# 安装 DrissionPage
pip install DrissionPage

# 安装备选方案（可选）
pip install playwright
pip install selenium

from DrissionPage import ChromiumPage

# 创建页面对象
page = ChromiumPage()

# 访问淘宝
page.get('https://www.taobao.com')

# 搜索商品
search_box = page.ele('#q')
search_box.input('手机')
search_box.after().click()

# 获取商品信息
products = page.eles('.item')
for product in products:
    title = product.ele('.title').text
    price = product.ele('.price').text
    print(f"{title}: {price}")

from DrissionPage import ChromiumPage
from crawler.gateway.proxy_server import ProxyServer

class TaobaoAutomator:
    def __init__(self):
        # 启动代理服务器
        self.proxy_server = ProxyServer()

        # 配置 DrissionPage 使用代理
        self.page = ChromiumPage()
        self.page.set.proxy(f'127.0.0.1:{self.proxy_server.port}')

    def search_products(self, keyword):
        # 实现搜索逻辑
        pass

def search_by_image(self, image_path: str):
    """图片搜索功能"""
    # 1. 打开淘宝首页
    self.browser.get('https://www.taobao.com')

    # 2. 点击搜同款按钮
    search_button = self.browser.ele('css:.image-search-icon-wrapper')
    search_button.click()

    # 3. 上传图片
    file_input = self.browser.ele('css:#image-search-custom-file-input')
    file_input.input(image_path)

    # 4. 等待上传完成并搜索
    self._wait_for_upload_complete()
    search_btn = self.browser.ele('css:#image-search-upload-button')
    search_btn.click()

    # 5. 提取商品数据
    return self._extract_products_from_page()

def response(flow: http.HTTPFlow) -> None:
    """拦截API响应"""
    if 'h5api.m.taobao.com' in flow.request.pretty_url:
        content = flow.response.text
        # 解析JSONP响应，提取商品数据
        data = parse_jsonp_response(content)
        save_to_file(data)

def generate_excel_report(self, products_data):
    """生成Excel报告"""
    workbook = openpyxl.Workbook()

    for sheet_data in products_data:
        worksheet = workbook.create_sheet(sheet_data['name'])

        # 添加商品数据
        self.add_product_data(worksheet, sheet_data['products'])

        # 下载并添加商品图片
        self.add_product_images(worksheet, sheet_data['products'])

    workbook.save('report.xlsx')

def compress_image(self, image_path: str) -> str:
    """智能图片压缩"""
    with Image.open(image_path) as img:
        # 调整尺寸到400x400
        if img.width > 400 or img.height > 400:
            img.thumbnail((400, 400), Image.Resampling.LANCZOS)

        # 压缩质量到40%
        img.save(compressed_path, "JPEG", quality=40, optimize=True)

    return compressed_path

# 随机延迟模拟人类行为
import random
time.sleep(random.uniform(1, 3))

# 滚动页面
self.browser.scroll_to_bottom()

# 直接设置文件路径
file_input = self.browser.ele('css:#image-search-custom-file-input')
self.browser.run_js(f"arguments[0].value = '{image_path}'", file_input)

def find_items_recursively(self, obj):
    """递归查找商品数据"""
    if isinstance(obj, dict) and self._is_product_item(obj):
        return [self._extract_product_info(obj)]

    if isinstance(obj, list):
        for item in obj:
            result = self.find_items_recursively(item)
            if result:
                return result

    return []

taobao-search/
├── run.py                    # 主启动脚本
├── src/                      # 源代码
│   ├── automation/           # 自动化模块
│   ├── email/               # 邮件服务
│   ├── excel/               # Excel处理
│   └── workflow/            # 工作流程
├── config/                  # 配置文件
├── IMG_LIST/                # 图片目录
└── data/                    # 数据目录