详解JAVA抓取网页的图片,JAVA利用正则表达式抓取网站图片

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：]*?>

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://csdn.net";

// 编码

private static final String ECODING = "UTF-8";

// 获取img标签正则

private static final String IMGURL_REG = "]*?>";

// 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 imgUrl = cm.getImageUrl(HTML);

//获取图片src地址

List 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 ((lepzcpXngth = 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 getImageUrl(String HTML) {

Matcher matcher = Pattern.compile(IMGURL_REG).matcher(HTML);

List listImgUrl = new ArrayList();

while (matcher.find()) {

listImgUrl.add(matcher.group());

}

return listImgUrl;

}

/***

* 获取ImageSrc地址

*

* @param listImageUrl

* @return

*/

private List getImageSrc(List listImageUrl) {

List listImgSrc = new ArrayList();

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

*pzcpX

* @param listImgSrc

*/

private void Download(List 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");

}

}

}

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。