Захват заголовков из удаленного RSS-файла

<?xml version="1.0"?>
<rss version="2.0">
 <channel>
  <title>Adam Curry: Adam Curry's Weblog</title>
  <link>http://www.blognewsnetwork.com/members/0000001/</link>
  <description>News and Views from Adam Curry</description>
  <language>en-us</language>
  <copyright>Copyright 2003 Adam Curry</copyright>
  <lastBuildDate>Thu, 24 Jul 2003 09:26:48 GMT</lastBuildDate>
  <docs>http://backend.userland.com/rss</docs>
  <generator>Radio UserLand v8.0.9b2</generator>
  <managingEditor>adam@curry.com</managingEditor>
  <webMaster>adam@curry.com</webMaster>
  <item>
   <title>weblog at work again</title>
   <link>
   http://www.blognewsnetwork.com/members/0000001/2003/07/24.html#a4158
   </link>
   <description><a href="http://radio.weblogs.com/0001014/images/2003/07/24/ad
amwheely.jpg"><img src="http://radio.weblogs.com/0001014/images/2003/07/24/
adamwheely.jpg" width="250" height="187.5" border="0" align="right" hspace="15" v
space="5" alt="A picture named adamwheely.jpg"></a>A few days ago I aske
d if anyone had taken pictures of me at the annual ...</description>
   <guid>
   http://www.blognewsnetwork.com/members/0000001/2003/07/24.html#a4158
   </guid>
   <pubDate>Thu, 24 Jul 2003 09:21:25 GMT</pubDate>
  </item>
  <item>
   <title>teens trouble with web</title>
   <link>
   http://www.blognewsnetwork.com/members/0000001/2003/07/23.html#a4156
   </link>
   <description>According to a report from Northumbria University, most teenagers
 lack the <a href="http://www.web-user.co.uk/news/news.php?id=33621">inform
ation gathering skills</a> needed for using the internet efficiently. This 
sounds like it shouldn't be happening in ...</description>
   <guid>
   http://www.blognewsnetwork.com/members/0000001/2003/07/23.html#a4156
   </guid>
   <pubDate>Wed, 23 Jul 2003 17:36:23 GMT</pubDate>
  </item>
...
 </channel>
</rss>

<h2>Adam Curry: Adam Curry's Weblog</h2>
<h3>News and Views from Adam Curry</h3>
<ul>
<li>

  <a 
href="http://www.blognewsnetwork.com/members/0000001/2003/07/24.html#a4158">weblog 
at work again</a>
  <p><a href="http://radio.weblogs.com/0001014/images/2003/07/24/adamwheely.jpg">
<img src="http://radio.weblogs.com/0001014/images/2003/07/24/adamwheely.jpg" 
width="250" height="187.5" border="0" align="right" hspace="15" vspace="5" alt="A 
picture named adamwheely.jpg"></a>A few days ago I asked if anyone had taken 
pictures of me at the annual ...

</li>
<li>

  <a 
href="http://www.blognewsnetwork.com/members/0000001/2003/07/23.html#a4156">teens 
trouble with web</a>
  <p>According to a report from Northumbria University, most teenagers lack the 
<a href="http://www.web-user.co.uk/news/news.php?id=33621">information gathering 
skills</a> needed for using the internet efficiently. This sounds like it 
shouldn't be happening in ...

</li>
...
</ul>
			

<?xml version="1.0"?> 
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
<xsl:output method="html"/>

<xsl:template match="/">
  <xsl:apply-templates select="//channel"/>
  <ul>
    <xsl:apply-templates select="//item"/>
  </ul>
</xsl:template>

<xsl:template match="channel">
    
<xsl:apply-templates select="../image"/>
 <h2><xsl:value-of select="title"/></h2>
 <h3><xsl:value-of select="description"/></h3>
</xsl:template>

<xsl:template match="item">
  <li>
    <xsl:element name="a">
      <xsl:attribute name="href"><xsl:value-of select="link"/></xsl:attribute>
      <xsl:value-of select="title" />
    </xsl:element>
    <p><xsl:value-of disable-output-escaping="yes" select="description" /></p>
  </li>
</xsl:template>

<xsl:template match="image">
  <xsl:element name="img">
    <xsl:attribute name="src"><xsl:value-of select="url"/></xsl:attribute>
    <xsl:attribute name="style">float:left; padding: 10px;</xsl:attribute>
  </xsl:element>
</xsl:template>

<xsl:template match="language">
</xsl:template>

</xsl:stylesheet>
<?xml version="1.0"?> 
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
<xsl:output method="html"/>

<xsl:template match="/">
  <xsl:apply-templates select="//channel"/>
  <ul>
    <xsl:apply-templates select="//item"/>
  </ul>
</xsl:template>

<xsl:template match="channel">
    
<xsl:apply-templates select="../image"/>
 <h2><xsl:value-of select="title"/></h2>
 <h3><xsl:value-of select="description"/></h3>
</xsl:template>

<xsl:template match="item">
  <li>
    <xsl:element name="a">
      <xsl:attribute name="href"><xsl:value-of select="link"/></xsl:attribute>
      <xsl:value-of select="title" />
    </xsl:element>
    <p><xsl:value-of disable-output-escaping="yes" select="description" /></p>
  </li>
</xsl:template>

<xsl:template match="image">
  <xsl:element name="img">
    <xsl:attribute name="src"><xsl:value-of select="url"/></xsl:attribute>
    <xsl:attribute name="style">float:left; padding: 10px;</xsl:attribute>
  </xsl:element>
</xsl:template>

<xsl:template match="language">
</xsl:template>

</xsl:stylesheet>

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<jsp:useBean id="rssBean" scope="request" class="RSSProcessor">
<% 
   rssBean.setRSSFile(
        "http://wolk.datashed.net/users/adam@curry.com/curryCom.xml");
 %>
</jsp:useBean>

<html>
<head>
   <title>Syndicated Feeds</TITLE>
</head>
<body>
   <jsp:include page="headlines.html" flush="true"/>
</body>
</html>

import javax.xml.transform.stream.StreamSource;
import javax.xml.transform.stream.StreamResult;
import java.io.FileOutputStream;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.Transformer;

public class RSSProcessor {

  public RSSProcessor(){ }

  String _RSSFile;
   
  public String getRSSFile(){
       return _RSSFile;
  }

  public void setRSSFile(String fileName){

       try {
            
          StreamSource source = new StreamSource(fileName);

          StreamSource finalStyle = new StreamSource("final.xsl");

          String outputURL = "headlines.html";
          StreamResult result = new StreamResult(new 
                                    FileOutputStream(outputURL));

          TransformerFactory transFactory = TransformerFactory.newInstance();
          Transformer transformer = transFactory.newTransformer(finalStyle);   
          transformer.transform(source, result);

       } catch (Exception e) {
           e.printStackTrace();        
       }
  }

   
}

<?xml version="1.0" encoding="iso-8859-1"?>
<rss version="2.0" 
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
    xmlns:admin="http://webns.net/mvcb/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:content="http://purl.org/rss/1.0/modules/content/">

  <channel>
    <title>Typographica</title>
    <link>http://typographi.ca/</link>
    <description>A daily journal of typography featuring news, observations, 
and open commentary on fonts and typographic design.</description>
    <dc:language>en-us</dc:language>
    <dc:creator>Stephen Coles</dc:creator>
    <dc:rights>Copyright 2003</dc:rights>
    <dc:date>2003-07-24T00:00:52-08:00</dc:date>
    <admin:generatorAgent rdf:resource="http://www.movabletype.org/?v=2.63" />
    <admin:errorReportsTo rdf:resource="mailto:scoles@gomakecontact.com" />
    <sy:updatePeriod>hourly</sy:updatePeriod>
    <sy:updateFrequency>1</sy:updateFrequency>
    <sy:updateBase>2000-01-01T12:00+00:00</sy:updateBase>

    <item>
      <title>Hot and Cold Fonts</title>
      <link>http://typographi.ca/000643.php</link>
      <description>LettError have developed a multiple master font 
for the Design Institute of the University of Minnesota that varies 
along three...</description>
      <guid isPermaLink="false">643@http://typographi.ca/</guid>
      <content:encoded><![CDATA[<p><a href="http://www.letterror.com/">
LettError</a> have developed a multiple master font for the 
<a href="http://design.umn.edu/">Design Institute</a> of the University of 
Minnesota that varies along three dimensions: formality, informality, and 
"weirdness." (It's apparently possible to be 100% formal and 100% informal at 
the same time.)  As the New York Times...]]></content:encoded>
      <dc:subject></dc:subject>
      <dc:date>2003-07-24T00:00:52-08:00</dc:date>
    </item>

    <item>
      <title>Textura Digita</title>
      <link>http://typographi.ca/000642.php</link>
      <description>CNN reports that the Gutenberg Bible is now available 
on the web via the Ransom Center at the University of...</description>
      <guid isPermaLink="false">642@http://typographi.ca/</guid>
      <content:encoded><![CDATA[<p><a href=
"http://www.cnn.com/2003/TECH/internet/07/23/digital.scripture.ap/index.html">
CNN reports</a> that the Gutenberg Bible is now available on the web via the 
<a href="http://www.hrc.utexas.edu/exhibitions/permanent/gutenberg/">Ransom 
Center</a> at the University of Texas.</p>
...]]></content:encoded>
      <dc:subject></dc:subject>
      <dc:date>2003-07-23T13:16:15-08:00</dc:date>
    </item>

    <item>
      <title>Fight! Fight! Fight!</title>
      <link>http://typographi.ca/000640.php</link>
      <description>Angry because you had to miss TypeCon ’03? 
Work out that aggression with Helvetica vs. Arial....</description>
      <guid isPermaLink="false">640@http://typographi.ca/</guid>
      <content:encoded><![CDATA[<p>Angry because you had to miss 
<a href="http://www.typecon2003.com/">TypeCon ’03</a>? Work out that 
aggression with <a href="http://www.engagestudio.com/helvetica/">Helvetica vs. 
Arial</a>.</p>]]></content:encoded>
      <dc:subject></dc:subject>
      <dc:date>2003-07-22T08:52:36-08:00</dc:date>
    </item>
...
  </channel>
</rss>

<?xml version="1.0"?> 
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">

<xsl:template match="/">
<rss>
  <channel>
     <xsl:apply-templates select="rss/channel" />
  </channel>
</rss>
</xsl:template>

<xsl:template match="title|link|/rss/channel/description|image|text()">
   <xsl:copy-of select="." />
</xsl:template>

<xsl:template match="item" >
   <item>
      <title><xsl:value-of select="title" /></title>
      <link><xsl:value-of select="link" /></link>
      <description><xsl:value-of select="description" /></description>
   </item>
</xsl:template>

<xsl:template match="item[encoded]" >
   <item>
      <title><xsl:value-of select="title" /></title>
      <link><xsl:value-of select="link" /></link>
      <description><xsl:value-of select="encoded" /></description>
   </item>
</xsl:template>
    
</xsl:stylesheet>

...
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.dom.DOMResult;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import org.w3c.dom.Document;

public class RSSProcessor {
...
 public void setRSSFile(String fileName){

      try {

         StreamSource interimSource = new StreamSource(fileName);
            
         String XSLSheetName = "2.0.xsl";
       StreamSource style = new StreamSource(XSLSheetName);

       DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
       DocumentBuilder db = dbf.newDocumentBuilder();
       Document interimDoc = db.newDocument();
       DOMResult interimResult = new DOMResult(interimDoc);

         TransformerFactory transFactory = TransformerFactory.newInstance();
         Transformer interimTransformer = null;
       interimTransformer = transFactory.newTransformer(style);
       interimTransformer.transform(interimSource, interimResult);

       DOMSource source = new DOMSource(interimDoc);

         StreamSource finalStyle = new StreamSource("final.xsl");

         String outputURL = "headlines.html";
         StreamResult result = new StreamResult(new 
                                   FileOutputStream(outputURL));

         Transformer transformer = transFactory.newTransformer(finalStyle);   
         transformer.transform(source, result);

      } catch (Exception e) {
          e.printStackTrace();
      }
 }
}

...
import org.xml.sax.InputSource;
import org.w3c.dom.Element;

public class RSSProcessor {
...
   public void setRSSFile(String fileName){

         try {
            
            InputSource docFile = new InputSource (fileName);
            DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
            DocumentBuilder db = dbf.newDocumentBuilder();

            Document inputDoc = db.parse(docFile);
           Element rss = inputDoc.getDocumentElement();
           String version = null;
           if (rss.getNodeName().equals("rss")){
               version = rss.getAttribute("version");
               if (version == null) {
                  version = "0.91";
               }
           } else if (rss.getNodeName().equals("feed")){
              version = "echo";
           }
            
            String XSLSheetName = version+".xsl";
            StreamSource style = new StreamSource(XSLSheetName);

            DOMSource interimSource = new DOMSource(inputDoc);

            Document interimDoc = db.newDocument();
            DOMResult interimResult = new DOMResult(interimDoc);

            TransformerFactory transFactory = TransformerFactory.newInstance();
            Transformer interimTransformer = null;
           if (version.equals("0.91")){
              interimTransformer = transFactory.newTransformer();
           } else {
               interimTransformer = transFactory.newTransformer(style);
           }
            interimTransformer.transform(interimSource, interimResult);


            DOMSource source = new DOMSource(interimDoc);
            StreamSource finalStyle = new StreamSource("final.xsl");

            String outputURL = "headlines.html";
            StreamResult result = new StreamResult(new 
                                      FileOutputStream(outputURL));

            Transformer transformer = transFactory.newTransformer(finalStyle);   
            transformer.transform(source, result);

         } catch (Exception e) {
             e.printStackTrace();
        
         }
   }
  
}

import java.util.Date;

public class RSSProcessor {
...
   static Date _LastUpdated = new Date();
   public Date getLastUpdated(){
         return _LastUpdated;
   }
      
   public void setRSSFile(String fileName){

      Date now = new Date();
      long diff = now.getTime() - _LastUpdated.getTime();

      double interval = .5;
      if ((diff == 0) || (diff > (interval * 60 * 1000))){
           _LastUpdated = now;
     
         try {
            
            InputSource docFile = new InputSource (fileName);
...
            Transformer transformer = transFactory.newTransformer(finalStyle);   
            transformer.transform(source, result);

         } catch (Exception e) {
             e.printStackTrace();
         }
      }  
   }
   
}