提取图片

package com.zhuyu_deng.test;

import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class ImageExtractor
{
	// 得到了图片地址并下载图片
	public void getHtmlPicture(String httpUrl)
	{
		URL url;
		BufferedInputStream in;
		FileOutputStream file;
		int count; // 图片文件名序号
		FileNumber num = new FileNumber();// 图片文件名序号类，num为对象
		count = num.NumberReadFromFile();// 获取图片文件序号
		try
		{
			System.out.println("获取网络图片");
			String fileName = (String.valueOf(count)).concat(httpUrl.substring(httpUrl.lastIndexOf(".")));// 图片文件序号加上图片的后缀名，后缀名用了String内的一个方法来获得
			// httpUrl.substring(httpUrl.lastIndexOf("/"));//这样获得的文件名即是图片链接里图片的名字
			String filePath = "/home/Jerry/imageTMP";// 图片存储的位置
			url = new URL(httpUrl);

			in = new BufferedInputStream(url.openStream());

			file = new FileOutputStream(new File(filePath + fileName));
			int t;
			while ((t = in.read()) != -1)
			{
				file.write(t);
			}
			file.close();
			in.close();
			System.out.println("图片获取成功");
			count = count + 1;// 图片文件序号加1
			num.NumberWriteToFile(count);// 将图片名序号保存
		} catch (MalformedURLException e)
		{
			e.printStackTrace();
		} catch (FileNotFoundException e)
		{
			e.printStackTrace();
		} catch (IOException e)
		{
			e.printStackTrace();
		}
	}

	// 获取网页的代码保存在String格式的Content中
	public String getHtmlCode(String httpUrl) throws IOException
	{
		String content = "";
		URL uu = new URL(httpUrl); // 创建URL类对象
		BufferedReader ii = new BufferedReader(new InputStreamReader(
				uu.openStream())); // //使用openStream得到一输入流并由此构造一个BufferedReader对象
		String input;
		while ((input = ii.readLine()) != null)
		{ // 建立读取循环，并判断是否有读取值
			content += input;
		}
		ii.close();
		return content;
	}

	// 分析网页代码，找到匹配的网页图片地址
	public void get(String url) throws IOException
	{

		String searchImgReg = "(?x)(src|SRC|background|BACKGROUND)=('|\")/?(([\\w-]+/)*([\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))('|\")";// 用于在网页代码Content中查找匹配的图片链接。
		String searchImgReg2 = "(?x)(src|SRC|background|BACKGROUND)=('|\")(http://([\\w-]+\\.)+[\\w-]+(:[0-9]+)*(/[\\w-]+)*(/[\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))('|\")";

		String content = this.getHtmlCode(url);// this指对象gcp，在此地调用获取网页代码，getHtmlCode方法
		// System.out.println(content); //输出的content将是一个连续的字符串。

		Pattern pattern = Pattern.compile(searchImgReg);// java.util.regex.Pattern
		Matcher matcher = pattern.matcher(content); // java.util.regex.Matcher
		while (matcher.find())
		{
			System.out.println(matcher.group(3));// 输出图片链接地址到屏幕
			// System.out.println(url);
			this.getHtmlPicture(matcher.group(3));// 对象调用getHtmlPicture从网上下载并输出图片文件到指定目录

		}

		pattern = Pattern.compile(searchImgReg2);
		matcher = pattern.matcher(content);
		while (matcher.find())
		{
			System.out.println(matcher.group(3));
			this.getHtmlPicture(matcher.group(3));

		}
		// searchImgReg =
		// "(?x)(src|SRC|background|BACKGROUND)=('|\")/?(([\\w-]+/)*([\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))('|\")";
	}

	// 主函数url网页的地址
	public static void main(String[] args) throws IOException
	{

		String url = "http://pp.baidu.com/";
		ImageExtractor gcp = new ImageExtractor();
		gcp.get(url);

	}

}