pdf-decomposer/dist/extract/extractImages.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 });
const child_process_1 = require("child_process");
const fs_1 = __importDefault(require("fs"));
function extractImages(pdfPath, outputPrefix = 'img') {
    return new Promise((resolve, reject) => {
        const pdfimages = (0, child_process_1.spawn)('pdfimages', ['-all', pdfPath, outputPrefix]);
        pdfimages.on('close', (code) => {
            if (code === 0) {
                const files = fs_1.default
                    .readdirSync('.')
                    .filter((f) => f.startsWith(outputPrefix));
                resolve(files);
            }
            else {
                reject(new Error(`pdfimages exited with code ${code}`));
            }
        });
        pdfimages.stderr.on('data', (data) => {
            console.error(`stderr: ${data}`);
        });
    });
}
// Exemple d’utilisation
extractImages('sample.pdf').then(console.log);