pdf-decomposer/dist/pdfToPng.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.pdfToPng = pdfToPng;
const child_process_1 = require("child_process");
const crypto_1 = require("crypto");
const fs_1 = __importDefault(require("fs"));
const path_1 = __importDefault(require("path"));
/**
 * Convert each pdf page into pdf
 * @param pdfPath path to pdf file
 * @returns png buffers
 */
function pdfToPng(pdfPath) {
    const tmpDir = path_1.default.join(path_1.default.dirname(pdfPath), (0, crypto_1.randomUUID)());
    if (!fs_1.default.existsSync(tmpDir)) {
        fs_1.default.mkdirSync(tmpDir);
    }
    return new Promise((resolve, reject) => {
        const proc = (0, child_process_1.spawn)('pdftoppm', [
            '-png',
            pdfPath,
            path_1.default.join(tmpDir, 'page'),
        ]);
        proc.on('close', (code) => {
            if (code === 0) {
                resolve(fs_1.default.readdirSync(tmpDir).map((f) => fs_1.default.readFileSync(`${tmpDir}/${f}`)));
            }
            else {
                reject(new Error(`pdftoppm exited with code ${code}`));
            }
        });
        proc.stderr.on('data', (err) => {
            throw new Error(`Fail to parse pdf ${err.toString()}`);
        });
    });
}