API OCR JavaScript Sumber Terbuka untuk Mencipta PDF Boleh Dicari

Pasang Scribe.js melalui npm

 npm install scribe.js-ocr 

Anda juga boleh memasangnya secara manual; muat turun fail keluaran terkini secara langsung dari repositori GitHub.

Bagaimana untuk Mengekstrak Teks daripada Imej melalui Perpustakaan JavaScript?

import scribe from 'scribe.js-ocr';

// Extract text from a single image
scribe.extractText(['https://example.com/sample-image.png'])
  .then((result) => {
    console.log('Extracted text:', result);
  })
  .catch((error) => {
    console.error('OCR failed:', error);
  });

Bagaimana untuk Membuat Dokumen PDF Boleh Carian melalui Perpustakaan JavaScript?

import scribe from 'scribe.js-ocr';

// Add searchable text layer to an image-based PDF
async function makeSearchablePDF(inputPdfUrl) {
  try {
    // First, perform OCR on the PDF
    const ocrResult = await scribe.extractText([inputPdfUrl]);
    
    // Then create a new PDF with the text layer embedded
    const searchablePdf = await scribe.createSearchablePDF(
      inputPdfUrl,
      ocrResult
    );
    
    // The resulting PDF maintains the original appearance
    // but now contains selectable, searchable text
    return searchablePdf;
  } catch (error) {
    console.error('Failed to create searchable PDF:', error);
    throw error;
  }
}

Pengesanan Teks Dokumen Lanjutan melalui JS

Untuk imej dokumen dengan teks padat dan susun atur yang kompleks (seperti halaman buku yang diimbas atau eksport PDF), perpustakaan Scribe.js menawarkan ciri "Document Text Detection". Ini menyediakan maklumat yang jauh lebih kaya, termasuk pengesan perenggan, perkataan, dan jeda, yang membantu mengekalkan struktur dokumen asal. Ia sangat berguna untuk aplikasi di mana susun atur dan struktur bahan sumber penting, seperti memproses borang, invois, atau susun atur berbilang lajur.

const Scribe = require('scribejs');
const serviceAccountKey = require('./path-to-your-key.json');
const scribe = new Scribe(serviceAccountKey);

const documentImageUrl = 'https://example.com/scanned-invoice.png';

// Use the `documentText` method for advanced detection
scribe.documentText(documentImageUrl)
  .then(fullTextAnnotation => {
    // The fullTextAnnotation object contains detailed data
    console.log('Full Document Text:');
    console.log(fullTextAnnotation.text); // The plain text of the entire document

    // You can also iterate through pages, blocks, paragraphs, and words
    fullTextAnnotation.pages.forEach(page => {
      page.blocks.forEach(block => {
        console.log('\nBlock Confidence:', block.confidence);
        block.paragraphs.forEach(paragraph => {
          console.log(paragraph.text);
        });
      });
    });
  })
  .catch(error => {
    console.error('Document OCR Error:', error);
  });

import scribe from 'scribe.js-ocr';

// Process multiple documents at once
async function batchProcess(fileUrls) {
  try {
    // Pass an array of URLs to process multiple files
    const results = await scribe.extractText(fileUrls);
    
    // Results are returned in the same order as input
    results.forEach((text, index) => {
      console.log(`Document ${index + 1} text:`, text);
    });
    
    return results;
  } catch (error) {
    console.error('Batch processing failed:', error);
    throw error;
  }
}

// Process a batch of documents
const documents = [
  'https://example.com/receipt1.jpg',
  'https://example.com/receipt2.jpg',
  'https://example.com/invoice.pdf'
];

batchProcess(documents)
  .then(allText => {
    console.log('All documents processed successfully');
  });