java抓取网页内容 - JAVA

今天做项目时用到java抓取网页内容，本以为很简单的一件事但是还是让我蛋疼了一会，网上资料一大堆但是都是通过url抓取网页内容，但是我要的是读取本地的html页面内容的方法，网上找不到怎么办我瞬间了！

首先还是向大家讲解一下通过url抓取网页内容吧，通过正则表达式摘取title、js、css等网页元素，代码如下：

[html]
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.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
*
* @author yaohucaizi
*/
public class Test {

/**
* 读取网页全部内容
*/
public String getHtmlContent(String htmlurl) {
URL url;
String temp;
StringBuffer sb = new StringBuffer();
try {
url = new URL(htmlurl);
BufferedReader in = new BufferedReader(new InputStreamReader(url.openStream(), "gbk"));// 读取网页全部内容
while ((temp = in.readLine()) != null) {
sb.append(temp);
}
in.close();
} catch (final MalformedURLException me) {
System.out.println("你输入的URL格式有问题!");
me.getMessage();
} catch (final IOException e) {
e.printStackTrace();
}
return sb.toString();
}

/**
*
* @param s
* @return 获得网页标题
*/
public String getTitle(String s) {
String regex;
String title = "";
List list = new ArrayList();
regex = ".* ";
Pattern pa = Pattern.compile(regex, Pattern.CANON_EQ);
Matcher ma = pa.matcher(s);
while (ma.find()) {
list.add(ma.group());
}
for (int i = 0; i < list.size(); i++) {
title = title + list.get(i);
}
return outTag(title);
}

/**
*
* @param s
* @return 获得链接
*/

public List getLink(String s) {
String regex;
List list = new ArrayList();
regex = "]*href=(\"([^\"]*)\"|\'([^\']*)\'|([^\\s>]*))[^>]*>(.* )";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
while (ma.find()) {
list.add(ma.group());
}
return list;
}

/**
*
* @param s
* @return 获得脚本代码
*/
public List getScript(String s) {
String regex;
List list = new ArrayList();
regex = "";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
while (ma.find()) {
list.add(ma.group());
}
return list;
}

public List getNews(String s) {
String regex = "";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
List list = new ArrayList();
while (ma.find()) {
list.add(ma.group());
}
return list;
}

/**
*
* @param s
* @return 获得CSS
*/
public List getCSS(String s) {
String regex;
List list = new ArrayList();
regex = "";
Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
Matcher ma = pa.matcher(s);
while (ma.find()) {
list.add(ma.group());
}
return list;
}

/**
*
* @param s
* @return 去掉标记
*/
public String outTag(final String s) {
return s.replaceAll("<.* >", "");
}

java抓取网页内容 (一)