Java Jsoup从Html中解析歌词

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;


import java.io.IOException;
import java.io.UnsupportedEncodingException;


public class Test
{
	private static String songName = "北京北京";


	public static void main(String args[])
	{
		Test getLrc = new Test();
		String lrcUrl = getLrc.getLrcUrl(songName);
		System.out.println(lrcUrl);
		String lrcTxt = getLrc.getLrcText(lrcUrl);
		System.out.println(lrcTxt);
	}


	public String getLrcUrl(String song)
	{
		String lrcUrl = null;


		try
		{
			String songEnc = toBrowserCode(song, "UTF-8");
			System.out.println(songEnc);
			Document doc = Jsoup.connect(
					"http://www.9ilrc.com/search.php?keyword=" + songEnc
							+ "&radio=song").get();


			Elements links = doc.select("a[href]");
			for (Element link : links)
			{
				if (toBrowserCode(trim(link.text(), 15), "UTF-8").equals(
						songEnc))
				{
					lrcUrl = link.attr("abs:href");
					break;
				}
			}
		} catch (IOException e)
		{
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		return lrcUrl;
	}


	public String getLrcText(String url)
	{
		String lrcTxt = null;
		try
		{
			Document doc = Jsoup.connect(url).get();
			Elements links = doc.select("[id]");
			for (Element ele : links)
			{
				if (ele.attr("id").equals("txt"))
				{
					lrcTxt = ele.text().replace(" ", "\n");
					break;
				}
			}
		} catch (IOException e)
		{
			// TODO Auto-generated catch block
			e.printStackTrace();
		}


		return lrcTxt;
	}


	private static String trim(String s, int width)
	{
		if (s.length() > width)
			return s.substring(0, width - 1) + ".";
		else
			return s;
	}


	public String toBrowserCode(String word, String encoding)
			throws UnsupportedEncodingException


	{
		byte[] textByte = word.getBytes(encoding);
		StringBuilder strBuilder = new StringBuilder();


		for (int j = 0; j < textByte.length; j++)
		{
			String hexStr = Integer.toHexString(textByte[j] & 0xff);
			strBuilder.append("%" + hexStr.toUpperCase());
		}


		return strBuilder.toString();
	}
}

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值