DE<// GetImages.java

import java.io.*;

import java.net.*;

import java.util.regex.*;

import javax.swing.text.*;
import javax.swing.text.html.*;
import javax.swing.text.html.parser.ParserDelegator;

public class GetImages
{
   public static void main (String [] args)
   {
      // Validate number of command-line arguments.

      if (args.length != 1)
      {
          System.err.println ("usage: java GetImages URL");
          return;
      }

      // Create a Base URI from the solitary command-line argument. This URI
      // will be used in the handleSimpleTag() callback method to convert a
      // potentially relative URI in an  tag's src attribute to an
      // absolute URI.

      final URI uriBase;

      try
      {
          uriBase = new URI (args [0]);
      }
      catch (URISyntaxException e)
      {
          System.err.println ("URI is improperly formed");
          return;
      }

      // Convert the URI to a URL, so that the HTML document can be read and
      // parsed.

      URL url;

      try
      {
          url = new URL (args [0]);
      }
      catch (MalformedURLException e)
      {
          System.err.println ("URL is improperly formed");
          return;
      }

      // Establish a callback whose handleSimpleTag() method is invoked for
      // each tag that does not have an end tag. The  tag is an example.

      HTMLEditorKit.ParserCallback callback;
      callback = new HTMLEditorKit.ParserCallback ()
                 {
                     public void handleSimpleTag (HTML.Tag tag,
                                                 MutableAttributeSet aset,
                                                 int pos)
                     {
                        // If an  tag is encountered ...

                        if (tag == HTML.Tag.IMG)
                        {
                            // Get the value of the src attribute.

                            String src = (String)
                                         aset.getAttribute (HTML.Attribute.SRC);

                            // Create a URI based on the src value, and then
                            // resolve this potentially relative URI against
                            // the document's base URI, to obtain an absolute
                            // URI.

                            URI uri = null;

                            try
                            {
                                // Handle this situation:
                                //
                                // 1) http://www.javajeff.mb.ca
                                //
                                // There is no trailing forward slash.
                                //
                                // 2) common/logo.jpg
                                //
                                // There is no leading forward slash.
                                //
                                // 3) http://www.javajeff.mb.cacommon/logo.jpg
                                //
                                // The resolved URI is not valid.

                                if (!uriBase.toString ().endsWith ("/") &&

                                    !src.startsWith ("/"))
                                    src = "/" + src;

                                uri = new URI (src);
                                uri = uriBase.resolve (uri);
                                System.out.println ("uri being " +
                                                    "processed ... " + uri);
                            }
                            catch (URISyntaxException e)                            {
                                System.err.println ("Bad URI");
                                return;
                            }

                            // Convert the URI to a URL so that its input
                            // stream can be obtained.

                            URL url = null;

                            try
                            {
                                url = uri.toURL ();
                            }
                            catch (MalformedURLException e)
                            {
                                System.err.println ("Bad URL");
                                return;
                            }

                            // Open the URL's input stream.

                            InputStream is;

                            try
                            {
                                is = url.openStream ();
                            }
                            catch (IOException e)
                            {
                                System.err.println ("Unable to open input " +
                                                    "stream");
                                return;
                            }

                            // Extract URL's file component and remove path
                            // information -- only the filename and its 
                            // extension are wanted.

                            String filename = url.getFile ();
                            int i = filename.lastIndexOf ('/');
                            if (i != -1)
                                filename = filename.substring (i+1);

                            // Save image to file.

                            saveImage (is, filename);

                        }
                     }
                 };

      // Read and parse HTML document.

      try
      {
          // Read HTML document via an input stream reader that assumes the
          // default character set for decoding bytes into characters.

          Reader reader = new InputStreamReader (url.openStream ());

          // Establish a ParserDelegator whose parse() method causes the
          // document to be parsed. Various callback methods are called and
          // the document's character set is not ignored. The parse() method
          // throws a ChangedCharSetException if it encounters a  tag
          // with a charset attribute that specifies a character set other
          // than the default.

          new ParserDelegator ().parse (reader, callback, false);
      }
      catch (ChangedCharSetException e)
      {
          // Reparse the entire file using the specified charset. A regexp
          // pattern is specified to extract the charset name.

          String csspec = e.getCharSetSpec ();
          Pattern p = Pattern.compile ("charset=\"?(.+)\"?\\s*;?",
                                       Pattern.CASE_INSENSITIVE);
          Matcher m = p.matcher (csspec);
          String charset = m.find () ? m.group (1) : "ISO-8859-1";

          // Read and parse HTML document using appropriate character set.

          try
          {
              // Read HTML document via an input stream reader that uses the
              // specified character set to decode bytes into characters.

              Reader reader;
              reader = new InputStreamReader (url.openStream (), charset);

              // This time, pass true to ignore the  tag with its charset 
              // attribute.

              new ParserDelegator ().parse (reader, callback, true);
          }
          catch (UnsupportedEncodingException e2)
          {
              System.err.println ("Invalid charset");
          }
          catch (IOException e2)
          {
              System.err.println ("Input/Output problem");
              e.printStackTrace ();
          }
      }
      catch (IOException e)
      {
          System.err.println ("Input/Output problem");
          e.printStackTrace ();
      }
   }

   public static void saveImage (InputStream is, String filename)
   {
      FileOutputStream fos = null;

      try
      {
          fos = new FileOutputStream (filename);

          int bYte;
          while ((bYte = is.read ()) != -1)
             fos.write (bYte);
      }
      catch (IOException e)
      {
          System.err.println ("Unable to save stream to file");
      }
      finally
      {
         if (fos != null)
             try
             {
                 fos.close ();
             }
             catch (IOException e)
             {
             }
      }
   }
}DE<

 DE<uri being processed ... http://www.javajeff.mb.ca/common/logo.jpg
uri being processed ... http://www.javajeff.mb.ca/common/logo.gif
uri being processed ... http://www.javajeff.mb.ca/na/images/wom.jpgDE<

本文链接地址: 抓图程序-Java grab 包的技术提示http://www.hongyanliren.com/2015m02/31352.html

相关文章

• 微信小程序中引入iconfont阿里矢量图库
• 微信小程序之toast等弹框提示
• 微信小程序-中处理json数据 （从json数据中提取想要的值 将变量json字符串转成json对象）
• 微信小程序中的变量和作用域
• 小程序 data变量用法 全局变量
• 微信小程序用setData修改数组或对象中的一个属性值
• 微信小程序多层嵌套循环，二级数组遍历【key】
• fastJSON使用（一）——对象转换成json