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呐喊教程。
声明:本文内容来源于网络,版权归原作者所有,内容由互联网用户自发贡献自行上传,本网站不拥有所有权,未作人工编辑处理,也不承担相关法律责任。如果您发现有涉嫌版权的内容,欢迎发送邮件至:notice#nhooo.com(发邮件时,请将#更换为@)进行举报,并提供相关证据,一经查实,本站将立刻删除涉嫌侵权内容。