.gitignore

.idea

README.md

experiments using pdf parsers

https://www.npmjs.com/package/pdf2json https://www.npmjs.com/package/pdf-parse https://www.pdfparser.org/demo

pdf2json provides good text extraction + the positioning

main.js

const fs = require('fs');
const pdf = require('pdf-parse');

const filename = '/media/hassen/linux-tmp/web_dld/spiro.pdf'

const PDFParser = require("pdf2json");

function t4()
{
  

  let pdfParser = new PDFParser(this, 1);

  pdfParser.on("pdfParser_dataError", errData => console.error(errData.parserError));
  pdfParser.on("pdfParser_dataReady", pdfData => {
    fs.writeFileSync('/tmp/gg.txt', pdfParser.getRawTextContent())
  });

  pdfParser.loadPDF(filename);
// let txt =   pdfParser.getRawTextContent(filename)
//   console.log(txt)
  // getRawTextContent
}
function t3()
{


  let pdfParser = new PDFParser();

  pdfParser.on("pdfParser_dataError", errData => console.error(errData.parserError));
  pdfParser.on("pdfParser_dataReady", pdfData => {
    console.log(JSON.stringify(pdfData))
    fs.writeFileSync('/tmp/gg.json', JSON.stringify(pdfData))
    // console.log(pdfData.formImage.Pages)
    // fs.writeFile("/tmp/gg.json", JSON.stringify(pdfData));
  });

  pdfParser.loadPDF(filename);

}

function t2()
{

  // default render callback
  function render_page(pageData)
  {
    //check documents https://mozilla.github.io/pdf.js/
    let render_options = {
      //replaces all occurrences of whitespace with standard spaces (0x20). The default value is `false`.
      normalizeWhitespace:     false,
      //do not attempt to combine same line TextItem's. The default value is `false`.
      disableCombineTextItems: false
    }

    return pageData.getTextContent(render_options)
      .then(function(textContent){
        let lastY, text = '';
        for(let item of textContent.items)
        {
          if(lastY == item.transform[5] || !lastY)
          {
            text += item.str;
          }
          else
          {
            text += '\n' + item.str;
          }
          lastY = item.transform[5];
        }
        return text;
      });
  }

  let options = {
    pagerender: render_page
  }

  let dataBuffer = fs.readFileSync(filename);

  pdf(dataBuffer, options).then(function(data){
    //use new format
    console.log(data, data.text)
  });
}

function t1()
{


  let dataBuffer = fs.readFileSync(filename);

  pdf(dataBuffer).then(function(data){

    // number of pages
    console.log(data.numpages);
    // number of rendered pages
    console.log(data.numrender);
    // PDF info
    console.log(data.info);
    // PDF metadata
    console.log(data.metadata);
    // PDF.js version
    // check https://mozilla.github.io/pdf.js/getting_started/
    console.log(data.version);
    // PDF text
    console.log(data.text);

  });
}

// t1()
// t2()
// t3()
t4()