网页截图 根据关键字定位 然后截取图片

maven

< dependency > < groupId > com.hynnet </ groupId > < artifactId > DJNativeSwing </ artifactId > < version > 1.0.0 </ version > </ dependency >

< dependency > < groupId > com.hynnet </ groupId > < artifactId > DJNativeSwing-SWT </ artifactId > < version > 1.0.0 </ version > </ dependency > 

< dependency > < groupId > org.eclipse.swt.org.eclipse.swt.win32.win32.x86_64.4.3.swt </ groupId > < artifactId > org.eclipse.swt.win32.win32.x86_64 </ artifactId > < version > 4.3 </ version > </ dependency >

public class TestPrint extends JPanel {

private static final long serialVersionUID = 1L ;

    // 行分隔符

final static public String LS = System. getProperty ( "line.separator" , "/n" ) ;

// 文件分割符

final static public String FS = System. getProperty ( "file.separator" , "//" ) ;

// 当网页超出目标大小时 截取

final static public int maxWidth = 2000 ;

final static public int maxHeight = 1400 ;

/**

* @param file 预生成的图片全路径

* @param url 网页地址

* @return boolean

*/

public TestPrint ( final String file , final String url , final String WithResult) {

super ( new BorderLayout()) ;

JPanel webBrowserPanel = new JPanel( new BorderLayout()) ;

final JWebBrowser webBrowser = new JWebBrowser( null ) ;

webBrowser.setBarsVisible( false ) ;

webBrowser.navigate(url) ;

webBrowserPanel.add(webBrowser , BorderLayout. CENTER ) ;

add(webBrowserPanel , BorderLayout. CENTER ) ;

JPanel panel = new JPanel( new FlowLayout()) ;

webBrowser.addWebBrowserListener( new WebBrowserAdapter() {

// 监听加载进度

public void loadingProgressChanged (WebBrowserEvent e) {

// 当加载完毕时

if (e.getWebBrowser().getLoadingProgress() == 100 ) {

String result = (String) webBrowser .executeJavascriptWithResult( WithResult ) ;

int index = result == null ? - 1 : result.indexOf( ":" ) ;

NativeComponent nativeComponent = webBrowser .getNativeComponent() ;

Dimension originalSize = nativeComponent.getSize() ;

Dimension imageSize = new Dimension(Integer. parseInt (result.substring( 0 , index)) ,

Integer. parseInt (result.substring(index + 1 ))) ;

imageSize. width = Math. max (originalSize. width , imageSize. width + 50 ) ;

imageSize. height = Math. max (originalSize. height , imageSize. height + 50 ) ;

nativeComponent.setSize(imageSize) ;

BufferedImage image = new BufferedImage(imageSize. width , imageSize. height ,

BufferedImage. TYPE_INT_RGB ) ;

nativeComponent.paintComponent(image) ;

nativeComponent.setSize(originalSize) ;

// 当网页超出目标大小时

if (imageSize. width > maxWidth || imageSize. height > maxHeight ) {

// 截图部分图形

image = image.getSubimage( 0 , 0 , maxWidth , maxHeight ) ;

// 此部分为使用缩略图

/*

* int width = image.getWidth(), height = image

* .getHeight(); AffineTransform tx = new

* AffineTransform(); tx.scale((double) maxWidth /

* width, (double) maxHeight / height);

* AffineTransformOp op = new AffineTransformOp(tx,

* AffineTransformOp.TYPE_NEAREST_NEIGHBOR); // 缩小 image

* = op.filter(image, null);

*/

}

try {

// 输出图像

ImageIO. write (image , "jpg" , new File( file )) ;

} catch (IOException ex) {

ex.printStackTrace() ;

}

// 退出操作

//System.exit(0);

}

}

}) ;

add(panel , BorderLayout. SOUTH ) ;

}

// 以 javascript 脚本获得网页全屏后大小

public static String getScreenWidthHeight () {

StringBuffer jsDimension = new StringBuffer() ;

jsDimension.append( "var width = 0;" ).append( LS ) ;

jsDimension.append( "var height = 0;" ).append( LS ) ;

jsDimension.append( "if(document.documentElement) {" ).append( LS ) ;

jsDimension.append( " width = Math.max(width, document.documentElement.scrollWidth);" ).append( LS ) ;

jsDimension.append( " height = Math.max(height, document.documentElement.scrollHeight);" ).append( LS ) ;

jsDimension.append( "}" ).append( LS ) ;

jsDimension.append( "if(self.innerWidth) {" ).append( LS ) ;

jsDimension.append( " width = Math.max(width, self.innerWidth);" ).append( LS ) ;

jsDimension.append( " height = Math.max(height, self.innerHeight);" ).append( LS ) ;

jsDimension.append( "}" ).append( LS ) ;

jsDimension.append( "if(document.body.scrollWidth) {" ).append( LS ) ;

jsDimension.append( " width = Math.max(width, document.body.scrollWidth);" ).append( LS ) ;

jsDimension.append( " height = Math.max(height, document.body.scrollHeight);" ).append( LS ) ;

jsDimension.append( "}" ).append( LS ) ;

jsDimension.append( "return width + ':' + height;" ) ;

return jsDimension.toString() ;

}

public static void printUrlScreen2jpg ( final ArrayList<Map<String , String>> mapList , final int width , final int height) {

NativeInterface. open () ;

SwingUtilities. invokeLater ( new Runnable() {

public void run () {

for ( int i = 0 ; i < mapList .size() ; i++) {

String withResult = "var temp = '" + mapList .get(i).get( "keyWord" ) + "'; var rng = document.body.createTextRange(); rng.findText(temp); rng.moveStart('character',-800); rng.scrollIntoView(); var width = " + width + ";var height = " + height + ";return width +':' + height;" ;

if ( width == 0 || height == 0 )

withResult = getScreenWidthHeight () ;

JFrame frame = new JFrame( " 网页截图 " ) ;

// 加载指定页面，最大保存为 640x480 的截图

frame.getContentPane().add( new TestPrint( "E:/zhf/print/" + System. currentTimeMillis () + ".jpg" , mapList .get(i).get( "url" ) , withResult) ,

BorderLayout. CENTER ) ;

frame.setSize( 640 , 480 ) ;

// 仅初始化，但不显示

frame.invalidate() ;

frame.pack() ;

frame.setVisible( false ) ;

}

}

}) ;

}

public static Logger log = Logger. getLogger (TestPrint. class ) ;

public static void main (String[] args) {

ArrayList<Map<String , String>> list = new ArrayList<>() ;

list.add( new HashMap<String , String>() {{

put( "url" , " http://tieba.baidu.com/p/4129073505 " ) ;

put( "keyWord" , " 百年前连云港有了国内第一条陇海铁路。百年后依然只是这条铁路。。呵呵 " ) ;

}}) ;

TestPrint. printUrlScreen2jpg (list , 1400 , 900 ) ;

}

}