1.需要引入Jsoup包
Jsoup包中的parse方法只有File和INputstream能传入charset，这里自己增加一个String类型的传入charset，解决爬取网页数据过程中返回的Unicode转成乱码

package com.isoft.util;



import java.io.IOException;

import java.nio.ByteBuffer;

import java.nio.charset.Charset;



import org.jsoup.helper.Validate;

import org.jsoup.nodes.Document;

import org.jsoup.parser.Parser;



public class IsJsoup {

	public static Document parse(String html, String charsetName, String uri) throws IOException {

		ByteBuffer byteData = ByteBuffer.wrap(html.getBytes(charsetName));

		return parseByteData(byteData, charsetName, uri, Parser.htmlParser());

	}



	public static Document parseByteData(ByteBuffer byteData, String charsetName, String baseUri, Parser parser) {

		String docData = null;

		Document doc = null;

		if (charsetName == null) {

		} else {

			Validate.notEmpty(charsetName,

					"Must set charset arg to character set of file to parse. Set to null to attempt to detect from HTML");

			docData = Charset.forName(charsetName).decode(byteData).toString();

		}

		if (doc == null) {

			if (docData.length() > 0 && docData.charAt(0) == 65279)

				docData = docData.substring(1);



			doc = parser.parseInput(docData, baseUri);

			doc.outputSettings().charset(charsetName);

		}

		return doc;

	}

}