n8n-nodes-mammoth/index.js

n8n node to extract text from DOCX using mammoth

const mammoth = require("mammoth");

module.exports = {
  nodes: [
    {
      name: "MammothDocxExtract",
      displayName: "DOCX Extract",
      description: "Extract text from a DOCX file using mammoth",
      group: ["transform"],
      version: 1,
      inputs: ["main"],
      outputs: ["main"],
      properties: [
        {
          displayName: "Binary Property",
          name: "binaryPropertyName",
          type: "string",
          default: "data",
          description: "Name of the binary property which contains the DOCX file",
        },
      ],
      async execute() {
        const items = this.getInputData();
        const returnData = [];

        for (let i = 0; i < items.length; i++) {
          const item = items[i];

          if (!item.binary) {
            throw new Error("No binary data found on input item.");
          }

          const binaryPropertyName = this.getNodeParameter("binaryPropertyName", i);
          const binaryData = item.binary[binaryPropertyName];

          if (!binaryData) {
            throw new Error(Binary property "${binaryPropertyName}" does not exist.);
          }

          const buffer = Buffer.from(binaryData.data, "base64");

          const result = await mammoth.extractRawText({ buffer });

          returnData.push({
            json: { text: result.value },
          });
        }

        return this.prepareOutputData(returnData);
      },
    },
  ],
};