API OCR JavaScript Foinse Oscailte chun PDFanna Inbhreathnaithe a Chruthú

Suiteáil Scribe.js trí npm

 npm install scribe.js-ocr 

Is féidir leat é a shuiteáil de láimh freisin; íosluchtaigh na comhaid scaoilte is déanaí go díreach ón stór GitHub.

Conas Téacs a Bhaint ó Íomhá trí Leabharlann 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);
  });

Conas Cáipéisí PDF Inathraithe a Chruthú trí Leabharlann 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;
  }
}

Braite Téacs Chláir Casta trí JS

Le haghaidh íomhánna de cháipéisí le téacs dlúth agus le leagan amach casta (mar leathanach leabhair scanáilte nó easpórtáil PDF), cuireann leabharlann Scribe.js gné "Document Text Detection" ar fáil. Soláthraíonn sé seo eolas i bhfad níos saibhre, lena n-áirítear brathadóirí alt, focal, agus briseadh, a chabhraíonn le struchtúr na cáipéise bhunaidh a chaomhnú. Tá sé an-úsáideach do fheidhmchláir a bhfuil leagan amach agus struchtúr an mhainne ábhair tábhachtach, mar shampla próiseáil bhfoirmeacha, sonrasáin, nó leaganacha iolraí il-cholúnna.

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');
  });