Java DomNode类代码示例

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
/**
 * Echo's the content of the current page to stdout. All empty lines will be
 * removed and separator containing of dashed will be inserted before and
 * after. This abuses the fact that all STiNE pages use a div element with
 * the id pageContent.
 */
public void showPageContent() {
    DomNode context = (DomNode) this.page.getElementById("pageContent");
    if (context == null) {
        context = this.page;
    }

    // This removes all the empty lines from the page's content and acquires
    // the result.
    String pageContent = Arrays.stream(context.asText().replaceAll("\\r\\n?", "\n").split("\n"))
            .filter(line -> !line.matches("\\p{Z}*")).collect(Collectors.joining("\n"));

    // This creates a 50 chars long sequence of dashes
    String horzLine = new String(new char[50]).replace("\0", "-");

    System.out.println(horzLine);
    System.out.println(pageContent);
    System.out.println(horzLine);
}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
/**
 * {@inheritDoc}
 */
@Override
public boolean test(Context context)
{
	LoggerFactory.getLogger(MatchesPath.class).debug("Testing condition: " + this);
	DomNode element = context.getXPathProcessor().getSingleElementOfType(Util.getCurrentPage(context), Util.replacePlaceholders(path, context), DomNode.class);
	String elementValue = (element instanceof DomAttr) ? element.getNodeValue() : element.asText();
	return elementValue.matches(regex);
}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
/**
 * Retrieves a single element from a {@link DomNode} by a given XPath expression.
 * If exactly one object of the expected type is returned, this method returns the cast object.
 * An exception is thrown if no object is found, more than one object is found or the object found is not of a subtype of {@code T}.
 *
 * @param node       DomNode from which the element is retrieved.
 * @param expression XPath expression.
 * @param type       Class of expected type of returned object.
 * @param <T>        Expected type of returned object.
 * @return Retrieved object cast into type {@code T}.
 */
public <T> T getSingleElementOfType(DomNode node, String expression, Class<T> type)
{
	List<?> elements = node.getByXPath(expression);
	if(elements.size() == 0)
		throw new RuntimeException("No element has been found for expression " + expression);
	else if(elements.size() > 1)
		throw new RuntimeException("Expecting exactly one element but " + elements.size() + " have been found for expression " + expression);
	else if(!(type.isInstance(elements.get(0))))
		throw new RuntimeException("Element for expression " + expression + " is not of type " + type.getName());

	LoggerFactory.getLogger(XPathProcessor.class).debug("Found 1 element matching XPath expression " + expression);
	return (T)elements.get(0);
}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
/**
 * Retrieves elements from a {@link DomNode} by a given XPath expression.
 * If all objects are of a type compatible with {@code T}, this method returns a {@code List<T>}.
 * An exception is thrown if at least one of the retrieved objects is not of a subtype of {@code T}.
 *
 * @param node       DomNode from which the elements are retrieved.
 * @param expression XPath expression.
 * @param type       Class of expected type of returned object.
 * @param <T>        Expected type of returned object.
 * @return List of objects cast into type {@code T}.
 */
public <T> List<T> getElementsOfType(DomNode node, String expression, Class<T> type)
{
	List<T> result = new ArrayList<>();
	node.getByXPath(expression).forEach(element ->
	{
		if(!(type.isInstance(element)))
			throw new RuntimeException("Elements for expression " + expression + " are not of type " + type.getName());
		result.add((T)element);
	});

	LoggerFactory.getLogger(XPathProcessor.class).debug("Found " + result.size() + " " + (result.size() == 1 ? "element" : "elements") + " matching XPath expression " + expression);
	return result;
}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
/**
 * {@inheritDoc}
 */
@Override
public void execute(Context context)
{
	LoggerFactory.getLogger(AddToListPath.class).debug("Executing action: " + this);
	List<DomNode> elements = context.getXPathProcessor().getElementsOfType(Util.getCurrentPage(context), Util.replacePlaceholders(path, context), DomNode.class);
	elements.forEach(element -> context.addToList(listName, (element instanceof DomAttr) ? element.getNodeValue().trim() : element.asText().trim()));
}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
/**
 * {@inheritDoc}
 */
@Override
public void execute(Context context)
{
	LoggerFactory.getLogger(SetVariablePath.class).debug("Executing action: " + this);
	DomNode element = context.getXPathProcessor().getSingleElementOfType(Util.getCurrentPage(context), Util.replacePlaceholders(path, context), DomNode.class);
	context.setVariable(variableName, (element instanceof DomAttr) ? element.getNodeValue() : element.asText());
}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
/**
 * {@inheritDoc}
 */
@Override
public void execute(Context context)
{
	LoggerFactory.getLogger(AddToMap.class).debug("Executing action: " + this);
	List<DomNode> keyElements = context.getXPathProcessor().getElementsOfType(Util.getCurrentPage(context), Util.replacePlaceholders(keyPath, context), DomNode.class);
	List<DomNode> valueElements = context.getXPathProcessor().getElementsOfType(Util.getCurrentPage(context), Util.replacePlaceholders(valuePath, context), DomNode.class);

	if(keyElements.size() != valueElements.size())
		throw new RuntimeException("Number of keys and values does not match for key expression " + Util.replacePlaceholders(keyPath, context) + " and value expression " + Util.replacePlaceholders(valuePath, context));

	for(int i = 0; i < keyElements.size(); i++)
		context.addToMap(mapName, (keyElements.get(i) instanceof DomAttr) ? keyElements.get(i).getNodeValue() : keyElements.get(i).asText(), (valueElements.get(i) instanceof DomAttr) ? valueElements.get(i).getNodeValue() : valueElements.get(i).asText());
}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
private Set<DomNode> getAllDomNodes(HtmlPage page) {
	Set<DomNode> ret = new HashSet<>();
	Iterable<DomNode> topLevelChildren = page.getBody().getChildren();
	for (DomNode n : topLevelChildren) {
		ret.addAll(recursiveGetChildren(n));
	}
	return ret;
}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
private Collection<? extends DomNode> recursiveGetChildren(DomNode n) {
	Set<DomNode> ret = new HashSet<>();
	if (n != null) {
		ret.add(n);
		Iterable<DomNode> children = n.getChildren();
		for (DomNode c : children) {
			ret.addAll(recursiveGetChildren(c));
		}
	}
	return ret;
}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
private void getEditedList() throws FailingHttpStatusCodeException, MalformedURLException, IOException
{
	List<String> articleListContributed=getEditedLinks();
	WebClient browser=new WebClient(BrowserVersion.CHROME);
	browser.getOptions().setJavaScriptEnabled(false);
	browser.getOptions().setThrowExceptionOnFailingStatusCode(false);
	browser.getOptions().setThrowExceptionOnScriptError(false);
	String wikiURL="https://en.wikipedia.org/w/index.php?title=";
	for(String s:articleListContributed)
	{//*[@id="pagehistory"]/li[2]
		String finalURL=wikiURL+s.replaceAll(" ", "_")+"&action=history";
		//System.out.println(finalURL);
		HtmlPage rawpage= browser.getPage(wikiURL+s.replaceAll(" ", "_")+"&action=history");
		@SuppressWarnings("unchecked")
		List<DomNode> totalEditsUsers =(List<DomNode>) rawpage.getByXPath("//span[@class='history-user']");
		//System.out.println(getFirstEditIndex(totalEditsUsers));
		@SuppressWarnings("unchecked")
		List<DomNode> sizeArticles = (List<DomNode>) rawpage.getByXPath("//span[@class='history-size']");
		int currentSize=getContentSize(sizeArticles,0);
		int beforeEditSize=getContentSize(sizeArticles, getFirstEditIndex(totalEditsUsers)+1);
		//System.out.println("Change in Size:"+(currentSize-beforeEditSize));
		int changeInSize=(currentSize-beforeEditSize);
		System.out.println(finalURL+"||"+changeInSize+"||"+getFirstEditIndex(totalEditsUsers));
	}


}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
private static int getContentSize(List<DomNode> sizeArticles, int index)
{
	int i=0;
	String sizeInBytes=sizeArticles.get(index).getChildNodes().get(0).asText();
	Pattern pattern = Pattern.compile("\\((.*?) bytes");	
	//System.out.println(sizeInBytes);
	Matcher m=pattern.matcher(sizeInBytes);
	if(m.find())
	{
		String bytes=m.group(1).replaceAll(",","");
		i=Integer.parseInt(bytes);
	}
	return i;
}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
private static int getFirstEditIndex(List<DomNode> totalEditsUsers)
{
	int i=0;
	for(DomNode d:totalEditsUsers)
	{
		String collaboratorName=d.getChildNodes().get(0).asText();
		if(collaboratorName.contentEquals(wikiUserName))
		{
			i=totalEditsUsers.indexOf(d);
		}
		
	}
	return i;
	
}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
@SuppressWarnings("unchecked")
public void test() throws Exception {
  String pageName = uniqueWikiPageName("HistoryTest");
  HtmlPage page = editWikiPage(pageName, "Initial content", "", "", true);
  page = editWikiPage(pageName, "Altered content", "", "s/Initial/Altered", false);
  HtmlPage history = clickHistoryLink(page);
  List<HtmlTableRow> historyRows = (List<HtmlTableRow>) history.getByXPath("//tr[td]");
  assertEquals(3, historyRows.size());
  HtmlTableRow altered = historyRows.get(1);
  // First column is date/time.
  verifyRow(altered, "s/Initial/Altered");
  HtmlTableRow initial = historyRows.get(2);
  verifyRow(initial, "None");

  final List<HtmlSubmitInput> compareButtons = (List<HtmlSubmitInput>) history.getByXPath("//input[@type='submit' and @value='Compare']/.");
  assertEquals(1, compareButtons.size());
  HtmlPage diff = (HtmlPage) compareButtons.get(0).click();
  assertEquals("Altered", ((DomNode) diff.getByXPath("//ins").iterator().next()).asText());
  assertEquals("Initial", ((DomNode) diff.getByXPath("//del").iterator().next()).asText());
  List<HtmlDivision> divs = (List<HtmlDivision>) diff.getByXPath("//div[@id='flash']/.");
  assertEquals(0, divs.size());

  // Check for the warning when viewing differences backwards
  final List<HtmlRadioButtonInput> radioButtons = (List<HtmlRadioButtonInput>) history.getByXPath("//input[@type='radio']/.");
  assertEquals(4, radioButtons.size());
  radioButtons.get(0).click();
  radioButtons.get(3).click();
  diff = (HtmlPage) compareButtons.get(0).click();
  divs = (List<HtmlDivision>) diff.getByXPath("//div[@id='flash']/.");
  assertEquals(1, divs.size());

}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
private void mineHackerNews(String url, int numPages) {
    HtmlPage page = null;
    String nextUrl = url;
    while (numPages-- > 0) {
        try {
            page = wc.getPage(nextUrl);
        } catch (IOException e) {
            logger.error("Unable to fetch page {}:", nextUrl, e);
        }
        List<?> nodes = page.getByXPath("//table//table[position()==1]");
        DomNode d = (DomNode)nodes.get(0);
        logger.info(d.getTextContent());
    }
}
 

import com.gargoylesoftware.htmlunit.html.DomNode; //导入依赖的package包/类
private String extractContent(final String endUrl, final String xpath) throws IOException {
    final String url = base.toExternalForm() + "jbatch/" + endUrl;
    final WebClient webClient = newWebClient();

    final HtmlPage page = webClient.getPage(url);
    final List<?> byXPath = page.getByXPath("//div[@id=\"content\"]" + xpath);
    assertTrue(byXPath.size() >= 1);

    final Object next = byXPath.iterator().next();
    if (!DomNode.class.isInstance(next)) {
        throw new IllegalArgumentException("Can't find text for " + next);
    }
    return DomNode.class.cast(next).asText();
}