图书检索功能实现---图书馆客户端

标签：android   图书馆客户端   jsoup   图书检索   

今天完成了图书的检索功能。相对来说，还是有点复杂，因为图书检索结果页面的Html并不是那么规范，解析时需要很大的耐心。

首先需要根据查询条件获取结果的HTML，查询条件可以有很多种，这里为了实用、方便，我特意限制了查询条件为：keyword、东校区、可借出

获取结果HTML的方法如下：

	/**
	 * 根据关键字检索图书
	 * 
	 * 检索可以是没有登录的情况，也可以是登录后的情况。 目前是声明了一个新的HTTPclient，即不需要登录，
	 * 如果想设置为在登陆后才可以检索，则需要使用全局的HTTPclient，而不能再声明一个
	 * 
	 * @param keyword
	 *            关键字
	 * @return 检索结果的html
	 */
	public static String serchBook(String keyword) {

		HttpGet httpGet = null;
		String searchResultHtml = null;
		HttpClient httpclient = new DefaultHttpClient();
		HttpResponse response;
		/**
		 * 字段顺序很重要
		 * 
		 * 设置查询条件为：关键字、东校区、可借出
		 */
		List<NameValuePair> params = new ArrayList<NameValuePair>();
		params.add(new BasicNameValuePair("searchtype", "X"));
		params.add(new BasicNameValuePair("searcharg", keyword));// 查询关键字
		params.add(new BasicNameValuePair("searchscope", "1"));// 1代表东区
		params.add(new BasicNameValuePair("sortdropdown", "-"));
		params.add(new BasicNameValuePair("SORT", "DZ"));// 设置排序方式为按日期倒排
		params.add(new BasicNameValuePair("extended", "0"));
		params.add(new BasicNameValuePair("SUBMIT", "检索"));// 查询按钮
		params.add(new BasicNameValuePair("availlim", "1"));// 设置查询条件---可借出
		params.add(new BasicNameValuePair("searchlimits", ""));
		params.add(new BasicNameValuePair("searchorigarg", ""));// 设置上次查询的关键字及排序方式

		// 对参数编码
		String param = URLEncodedUtils.format(params, "UTF-8");
		System.out.println(param);
		try {
			// 将URL与参数拼接
			// http://innopac.lib.xjtu.edu.cn/search~S1*chx/
			String test_url = "http://innopac.lib.xjtu.edu.cn/search~S1*chx/";
			httpGet = new HttpGet(test_url + "?" + param);
			httpGet.setHeader("Host", "innopac.lib.xjtu.edu.cn");
			httpGet.setHeader("Referer", test_url + "?" + param);
			response = httpclient.execute(httpGet);

			int code = response.getStatusLine().getStatusCode();
			System.out
					.println("---------------searchbook------------------------");
			System.out.println(response.getStatusLine());
			if (code == 200) {

				if (response != null) {

					searchResultHtml = EntityUtils.toString(
							response.getEntity(), HTTP.UTF_8);
					return searchResultHtml;
				}
			}
		} catch (ClientProtocolException e) {

			e.printStackTrace();
		} catch (IOException e) {

			e.printStackTrace();
		} finally {
			httpGet.abort();
		}
		return "";
	}

首先来看看，页面上的显示状况：

根据所需解析的信息，我们需要两个封装类。

一个类封装书目信息，另一个封装馆藏信息。这两个类如下：

1.类BookInfo

package com.ali.login.bean;

import java.util.List;

/**
 * 搜索结果中书目的具体信息
 * 
 * @author shuyan
 * 
 */
public class BookInfo {

	private String imgLink;// 图片链接
	private String briefTitle;// Java JDK 7实例宝典 Java JDK 7 shi li bao dian / 韩雪,
								// 郭天娇编著

	private String year;// 2014 文字印刷资料

	private List<BookAddress> bookAddresses;// 书目馆藏信息

	private String reserveLink;// 预约链接

	public BookInfo() {
		super();

	}

	public BookInfo(String imgLink, String briefTitle, String year,
			List<BookAddress> bookAddresses, String reserveLink) {
		super();
		this.imgLink = imgLink;
		this.briefTitle = briefTitle;
		this.year = year;
		this.bookAddresses = bookAddresses;
		this.reserveLink = reserveLink;
	}

	public String getImgLink() {
		return imgLink;
	}

	public void setImgLink(String imgLink) {
		this.imgLink = imgLink;
	}

	public String getBriefTitle() {
		return briefTitle;
	}

	public void setBriefTitle(String briefTitle) {
		this.briefTitle = briefTitle;
	}

	public String getYear() {
		return year;
	}

	public void setYear(String year) {
		this.year = year;
	}

	public List<BookAddress> getBookAddresses() {
		return bookAddresses;
	}

	public void setBookAddresses(List<BookAddress> bookAddresses) {
		this.bookAddresses = bookAddresses;
	}

	public String getReserveLink() {
		return reserveLink;
	}

	public void setReserveLink(String reserveLink) {
		this.reserveLink = reserveLink;
	}

	@Override
	public String toString() {
		return "BookInfo [imgLink=" + imgLink + ", briefTitle=" + briefTitle
				+ ", year=" + year + ", bookAddresses=" + bookAddresses
				+ ", reserveLink=" + reserveLink + "]";
	}

}

2.BookAdress

package com.ali.login.bean;

/**
 * 书目的馆藏信息
 * 
 * @author shuyan
 * 
 */
public class BookAddress {

	private String holdLand;// 馆藏地
	private String callNumber;// 索书号
	private String status;// 状态

	public BookAddress() {
		super();

	}

	public BookAddress(String holdLand, String callNumber, String status) {

		this.holdLand = holdLand;
		this.callNumber = callNumber;
		this.status = status;
	}

	public String getHoldLand() {
		return holdLand;
	}

	public void setHoldLand(String holdLand) {
		this.holdLand = holdLand;
	}

	public String getCallNumber() {
		return callNumber;
	}

	public void setCallNumber(String callNumber) {
		this.callNumber = callNumber;
	}

	public String getStatus() {
		return status;
	}

	public void setStatus(String status) {
		this.status = status;
	}

	@Override
	public String toString() {
		return "BookAddress [holdLand=" + holdLand + ", callNumber="
				+ callNumber + ", status=" + status + "]";
	}
}

这里开始变得有点麻烦，因为这里的标签很是不规范。

代码如下：

/**
	 * 处理查询结果的HTML
	 * 
	 * @param searchResultHtml
	 *            html字符串
	 * 
	 * @return 书目信息集合
	 */
	public static List<BookInfo> getSearchResult(String searchResultHtml) {
		List<BookInfo> bookInfos = new ArrayList<BookInfo>();
		Document document = Jsoup.parse(searchResultHtml);

		Elements items = document.getElementsByClass("briefCitRow");// 书目集合
		int i = 1;
		for (Element item : items) {
			BookInfo bookInfo = null;
			List<BookAddress> bookAddresses = new ArrayList<>();
			Element ele_par = item.select("a[href]").get(0);
			// http://202.117.24.227/bibimage/zycover.php?isbn=9787121217074
			String imgLink = ele_par.child(0).attr("src");// 图片链接

			Element ele_reserve = item.getElementsByClass("briefcitRequest")
					.get(0);// 预约图书的链接
			Element ele_ahref = ele_reserve.select("a[href]").get(0);
			String reserveLink = ele_ahref.attr("href");// 预约链接
			// 需要添加host在前面
			// /availlim/search~S1*chx?/XJava&searchscope=1&SORT=DZ/XJava&searchscope=1&SORT=DZ&extended=0&SUBKEY=Java/1%2C2973%2C2973%2CC/requestbrowse~b3838346&FF=XJava&searchscope=1&SORT=DZ&1%2C1%2C

			// 注意有两个 class = briefcitDetail
			Elements ele_briefcitDetails = item
					.getElementsByClass("briefcitDetail");
			// 先处理第一个

			String briefTitle = ele_briefcitDetails.get(0)
					.getElementsByClass("briefcitTitle").get(0).text();// 书目简要描述

			// 处理第二个
			String year = ele_briefcitDetails.get(1).text();// 年份

			Elements ele_addresses = item.getElementsByClass("briefcitItems")
					.get(0).getElementsByClass("bibItems").get(0)
					.getElementsByClass("bibItemsEntry");// 书目的馆藏信息

			/**
			 * 预约也在这里面处理
			 */
			for (Element ele_add : ele_addresses) {

				BookAddress address = null;
				// 这里有3个td标签
				Elements ele_tds = ele_add.getElementsByTag("td");
				String bookStore = ele_tds.get(0).text();
				String callNumber = ele_tds.get(1).text();
				String status = ele_tds.get(2).text();

				address = new BookAddress(bookStore, callNumber, status);
				bookAddresses.add(address);

			}

			bookInfo = new BookInfo(imgLink, briefTitle, year, bookAddresses,
					reserveLink);
			bookInfos.add(bookInfo);

		}
		return bookInfos;

	}

这样便得到了封装好的书目信息集合，测试如下：

public static void main(String[] args) {
		String searchResultHtml = LibraryUtil.serchBook("Java");
		List<BookInfo> bookInfos = getSearchResult(searchResultHtml);

		int i = 0;

		for (BookInfo bookInfo : bookInfos) {

			if(i<5)
			{
				System.out.println(bookInfo.toString());	
			}
			i++;

		}
	}

如此便实现了图书的检索功能...

当然这里还有许多需要考虑的地方，如：检索结果总数，每页需要显示多少条记录，筛选无意义的结果，预约功能等...

图书检索功能实现---图书馆客户端

标签：android   图书馆客户端   jsoup   图书检索   

原文地址：http://blog.csdn.net/leokelly001/article/details/42042355