抓取一个医学方面的分类导航

public class GetNav {

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

	}

	public static String Html2Text(String inputString) {
		String htmlStr = inputString; // 含html标签的字符串
		String textStr = "";
		java.util.regex.Pattern p_script;
		java.util.regex.Matcher m_script;
		java.util.regex.Pattern p_style;
		java.util.regex.Matcher m_style;
		java.util.regex.Pattern p_html;
		java.util.regex.Matcher m_html;

		java.util.regex.Pattern p_html1;
		java.util.regex.Matcher m_html1;

		try {
			String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>"; // 定义script的正则表达式{或<script[^>]*?>[\\s\\S]*?<\\/script>
			String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; // 定义style的正则表达式{或<style[^>]*?>[\\s\\S]*?<\\/style>
			String regEx_html = "<[^>]+>"; // 定义HTML标签的正则表达式
			String regEx_html1 = "<[^>]+";
			p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
			m_script = p_script.matcher(htmlStr);
			htmlStr = m_script.replaceAll(""); // 过滤script标签

			p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
			m_style = p_style.matcher(htmlStr);
			htmlStr = m_style.replaceAll(""); // 过滤style标签

			p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
			m_html = p_html.matcher(htmlStr);
			htmlStr = m_html.replaceAll(""); // 过滤html标签

			p_html1 = Pattern.compile(regEx_html1, Pattern.CASE_INSENSITIVE);
			m_html1 = p_html1.matcher(htmlStr);
			htmlStr = m_html1.replaceAll(""); // 过滤html标签

			textStr = htmlStr;

		} catch (Exception e) {
			System.err.println("Html2Text: " + e.getMessage());
		}

		return textStr;// 返回文本字符串
	}

	public static void getBaiduKeyword() throws ParserException {
		String url = "http://www.meddir.cn/cate/1120.htm";
		Parser parser = new Parser(url);
		parser.setEncoding("gb2312");
		NodeList nodeList = null;
		NodeFilter DivFilter = new NodeClassFilter(Div.class);
		OrFilter lastFilter = new OrFilter();
		lastFilter.setPredicates(new NodeFilter[] { DivFilter });
		nodeList = parser.parse(lastFilter);
		Node[] nodes = nodeList.toNodeArray();
		StringBuilder sb = new StringBuilder();
		for (int i = 0; i < nodes.length; i++) {
			Node anode = (Node) nodes[i];
			if (anode instanceof Div) {
				Div div = (Div) anode;
				if (div.getAttribute("style") != null) {
					if (div.getAttribute("style").equals("cursor:hand;cursor:pointer")) {
						String prefix = "(";
						int start = div.getAttribute("onClick").indexOf(prefix);
						String nav = div.getAttribute("onClick").substring(start);
						int ss = nav.indexOf(",");
						String urls = nav.substring(ss + 1).replaceAll("\\)","").replaceAll("\\'", "");
						String urlName = div.getStringText().replaceAll("\r\n","");
						sb.append(urls + "," + Html2Text(urlName).replaceAll("\\*","")+"\r\n");
						System.out.println("---" + urls + "---" + Html2Text(urlName).replaceAll("\\*",""));
					}
				}
			}
		}
		if (sb != null) {
			FileUtil.newFile("d:/html/医学论文.txt",sb.toString());
		}

	}

}