java 获取网页标题_java 网页页面抓取标题和正文

import java.io.BufferedReader;

import java.io.IOException;

import java.io.InputStreamReader;

import java.net.MalformedURLException;

import java.net.URL;

import java.util.ArrayList;

import java.util.HashMap;

import java.util.List;

import java.util.regex.Matcher;

import java.util.regex.Pattern;

public class WebContent

{

public String getOneHtml(final String htmlurl)

throws IOException

{

URL url;

String temp;

final StringBuffer sb = new

StringBuffer();

try

{

url = new URL(htmlurl);

final BufferedReader in = new

BufferedReader(new InputStreamReader(url.openStream(), "utf-8"));//

读取网页全部内容

while ((temp = in.readLine())

!= null)

{

sb.append(temp);