html_extract_resources
Extract images, videos, and links from HTML files to save resources in a specified directory for document processing.
Instructions
Extract all resources (images, videos, links) from HTML
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| inputPath | Yes | Path to the input HTML file | |
| outputDir | Yes | Directory where resources should be saved |
Implementation Reference
- src/tools/htmlTools.ts:245-297 (handler)The main handler function that extracts images, links, and videos from HTML using JSDOM, saves them as JSON.
export async function extractHtmlResources( inputPath: string, outputDir: string ) { try { console.error(`Starting resource extraction...`); console.error(`Input file: ${inputPath}`); console.error(`Output directory: ${outputDir}`); // 確保輸出目錄存在 try { await fs.access(outputDir); console.error(`Output directory exists: ${outputDir}`); } catch { console.error(`Creating output directory: ${outputDir}`); await fs.mkdir(outputDir, { recursive: true }); console.error(`Created output directory: ${outputDir}`); } const uniqueId = generateUniqueId(); const htmlContent = await fs.readFile(inputPath, "utf-8"); const dom = new JSDOM(htmlContent); const { document } = dom.window; // 提取資源 const resources = { images: Array.from(document.querySelectorAll("img")).map( (img) => (img as HTMLImageElement).src ), links: Array.from(document.querySelectorAll("a")).map( (a) => (a as HTMLAnchorElement).href ), videos: Array.from(document.querySelectorAll("video source")).map( (video) => (video as HTMLSourceElement).src ), }; const outputPath = path.join(outputDir, `resources_${uniqueId}.json`); await fs.writeFile(outputPath, JSON.stringify(resources, null, 2)); console.error(`Written resources to ${outputPath}`); return { success: true, data: `Successfully extracted resources: ${outputPath}`, }; } catch (error) { console.error(`Error in extractHtmlResources:`, error); return { success: false, error: error instanceof Error ? error.message : "Unknown error", }; } } - src/tools/htmlTools.ts:73-90 (schema)Tool schema definition including name, description, and input schema requiring inputPath and outputDir.
export const HTML_EXTRACT_RESOURCES_TOOL: Tool = { name: "html_extract_resources", description: "Extract all resources (images, videos, links) from HTML", inputSchema: { type: "object", properties: { inputPath: { type: "string", description: "Path to the input HTML file", }, outputDir: { type: "string", description: "Directory where resources should be saved", }, }, required: ["inputPath", "outputDir"], }, }; - src/index.ts:204-220 (registration)Server request handler dispatches calls to 'html_extract_resources' by invoking the extractHtmlResources function.
if (name === "html_extract_resources") { const { inputPath, outputDir } = args as { inputPath: string; outputDir: string; }; const result = await extractHtmlResources(inputPath, outputDir); if (!result.success) { return { content: [{ type: "text", text: `Error: ${result.error}` }], isError: true, }; } return { content: [{ type: "text", text: fileOperationResponse(result.data) }], isError: false, }; } - src/tools/_index.ts:9-9 (registration)The tools array includes HTML_EXTRACT_RESOURCES_TOOL, served via listTools endpoint.
export const tools = [DOCUMENT_READER_TOOL, PDF_MERGE_TOOL, PDF_SPLIT_TOOL, DOCX_TO_PDF_TOOL, DOCX_TO_HTML_TOOL, HTML_CLEAN_TOOL, HTML_TO_TEXT_TOOL, HTML_TO_MARKDOWN_TOOL, HTML_EXTRACT_RESOURCES_TOOL, HTML_FORMAT_TOOL, TEXT_DIFF_TOOL, TEXT_SPLIT_TOOL, TEXT_FORMAT_TOOL, TEXT_ENCODING_CONVERT_TOOL, EXCEL_READ_TOOL, FORMAT_CONVERTER_TOOL];