解析HTML

[GuoGongZhou]

上面给我个任务 叫我解析整个html页面 这个HTML包含各城市的天气情况 我要拿到这些个城市的天气
高手支招 O(∩_∩)O谢谢

[GuoGongZhou]

不要沉了 自己顶起

[GuoGongZhou]

各位 要是有 稳定的web服务（最好免费的）也提供一下

[GuoGongZhou]

用dom 解析可以吗

[GuoGongZhou]

不要沉了 自己顶起

[xuqi2850661]

试试dom4j

[xuyang840117]

代码才是硬道理 拿去参考吧
写的不是很共通

package cn.ccb.common.util;

import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.InputStreamReader;
import java.io.UnsupportedEncodingException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;

public class ReadXml {

	private Document getDocument(String xmlUrl) {
		Document document = null;
		SAXReader saxReader = new SAXReader();
		FileInputStream file;
		try {
			file = new FileInputStream(xmlUrl);
			InputStreamReader reader = new InputStreamReader(file, "UTF-8");
			document = saxReader.read(reader);
		} catch (FileNotFoundException e) {
			
			e.printStackTrace();
		} catch (UnsupportedEncodingException e) {
			
			e.printStackTrace();
		} catch (DocumentException e) {
			
			e.printStackTrace();
		}

		// SAXReader reader = new SAXReader();
		// Document document = null;
		// try {
		// document = reader.read(new File(xmlUrl));
		// } catch (DocumentException e) {
		// e.printStackTrace();
		// } catch (MalformedURLException e) {
		// e.printStackTrace();
		// }
		return document;
	}

	/**
	 * 获取当前步骤号对应的部门ID
	 * 
	 * @param xmlUrl
	 *            获取XML地址
	 * @param step
	 *            步骤号
	 * @return 部门ID
	 */
	public String getRole(String xmlUrl, String step) {
		Document document = this.getDocument(xmlUrl);
		Element elt = (Element) document.selectSingleNode("//step[@id='" + step
				+ "']/receiver");
		return elt.attributeValue("role");
	}

	/**
	 * 通过当前step查询下一步对应的角色
	 * 
	 * @param xmlUrl
	 * @param step
	 * @return
	 */
	public String getNextRole(String xmlUrl, String step) {
		Document document = this.getDocument(xmlUrl);
		Element elt = (Element) document.selectSingleNode("//step[@id='" + step
				+ "']/receiver/target/choice/sender");
		return elt.attributeValue("role");
	}

	/**
	 * 通过当前step查询下一步对应的step
	 * 
	 * @param xmlUrl
	 * @param step
	 * @return
	 */
	public String getNextStep(String xmlUrl, String step) {
		Document document = this.getDocument(xmlUrl);
		Element elt = (Element) document.selectSingleNode("//step[@id='" + step
				+ "']/receiver/target/choice/sender");
		return elt.attributeValue("step");
	}

	/**
	 * 获取下一步发送部门数组
	 * 
	 * @param xmlUrl
	 *            XML地址
	 * @param step
	 *            当前步骤号
	 * @param node
	 *            choice or split
	 * @return Map<role,step>
	 */
	public Map getNextStepItems(String xmlUrl, String step, String node) {
		Document document = this.getDocument(xmlUrl);
		List list = document.selectNodes("//step[@id='" + step
				+ "']/receiver/target/" + node + "/sender");
		Map map = new HashMap();
		Element elt;
		if (null != list) {
			for (int i = 0; i < list.size(); i++) {
				elt = (Element) list.get(i);
				map.put(elt.attributeValue("role"), elt.attributeValue("step"));
			}
		}
		return map;
	}

	/**
	 * 通过角色ID获取步骤号
	 * 
	 * @param xmlUrl
	 * @param role
	 *            角色ID
	 * @return 步骤号
	 */
	public String getStepByRole(String xmlUrl, String role) {
		Document document = this.getDocument(xmlUrl);
		List list = document.selectNodes("//step");
		String step = "";
		Element elt;
		if (null != list) {
			for (int i = 0; i < list.size(); i++) {
				elt = (Element) list.get(i);
				if (role.equals(elt.element("receiver").attribute("role"))) {
					step = elt.attributeValue("id");
					break;
				}
			}
		}
		return step;
	}

	/**
	 * 获取当前步骤需要的直线数
	 * 
	 * @param xmlUrl
	 * @param step
	 * @return
	 */
	public String getNeedStepNum(String xmlUrl, String step) {
		Document document = this.getDocument(xmlUrl);
		List list = document.selectNodes("//step[@id='" + step
				+ "']/receiver/join/target-from");
		Element elt;
		String str = "";
		if (null == list || 0 == list.size()) {
			return "";
		} else {
			elt = (Element) list.get(0);
			str = elt.attributeValue("step");
			for (int i = 1; i < list.size(); i++) {
				elt = (Element) list.get(i);
				str = str + "," + elt.attributeValue("step");
			}
			return str;
		}
	}

	public String getDescriptionByStep(String xmlUrl, String step) {
		Document document = this.getDocument(xmlUrl);
		Element elt = (Element) document.selectSingleNode("//step[@id='" + step
				+ "']");
		return elt.attributeValue("description");
	}
}