firecrawl/apps/api/src/scraper/scrapeURL/engines/docx/index.ts

import { Meta } from "../..";
import { EngineScrapeResult } from "..";
import { downloadFile } from "../utils/downloadFile";
import mammoth from "mammoth";

export async function scrapeDOCX(meta: Meta): Promise<EngineScrapeResult> {
    const { response, tempFilePath } = await downloadFile(meta.id, meta.url);

    return {
        url: response.url,
        statusCode: response.status,

        html: (await mammoth.convertToHtml({ path: tempFilePath })).value,
    }
}