import java.io.*; import net.htmlparser.jericho.*; public class HTMLParserExample { public static void main(String[] args) throws IOException { String fileName = "example.html"; String source = new String(Files.readAllBytes(Paths.get(fileName))); Source htmlSource = new Source(source); Element titleElement = htmlSource.getFirstElement(HTMLElementName.TITLE); String title = titleElement.getTextExtractor().toString(); StringBuilder content = new StringBuilder(); for (Element element : htmlSource.getAllElementsByClass("content")) { content.append(element.getTextExtractor().toString()).append(" "); } " + content); } }


上一篇:
下一篇:
切换中文