网络图片抓取--web开发批量盗图！！！！！

该类用于网络图片抓取，只需要一个记录了所需图片URL的文本文件，就可自动解析抓取图片，并且可以按照url的路径自动存储，方便快捷，盗图利器

package com.mms.utils;import java.io.BufferedReader;import java.io.DataInputStream;import java.io.File;import java.io.FileInputStream;import java.io.FileNotFoundException;import java.io.FileOutputStream;import java.io.IOException;import java.io.InputStreamReader;import java.net.URL;import java.util.regex.Matcher;import java.util.regex.Pattern;public class ImageTerminator {//记录文件数private static int COUNT = 1;private static String savePath;public static void setSavePath(String savePath) {ImageTerminator.savePath = savePath;}// 一次读一行public static void readByLine(String filePath) {FileInputStream fis = null;InputStreamReader isr = null;BufferedReader br = null;try {File file = new File(filePath);if (!file.exists()) {return;}fis = new FileInputStream(file);isr = new InputStreamReader(fis, "GBK");br = new BufferedReader(isr);String line = "";while ((line = br.readLine()) != null) {// 空行跳过if ("".equals(line.trim())) {continue;}// System.out.println(imageUrlFilter(line));// System.out.println(getDirPath(null,imageUrlFilter(line)));// System.out.println(getFileName(imageUrlFilter(line)));// 获取图片getImage(imageUrlFilter(line));}} catch (Exception e) {e.printStackTrace();} finally {try {if (br != null)br.close();if (isr != null)isr.close();if (fis != null)fis.close();} catch (IOException e) {// TODO Auto-generated catch blocke.printStackTrace();}}}// 截取图片格式的urlpublic static String imageUrlFilter(String str) {if (str.indexOf("http") == -1) {return str;}// 保留从http开始以后的字符串if (str.indexOf("src=\"http") > -1) {str = str.substring(str.indexOf("src=\"http"));}str = str.substring(str.indexOf("http"));// 过滤带有图片格式后缀的urlif (str.indexOf(".jpg") > -1) {str = str.substring(0, str.indexOf(".jpg"));str += ".jpg";} else if (str.indexOf(".jpeg") > -1) {str = str.substring(0, str.indexOf(".jpeg"));str += ".jpeg";} else if (str.indexOf(".png") > -1) {str = str.substring(0, str.indexOf(".png"));str += ".png";} else if (str.indexOf(".gif") > -1) {str = str.substring(0, str.indexOf(".gif"));str += ".gif";} else {str = null;}return str;}// 通过url截取存储路径// e.g：http://img.j1.com/images/images1308/logo/yplogo_59.jpg---->/img.j1.com/images/images1308/logo/// 该url参数为已调用imageUrlFilter方法后得到的url// root用于指定存入路径e.g: root=d://abc/123,默认在D盘public static String getDirPath(String root, String url) {if (url == null || url.indexOf("http:") == -1) {return null;}// 指定url字符串中“/”第三次出现的位置索引，到最后一个“/”出现的位置索引url = url.substring(getCharacterPosition(url, "/", 3) + 1, url.lastIndexOf("/"));if (root == null) {url = "D://" + url;} else {url = root.trim() + url;}return url;}// 计算指定字符在字符串中第N次出现的位置// string : 要进行匹配的字符串// specify : 指定需要匹配的字符// n : 指定计算此匹配字符在字符串中第几次出现// return ： 第n次出现在该字符串中的索引public static int getCharacterPosition(String string, String specify, int n) {// 这里是获取"#"符号的位置Matcher slashMatcher = Pattern.compile(specify).matcher(string);int mIdx = 0;while (slashMatcher.find()) {mIdx++;// 当"#"符号第二次出现的位置if (mIdx == n) {break;}}return slashMatcher.start();}public static String getFileName(String url) {if (url != null && !"".equals(url.trim())) {if (url.lastIndexOf("/") != -1) {url = url.substring(url.lastIndexOf("/") + 1);}}return url;}// 通过url获取图片（储存路径对应url中的相对路径）public static void getImage(String urls) {DataInputStream dis = null;FileOutputStream fos = null;try {if (urls == null || "".equals(urls.trim())) {return;}URL url = new URL(urls);System.out.println("正在下载：" + urls);// 根据截取到的图片url截取图片相对路径String dirPath = getDirPath(savePath, urls);System.out.println("存入位置：" + dirPath);File outFile = new File(dirPath);if (!outFile.isDirectory()) {outFile.mkdirs();outFile = new File(dirPath + "/" + getFileName(urls));} else {outFile = new File(dirPath + "/" + getFileName(urls));}System.out.println("文件名：" + getFileName(urls));// 此处异常捕获是为了捕获在服务器端未找到文件的异常try {dis = new DataInputStream(url.openStream());} catch (Exception e) {System.err.println("该文件未找到！！");return;}fos = new FileOutputStream(outFile);byte[] buff = new byte[1024];int length;while ((length = dis.read(buff)) > 0) {fos.write(buff, 0, length);}fos.flush();System.out.println("第" + (COUNT++) + "个文件，已完成下载");} catch (Exception e) {e.printStackTrace();} finally {try {if (fos != null)fos.close();if (dis != null)dis.close();} catch (Exception e2) {e2.printStackTrace();}}return;}public static void main(String[] args) {// 调用：只需输入需要扫描的记录了url集的文件(存储路径可选参数，不填默认下载到D盘根目录)setSavePath("D://abc/456/");readByLine("D:\\\\slk\\开发归纳\\批量抓图\\url.txt");}}

演示需解析的文本如下，只要是标准的http请求都能解析到。。。。

执行结果