android 封装抓取网页信息的实例代码

package cn.mypic; 

 
    import java.io.bufferedinputstream; 
    import java.io.bufferedreader; 
    import java.io.file; 
    import java.io.filenotfoundexception; 
    import java.io.fileoutputstream; 
    import java.io.ioexception; 
    import java.io.inputstreamreader; 
    import java.net.malformedurlexception; 
    import java.net.url; 
    import java.util.regex.matcher; 
    import java.util.regex.pattern; 

 
    public class getcontentpicture { 
    //得到了图片地址并下载图片 
    public void gethtmlpicture(string httpurl) { 
    url url; 
    bufferedinputstream in; 
    fileoutputstream file; 
    int count;                      //图片文件名序号  
    filenumber num=new filenumber();//图片文件名序号类，num为对象 
    count=num.numberreadfromfile();//获取图片文件序号 
    try { 
    system.out.println("获取网络图片"); 
       string filename = (string.valueof(count)).concat(httpurl.substring(httpurl.lastindexof(".")));//图片文件序号加上图片的后缀名，后缀名用了string内的一个方法来获得 
        //httpurl.substring(httpurl.lastindexof("/"));//这样获得的文件名即是图片链接里图片的名字 
       string filepath = "d:/image/";//图片存储的位置 
       url = new url(httpurl); 

       in = new bufferedinputstream(url.openstream()); 

       file = new fileoutputstream(new file(filepath+filename)); 
       int t; 
       while ((t = in.read()) != -1) { 
        file.write(t); 
       } 
       file.close(); 
       in.close(); 
       system.out.println("图片获取成功"); 
       count=count+1;//图片文件序号加1 
       num.numberwritetofile(count);//将图片名序号保存 
    } catch (malformedurlexception e) { 
       e.printstacktrace(); 
    } catch (filenotfoundexception e) { 
       e.printstacktrace(); 
    } catch (ioexception e) { 
       e.printstacktrace(); 
    } 
    } 

    //获取网页的代码保存在string格式的content中 
    public string gethtmlcode(string httpurl) throws ioexception { 
    string content =""; 
    url uu = new url(httpurl); // 创建url类对象 
    bufferedreader ii = new bufferedreader(new inputstreamreader(uu 
        .openstream())); // //使用openstream得到一输入流并由此构造一个bufferedreader对象 
    string input; 
    while ((input = ii.readline()) != null) { // 建立读取循环，并判断是否有读取值 
       content += input; 
    } 
    ii.close(); 
    return content; 
    } 
    //分析网页代码，找到匹配的网页图片地址 
    public void get(string url) throws ioexception { 

    string searchimgreg = "(?x)(src|src|background|background)=('|\")/?(([\\w-]+/)*([\\w-]+\\.(jpg|jpg|png|png|gif|gif)))('|\")";//用于在网页代码content中查找匹配的图片链接。 
    string searchimgreg2 = "(?x)(src|src|background|background)=('|\")(http://([\\w-]+\\.)+[\\w-]+(:[0-9]+)*(/[\\w-]+)*(/[\\w-]+\\.(jpg|jpg|png|png|gif|gif)))('|\")"; 

    string content = this.gethtmlcode(url);//this指对象gcp，在此地调用获取网页代码，gethtmlcode方法 
    //system.out.println(content); //输出的content将是一个连续的字符串。 

    pattern pattern = pattern.compile(searchimgreg);//java.util.regex.pattern 
    matcher matcher = pattern.matcher(content);     //java.util.regex.matcher 
    while (matcher.find()) { 
       system.out.println(matcher.group(3));//输出图片链接地址到屏幕 
    // system.out.println(url); 
       this.gethtmlpicture(matcher.group(3));//对象调用gethtmlpicture从网上下载并输出图片文件到指定目录 

    } 

    pattern = pattern.compile(searchimgreg2); 
    matcher = pattern.matcher(content); 
    while (matcher.find()) { 
       system.out.println(matcher.group(3)); 
       this.gethtmlpicture(matcher.group(3)); 

    } 
    // searchimgreg = 
    // "(?x)(src|src|background|background)=('|\")/?(([\\w-]+/)*([\\w-]+\\.(jpg|jpg|png|png|gif|gif)))('|\")"; 
    } 
    //主函数url网页的地址 
    public static void main(string[] args) throws ioexception { 

    string url = "http://www.baidu.com"; 
    getcontentpicture gcp = new getcontentpicture(); 
    gcp.get(url); 

 
    } 

} 

package cn.mypic; 

    import java.io.*; 

    public class filenumber{ 
    //文件写 
    public void numberwritetofile(int x){ 
       int c=0; 
       c=x; 
       file filepath=new file("d:/image");//文件名序号txt文件保存地址 
       file f1=new file(filepath,"number.txt"); 
       try{ 
        fileoutputstream fout=new fileoutputstream(f1); 
        dataoutputstream out=new dataoutputstream(fout); 
        out.writeint(c); 

       } 
       catch(filenotfoundexception e){ 
        system.err.println(e); 
       } 
       catch(ioexception e){ 
        system.err.println(e); 
       } 

    } 
    //文件读 
    public int numberreadfromfile(){ 
       int c1 = 0; 
       file filepath=new file("d:/image"); 
       file f1=new file(filepath,"number.txt"); 
       try{ 
        fileinputstream fin=new fileinputstream(f1); 
        datainputstream in=new datainputstream(fin); 
        c1=in.readint(); 
        system.out.println(c1);//输出文件内容至屏幕 
       } 
       catch(filenotfoundexception e){ 
        system.err.println(e); 
       } 
       catch(ioexception e){ 
        system.err.println(e); 
       } 
       return c1; 
    } 
    public static void main(string args[]){ 

    } 

}