# 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

brew install --cask iterm2

sh -c "$(curl -fsSL https://raw.github.com/robbyrussell/oh-my-zsh/master/tools/install.sh)"

chsh -s /bin/zsh

vim ~/.zshrc  # 修改 ZSH_THEME="agnoster"

# 安装
brew install zsh-syntax-highlighting

# 配置
echo "source /usr/local/share/zsh-syntax-highlighting/zsh-syntax-highlighting.zsh" >> ~/.zshrc

# 安装
git clone https://github.com/zsh-users/zsh-autosuggestions ~/.oh-my-zsh/custom/plugins/zsh-autosuggestions

# 配置
vim ~/.zshrc
# 在 plugins 中添加 zsh-autosuggestions
plugins=(git zsh-autosuggestions zsh-syntax-highlighting)

# 在 ~/.zshrc 中添加
DEFAULT_USER="heyaohua"

# 在 ~/.zshrc 中添加
alias proxy='export all_proxy=socks5://127.0.0.1:1086'
alias unproxy='unset all_proxy'

{
    "success": True,
    "output_path": "screenshots/douyin_long_screenshot_20250916_135333.png",
    "screenshot_count": 4,
    "total_height": 9228,
    "file_size": 2764800,
    "original_url": "https://v.douyin.com/...",
    "current_url": "https://haohuo.jinritemai.com/...",
    "title": "页面标题"
}

{
  "url": "https://v.douyin.com/Zdo3P7Zv51o/"
}

{
  "message": "长截图完成",
  "data": {
    "success": true,
    "output_path": "screenshots/douyin_long_screenshot_20250916_135333.png",
    "screenshot_count": 4,
    "total_height": 9228,
    "file_size": 2764800
  }
}

from app.services.playwright_service import playwright_service

async def example():
    await playwright_service.initialize()

    result = await playwright_service.take_long_screenshot(
        url="https://v.douyin.com/Zdo3P7Zv51o/",
        output_dir="screenshots"
    )

    if result["success"]:
        print(f"截图完成: {result['output_path']}")
        print(f"截图数量: {result['screenshot_count']}")
        print(f"总高度: {result['total_height']}px")

    await playwright_service.close()

curl -X POST "http://localhost:8000/douyin/long-screenshot" \
     -H "Content-Type: application/json" \
     -d '{"url": "https://v.douyin.com/Zdo3P7Zv51o/"}'

curl -X POST "http://localhost:8000/douyin/test-long-screenshot"

cd tests
python test_service.py

app/services/
├── playwright_service.py     # 主服务入口
│   ├── take_long_screenshot  # 长截图方法
│   └── _stitch_screenshots   # 图片拼接方法

app/api/
├── douyin.py                 # HTTP API 定义
│   ├── /long-screenshot      # 长截图接口
│   └── /test-long-screenshot # 测试接口

tests/
├── test_service.py           # 集成测试脚本
└── simple_douyin_test.py     # 快速验证脚本

2025-09-16 13:53:33,832 - INFO - 拼接图片尺寸: 1170 x 9228
2025-09-16 13:53:35,160 - INFO - ✅ 成功: True
2025-09-16 13:53:35,160 - INFO - 📊 截图数量: 4
2025-09-16 13:53:35,160 - INFO - 💾 文件大小: 2.64MB

# 传统写法
squares = []
for x in range(10):
    squares.append(x**2)

# 列表推导式
squares = [x**2 for x in range(10)]

# 搭配条件过滤
even_squares = [x**2 for x in range(10) if x % 2 == 0]

# 可能抛出 KeyError
user_name = user_dict['name']

# 更稳健的写法
user_name = user_dict.get('name', 'Unknown')

fruits = ['apple', 'banana', 'orange']

for index, fruit in enumerate(fruits, start=1):
    print(f"{index}. {fruit}")

names = ['Alice', 'Bob', 'Charlie']
ages = [25, 30, 35]

for name, age in zip(names, ages):
    print(f"{name} 的年龄是 {age} 岁")

name = "World"
age = 25

message = f"Hello, {name}! You are {age} years old."