Java NodeFilter类代码示例

import org.htmlparser.NodeFilter; //导入依赖的package包/类
@Override
public NodeList parserUrl(Parser parser) {
	NodeFilter hrefNodeFilter = new NodeFilter() {
		@Override
		public boolean accept(Node node) {
			if (node.getText().startsWith("a href=")) {
				return true;
			} else {
				return false;
			}
		}
	};
	try {
		return parser.extractAllNodesThatMatch(hrefNodeFilter);
	} catch (ParserException e) {
		e.printStackTrace();
	}
	return null;
}
 

import org.htmlparser.NodeFilter; //导入依赖的package包/类
/**
   * parses the body of the message, and returns a parsed representation
   * See {@link http://htmlparser.sourceforge.net/} for details
   * @param url the url that the message resulted from
   * @param message the Message to parse
   * @return a NodeList containing the various Nodes making up the page
   */
  public Object parseMessage(HttpUrl url, Message message) {
      String contentType = message.getHeader("Content-Type");
      if (contentType == null || !contentType.matches("text/html.*")) {
          return null;
      }
      byte[] content = message.getContent();
      if (content == null || content.length == 0) {
          return null;
      }
      Parser parser = Parser.createParser(new String(content), null);
      try {
          NodeList nodelist = parser.extractAllNodesThatMatch(new NodeFilter() {
public boolean accept(Node node) {
                  return true;
              }
          });
          return nodelist;
      } catch (ParserException pe) {
          _logger.severe(pe.toString());
          return null;
      }
  }
 

import org.htmlparser.NodeFilter; //导入依赖的package包/类
public List<String> getGangliaAttribute(String clusterName)
		throws ParserException, MalformedURLException, IOException {
	String url = gangliaMetricUrl.replaceAll(clusterPattern, clusterName);
	Parser parser = new Parser(new URL(url).openConnection());
	NodeFilter nodeFilter = new AndFilter(new TagNameFilter("select"),
			new HasAttributeFilter("id", "metrics-picker"));
	NodeList nodeList = parser.extractAllNodesThatMatch(nodeFilter);
	SimpleNodeIterator iterator = nodeList.elements();
	List<String> metricList = new ArrayList<String>();
	while (iterator.hasMoreNodes()) {
		Node node = iterator.nextNode();

		SimpleNodeIterator childIterator = node.getChildren().elements();
		while (childIterator.hasMoreNodes()) {
			OptionTag children = (OptionTag) childIterator.nextNode();
			metricList.add(children.getOptionText());
		}
	}

	return metricList;

}
 

import org.htmlparser.NodeFilter; //导入依赖的package包/类
public static void main(String[] args) throws Exception {
	Parser parser = new Parser(new URL("http://10.8.75.3/ganglia/?r=hour&cs=&ce=&s=by+name&c=Zookeeper_Cluster&tab=m&vn=&hide-hf=false").openConnection());
	NodeFilter nodeFilter = new AndFilter(new TagNameFilter("select"),
			new HasAttributeFilter("id", "metrics-picker"));
	NodeList nodeList = parser.extractAllNodesThatMatch(nodeFilter);
	SimpleNodeIterator iterator = nodeList.elements();
	while (iterator.hasMoreNodes()) {
		Node node = iterator.nextNode();

		SimpleNodeIterator childIterator = node.getChildren().elements();
		while (childIterator.hasMoreNodes()) {
			OptionTag children = (OptionTag) childIterator.nextNode();
			System.out.println(children.getOptionText());
		}
	}

}
 

import org.htmlparser.NodeFilter; //导入依赖的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.NodeFilter; //导入依赖的package包/类
/***
 * 解析价格
 *
 * @param node
 * @return
 */
private String parseSpan(Node node) {
    StringBuilder sb = new StringBuilder();
    NodeList priceNodeList = new NodeList();
    NodeFilter nodeFilter = new TagNameFilter("span");
    node.collectInto(priceNodeList, nodeFilter);
    for (Node spanNode : priceNodeList.toNodeArray()) {
        if (spanNode instanceof Span) {
            String attribute = ((Span) spanNode).getAttribute("class");
            sb.append(MappingSet.NUMBER_MAPPING.get(attribute));
        }
    }
    return CharMatcher.WHITESPACE.removeFrom(sb.toString());
}
 

import org.htmlparser.NodeFilter; //导入依赖的package包/类
/***
 * 爬取透明网最近的预售证信息
 * @param url
 * @throws InterruptedException
 * @throws IOException
 * @throws ParserException
 */
public void run(String url) throws InterruptedException, IOException, ParserException {

    URLConnection urlConnection = CommonHttpURLConnection.getURLConnection(url);
    Parser parser = new Parser(urlConnection);
    NodeFilter nodeFilter = new HasAttributeFilter("class", "sale1");
    NodeList nodeList = parser.extractAllNodesThatMatch(nodeFilter);

    if (nodeList.toNodeArray().length > 0) {
        Node[] sellCreditNodeArray = nodeList.elementAt(0).getChildren().toNodeArray();
        for (int i = 2; i < sellCreditNodeArray.length; i++) {
            if (sellCreditNodeArray[i] instanceof TableRow) {
                SellCreditInfo sellCreditInfo = parseSellParser(sellCreditNodeArray[i]);
                log.info("get sell credit info:{}", sellCreditInfo);
                //该预售证是否已经爬过
                HouseInfo houseInfo = dataOP.getHouseInfoByDepartmentNameAndSellCredit(sellCreditInfo);
                if(houseInfo != null){
                    log.info("already parsing sell credit:{}",sellCreditInfo);
                    break;
                }
                dataOP.insertSellCreditInfo(sellCreditInfo);
                if(i==2) continue;
                parseHouseInfo(sellCreditInfo);
            }
        }
    }
}
 

import org.htmlparser.NodeFilter; //导入依赖的package包/类
private String parseSpan(Node node) {
    StringBuilder sb = new StringBuilder();
    NodeList priceNodeList = new NodeList();
    NodeFilter nodeFilter = new TagNameFilter("span");
    node.collectInto(priceNodeList, nodeFilter);
    for (Node spanNode : priceNodeList.toNodeArray()) {
        if (spanNode instanceof Span) {
            String attribute = ((Span) spanNode).getAttribute("class");
            sb.append(MappingSet.NUMBER_MAPPING.get(attribute));
        }
    }
    return sb.toString();
}
 

import org.htmlparser.NodeFilter; //导入依赖的package包/类
public List<DailyBriefInfo> parseDailyBriefInfo() throws IOException, ParserException {

        Parser parser = new Parser(CommonHttpURLConnection.getURLConnection("http://www.tmsf.com/index.jsp"));
        NodeFilter nodeFilter = new HasAttributeFilter("id", "myCont5");
        NodeList nodeList = parser.extractAllNodesThatMatch(nodeFilter);
        if (nodeList.toNodeArray().length == 0) {
            return Collections.EMPTY_LIST;
        }

        List<DailyBriefInfo> dailyBriefInfoList = new ArrayList<>();

        //到1970/01/01 00:00:00的小时数
        int parseHour = (int) (Clock.systemUTC().millis() / (1000 * 3600));

        //到1970/01/01 00:00:00的天数
        int parseDay = (int) parseHour / 24;

        NodeList infoNodeList = nodeList.elementAt(0).getChildren().elementAt(1)
                .getChildren().elementAt(1).getChildren();

        for (int i = 5; i <= 13; i = i + 2) {
            DailyBriefInfo dailyBriefInfo = new DailyBriefInfo(CharMatcher.WHITESPACE.trimFrom(infoNodeList.elementAt(i).getChildren().elementAt(1).toPlainTextString()),
                    Integer.parseInt(CharMatcher.WHITESPACE.trimFrom(infoNodeList.elementAt(i).getChildren().elementAt(3).toPlainTextString())),
                    Integer.parseInt(CharMatcher.WHITESPACE.trimFrom(infoNodeList.elementAt(i).getChildren().elementAt(5).toPlainTextString())),
                    Integer.parseInt(CharMatcher.WHITESPACE.trimFrom(infoNodeList.elementAt(i).getChildren().elementAt(7).toPlainTextString())),
                    parseDay,parseHour);

            dailyBriefInfoList.add(dailyBriefInfo);
            dataOP.insertBriefDealInfo(dailyBriefInfo);

            ESOP.writeToES("log/daily_brief_info_es", JSONObject.toJSONString(dailyBriefInfo));
        }

        return dailyBriefInfoList;

    }
 

import org.htmlparser.NodeFilter; //导入依赖的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.NodeFilter; //导入依赖的package包/类
/**
 * 分别读纯文本和链接.
 * @param result 网页的内容
 * @throws Exception
 */
public static void readTextAndLinkAndTitle(String result) throws Exception {
    Parser parser;
    NodeList nodelist;
    parser = Parser.createParser(result, "utf8");

    NodeFilter textFilter = new NodeClassFilter(TextNode.class);
    NodeFilter linkFilter = new NodeClassFilter(LinkTag.class);
    NodeFilter titleFilter = new NodeClassFilter(TitleTag.class);
    OrFilter lastFilter = new OrFilter();
    lastFilter.setPredicates(new NodeFilter[] { textFilter, linkFilter, titleFilter });
    nodelist = parser.parse(lastFilter);
    Node[] nodes = nodelist.toNodeArray();
    String line = "";
    
    for (int i = 0; i < nodes.length; i++) {
        Node node = nodes[i];
        if (node instanceof TextNode) {
            TextNode textnode = (TextNode) node;
            line = textnode.getText();
        } else if (node instanceof LinkTag) {
            LinkTag link = (LinkTag) node;
            line = link.getLink();
        } else if (node instanceof TitleTag) {
            TitleTag titlenode = (TitleTag) node;
            line = titlenode.getTitle();
        }
        
        if (isTrimEmpty(line))
            continue;
        System.out.println(line);
    }
}
 

import org.htmlparser.NodeFilter; //导入依赖的package包/类
public static List<String> extractTextByTextNode(String content){
  	List<String> doc=new ArrayList<String>();//每个元素为一个段落
  	 if (content == null) {
    	return doc;
  }
  	 try{
	     Parser parser = Parser.createParser(content, "utf8");      
	     NodeFilter textFilter = new NodeClassFilter(TextNode.class);
        NodeList nodelist=parser.extractAllNodesThatMatch(textFilter);
        HashMap<String,Integer> parentWeight=new HashMap<String,Integer>();
        for (int i = 0; i < nodelist.size(); i++) {
        	Node textnode = (Node) nodelist.elementAt(i);
        	if(textnode.toPlainTextString().trim().length()>0)
        		log.debug(i+": "+" content: "+textnode.toPlainTextString());
        	if(isInformativeStricter(textnode,parentWeight)){
	        	log.debug(i+": "+" content: "+textnode.toPlainTextString());
	        	doc.add(textnode.toPlainTextString());
        	}        	
        }  
}catch(Exception e){
	e.printStackTrace();
	log.error("Text extractor  has encountered a problem!! "+e.getMessage());
}
  	 
    return doc;

  }
 

import org.htmlparser.NodeFilter; //导入依赖的package包/类
private NodeList filterSelectNode(String responseBody) throws ParserException {
    Parser parser = Parser.createParser(responseBody, HTTP.ISO_8859_1);
    return parser.extractAllNodesThatMatch(new NodeFilter() {
        @Override
        public boolean accept(Node node) {
            if (node.getText().startsWith("select")) {
                return true;
            }
            return false;
        }
    });
}
 

import org.htmlparser.NodeFilter; //导入依赖的package包/类
private NodeList filterTable(String responseBody) throws ParserException {
    Parser parser = Parser.createParser(responseBody, HTTP.ISO_8859_1);
    return parser.extractAllNodesThatMatch(new NodeFilter() {
        @Override
        public boolean accept(Node node) {
            if (node.getText().toUpperCase().startsWith("TABLE") || node.getText().toUpperCase().startsWith("H3")) {
                return true;
            }
            return false;
        }
    });
}
 

import org.htmlparser.NodeFilter; //导入依赖的package包/类
/**
 * 获取一个网站上的a链接
 * @param url
 * @return
 */
public static Set<String> extracLinks(String url) {
    Set<String> links = new HashSet<String>();

    try {
        Parser parser = new Parser(url);
        parser.setEncoding("utf-8");
        // 过滤 <frame >标签的 filter，用来提取 frame 标签里的 src 属性所表示的链接
        @SuppressWarnings("serial")
        NodeFilter frameFilter = new NodeFilter() {
            public boolean accept(Node node) {
                if (node.getText().startsWith("frame src=")) {
                    return true;
                } else {
                    return false;
                }
            }
        };
        // OrFilter 来设置过滤 <a> 标签，和 <frame> 标签
        OrFilter linkFilter = new OrFilter(new NodeClassFilter(LinkTag.class), frameFilter);
        // 得到所有经过过滤的标签
        NodeList list = parser.extractAllNodesThatMatch(linkFilter);
        for (int i = 0; i < list.size(); i++) {
            Node tag = list.elementAt(i);
            if (tag instanceof LinkTag) {
                // <a> 标签
                LinkTag link = (LinkTag) tag;
                String linkUrl = link.getLink();
                links.add(linkUrl);
            } else {
                // 提取 frame 里 src 属性的链接如 <frame src="test.html"/>
                String frame = tag.getText();
                int start = frame.indexOf("src=");
                frame = frame.substring(start);
                int end = frame.indexOf(" ");
                if (end == -1) {
                    end = frame.indexOf(">");
                }
                String frameUrl = frame.substring(5, end - 1);
                links.add(frameUrl);
            }
        }
    } catch (ParserException e) {
        logger.error("", e);
    }
    return links;
}