java爬虫-简单爬取网页图片

　　刚刚接触到“爬虫”这个词的时候是在大一，那时候什么都不明白，但知道了百度、谷歌他们的搜索引擎就是个爬虫。

现在大二。再次燃起对爬虫的热爱，查阅资料，知道常用java、python语言编程，这次我选择了java。在网上查找的

代码在本地跑大部分都不能使用，查找相关的资料教程也没有适合的。实在头疼、、、

　　现在自己写了一个简单爬取网页图片的代码，先分析一下自己写的代码吧

            //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);

　　简单分为四个功能方法（函数），首先是要获取html文本

 //获取HTML内容private String getHtml(String url)throws Exception{URL url1=new URL(url);//使用java.net.URLURLConnection connection=url1.openConnection();//打开链接InputStream in=connection.getInputStream();//获取输入流InputStreamReader isr=new InputStreamReader(in);//流的包装BufferedReader br=new BufferedReader(isr);String line;StringBuffer sb=new StringBuffer();while((line=br.readLine())!=null){//整行读取sb.append(line,0,line.length());//添加到StringBuffer中sb.append('\n');//添加换行符
        }//关闭各种流，先声明的后关闭
        br.close();isr.close();in.close();return sb.toString();}

然后在获取的html文本中寻找图片，根据html标记语言不难发现图片通常带有<img>，所以

写一个关于img的正则表达式

    // 获取img标签正则private static final String IMGURL_REG = "<img.*src=(.*?)[^>]*?>";

接着是获取img标签信息，大部分涉及的是集合接口和正则表达式的知识

//获取ImageUrl地址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;}

然后获取img标签信息中找取图片的地址信息，需要构造图片地址的正则表达式

// 获取src路径的正则private static final String IMGSRC_REG = "[a-zA-z]+://[^\\s]*";

接着是获取图片地址的信息，大部分涉及的也是集合接口和正则表达式的知识

//获取ImageSrc地址private List<String> getImageSrc(List<String> listimageurl){List<String> listImageSrc=new ArrayList<String>();for (String image:listimageurl){Matcher matcher=Pattern.compile(IMGSRC_REG).matcher(image);while (matcher.find()){listImageSrc.add(matcher.group().substring(0, matcher.group().length()-1));}}return listImageSrc;}

最后通过图片地址信息下载图片

//下载图片private void Download(List<String> listImgSrc) {try {//开始时间Date begindate = new Date();for (String url : listImgSrc) {//开始时间Date begindate2 = new Date();String imageName = url.substring(url.lastIndexOf("/") + 1, url.length());URL uri = new URL(url);InputStream in = uri.openStream();FileOutputStream fo = new FileOutputStream(new File("src/res/"+imageName));//文件输出流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);}//关闭流
                in.close();fo.close();System.out.println(imageName + "下载完成");//结束时间Date overdate2 = new Date();double time = overdate2.getTime() - begindate2.getTime();System.out.println("耗时：" + time / 1000 + "s");}Date overdate = new Date();double time = overdate.getTime() - begindate.getTime();System.out.println("总耗时：" + time / 1000 + "s");} catch (Exception e) {System.out.println("下载失败");}}

展示一下运行结果：

上一下全部代码：

import java.io.*;
import java.net.URL;
import java.net.URLConnection;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;public class Main {// 地址private static final String URL = "http://www.tooopen.com/view/1439719.html";// 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 = "[a-zA-z]+://[^\\s]*";public static void main(String[] args) {try {Main cm=new Main();//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);}catch (Exception e){System.out.println("发生错误");}}//获取HTML内容private String getHtml(String url)throws Exception{URL url1=new URL(url);URLConnection connection=url1.openConnection();InputStream in=connection.getInputStream();InputStreamReader isr=new InputStreamReader(in);BufferedReader br=new BufferedReader(isr);String line;StringBuffer sb=new StringBuffer();while((line=br.readLine())!=null){sb.append(line,0,line.length());sb.append('\n');}
        br.close();isr.close();in.close();return sb.toString();}//获取ImageUrl地址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private List<String> getImageSrc(List<String> listimageurl){List<String> listImageSrc=new ArrayList<String>();for (String image:listimageurl){Matcher matcher=Pattern.compile(IMGSRC_REG).matcher(image);while (matcher.find()){listImageSrc.add(matcher.group().substring(0, matcher.group().length()-1));}}return listImageSrc;}//下载图片private void Download(List<String> listImgSrc) {try {//开始时间Date begindate = new Date();for (String url : listImgSrc) {//开始时间Date begindate2 = new Date();String imageName = url.substring(url.lastIndexOf("/") + 1, url.length());URL uri = new URL(url);InputStream in = uri.openStream();FileOutputStream fo = new FileOutputStream(new File("src/res/"+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");//结束时间Date overdate2 = new Date();double time = overdate2.getTime() - begindate2.getTime();System.out.println("耗时：" + time / 1000 + "s");}Date overdate = new Date();double time = overdate.getTime() - begindate.getTime();System.out.println("总耗时：" + time / 1000 + "s");} catch (Exception e) {System.out.println("下载失败");}}
}