htmlparser解析html分页

       在编写cms内容标签时有这样一种情况：

 

      1.数据中内容字段存储结构如下

 

 
  <div>我是<b>第1页 </b>啊</div>
  <div class="page">1</div>

  <div>我是<b>第2页</b>啊</div>
  <div class="page">2</div>

  <div>我是<b>第3页</b>啊</div>
  <div class="page">3</div>

  <div>我是<b>第4页</b>啊</div>
  <div class="page">4</div>
  

  

    2.其中 <div class="page">1,2,3,</div>是分页标签。要做到就是根据这个分页标签实现分页，即把 <div>我是<b>第1页 </b>啊</div> 给提取出来。输出结果如下：

 

 

取第1页: <div>我是<b>第1页</b>啊</div>
取第2页: <div>我是<b>第2页</b>啊</div>
取第3页: <div>我是<b>第3页</b>啊</div>
取第4页: <div>我是<b>第4页</b>啊</div>

 

 

 

    java代码如下：  

 

 

import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.AndFilter;
import org.htmlparser.filters.HasAttributeFilter;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;

public class PageTagParser {
	/**
	 * @param args
	 * @throws ParserException
	 */
	public static void main(String[] args) throws ParserException {

		String fileName = "E:/workspace/Test_htmlparser/res/test.html";
		// fileName =
		// "E:/workspace/Test_htmlparser/res/test_un_page_tag.html";//没分页标签
		String inputHTML = readFileByLines(fileName);
		// System.out.println("inputHTML:" + inputHTML);

		PageTagParser p = new PageTagParser(inputHTML);
		p.parserInputHTMLByPageTag();// 分析
		for (int currPageNum = 1; currPageNum <= p.getSumPageSize(); currPageNum++) {
			System.out.println("取第" + currPageNum + "页:"
					+ p.getContentByCurrPageNum(currPageNum));

		}

		//
	}

	private Node[] nodes;
	private int sumPageSize;
	private String inputHTML;

	/**
	 * 获取总页数
	 * 
	 * @return
	 */
	public int getSumPageSize() {
		return sumPageSize;
	}

	/**
	 * 根据分页标签分析HTML
	 * 
	 * @param inputHTML
	 * @param currPageNum
	 * @throws ParserException
	 */
	public void parserInputHTMLByPageTag() throws ParserException {
		Parser parser;
		NodeFilter filter;

		parser = new Parser();
		NodeFilter filterTag = new TagNameFilter("div");
		NodeFilter filterAttribute = new HasAttributeFilter("class", "page");

		filter = new AndFilter(new NodeFilter[] { filterTag, filterAttribute });

		// parser.setResource("http://www.baidu.com");
		// parser.setResource("E:/workspace/Test_htmlparser/res/test.html");
		parser.setInputHTML(inputHTML);

		NodeList nodeList = parser.parse(filter);
		nodes = nodeList.toNodeArray();

		// System.out.println(parser.parse(filter));

		// System.out.println("nodes.length:" + nodes.length);
		// System.out.println(nodes[0]);

		if (null == nodes || 0 == nodes.length) {
			sumPageSize = 1;
		} else {
			sumPageSize = nodes.length;
		}

	}

	/**
	 * 根据页面获取页面
	 * 
	 * @param currPageNum
	 * @return
	 */
	public String getContentByCurrPageNum(int currPageNum) {

		// System.out.println(parser.parse(filter));

		// System.out.println("nodes.length:" + nodes.length);
		// System.out.println(nodes[0]);

		if (null == nodes || 0 == nodes.length) {
			System.out.println("没有分页标签！");
			return inputHTML;
		} else if (1 >= currPageNum) {// 取第一页
			// System.out.println("取第一页！");
			return inputHTML.substring(0, nodes[0].getStartPosition());
		} else {

			// beginIndex这一点写的有点龌龊了，getEndPosition()返回的是<div>的后面位置不是</div>的后面位置，小郁闷
			Node beginNode = nodes[currPageNum - 2];
			int beginIndex = beginNode.getStartPosition()
					+ beginNode.toHtml().length();

			return inputHTML.substring(beginIndex, nodes[currPageNum - 1]
					.getStartPosition());
		}

		// System.out.println());
		// return inputHTML;
	}

	public PageTagParser(String inputHTML) {
		super();
		this.inputHTML = inputHTML;
	}

	/**
	 * 读取文件（非重点）
	 */
	public static String readFileByLines(String fileName) {
		File file = new File(fileName);
		StringBuilder sb = new StringBuilder();
		BufferedReader reader = null;
		try {
			// System.out.println("以行为单位读取文件内容，一次读一整行：");
			reader = new BufferedReader(new FileReader(file));
			String tempString = null;
			int line = 1;
			// 一次读入一行，直到读入null为文件结束
			while ((tempString = reader.readLine()) != null) {
				// 显示行号
				// System.out.println("line " + line + ": " + tempString);
				sb.append(tempString);
				line++;
			}
			reader.close();
		} catch (IOException e) {
			e.printStackTrace();
		} finally {
			if (reader != null) {
				try {
					reader.close();
				} catch (IOException e1) {
				}
			}
			return sb.toString();
		}
	}
}

 

 

呵呵，简单的就这么完成了，没缓存之类的……