Java Node.toPlainTextString方法代码示例

import org.htmlparser.Node; //导入方法依赖的package包/类
private static void processNodeList(NodeList list, String keyword) {
	// 迭代开始
	SimpleNodeIterator iterator = list.elements();
	while (iterator.hasMoreNodes()) {
		Node node = iterator.nextNode();
		// 得到该节点的子节点列表
		NodeList childList = node.getChildren();
		// 孩子节点为空，说明是值节点
		if (null == childList) {
			// 得到值节点的值
			String result = node.toPlainTextString();
			// 若包含关键字，则简单打印出来文本
			if (result.indexOf(keyword) != -1)
				System.out.println(result);
		} // end if
			// 孩子节点不为空，继续迭代该孩子节点
		else {
			processNodeList(childList, keyword);
		}// end else
	}// end wile
}
 

import org.htmlparser.Node; //导入方法依赖的package包/类
/***
 * 解析小区的页数
 *
 * @param url
 * @return
 * @throws IOException
 * @throws ParserException
 */
private int parsePageInfo(final String url) throws IOException, ParserException {
    Parser parser = new Parser(CommonHttpURLConnection.getURLConnection(url));

    NodeFilter nodeFilter = new HasAttributeFilter("class", "pagenumber");
    NodeList nodeList = parser.extractAllNodesThatMatch(nodeFilter);
    for (Node node : nodeList.toNodeArray()) {
        if (!(node instanceof Div)) {
            continue;
        }
        for (Node innerNode : node.getChildren().elementAt(1).getChildren().toNodeArray()) {
            if (!(innerNode instanceof TextNode)) {
                continue;
            }
            String pageStr = innerNode.toPlainTextString();
            if (!pageStr.contains("/")) {
                continue;
            }
            pageStr = pageStr.substring(pageStr.indexOf("/") + 1);
            try {
                return Integer.parseInt(pageStr);
            } catch (Exception e) {

            }
        }
    }
    return 0;
}
 

import org.htmlparser.Node; //导入方法依赖的package包/类
/**
 * 爬取当前楼幢的页数
 *
 * @return
 * @throws InterruptedException
 * @throws IOException
 * @throws Exception
 */
public int parsePageInfo(String url, DepartmentInfo departmentInfo) throws ParserException, IOException {

    Parser parser = new Parser(CommonHttpURLConnection.getURLConnection(url));

    int page = 0;
    //解析页数
    NodeFilter nodeFilter = new HasAttributeFilter("class", "spagenext");
    NodeList nodeList = parser.extractAllNodesThatMatch(nodeFilter);
    if (nodeList.size() == 0) {
        return page;
    }

    for (Node pageNode : nodeList.elementAt(0).getChildren().toNodeArray()) {
        if (pageNode instanceof Span) {
            try {
                String tmp = pageNode.toPlainTextString();
                page = Integer.parseInt(tmp.substring(tmp.indexOf("/") + 1, tmp.indexOf("总数") - 1).trim());
                break;
            } catch (Exception e) {
            }
        }
    }

    log.info("get total page [{}] for department:[{}]", page, departmentInfo.toString());

    return page;
}
 

import org.htmlparser.Node; //导入方法依赖的package包/类
/**
 * 解析楼幢数
 *
 * @param nodeList
 * @return
 */
private String parseLinkTag(NodeList nodeList) {
    for (Node node : nodeList.toNodeArray()) {
        if (node instanceof LinkTag) {
            return node.toPlainTextString();
        }
    }
    return StringUtils.EMPTY;
}
 

import org.htmlparser.Node; //导入方法依赖的package包/类
/**
 * 解析房号、状态
 *
 * @param nodeList
 * @return
 */
private String parseDiv(NodeList nodeList) {
    for (Node node : nodeList.toNodeArray()) {
        if (node instanceof Div) {
            return node.toPlainTextString();
        }
    }
    return StringUtils.EMPTY;
}
 

import org.htmlparser.Node; //导入方法依赖的package包/类
@SuppressWarnings({ "rawtypes", "unchecked" })
@Action(value = "dstlist", results = { @Result(type = "json", params = {
		"root", "list" }) })
public String list() {
	Cache c = CacheManager.getInstance().getCache("News");
	String ckey = "dstlist" + page;
	Element ele = c.get(ckey);
	if (!CommonUtil.isEmpty(ele)) {
		list = (List) ele.getObjectValue();

	} else {
		try {
		StringBuffer retstr = CommonUtil.postWebRequest(RD+"/news.aspx?info_lb=822", ("__EVENTTARGET=_ctl0$ContentPlaceHolder1$Pager22&__EVENTARGUMENT="+page).getBytes("utf-8"), "application/x-www-form-urlencoded");
		Parser p = Parser.createParser(retstr.toString(), "utf-8");
		list = new ArrayList<News>();
		
			NodeList ls = p
					.extractAllNodesThatMatch(new AttributeRegexFilter(
							"href", "show\\.aspx\\?.+"));
			SimpleNodeIterator i = ls.elements();
			while (i.hasMoreNodes()) {
				Node n = i.nextNode();
				if (n instanceof TagNode) {
					TagNode tn = (TagNode) n;
					News news = new News();
					String href = tn.getAttribute("href");
					news.setId(href);
					news.setTitle(tn.toPlainTextString().trim());
					Node tmp=tn.getParent().getNextSibling();
					while(tmp!=null &&!(tmp instanceof Span))
						tmp=tmp.getNextSibling();
					if(tmp!=null){
						String dtstr=tmp.toPlainTextString();
						if(dtstr!=null &&dtstr.length()>2)
						news.setPubdate(dtstr.substring(1,dtstr.length()-1));
					}
					list.add(news);
				}
			}
			c.put(new Element(ckey, list));
		} catch (Exception e) {

			e.printStackTrace();
		}
	}

	return SUCCESS;
}