SELECTOR_MAP = {
    "xiaohongshu": {
        "url": "https://www.xiaohongshu.com/notification",
        "comment_item": ".interaction-item, .comment-item",
        "comment_text": ".interaction-content, .comment-text, .content",
        "reply_trigger": "button:has(svg.reply-icon), svg.reply-icon, .reply-btn",
        "input": "p#content-textarea.content-input, [contenteditable='true'].content-input, textarea.comment-input",
        "submit": "button.submit, button:has-text('发送')",
        "success": "text=评论成功",
        "replied_marker": "作者"
    },
    "douyin": {
        "url": "<TO_FILL_DOUYIN_URL>",
        "comment_item": "<TO_FILL>",
        "comment_text": "<TO_FILL>",
        "reply_trigger": "<TO_FILL>",
        "input": "<TO_FILL>",
        "submit": "<TO_FILL>",
        "success": "<TO_FILL_SUCCESS_TEXT>",
        "replied_marker": "<TO_FILL_MARKER>"
    },
    "kuaishou": {
        "url": "<TO_FILL_KUAISHOU_URL>",
        "comment_item": "<TO_FILL>",
        "comment_text": "<TO_FILL>",
        "reply_trigger": "<TO_FILL>",
        "input": "<TO_FILL>",
        "submit": "<TO_FILL>",
        "success": "<TO_FILL_SUCCESS_TEXT>",
        "replied_marker": "<TO_FILL_MARKER>"
    }
}

# 安装依赖
pip install -r requirements.txt
python -m playwright install chromium

# 本地模型检查
python -c "import requests;print(requests.get('http://127.0.0.1:11434/api/tags',timeout=5).status_code)"

# 单轮 dry-run
python auto_responder_production.py --platform xiaohongshu --once --recent-hours 1 --max-replies 3

# 构建 EXE
powershell -ExecutionPolicy Bypass -File .\build_exe.ps1

# EXE 参数模式
.\dist\auto_responder.exe --platform xiaohongshu --interval-minutes 5 --recent-hours 2 --max-replies 3

# EXE 交互模式
.\dist\auto_responder.exe --interactive

按 social-auto-tool-builder v1.1.0 的流程，帮我做一个【平台名】自动化工具。
要求：
1) Python + Playwright + 本地 Ollama
2) 用 persistent_context 保存登录状态
3) 先 dry-run 列候选，再真实发送
4) 支持 --platform --interval-minutes --recent-hours --max-replies --once --interactive
5) 用多平台选择器映射模板实现，允许按我提供的DOM增量修正
6) 最后打包EXE并给 QUICK_START