htmlparser使用2

import java.net.*;

import java.io.*;

import org.htmlparser.NodeFilter;

import org.htmlparser.Parser;

import org.htmlparser.filters.TagNameFilter;

import org.htmlparser.tags.TableColumn;

import org.htmlparser.tags.TableRow;

import org.htmlparser.tags.TableTag;

import org.htmlparser.util.NodeList;

 

public class Test {

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

// TODO Auto-generated method stub

test5(readNetFile());// 当然这里可以写成一个链接地址比如将html代替为"http://www.baidu.com"

}

 

public static String readNetFile() {

// System.out

// .println("-------------------------读取网页文件开始---------------------");

URL url = null;

try {

url = new URL(

"http://www.dailyfx.com.hk/calendar/index.php?date=2011-02-14");

} catch (MalformedURLException ex2) {

ex2.printStackTrace();

}

URLConnection conn = null;

BufferedReader br = null;

try {

conn = url.openConnection();

br = new BufferedReader(new InputStreamReader(

conn.getInputStream(), "utf-8"));

} catch (IOException ex1) {

ex1.printStackTrace();

}

 

String temp = null;

StringBuffer sb = new StringBuffer();

try {

temp = br.readLine();

while (temp != null) {

sb.append(temp + "\n");

temp = br.readLine();

}

} catch (IOException ex) {

ex.printStackTrace();

}

// System.out.println(sb.toString());

// System.out

// .println("-------------------------读取网页文件结束---------------------");

return sb.toString();

}

 

// static String html = "http://www.baidu.com";

 

public static void test5(String resource) throws Exception {

Parser myParser = new Parser(resource);

// Parser parser = new Parser(content);

// 设置编码

myParser.setEncoding("utf-8");

// String filterStr = "table";//这里析取得是标签为table的元素

String filterStr = "table";

NodeFilter filter = new TagNameFilter(filterStr);// 过滤这个标签

NodeList tableList = myParser.extractAllNodesThatMatch(filter);// 抽取所有table列表

 

// 只需要读取最后一个表格

for (int i = tableList.size() - 1; i < tableList.size(); i++) {

TableTag table = (TableTag) tableList.elementAt(i);

// 取得表中的行集

TableRow[] rows = table.getRows();

// 遍历每行

for (int r = 0; r < rows.length; r++) {

TableRow tr = rows[r];

TableColumn[] td = tr.getColumns();

// 行中的列

for (int c = 0; c < td.length; c++) {

System.out.print(td[c].toPlainTextString() + " ");

}

System.out.println();

 

}

 

}

}

}

转载于:https://www.cnblogs.com/licomeback/articles/3091044.html