_url):
        product_data_list = []

        tab = self.get_detail_tab(url, '//button[contains(@class, "eventBenefitItem__cursor___yB4w5")]//ul[@class="eventBenefitItem__event-benefit-right-list___+mo5x"]/li | //div[@id="product-detail"]') # 第4个请求

        # ----------------------------------------------
        # 获取图片
        small_img_url_ele_len = len(tab.eles('x://ul[contains(@class, "CarouselPreview__dots")]/li/a//img'))
        for i in range(small_img_url_ele_len - 1):
            self.ele_click(tab, tab.ele('x://div[contains(@class, "slick-next")]'))

        temp_img_url_ele_list = tab.eles('x://div[@class="slick-track"]/a//img')

        product_img_url_list = []

        for temp_img_url_ele in temp_img_url_ele_list:
            temp_img_url = temp_img_url_ele.attr('src').split('?')[0].replace('.webp', '.jpg')

            if temp_img_url in product_img_url_list:
                continue

            product_img_url_list.append(temp_img_url)

        product_img_url_len = len(product_img_url_list)

        # ----------------------------------------------

        _data = deepcopy(data)

        _data['Handle'] = url.split('?')[0].split('/')[-1] + '-' + str(url.split('?')[-1].split('=')[-1])
        _data['Variant SKU'] = _data['Handle']

        body_ele_list = tab.eles('x://button[contains(@class, "eventBenefitItem__cursor___yB4w5")]//ul[@class="eventBenefitItem__event-benefit-right-list___+mo5x"]/li | //div[@id="product-detail"]')

        for body_ele in body_ele_list:
            _data['Body (HTML)'] += body_ele.html  # 到时候看看效果,div标签应该会自己换行吧?会,但是不会跟随颜色换

        _data['Variant Price'] = tab.ele('x://section[@class="info-section"]/div[contains(@class, "money-wrapper")]//span[contains(@class, "normal-price")]').text.split(' ')[-1].replace('$', '').strip()
        _data['Title'] = tab.ele('x://h1[contains(@class, "style__product-title")]').text.strip()  # 颜色标题不一样,到时候看看是什么效果?不会跟随颜色换

        _data['Image Src'] = self.handle_img_url(product_img_url_list[0])
        _data['Image Position'] = 1
        _data['Variant Image'] = product_host_img_url

        print('第', self.id, '个产品的图片个数为:', product_img_url_len)

        product_data_list.append(_data)
        print(_data)

        for i in range(1, product_img_url_len):
            temp_data = deepcopy(self.empty_data)

            temp_data['Handle'] = _data['Handle']
            temp_data['Published'] = 'TRUE'
            temp_data['Image Src'] = self.handle_img_url(product_img_url_list[i])
            temp_data['Image Position'] = i + 1

            product_data_list.append(temp_data)
            print(temp_data)

        return product_data_list

    def parse(self, url, interface_url):
        data = deepcopy(self.init_data)

        data['Type'] = 'Shop Handheld'
        data['Collection'] = data['Type']

        tab = self.tab_get(self.tab, url, '//a[contains(@class, "productItem__content")]') # 第1个请求

        self.translate_english(self.tab)

        index_product_url_json_list = self.get_response(interface_url).json()['data']['items'] # 第2个请求

        while True:
            index_product_host_img_url_ele_list = tab.eles('x://div[contains(@class, "productItem__cover")]//img') # 可能缺少https:
            if len(index_product_host_img_url_ele_list) == len(index_product_url_json_list):
                break

            print('没获取到所有的产品主图,重新定位')
            tab.wait(3)

        index_product_url_list = []
        index_product_host_img_url_list = []

        temp_id = 0
        for index_product_url_json in index_product_url_json_list:
            index_product_url = 'https://store.dji.com/product/' + index_product_url_json['slug'] + '?vid=' + str(index_product_url_json['variantId'])

            index_product_url_list.append(index_product_url)

            index_product_host_img_url = index_product_host_img_url_ele_list[temp_id].attr('src').strip().split('?')[0].replace('@small.', '@ultra.').replace('@xlarge.', '@ultra.').replace('.webp', '.png')

            if 'https' not in index_product_host_img_url:
                index_product_host_img_url = 'https:' + index_product_host_img_url

            index_product_host_img_url_list.append(index_product_host_img_url)

            temp_id += 1

        t_id = 0
        for index_product_url in index_product_url_list:
            self.id += 1

            with open('./filter.txt', 'r', encoding='utf-8') as f:
                filter_txt = f.read()

            if index_product_url in filter_txt:
                print(self.id, index_product_url, '已完成')
                t_id += 1
                continue

            print(self.id, '开始')

            tab = self.get_detail_tab(index_product_url, '//button[contains(@class, "eventBenefitItem__cursor___yB4w5")]//ul[@class="eventBenefitItem__event-benefit-right-list___+mo5x"]/li | //div[@id="product-detail"]')  # 第3个请求

            product_url_list = [ index_product_url ]
            product_host_img_url_list = [ index_product_host_img_url_list[t_id] ]

            t_id += 1

            sub_product_ele_len = len(tab.eles('x://div/section[@class="style__group-small___mv2eL"]//ul[@class="style__list___GhTDt"]/li/label'))
            for i in range(sub_product_ele_len):
                sub_product_ele_list = tab.eles('x://div/section[@class="style__group-small___mv2eL"]//ul[@class="style__list___GhTDt"]/li/label')

                self.ele_click(tab, sub_product_ele_list[i])

                product_host_img_url = tab.eles('x://div/section[@class="style__group-small___mv2eL"]//ul[@class="style__list___GhTDt"]/li/label//div[contains(@class, "accessory-item-thumb")]/img')[i].attr('src') # 可能缺少https:

                if 'https' not in product_host_img_url:
                    product_host_img_url = 'https:' + product_host_img_url

                product_host_img_url.strip().split('?')[0].replace('@small.', '@ultra.').replace('@xlarge.', '@ultra.').replace('.webp', '.png')

                if product_host_img_url not in product_host_img_url_list:
                    product_host_img_url_list.append(product_host_img_url)

                if tab.url in product_url_list:
                    print(tab.url, '已在产品url列表里')
                    continue

                product_url_list.append(tab.url)

            temp_id = 0
            for product_url in product_url_list:
with open('./filter.txt', 'r', encoding='utf-8') as f:
                    filter_txt = f.read()

                if product_url in filter_txt:
                    print(self.id, product_url, '已完成')
                    temp_id += 1
                    continue

                product_data_list = self.product_detail_parse(product_url, data, product_host_img_url_list[temp_id])

                self.save_all_data(product_data_list)

                with open('./filter.txt', 'a', encoding='utf-8') as f:
                    f.write(product_url + '\n')

                temp_id += 1

            print(self.id, '结束')

    def run(self, is_continue=False):
        if is_continue:
            self.file = open('./dji.csv', 'a', newline='', encoding='utf-8-sig')
            self.writer = csv.DictWriter(self.file, fieldnames=self.field_names)
        else:
            self.file = open('./dji.csv', 'w', newline='', encoding='utf-8-sig')
            self.writer = csv.DictWriter(self.file, fieldnames=self.field_names)
            self.writer.writeheader()

            with open('./filter.txt', 'w', encoding='utf-8') as f:
                f.write('')

            with open('./title_filter.txt', 'w', encoding='utf-8') as f:
                f.write('')

        self.init_tab()

        logging.captureWarnings(True)

        temp_id = 0
        for url in self.url_list:

            print('第', temp_id + 1, '的链接开始')
            self.parse(url, self.interface_url_list[temp_id])
            print('第', temp_id + 1, '的链接结束')
            temp_id += 1

        if self.file:
            self.file.close()

        if self.browser:
            self.browser.quit()

if __name__ == '__main__':
    dji = Dji()
    dji.run()

    url1 = 'https://store.dji.com/product/dji-mic-2?vid=161301' # 详情有文字,视频,但不采集视频详情
    img1 = 'https://se-cdn.djiits.com/tpc/uploads/spu/cover/c17064092388fdfb18ea7f1ec0dd0ef0@ultra.png'

    url2 = 'https://store.dji.com/product/kingston-64g-go-plus-microsd?vid=123351' # 全文字详情
    img2 = 'https://se-cdn.djiits.com/tpc/uploads/spu/cover/07d367df2dfd46fcc2616d5339df5c5f@ultra.png'

    url3 = 'https://store.dji.com/product/dji-care-refresh-2-year-osmo-pocket-3?vid=153262' # 详情有文字,有图片
    img3 = 'https://se-cdn.djiits.com/tpc/uploads/spu/cover/ecc9548db1546586844a30ddf7071078@ultra.png'

    url4 = 'https://store.dji.com/product/osmo-pocket-3-vlog-combo-dji-mic-mini?vid=178161' # 图片获取不全
    img4 = 'https://se-cdn.djiits.com/tpc/uploads/carousel/image/b000f0ae5d40763fe3bd16a87aec0fb5@ultra.jpg'
    # dji.test_product(url4, img4, 'Shop Handheld')

# https://store.dji.com/list/handheld?tab=102&sort=recommendation&page=1&category=101%3D101.202.303&from=store_homepage
# https://store.dji.com/list/handheld?tab=102&sort=recommendation&page=1&category=101%3D101.203.306&from=store_homepage

# 上传代码的时候把True给去掉 √
# 试试全部产品数据 √
# 试试部分产品数据 √
# 采集 √
# 试试那几个产品详情 √