使用dom4j 和xpath 通过url读取xml数据的实例

我这个实例是在我开发过程中用到的，本人是菜鸟，希望高手勿喷！

首先dom4j 需要在项目中添加一些包，另外调用xpath 也需要一些包，然后我这里就不多说了，直接说一下我这个代码的具体思路：

1、根据一定的规则，创建读取xml的url （由于我这个代码是根据用户不同的选择读取不同的xml）

2、检查url的合法性，主要是看url是否是有效链接

3、创建saxReader实例，接着创建doc实例

4、通过xpath中的selectNodes读取出数据，（其实这个是dom4j的一个方法，主要需要xpath的支持）

5、打包数据，挂在arraylist中，最后写入数据库

代码如下：

public class ParseXML {
	private ImportNameForm dataform;
	private int type;
	private Academic ac;
	private int count = 0; // 返回文章的数量
	private StringBuffer finalStrBuffer = new StringBuffer();
	ArrayList<Academic> ar = new ArrayList<Academic>();

	// 把年份和账号通过构造函数传过来
	public ParseXML(ImportNameForm dataform, int type) {
		this.dataform = dataform;
		this.type = type;

	}

	// 返回文章的数量
	public int getCount() {
		return count;
	}

	public ArrayList<Academic> xml2arraylist() {
		this.parsing(1);
		return ar;
	}

	public String xml2string() {
		this.parsing(2);
		return finalStrBuffer.toString();
	}

	// 根据地址在xml中把数据读出，当flag等于1，把数据放在academic中，然后再放在arraylist中
	// 当flag=2 把数据转化成html放在buffer中
	//flag等于1是为了方便存储，flag等于2是为了在选择名字后的显示

	public void parsing(int flag) {
		switch (type) {
		case 1:
			this.getPaperXML(flag);
			break;
		case 2:
			this.getPublicationXML(flag);
			break;
		case 3:
			this.getProjectXML(flag);			
			break;
		case 4:
			this.getPatentXML(flag);
			break;
		}
	}

	public String xzmTemplate(int i) {
		String str;
		String[] xzm = dataform.getXzm();
		str = "<tr><td bgcolor='#dddddd'>学者：";
		str = str + xzm[i] + " 的相关信息</td></tr>";
		return str;
	}

	public String checkboxTemplate(Academic ac) {
		String str;
		str = "<tr><td><input type='checkbox' name='ckb' value='";
		str = str + ac.getId() + "'/>";
		str = str + ac.getTitle() + "</td></tr>";
		return str;
	}

	// 根据用户的账号和选择的年份生成URL
	public String[] createURL() {		
		String year1 = dataform.getYear1();
		String year2 = dataform.getYear2();
		String[] ckb = dataform.getCkb();
		String[] str = new String[ckb.length];
		String strType;
		switch (type) {
		case 1:
			strType = "Paper";
			break;
		case 2:
			strType = "Publication";
			break;
		case 3:
			strType = "Project";			
			break;
		case 4:
			strType = "Patent";
			break;
		default:
			strType = "Paper";
			break;
		}
		for (int i = 0; i < ckb.length; i++) {
			str[i] = "http://www.XXXXXX.com/rest/";
			str[i] = str[i] + strType + "/" + ckb[i].trim() + "/" + year1 + "-"
					+ year2;
		}
		return str;
	}

	// 检查URL是否有效
	private boolean isConnect(String url) {
		boolean flag = false;
		int counts = 0;
		if (url == null || url.length() <= 0) {
			return flag;
		}
		while (counts < 5) {
			try {
				HttpURLConnection connection = (HttpURLConnection) new URL(url)
						.openConnection();
				int state = connection.getResponseCode();
				if (state == 200) {

					flag = true;
				}
				break;
			} catch (Exception ex) {
				counts++;
				continue;
			}
		}
		return flag;
	}

	public void getPaperXML(int flag) {
		System.out.println("Paper_parsing");
		String[] strURL = this.createURL();
		SAXReader saxReader = new SAXReader();
		try {
			for (int i = 0; i < strURL.length; i++) {
				if (isConnect(strURL[i])) {
					URL url;
					url = new URL(strURL[i]);
					Document doc = saxReader.read(url);
					List paperids = doc
							.selectNodes("/scholarPapers/scholarPaper/id");
					List titles = doc
							.selectNodes("/scholarPapers/scholarPaper/title");
					List authors = doc
							.selectNodes("/scholarPapers/scholarPaper/authors");
					List dates = doc
							.selectNodes("/scholarPapers/scholarPaper/date");
					List sources = doc
							.selectNodes("/scholarPapers/scholarPaper/source");
					List types = doc
							.selectNodes("/scholarPapers/scholarPaper/type");
					List citations = doc.selectNodes("/scholarPapers/scholarPaper/citation");
					if (flag == 2) {
						finalStrBuffer.append(xzmTemplate(i));
					}
					for (int j = 0; j < paperids.size(); j++) {
						count++;
						ac = new Academic();
						ac.setAcademic_class(String.valueOf(type));
						ac.setAuthor(((Element) authors.get(j)).getText());
						ac.setPaper(((Element) sources.get(j)).getText());
						ac.setPtype(((Element) types.get(j)).getText());
						ac.setTitle(((Element) titles.get(j)).getText());
						ac.setId(Integer.parseInt(((Element) paperids.get(j))
								.getText()));
						ac.setYear(Integer.parseInt(((Element) dates.get(j))
								.getText().substring(0, 4)));
						ac.setContent(((Element)citations.get(j)).getText());

						if (flag == 1) {
							ar.add(ac);
						} else
							finalStrBuffer.append(checkboxTemplate(ac));

					}
				}
			}
		} catch (MalformedURLException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (DocumentException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
}