pdf-decomposer/dist/extract/extractText.js

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

"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
const child_process_1 = require("child_process");
function extractTextFromPdf(pdfPath) {
    return new Promise((resolve, reject) => {
        const pdftotext = (0, child_process_1.spawn)('pdftotext', ['-layout', pdfPath, '-']);
        let output = '';
        pdftotext.stdout.on('data', (data) => {
            output += data.toString();
        });
        pdftotext.stderr.on('data', (data) => {
            console.error(`stderr: ${data}`);
        });
        pdftotext.on('close', (code) => {
            if (code === 0)
                resolve(output);
            else
                reject(new Error(`pdftotext exited with code ${code}`));
        });
    });
}
// Exemple d’utilisation
extractTextFromPdf('sample.pdf').then(console.log);