Extract text from pdf file using javascript [duplicate]

Answer 1

I've made an easier approach that doesn't need to post messages between iframes using the same library (using the latest version), using pdf.js.

The following example would extract all the text only from the first page of the PDF:

/**
 * Retrieves the text of a specif page within a PDF Document obtained through pdf.js 
 * 
 * @param {Integer} pageNum Specifies the number of the page 
 * @param {PDFDocument} PDFDocumentInstance The PDF document obtained 
 **/
function getPageText(pageNum, PDFDocumentInstance) {
    // Return a Promise that is solved once the text of the page is retrieven
    return new Promise(function (resolve, reject) {
        PDFDocumentInstance.getPage(pageNum).then(function (pdfPage) {
            // The main trick to obtain the text of the PDF page, use the getTextContent method
            pdfPage.getTextContent().then(function (textContent) {
                var textItems = textContent.items;
                var finalString = "";

                // Concatenate the string of the item to the final string
                for (var i = 0; i < textItems.length; i++) {
                    var item = textItems[i];

                    finalString += item.str + " ";
                }

                // Solve promise with the text retrieven from the page
                resolve(finalString);
            });
        });
    });
}

/**
 * Extract the test from the PDF
 */

var PDF_URL  = '/path/to/example.pdf';
PDFJS.getDocument(PDF_URL).then(function (PDFDocumentInstance) {

    var totalPages = PDFDocumentInstance.pdfInfo.numPages;
    var pageNumber = 1;

    // Extract the text
    getPageText(pageNumber , PDFDocumentInstance).then(function(textPage){
        // Show the text of the page in the console
        console.log(textPage);
    });

}, function (reason) {
    // PDF loading error
    console.error(reason);
});

Read the article about this solution here. As @xarxziux mentioned, the library has changed since the first solution was posted (it shouldn't work with the latest version of pdf.js anymore). This should work for most of the cases.