Java Element.getName方法代码示例

import net.htmlparser.jericho.Element; //导入方法依赖的package包/类
private static boolean isValidTRTag(Tag tag) {
	Element parentElement=tag.getElement().getParentElement();
	if (parentElement==null) return false; // ignore TR elements without a parent
	if (parentElement.getStartTag().getUserData()!=VALID_MARKER) return false; // ignore TR elements who's parent is not valid
	if(parentElement.getName()==HTMLElementName.TABLE){
		return true;
	}
	if(parentElement.getName()==HTMLElementName.TBODY
			||parentElement.getName()==HTMLElementName.THEAD){
		Element gradParent=parentElement.getParentElement();
		if(gradParent==null){
			return false;
		}
		if (gradParent.getStartTag().getUserData()!=VALID_MARKER) return false;
		return (gradParent.getName()==HTMLElementName.TABLE);
	}else{
		return false;
	}
}
 

import net.htmlparser.jericho.Element; //导入方法依赖的package包/类
private boolean isValidLITag(Tag tag) {
	Element parentElement = tag.getElement().getParentElement();
	if (parentElement == null)
		return false; // ignore LI elements without a parent
	if (parentElement.getStartTag().getUserData() != VALID_MARKER)
		return false; // ignore LI elements who's parent is not valid
	return parentElement.getName() == HTMLElementName.UL
			|| parentElement.getName() == HTMLElementName.OL; // only accept
																// LI tags
																// who's
																// immediate
																// parent is
																// UL or OL.
}
 

import net.htmlparser.jericho.Element; //导入方法依赖的package包/类
private boolean isValidLITag(Tag tag) {
	Element parentElement = tag.getElement().getParentElement();
	if (parentElement == null)
		return false; // ignore LI elements without a parent
	if (parentElement.getStartTag().getUserData() != VALID_MARKER)
		return false; // ignore LI elements who's parent is not valid
	// only accept LI tags who's immediate parent is UL or OL.
	return parentElement.getName() == HTMLElementName.UL || parentElement.getName() == HTMLElementName.OL; 
}
 

import net.htmlparser.jericho.Element; //导入方法依赖的package包/类
private static boolean isValidLITag(Tag tag) {
	Element parentElement=tag.getElement().getParentElement();
	if (parentElement==null) return false; // ignore LI elements without a parent
	if (parentElement.getStartTag().getUserData()!=VALID_MARKER) return false; // ignore LI elements who's parent is not valid
	return parentElement.getName()==HTMLElementName.UL || parentElement.getName()==HTMLElementName.OL; // only accept LI tags who's immediate parent is UL or OL.
}
 

import net.htmlparser.jericho.Element; //导入方法依赖的package包/类
private static boolean isValidTDTHTag(Tag tag) {
	Element parentElement=tag.getElement().getParentElement();
	if (parentElement==null) return false; // ignore TD, TH elements without a parent
	if (parentElement.getStartTag().getUserData()!=VALID_MARKER) return false; // ignore TD,TH elements who's parent is not valid
	return parentElement.getName()==HTMLElementName.TR; // only accept TD,TH tags who's immediate parent is TR.
}
 

import net.htmlparser.jericho.Element; //导入方法依赖的package包/类
private static boolean isValidTbodyTHeadTag(Tag tag) {
	Element parentElement=tag.getElement().getParentElement();
	if (parentElement==null) return false;
	if (parentElement.getStartTag().getUserData()!=VALID_MARKER) return false;
	return parentElement.getName()==HTMLElementName.TABLE;
}
 

import net.htmlparser.jericho.Element; //导入方法依赖的package包/类
/**
    * Serduszko dla Bartka od Kasi <3
    * @param htmlFragment
    * @param docUri
    * @return
    */
   private String removeNotAllowedTags(String htmlFragment, URI docUri) {
       Source source = new Source(htmlFragment);
       OutputDocument outputDocument = new OutputDocument(source);
       List<Element> elements = source.getAllElements();


    for (Element element : elements) {
    	Attributes attrs = element.getAttributes();
    	Map<String, String> attrsUpdate = outputDocument.replace(attrs, true);
    	if (!element.getName().contains("a")) {
			attrsUpdate.clear();
		} else {
    		if (attrsUpdate.get("href")!=null) {
	    		String link = attrsUpdate.get("href");
	    		if (!link.contains("http")) {
		    		URI documentUri = docUri;

		    		URI anchorUri;
					try {
						anchorUri = new URI(link);
						URI result = documentUri.resolve(anchorUri);

						attrsUpdate.put("href",	result.toString());
					} catch (URISyntaxException e) {
						outputDocument.remove(element);
					}
	    		}
    		}
    	}

    	if (NOT_ALLOWED_HTML_TAGS.contains(element.getName())) {
    		Segment content = element.getContent();
    		if (element.getName() == "script"
    				|| element.getName() == "style"
    				|| element.getName() == "form") {
    			outputDocument.remove(content);
    		}
            outputDocument.remove(element.getStartTag());

            if (!element.getStartTag().isSyntacticalEmptyElementTag()) {
                outputDocument.remove(element.getEndTag());
            }
        }
    }

    String out = outputDocument.toString();
    out = out.replaceAll("\\n", "");
    out = out.replaceAll("\\t", "");

    return out;
}