html写入java,java解析HTML，并写入TXT

package foo;

import java.io.File;

import java.io.IOException;

import java.io.PrintStream;

import java.util.Iterator;

import java.util.List;

import org.jsoup.Jsoup;

import org.jsoup.nodes.Document;

import org.jsoup.nodes.Element;

/**

* 解析HTML，并写入到TXT。

* @author Administrator

*

*/

public class ReadHtml {

public static void main(String[] args) throws IOException {

//输出打印流

PrintStream ps = new PrintStream(new File("E:\\test\\result.txt"));

Document doc;

doc = Jsoup.parse(new File("E:\\test\\list.html") , "UTF-8");

//获取所有的

List list = doc.select("tr");

Iterator iter = list.iterator();

String newName = null;

String oldName = "";

while (iter.hasNext()) {

Element ele = iter.next();

List tds = ele.select("td");

// 统一格式(即

标签内都有5个的才解析)

if (tds.size() == 5) {

//过滤掉某些内容

if ("撤销建制".equals(tds.get(2).text()) || "新建".equals(tds.get(2).text()) || "去筹新建".equals(tds.get(2).text())) {

continue;

}

List as = tds.get(3).select("td");

if (as.size() > 0) {

for (Element a : as) {

// 有多个学校名称合并的，以“,”分隔

oldName += a.text().replace(" ", ",") + ",";

}

} else {

oldName = tds.get(3).text();

}

if (oldName.endsWith(",")) {

oldName = oldName.substring(0, oldName.length() - 1);

}

newName = tds.get(1).text();

ps.println(newName + "," + oldName);

System.out.println(newName + "," + oldName);

}

oldName = "";

}

ps.close();

}

}