Blank text file when Parsing a PDF to create a .txt file but works with command line

[jkomaragiri]

The code provided to create a text file produces a blank text file. The process to create a text file however works with running the command line argument. Here command line also produces the json and the text file.

let fs = require('fs'), PDFParser = require("./pdf2json/PDFParser");

let pdfParser = new PDFParser();

pdfParser.on("pdfParser_dataError", errData => console.error(errData.parserError) );
pdfParser.on("pdfParser_dataReady", pdfData => {
    fs.writeFile("./pdf2json/test/F1040EZ.content.txt", pdfParser.getRawTextContent());
});

pdfParser.loadPDF("./pdf2json/test/pdf/fd/form/F1040EZ.pdf");

my pdf file only contains text.

This has been also raised on the stackoverflow but no one has been able to resolve this.

Hope you can help.

Regards, Jai

[AshishGogna]

Having the same issue... getRawTextContent() outputs a blank string. Hope this is solved soon...

var PDFParser = require("pdf2json/pdfParser");

var pdfParser = new PDFParser();

pdfParser.on("pdfParser_dataError", errData => console.error(errData.parserError) );
pdfParser.on("pdfParser_dataReady", pdfData => {

    console.log("Raw - ");
    console.log(pdfParser.getRawTextContent());
});
pdfParser.loadPDF("./test3.pdf");

[xdvarpunen]

Having same issue here too.

var fs = require("fs");

// https://github.com/modesty/pdf2json
var PDFParser = require("./node_modules/pdf2json/PDFParser");
var pdfParser = new PDFParser();


pdfParser.on("pdfParser_dataError", errData => console.error(errData.parserError));
pdfParser.on("pdfParser_dataReady", pdfData => {
    //console.log(JSON.stringify(pdfData))
    // console.log(pdfParser)
    // console.log(pdfParser.pages)
    console.log(pdfParser.getRawTextContent())
    fs.writeFile("./content.txt", pdfParser.getRawTextContent());
    // fs.writeFile("./content.json", JSON.stringify(pdfData));
});

pdfParser.loadPDF("./asdf.pdf");

[xdvarpunen]

http://stackoverflow.com/questions/37757670/pdf2json-gives-me-a-blank-output-txt-file

[xdvarpunen]

In order to getRawTextContent pdf.js requires to set needRawText attribute truthy: https://github.com/modesty/pdf2json/blob/master/lib/pdf.js#L223

[xdvarpunen]

Okey guys, the frontpage documentation is a bit wrong! In order to make this work simply set to PDFParser parameters null and 1

[xdvarpunen]

This one works:

var fs = require("fs");

// https://github.com/modesty/pdf2json
var PDFParser = require("./node_modules/pdf2json/PDFParser");
var pdfParser = new PDFParser(this,1);

pdfParser.on("pdfParser_dataError", errData => console.error(errData.parserError));
pdfParser.on("pdfParser_dataReady", pdfData => {
    console.log(pdfParser)
    fs.writeFile("./content.txt", pdfParser.getRawTextContent());
});

HTH -XDVarpunen

[AshishGogna]

Thanks a lot @xdvarpunen !

[xdvarpunen]

Putting soon fix to pull request c:

-XDVarpunen

[xdvarpunen]

Answered Stackoverflow question too @jkomaragiri c:

[Fazila-A]

This code parses two pdf files and converts to rawtext and removes the line starting with 'Generated' and then compares those two text files.This method is called more than once sequentially and for each call the arguments to the method changes, but the raw content is not getting replaced for the last call.

function compareGeneratedReportContent(samplePDFFile, sampleXLSXText) {
    const pdfParser = new PDFParser(this, true)
    const pdfParser2 = new PDFParser(this, true)
    const pdfExportPath = path.join(__dirname, '../../resources/report-test/PDFExportedFile.pdf')
    const xlsxExportPath = path.join(__dirname, '../../resources/report-test/XLSXExportedFile.xlsx')
    let content1 = ''
    let content2 = ''
    let result = false

    pdfParser2.on('pdfParser_dataError', errData => console.log(errData))
    pdfParser2.on('pdfParser_dataReady', () => {
        content2 = pdfParser2.getRawTextContent().replace(/^.*(Generated).+$/mg, '')
        // console.log('content2 ', content2)
        fs.writeFileSync(path.join(__dirname, '../../resources/report-test/sample.txt'), content2, 'utf-8')
    })
    pdfParser2.loadPDF(path.join(__dirname, `../../resources/report-test/${samplePDFFile}.pdf`))

    pdfParser.on('pdfParser_dataError', errData => console.log(errData))
    pdfParser.on('pdfParser_dataReady', () => {
        content1 = pdfParser.getRawTextContent().replace(/^.*(Generated).+$/mg, '')
        // console.log('content1 ', content1)
        fs.writeFileSync(path.join(__dirname, '../../resources/report-test/generated.txt'), content2, 'utf-8')
    })
    pdfParser.loadPDF(pdfExportPath)

    let readContent2 = fs.readFileSync(path.join(__dirname, '../../resources/report-test/sample.txt'), 'utf-8')
    let readContent1 = fs.readFileSync(path.join(__dirname, '../../resources/report-test/generated.txt'), 'utf-8')
    if (readContent2 === readContent1) {
        console.log('Report pdf file content matches')
        result = true
    } else {
        console.log('Error in matching contents of report pdf')
        result = false
    }
}

Can anybody help? Regards, Fazi