pdf2json example using Node VM

pdf2json.js

const https = require('node:https');
const PDFParser = require('pdf2json');
const url = require('node:url');

const PDF_URL = 'https://ontheline.trincoll.edu/images/bookdown/sample-local-pdf.pdf';

const parsedUrl = url.parse(PDF_URL);
const options = {
  hostname: parsedUrl.hostname,
  port: parsedUrl.port || 443,
  path: parsedUrl.pathname,
  method: 'GET'
};

console.log(options);

const chunks = [];

const request = https.request(options, (response) => {
  response.on('data', (chunk) => {
    chunks.push(chunk);
  });

  response.on('end', async () => {
    const buffer = Buffer.concat(chunks);
    console.log(buffer.length);
    
    // Create PDFParser instance
    const pdfParser = new PDFParser();
    
    // Set up event handlers
    pdfParser.on('pdfParser_dataError', errData => {
      console.error('PDF parsing error:', errData.parserError);
    });
    
    pdfParser.on('pdfParser_dataReady', pdfData => {
      console.log('PDF parsed successfully');
      // Access text content with: pdfParser.getRawTextContent()
    });
    
    // Parse the buffer - you'll need to write it to a temp file first
    // or use an alternative approach
    const fs = require('fs');
    const tempFile = './temp.pdf';
    fs.writeFileSync(tempFile, buffer);
    pdfParser.loadPDF(tempFile);
    
    // Clean up temp file after parsing
    setTimeout(() => {
      fs.unlinkSync(tempFile);
    }, 1000);
  });
});

request.on('error', (error) => {
  console.error('Request error:', error);
});

request.end();