Read PDF file using Selenium Webdriver

Download pdfbox and fontbox jars from https://pdfbox.apache.org/download.cgi
To read pdf file and verify the content is present in the pdf using.

import java.io.BufferedInputStream; import java.io.IOException; import java.net.URL;


import org.apache.pdfbox.pdfparser.PDFParser;

import org.apache.pdfbox.util.PDFTextStripper;

import org.openqa.selenium.WebDriver;

import org.openqa.selenium.firefox.FirefoxDriver;

import org.testng.annotations.Test;
public class PdfRead {

	WebDriver driver = new FirefoxDriver();
	public void verifyPdfContent(String[] values) throws IOException {
		URL url = new URL(driver.getCurrentUrl());

		BufferedInputStream inputPdfFile = new BufferedInputStream(

				url.openStream());

		PDFParser pdfParser = new PDFParser(inputPdfFile);

		pdfParser.parse();

		String pdfContent = new PDFTextStripper().getText(pdfParser

				.getPDDocument());

		// pdfParser.getPDDocument().close();

		System.out.println("printing PDF content fully :" + pdfContent);

		for (int i = 0; i < values.length; i++) {

			if (pdfContent.contains(values[i])) {

				System.out.println((values[i] + " is present in the PDF file"));
			} else {

				System.out

						.println((values[i] + " is not present in the PDF file"));
			}

		}

	}
	@Test

	public void myTest() throws IOException {

		driver.get("http://partners.adobe.com/public/developer/en/acrobat/PDFOpenParameters.pdf");

		// Values to verify

		String[] values = new String[2];

		values[0] = "xxxcsds";

		values[1] = "hey";

		// verifying the pdf with given values

		verifyPdfContent(values);
	}
}

No images available.