html_extract_resources

Instructions

Implementation Reference

• src/tools/htmlTools.ts:72-90 (schema)

  The Tool schema definition for html_extract_resources, defining its name, description, and input schema (inputPath, outputDir).

  // HTML 資源提取工具
  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/tools/htmlTools.ts:244-297 (handler)

  The handler function extractHtmlResources that implements the resource extraction logic: reads HTML, extracts images/videos/links, and saves to JSON.

  // HTML 資源提取實作
  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/_index.ts:1-32 (registration)

  The tool registration/index file that imports HTML_EXTRACT_RESOURCES_TOOL and includes it in the exported tools array.

  import { DOCUMENT_READER_TOOL } from "./documentReader.js";
  import { DOCX_TO_HTML_TOOL, DOCX_TO_PDF_TOOL } from "./docxTools.js";
  import { EXCEL_READ_TOOL } from "./excelTools.js";
  import { FORMAT_CONVERTER_TOOL } from "./formatConverterPlus.js";
  import { HTML_CLEAN_TOOL, HTML_EXTRACT_RESOURCES_TOOL, HTML_FORMAT_TOOL, HTML_TO_MARKDOWN_TOOL, HTML_TO_TEXT_TOOL } from "./htmlTools.js";
  import { PDF_MERGE_TOOL, PDF_SPLIT_TOOL } from "./pdfTools.js";
  import { TEXT_DIFF_TOOL, TEXT_ENCODING_CONVERT_TOOL, TEXT_FORMAT_TOOL, TEXT_SPLIT_TOOL } from "./txtTools.js";
  
  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];
  
  export * from "./documentReader.js";
  export * from "./docxTools.js";
  export * from "./excelTools.js";
  export * from "./formatConverterPlus.js";
  export * from "./htmlTools.js";
  export * from "./pdfTools.js";
  export * from "./txtTools.js";

• src/index.ts:204-220 (registration)

  The request handler in src/index.ts that routes the 'html_extract_resources' tool call to the extractHtmlResources handler 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,
    };
  }