Created
February 22, 2014 05:46
-
-
Save alexandrevicenzi/9149274 to your computer and use it in GitHub Desktop.
Plain text PDF with pdf.js
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <!doctype html> | |
| <html> | |
| <head> | |
| <script src="http://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script> | |
| <script src="http://mozilla.github.io/pdf.js/build/pdf.js"></script> | |
| <script> | |
| function pdfToPlainText(pdfData) { | |
| PDFJS.disableWorker = true; | |
| var pdf = PDFJS.getDocument(pdfData); | |
| pdf.then(getPages); | |
| } | |
| function getPages(pdf) { | |
| for (var i = 0; i < pdf.numPages; i++) { | |
| pdf.getPage(i + 1).then(getPageText); | |
| } | |
| } | |
| function getPageText(page) { | |
| page.getTextContent().then(function(textContent) { | |
| textContent.forEach(function(o) { | |
| $("#pdf").append(o.str + '</br>'); | |
| }); | |
| }); | |
| } | |
| </script> | |
| </head> | |
| <body onload="pdfToPlainText('TestDocument.pdf')"> | |
| <h1>Plain Text PDF with pdf.js</h1> | |
| </br> | |
| <div id="pdf"></div> | |
| </body> | |
| </html> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment