java 抓取网页图片

import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.HttpURLConnection;
import java.net.URL;
import java.net.URLConnection;
import java.text.SimpleDateFormat;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.UUID;
import java.util.regex.Matcher;
import java.util.regex.Pattern; /***
* java抓取网络图片
*
* @author ITWANG
*
*/
public class CatchImage
{ // 地址
private static final String URL = "http://www.4493.com/";
// 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+)"; private static final String IMGDSRC_REG = "[\"\'](http.+\\.(jpg|JPG|png|PNG|gif|GIF))[\"\']";
private static final String[] picstuffix = { "jpg", "JPG", "gif", "GIF", "png", "PNG" }; private static List<String> pList = new ArrayList<>(); public static void main(String[] args) throws Exception
{
CatchImage cm = new CatchImage();
// 获得html文本内容
String HTML = cm.getHTML(URL);
// System.out.println(HTML);
// 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, "E:\\Imagesave"+saveDiff()); // cm.getImageSrc(HTML);
// cm.ThreadDownload(imgSrc, "E:\\Imagesave"+saveDiff() , 6);
// cm.TOThreadDownload(pList, "E:\\Imagesave" + saveDiff(), 6, 6000);
} /***
* 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;
} /**
* 获取html里面的图片
*
* @param html
* @return
*/
private void getImageSrc(String html)
{
Pattern p = Pattern.compile(IMGDSRC_REG);
Matcher m = p.matcher(html);
while (m.find())
{
getpicsrc(m.group(1));
}
} /**
* 截取字符串里面的图片
*
* @param src
* @return
*/
public void getpicsrc(String src)
{
if (src.contains("http:"))
{
String[] app = src.split("http:");
for (int i = 0; i < app.length; i++)
{
if (!isBlank(app[i]))
{
for (int j = 0; j < picstuffix.length; j++)
{
if (app[i].contains("." + picstuffix[j]))
{
int inum = app[i].indexOf(picstuffix[j]);
String url = "http:" + app[i].substring(0, inum) + picstuffix[j];
pList.add(url);
}
}
}
}
}
} /**
* 去处重复元素
*
* @param result
* @return
*/
public static List<String> RemoveRepeated(List<String> result)
{
List<String> tmpArr = new ArrayList<String>();
for (int i = 0; i < result.size(); i++)
{
if (!tmpArr.contains(result.get(i)))
{
tmpArr.add((String) result.get(i));
}
}
return tmpArr;
} /**
* 判断非空
*
* @param cs
* @return
*/
public static boolean isBlank(CharSequence cs)
{
int strLen;
if (cs == null || (strLen = cs.length()) == 0)
{
return true;
}
for (int i = 0; i < strLen; i++)
{
if (Character.isWhitespace(cs.charAt(i)) == false)
{
return false;
}
}
return true;
} /***
* 单线程下载图片
*
* @param listImgSrc
*/
private void Download(List<String> listImgSrc, String savedir)
{
for (String url : listImgSrc)
{
try
{
String imageName = url.substring(url.lastIndexOf("/") + 1, url.length());
URL uri = new URL(url);
InputStream in = uri.openStream();
FileOutputStream fo = new FileOutputStream(new File(savedir + imageName));
byte[] buf = new byte[1024];
int length = 0;
while ((length = in.read(buf, 0, buf.length)) != -1)
{
fo.write(buf, 0, length);
}
in.close();
fo.close();
System.out.println("*^_^*");
} catch (Exception e)
{
System.out.println("-_-!");
}
}
} /**
* 多线程下载图片
*
* @param listImgSrc
* @param savedir
* @param tnum
*/
private void ThreadDownload(List<String> listImgSrc, String savedir, int tnum)
{
for (int i = 0; i < listImgSrc.size(); i += tnum)
{
new DThread(savedir, tnum, listImgSrc, i).start();
}
} /**
*
* 2014-4-3上午10:52:38 Describe: 多线程下载照片
*
* @author: ITWANG
*/
class DThread extends Thread
{ private String savedir = null;
private int tnum;
private List<String> listImgSrc;
private int bunm; public DThread(String savedir, int tnum, List<String> listImgSrc, int bnum)
{
this.savedir = savedir;
this.tnum = tnum;
this.listImgSrc = listImgSrc;
this.bunm = bnum;
} @Override
public void run()
{
for (int i = 0; i < tnum; i++)
{
try
{
String url = listImgSrc.get(bunm + i);
String sps = url.substring(url.lastIndexOf("."), url.length());
String imageName = UUID.randomUUID().toString() + sps;
URL uri = new URL(url);
InputStream in = uri.openStream();
System.out.println(savedir + imageName);
FileOutputStream fo = new FileOutputStream(new File(savedir + imageName));
byte[] buf = new byte[1024];
int length = 0;
while ((length = in.read(buf, 0, buf.length)) != -1)
{
fo.write(buf, 0, length);
}
in.close();
fo.close();
System.out.println("*^_^*");
} catch (Exception e)
{
System.out.println("-_-!");
}
}
}
} /**
* 多线程超时下载
*
* @param listImgSrc
* @param savedir
* @param tnum
* @param timeout
*/
private void TOThreadDownload(List<String> listImgSrc, String savedir, int tnum, int timeout)
{
for (int i = 0; i < listImgSrc.size(); i += tnum)
{
new TODThread(savedir, tnum, listImgSrc, i, timeout).start();
}
} /**
*
* 2014-4-3上午10:52:07 Describe: 超时方式下载照片线程
*
* @author: ITWANG
*/
class TODThread extends Thread
{
private String savedir = null;
private int tnum;
private List<String> listImgSrc;
private int bunm;
private int timeout = 3000; public TODThread(String savedir, int tnum, List<String> listImgSrc, int bnum, int timeout)
{
this.savedir = savedir;
this.tnum = tnum;
this.listImgSrc = listImgSrc;
this.bunm = bnum;
this.timeout = timeout;
} @Override
public void run()
{
for (int i = 0; i < tnum; i++)
{
String url = listImgSrc.get(bunm + i);
String sps = url.substring(url.lastIndexOf("."), url.length());
String imageName = UUID.randomUUID().toString() + sps;
try
{
if (getPic(url, savedir, imageName, timeout))
{
System.out.println("*^_^*");
} else
{
System.out.println("-_-!");
}
} catch (Exception e)
{
System.out.println("下载异常");
}
} }
} /**
* GET方式下载照片
*
* @param purl
* @param folder
* @param filename
* @param timeout
* @return
* @throws Exception
*/
public boolean getPic(String purl, String folder, String filename, int timeout) throws Exception
{
URL url = new URL(purl);
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setConnectTimeout(timeout);
conn.setRequestMethod("GET");
conn.setDoOutput(true);
conn.setDoInput(true);
if (conn.getResponseCode() == 200)
{
InputStream is = conn.getInputStream();
byte[] bs = new byte[1024];
int len;
File sf = new File(folder);
if (!sf.exists())
{
sf.mkdirs();
}
OutputStream os = new FileOutputStream(sf.getPath() + "\\" + filename);
while ((len = is.read(bs)) != -1)
{
os.write(bs, 0, len);
}
os.close();
is.close();
return true;
}
return false;
} /**
* 时间文件夹
*
* @return
*/
public static String saveDiff()
{
SimpleDateFormat formate = new SimpleDateFormat("yyyy-MM-dd-HH-mm-ss");
return "\\" + formate.format(System.currentTimeMillis()) + "\\";
} }

  

上一篇:IOS 学习日志 2015-3-16


下一篇:CF830A Office Keys(贪心)