Java CleanerProperties.setBooleanAttributeValues方法代码示例

import org.htmlcleaner.CleanerProperties; //导入方法依赖的package包/类
/**
 * Convenience method (for xml/xhtml): serializes the parsed page.
 *
 * @param inSerializer
 *            {@link XmlSerializer}
 * @return String the cleaned and serialized html
 * @throws IOException
 */
public String getSerialized(final XmlSerializer inSerializer)
        throws IOException {
	if (docNode == null) {
		return ""; //$NON-NLS-1$
	}

	final CleanerProperties lProps = new HtmlCleaner().getProperties();
	lProps.setUseCdataForScriptAndStyle(true);
	lProps.setRecognizeUnicodeChars(true);
	lProps.setUseEmptyElementTags(true);
	lProps.setAdvancedXmlEscape(true);
	lProps.setTranslateSpecialEntities(true);
	lProps.setBooleanAttributeValues("empty"); //$NON-NLS-1$
	lProps.setNamespacesAware(true);
	lProps.setOmitXmlDeclaration(false);
	lProps.setOmitDoctypeDeclaration(true);
	lProps.setOmitHtmlEnvelope(false);

	docNode.getAttributes().remove(NS_XML);

	return inSerializer.getSerializer(lProps).getXmlAsString(docNode);
}
 

import org.htmlcleaner.CleanerProperties; //导入方法依赖的package包/类
private ExtractInfoWithHtmlCleaner()
{
	CleanerProperties props = cleaner.getProperties();     
       props.setUseCdataForScriptAndStyle(true);     
       props.setRecognizeUnicodeChars(true);     
       props.setUseEmptyElementTags(true);     
       props.setAdvancedXmlEscape(true);     
       props.setTranslateSpecialEntities(true);     
       props.setBooleanAttributeValues("empty");
}
 

import org.htmlcleaner.CleanerProperties; //导入方法依赖的package包/类
public static void main(String[] args) throws IOException, XPatherException {
	CleanerProperties props = cleaner.getProperties();     
       props.setUseCdataForScriptAndStyle(true);     
       props.setRecognizeUnicodeChars(true);     
       props.setUseEmptyElementTags(true);     
       props.setAdvancedXmlEscape(true);     
       props.setTranslateSpecialEntities(true);     
       props.setBooleanAttributeValues("empty");     
       String result ="";
       File file = new File("E:/test4java/tangniaobing.htm");
       
       
       URL url = new URL("http://www.haodf.com/wenda/anzhentaohong_g_638200415.htm");
	 TagNode node = cleaner.clean(url,"gb2312");
	 //Object[] ns = node.getElementsByName("", true);
	 Object[] ns = node.evaluateXPath("//*[@class=\"bb_d3 bl_d3 pb20\"]/div[3]/div[2]/p[2]");
	 //Object[] ns = node.("//*[@id=\"shequREP_pageNumLab\"]/a");
	 for (Object object : ns) 
	 {
	    TagNode dd = (TagNode) object;
	    
	    result = result +dd.getText()+"\n";
	 }
	 result = result.replace("&nbsp", "").replace("\r", "").replace(";", "");
	 
			result = CommonUtil.getDateString(result,".*?([0-9]+.[0-9]+.[0-9]+).*");

	 /*result = "?uthorid=4917458&page=6&tid=16785968";
	 String rex = "\\?(?!authorid=).*";
	 Pattern p = Pattern.compile(rex);
	 Matcher m = p.matcher(result);
	 boolean s = m.matches();
	 for(int i=1;i<=m.groupCount();i++)
	 {
		 System.out.println(m.group(i));
	 }*/
	 
	 System.out.print(result);
}
 

import org.htmlcleaner.CleanerProperties; //导入方法依赖的package包/类
public static ArrayList<String> getStandardCredit(String year, int index,
                                                  String department) throws Exception {
    try {
        ArrayList<String> standard = new ArrayList<>();
        HashMap<String, String> params = new HashMap<>();
        params.put("format", "-3");
        params.put("year", year);
        params.put("matric", matrics.get(index));
        String result = Connector
                .getDataByPost(getStandardUri(lang), params, "big5");
        result = result.replace("<td", "</td><td");
        result = result.replace("<tr>", "</td><tr>");
        HtmlCleaner cleaner = new HtmlCleaner();
        CleanerProperties props = cleaner.getProperties();
        props.setUseCdataForScriptAndStyle(true);
        props.setRecognizeUnicodeChars(true);
        props.setUseEmptyElementTags(true);
        props.setAdvancedXmlEscape(true);
        props.setTranslateSpecialEntities(true);
        props.setBooleanAttributeValues("empty");
        result = new PrettyHtmlSerializer(props).getAsString(result);
        TagNode tagNode = cleaner.clean(result);
        TagNode[] tables = tagNode.getElementsByAttValue("border", "1",
                true, false);
        TagNode[] rows = tables[0].getElementsByName("tr", true);
        for (int i = 1; i < rows.length; i++) {
            TagNode[] cols = rows[i].getElementsByName("td", true);
            String temp = cols[0].getText().toString();
            if (temp.replace(" ", "").replace("\n", "").contains(department.replace(" ", "").replace("\n", ""))) {
                for (int j = 1; j < 9; j++) {
                    String credit = Utility.cleanString(cols[j].getText()
                            .toString());
                    standard.add(credit);
                }
                return standard;
            }
        }
        throw new Exception();
    } catch (Exception e) {
        e.printStackTrace();
        throw new Exception("畢業學分標準讀取時發生錯誤");
    }
}