Java HTML API para Crear, Editar y Convertir Archivos HTML

Agregar Aspose.HTML como dependencia de Maven para Java

<dependencia>
  <groupId>com.aspose</groupId>
  <artifactId>aspose-html</artifactId>
  <version>20.9.1</version>
   jdk16
</dependencia>

Puede descargar la biblioteca directamente desde la página del producto Aspose.HTML para Java

Convertir archivo HTML a PDF usando la API de Java

// Load HTML document
HTMLDocument document = new HTMLDocument("template.html");

// Convert HTML to PDF
Converter.convertHTML(document, new PdfSaveOptions(), "output.pdf");   

Crear un Documento HTML Vacío a través de la API de Java

// Initialize an empty HTML Document
com.aspose.html.HTMLDocument document = new com.aspose.html.HTMLDocument();
try {
    // Save the HTML document to a disk
    document.save("create-empty-document.html");
} finally {
    if (document != null) {
        document.dispose();
    }
}

Renderizado y Extracción de HTML usando la API de Java

import com.aspose.html.dom.Document;
import com.aspose.html.rendering.HtmlRenderer;
import com.aspose.html.rendering.pdf.PdfDevice;
import com.aspose.html.rendering.pdf.PdfRenderingOptions;

public class HtmlRenderingExample {
    public static void main(String[] args) {
        // Load the HTML document
        Document document = new Document("input.html");

        // Render HTML to PDF
        PdfRenderingOptions options = new PdfRenderingOptions();
        options.getPageSetup().setAnyPage(new com.aspose.html.drawing.Page(new com.aspose.html.drawing.Size(800, 600)));
        PdfDevice device = new PdfDevice("output.pdf");
        HtmlRenderer renderer = new HtmlRenderer();
        renderer.render(device, document, options);

        System.out.println("HTML rendered to PDF successfully!");

        // Extract HTML content
        String htmlContent = document.getBody().getInnerHTML();
        System.out.println("Extracted HTML content:\n" + htmlContent);
    }
}

Realizar el análisis de documentos HTML utilizando la API de Java

import com.aspose.html.HTMLDocument;
import com.aspose.html.IHTMLDocument;
import com.aspose.html.IHTMLHtmlElement;

public class HTMLParsingExample {
    public static void main(String[] args) {
        // Load the HTML document
        HTMLDocument document = new HTMLDocument("input.html");

        // Access the root HTML element
        IHTMLHtmlElement rootElement = document.getRootElement();

        // Print the inner text of the body element
        System.out.println("Body content:");
        System.out.println(rootElement.getBody().getTextContent());

        // Access and print the values of specific elements
        System.out.println("Links:");
        document.querySelectorAll("a").forEach(element -> {
            System.out.println("URL: " + element.getAttribute("href"));
            System.out.println("Text: " + element.getTextContent());
        });

        // Manipulate the document structure
        IHTMLHtmlElement newElement = document.createElement("div");
        newElement.setTextContent("This is a new element");
        rootElement.appendChild(newElement);

        // Save the modified document
        document.save("output.html");
    }
}