pip install -r requirements.txt
playwright install chromium

python screenshot_scraper_mcp.py
# 或
python -m webscraper.server

python run_webui.py                 # 默认 http://127.0.0.1:8765
python run_webui.py --port 9000     # 自定义端口

{
  "mcpServers": {
    "VisualWebScraper": {
      "command": "python",
      "args": ["d:/BaiduSyncdisk/desktop/WebSearchMCP/screenshot_scraper_mcp.py"],
      "env": {
        "LMSTUDIO_BASE_URL": "http://localhost:1234/v1"
      }
    }
  }
}

webscraper/
├── config.py          # 集中配置：超时、限额、环境变量
├── browser.py         # Playwright 浏览器池（复用实例）
├── extractors.py      # 文章提取、正文抓取、文本清洗
├── llm.py             # LM Studio 调用（OpenAI 兼容接口）
├── reporter.py        # 简报 Markdown 落盘与文本渲染
├── server.py          # MCP 入口：handler 注册与生命周期
└── tools/
    ├── base.py        # 工具注册表、参数校验、结果构造
    ├── screenshot.py  # fetch_webpage_with_screenshot
    ├── search.py      # search_webpage_articles
    └── brief.py       # generate_webpage_brief

ARTICLE_PATH_MARK = "/article/"                      # 文章链接特征
ARTICLE_DATE_RE = re.compile(r"/article/(\d{4})/(\d{1,2})/")  # URL 日期格式