Video And Audio Metadata Text Extractor Tool

async function processImage(originalImg, language = 'eng') {
    const container = document.createElement('div');
    container.style.width = '100%';
    container.style.minHeight = '120px';
    container.style.padding = '20px';
    container.style.fontFamily = '"Courier New", Courier, monospace';
    container.style.fontSize = '14px';
    container.style.backgroundColor = '#f9f9f9';
    container.style.border = '1px solid #ccc';
    container.style.borderRadius = '5px';
    container.style.whiteSpace = 'pre-wrap';
    container.style.wordBreak = 'break-word';
    container.style.color = '#333';
    container.style.boxSizing = 'border-box';
    container.innerText = 'Loading OCR Engine...\nPlease wait.';

    const canvas = document.createElement('canvas');
    canvas.width = originalImg.width;
    canvas.height = originalImg.height;
    const ctx = canvas.getContext('2d');
    ctx.drawImage(originalImg, 0, 0);

    const startOCR = async () => {
        try {
            if (typeof Tesseract === 'undefined') {
                await new Promise((resolve, reject) => {
                    const script = document.createElement('script');
                    script.src = 'https://cdn.jsdelivr.net/npm/tesseract.js@4.1.1/dist/tesseract.min.js';
                    script.onload = resolve;
                    script.onerror = () => reject(new Error('Failed to load Tesseract.js script.'));
                    document.head.appendChild(script);
                });
            }

            const result = await Tesseract.recognize(canvas, language, {
                logger: m => {
                    if (m.status === 'recognizing text') {
                        container.innerText = `Recognizing text... ${Math.round(m.progress * 100)}%`;
                    } else {
                        // Capitalize first letter of status for prettier logging
                        const statusText = m.status.charAt(0).toUpperCase() + m.status.slice(1);
                        container.innerText = `${statusText}...`;
                    }
                }
            });

            const text = result.data.text.trim();
            if (text) {
                // Sanitize and display extracted text
                const escapedText = text.replace(/&/g, "&amp;").replace(/</g, "&lt;").replace(/>/g, "&gt;");
                container.innerHTML = `<strong style="color: #0056b3;">Extracted Metadata Text:</strong><br><br>${escapedText}`;
            } else {
                container.innerHTML = '<strong>Result:</strong><br>No readable text could be extracted from this image.';
            }
        } catch (error) {
            container.innerHTML = `<strong style="color: red;">Error during text extraction:</strong><br>${error.message}`;
        }
    };

    // Initialize extraction process asynchronously
    startOCR();

    return container;
}