HTML 파일의 메타정보 인코딩 방식 일괄 변경

有的时候html文件的编码方式与meta信息中指定的编码方式不同，可以通过这段代码搞一下。 此程序依赖jsoup和commons-io包

import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.io.Writer;
import java.util.Iterator;

import org.apache.commons.io.FileUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class main {

	/**
	 * @param args
	 * @throws IOException
	 */
	public static void main(String[] args) throws IOException {
		// TODO Auto-generated method stub

		File input = new File("C:\Users\jack\Desktop\新建文件夹\jdk-zh");
		Iterator it = FileUtils.iterateFiles(input, null, true);
		while (it.hasNext()) {
			File file = it.next();
			Document doc = Jsoup.parse(file, "gb2312");
			Elements content = doc.getElementsByAttributeValueStarting("content", "text/html;");
			for (Element meta : content) {
				meta.attr("content", "text/html; charset=utf-8");
				System.out
						.println("修改content--------"   file.getName()   "---");
			}
			FileUtils.writeStringToFile(file, doc.html(),"utf-8");
		}
	}
}