HTML File Parsing using XPATH

The javax.xml parsers DO NOT work as it takes ONLY WELL formatted xml file. Use Selenium and open local html file in driver.get("file:///d:/somefile.html") and use the normal driver.findElement(By.xpath) etc., Use HtmlUnitDriver so that no browser is opened visually. Sample CODE import org.openqa.selenium.By; import org.openqa.selenium.WebElement; import org.openqa.selenium.htmlunit.HtmlUnitDriver; import java.io.BufferedWriter; import java.io.File; import java.io.FileWriter; import java.util.List; import java.util.concurrent.TimeUnit; public class Main { public static void main(String... args) { HtmlUnitDriver driver; try { driver = new HtmlUnitDriver(); driver.manage().timeouts().pageLoadTimeout(10000, TimeUnit.MILLISECONDS); driver.get("file:///" + "c:/localfile.html"); List storiesPassed = driver.findElements(By.xpath("//td[@class='story successful']")); List storiesFailed = driver.findElements(By.xpath("//td[@class='story failed']")); System.out.println( "H3 " + driver.findElement(By.tagName("h3")).getText()); System.out.println(); createHtmlBody(sBuffer, storiesPassed ); createHtmlBody(sBuffer, storiesFailed ); sBuffer.append(HtmlEnd); bw.write(sBuffer.toString()); bw.flush(); bw.close(); }catch(Exception e){ e.printStackTrace(); } } }