简易新闻网站NewsWeb-网页抓取

本文转载自姚虎才子

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<String> list = new ArrayList<String>(); 
        regex = "<title>.*?</title>"; 
        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<String> getLink(String s) { 
        String regex; 
        List<String> list = new ArrayList<String>(); 
        regex = "<a[^>]*href=(\"([^\"]*)\"|\'([^\']*)\'|([^\\s>]*))[^>]*>(.*?)</a>"; 
        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<String> getScript(String s) { 
        String regex; 
        List<String> list = new ArrayList<String>(); 
        regex = "<SCRIPT.*?</SCRIPT>"; 
        Pattern pa = Pattern.compile(regex, Pattern.DOTALL); 
        Matcher ma = pa.matcher(s); 
        while (ma.find()) { 
            list.add(ma.group()); 
        } 
        return list; 
    } 
     
    public List<String> getNews(String s) { 
        String regex = "<a.*?</a>"; 
        Pattern pa = Pattern.compile(regex, Pattern.DOTALL); 
        Matcher ma = pa.matcher(s); 
        List<String> list = new ArrayList<String>(); 
        while (ma.find()) { 
            list.add(ma.group()); 
        } 
        return list; 
    } 
 
    /** 
     * 
     * @param s 
     * @return 获得CSS 
     */ 
    public List<String> getCSS(String s) { 
        String regex; 
        List<String> list = new ArrayList<String>(); 
        regex = "<style.*?</style>"; 
        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("<.*?>", ""); 
    } 
     
    public static void main(String[] args) { 
        Test t = new Test(); 
        String content = t.getHtmlContent("http://www.taobao.com"); 
        //content = content.replaceAll("(<br>)+?", "\n");// 转化换行 
        //content = content.replaceAll("<p><em>.*?</em></p>", "");// 去图片注释 
        System.out.println(content); 
        System.out.println(t.getTitle(content)); 
        List<String> a = t.getNews(content); 
        List<String> news = new ArrayList<String>(); 
        for (String s : a) { 
            news.add(s.replaceAll("<.*?>", "")); 
        } 
        System.out.println(news); 
        //…… 获取js、css等操作省略 
    } 
}

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

/**
     *
     * @param s
     * @return 获得CSS
     */
    public List<String> getCSS(String s) {
        String regex;
        List<String> list = new ArrayList<String>();
        regex = "<style.*?</style>";
        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("<.*?>", "");
    }
   
    public static void main(String[] args) {
        Test t = new Test();
        String content = t.getHtmlContent("http://www.taobao.com");
        //content = content.replaceAll("(<br>)+?", "\n");// 转化换行
        //content = content.replaceAll("<p><em>.*?</em></p>", "");// 去图片注释
        System.out.println(content);
        System.out.println(t.getTitle(content));
        List<String> a = t.getNews(content);
        List<String> news = new ArrayList<String>();
        for (String s : a) {
            news.add(s.replaceAll("<.*?>", ""));
        }
        System.out.println(news);
        //…… 获取js、css等操作省略
    }
}
后来我想了想我觉得读取本地和通过url读取原理不是一样的嘛，但是我尝试了好多种写法都不行，不是乱码问题就是报错，我该怎么办 老天就是这样捉弄人，功夫不负有心人当我尝试至999次时候突然眼前一亮，我成功实现读取本地html了……说真的代码不难但是你需要多次尝试，把我的代码分享给大家：

[html]
/** 
 * 抓取本地网页内容 
 * 
 * @param filePath 
 * @return 
 */ 
public static String getHtmlContent(String filePath) { 
    String temp; 
    BufferedReader br; 
    StringBuffer sb = new StringBuffer(); 
    try { 
        br = new BufferedReader(new InputStreamReader(new FileInputStream(filePath), "GB2312")); 
        while ((temp = br.readLine()) != null) { 
            sb.append(temp); 
        } 
    } catch (IOException e) { 
        e.printStackTrace(); 
    } 
    return sb.toString(); 
}

/**
     * 抓取本地网页内容
     *
     * @param filePath
     * @return
     */
    public static String getHtmlContent(String filePath) {
        String temp;
        BufferedReader br;
        StringBuffer sb = new StringBuffer();
        try {
            br = new BufferedReader(new InputStreamReader(new FileInputStream(filePath), "GB2312"));
            while ((temp = br.readLine()) != null) {
                sb.append(temp);
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        return sb.toString();
    }