String html = "<html><head><title>Example</title></head><body>Hello, world!</body></html>"; Source source = new Source(html); String title = source.getFirstElement("title").getContent().getTextExtractor().toString(); System.out.println("Title: " + title); String html = "<p>This is <script>alert('danger!')</script> a <em>clean</em> paragraph.</p>"; Source source = new Source(html); source.fullSequentialParse(); List<Element> elementsToRemove = source.getAllElements(StartTagType.SCRIPT); for (Element element : elementsToRemove) { element.removeFromTree(); } String filteredHtml = source.toString(); System.out.println("Filtered HTML: " + filteredHtml); String title = "Example"; String content = "Hello, world!"; OutputDocument outputDocument = new OutputDocument(); outputDocument.insert(new Element(Tag.valueOf("html")), "<html>"); outputDocument.insert(new Element(Tag.valueOf("head")), "<head>"); outputDocument.insert(new Element(Tag.valueOf("title")), "<title>" + title + "</title>"); outputDocument.insert(new Element(Tag.valueOf("body")), "<body>"); outputDocument.insert(outputDocument.getBody(), content); String generatedHtml = outputDocument.toString(); System.out.println("Generated HTML: " + generatedHtml);


上一篇:
下一篇:
切换中文