get_page_content
Extract HTML content from the current webpage using Chrome debugging for browser automation and persistent sessions.
Instructions
获取当前页面的HTML内容
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Implementation Reference
- src/browserSession.ts:554-574 (handler)The handler function that executes the get_page_content tool logic. It retrieves the HTML content of the current page using Puppeteer's page.content() and returns it in the logs field of BrowserActionResult.async getPageContent(): Promise<BrowserActionResult> { if (!this.page) { return { success: false, error: "浏览器未启动或页面不存在" }; } try { const content = await this.page.content(); return { success: true, logs: content }; } catch (error) { return { success: false, error: error instanceof Error ? error.message : String(error) }; } }
- src/index.ts:225-227 (registration)Registration/dispatch point in the CallToolRequestSchema handler where the get_page_content tool call is routed to BrowserSession.getPageContent().case "get_page_content": result = await this.browserSession.getPageContent(); break;
- src/index.ts:154-162 (schema)Tool schema definition including name, description, and empty input schema (no parameters required) registered in the ListToolsRequestSchema handler.{ name: "get_page_content", description: "获取当前页面的HTML内容", inputSchema: { type: "object", properties: {}, }, }, ] as Tool[],
- src/index.ts:321-322 (helper)Helper function to generate success message for the get_page_content tool.case "get_page_content": return "✅ 页面内容获取完成";