详解JAVA抓取网页的图片,JAVA利用正则表达式抓取网站图片

利用java抓取网页上的所有图片：

用两个正则表达式：

1、匹配html中img标签的正则：<img.*src=(.*?)[^>]*?>

2、匹配img标签中得src中http路径的正则：http:\"?(.*?)(\"|>|\\s+)

实现：

package org.swinglife.main; 
 
import java.io.file; 
import java.io.fileoutputstream; 
import java.io.inputstream; 
import java.net.url; 
import java.net.urlconnection; 
import java.util.arraylist; 
import java.util.list; 
import java.util.regex.matcher; 
import java.util.regex.pattern; 
 
/*** 
 * java抓取网络图片 
 * @author swinglife 
 * 
 */ 
public class catchimage { 
 
  // 地址 
  private static final string url = "http://www.csdn.net"; 
  // 编码 
  private static final string ecoding = "utf-8"; 
  // 获取img标签正则 
  private static final string imgurl_reg = "<img.*src=(.*?)[^>]*?>"; 
  // 获取src路径的正则 
  private static final string imgsrc_reg = "http:\"?(.*?)(\"|>|\\s+)"; 
 
   
  public static void main(string[] args) throws exception { 
    catchimage cm = new catchimage(); 
    //获得html文本内容 
    string html = cm.gethtml(url); 
    //获取图片标签 
    list<string> imgurl = cm.getimageurl(html); 
    //获取图片src地址 
    list<string> imgsrc = cm.getimagesrc(imgurl); 
    //下载图片 
    cm.download(imgsrc); 
  } 
   
   
  /*** 
   * 获取html内容 
   * 
   * @param url 
   * @return 
   * @throws exception 
   */ 
  private string gethtml(string url) throws exception { 
    url uri = new url(url); 
    urlconnection connection = uri.openconnection(); 
    inputstream in = connection.getinputstream(); 
    byte[] buf = new byte[1024]; 
    int length = 0; 
    stringbuffer sb = new stringbuffer(); 
    while ((length = in.read(buf, 0, buf.length)) > 0) { 
      sb.append(new string(buf, ecoding)); 
    } 
    in.close(); 
    return sb.tostring(); 
  } 
 
  /*** 
   * 获取imageurl地址 
   * 
   * @param html 
   * @return 
   */ 
  private list<string> getimageurl(string html) { 
    matcher matcher = pattern.compile(imgurl_reg).matcher(html); 
    list<string> listimgurl = new arraylist<string>(); 
    while (matcher.find()) { 
      listimgurl.add(matcher.group()); 
    } 
    return listimgurl; 
  } 
 
  /*** 
   * 获取imagesrc地址 
   * 
   * @param listimageurl 
   * @return 
   */ 
  private list<string> getimagesrc(list<string> listimageurl) { 
    list<string> listimgsrc = new arraylist<string>(); 
    for (string image : listimageurl) { 
      matcher matcher = pattern.compile(imgsrc_reg).matcher(image); 
      while (matcher.find()) { 
        listimgsrc.add(matcher.group().substring(0, matcher.group().length() - 1)); 
      } 
    } 
    return listimgsrc; 
  } 
 
  /*** 
   * 下载图片 
   * 
   * @param listimgsrc 
   */ 
  private void download(list<string> listimgsrc) { 
    try { 
      for (string url : listimgsrc) { 
        string imagename = url.substring(url.lastindexof("/") + 1, url.length()); 
        url uri = new url(url); 
        inputstream in = uri.openstream(); 
        fileoutputstream fo = new fileoutputstream(new file(imagename)); 
        byte[] buf = new byte[1024]; 
        int length = 0; 
        system.out.println("开始下载:" + url); 
        while ((length = in.read(buf, 0, buf.length)) != -1) { 
          fo.write(buf, 0, length); 
        } 
        in.close(); 
        fo.close(); 
        system.out.println(imagename + "下载完成"); 
      } 
    } catch (exception e) { 
      system.out.println("下载失败"); 
    } 
  } 
 
   
} 

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。