pdf-decomposer/dist/pdfParser.js

📚 Extract text and images (as buffers) from PDF files using native parsing and OCR with Tesseract.

"use strict";
var __importDefault = (this && this.__importDefault) || function (mod) {
    return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.extractFromPDF = extractFromPDF;
const os_1 = __importDefault(require("os"));
const path_1 = __importDefault(require("path"));
const fs_1 = __importDefault(require("fs"));
const crypto_1 = require("crypto");
const pdfToPng_1 = require("./pdfToPng");
/**
 * Extract all from pdf
 * @param buffer file buffer
 */
async function extractFromPDF(buffer) {
    // Work in temp folder
    const tmpDir = path_1.default.join(os_1.default.tmpdir(), 'pdf-decomposer');
    // Clean old parsing
    if (fs_1.default.existsSync(tmpDir)) {
        fs_1.default.rmSync(tmpDir, { recursive: true });
    }
    fs_1.default.mkdirSync(tmpDir);
    const tmpFilePath = path_1.default.join(tmpDir, `${(0, crypto_1.randomUUID)()}.pdf`);
    fs_1.default.writeFileSync(tmpFilePath, buffer);
    const pages = await (0, pdfToPng_1.pdfToPng)(tmpFilePath);
    console.log(`Successfully convert ${pages.length} pdf pages`);
}