詳解JAVA抓取網頁的圖片,JAVA應用正則表達式抓取網站圖片

應用Java抓取網頁上的一切圖片：

用兩個正則表達式：

1、婚配html中img標簽的正則：<img.*src=(.*?)[^>]*?>

2、婚配img標簽中得src中http途徑的正則：http:\"?(.*?)(\"|>|\\s+)

完成：

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抓取網絡圖片 
 * @author swinglife 
 * 
 */ 
public class CatchImage { 
 
  // 地址 
  private static final String URL = "http://www.csdn.net"; 
  // 編碼 
  private static final String ECODING = "UTF-8"; 
  // 獲取img標簽正則 
  private static final String IMGURL_REG = "<img.*src=(.*?)[^>]*?>"; 
  // 獲取src途徑的正則 
  private static final String IMGSRC_REG = "http:\"?(.*?)(\"|>|\\s+)"; 
 
   
  public static void main(String[] args) throws Exception { 
    CatchImage cm = new CatchImage(); 
    //取得html文本內容 
    String HTML = cm.getHTML(URL); 
    //獲取圖片標簽 
    List<String> imgUrl = cm.getImageUrl(HTML); 
    //獲取圖片src地址 
    List<String> imgSrc = cm.getImageSrc(imgUrl); 
    //下載圖片 
    cm.Download(imgSrc); 
  } 
   
   
  /*** 
   * 獲取HTML內容 
   * 
   * @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(); 
  } 
 
  /*** 
   * 獲取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; 
  } 
 
  /*** 
   * 獲取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; 
  } 
 
  /*** 
   * 下載圖片 
   * 
   * @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("開端下載:" + url); 
        while ((length = in.read(buf, 0, buf.length)) != -1) { 
          fo.write(buf, 0, length); 
        } 
        in.close(); 
        fo.close(); 
        System.out.println(imageName + "下載完成"); 
      } 
    } catch (Exception e) { 
      System.out.println("下載失敗"); 
    } 
  } 
 
   
} 

以上就是本文的全部內容，希望對大家的學習有所協助，也希望大家多多支持。