<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic split a pdf into single pages in Talend Studio</title>
    <link>https://community.qlik.com/t5/Talend-Studio/split-a-pdf-into-single-pages/m-p/2201705#M3692</link>
    <description>&lt;P&gt;Hi,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;I need a way to split PDFs into their single Pages within a Talend job to further process them.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Does anybody has a good solution for this?&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Thanks&lt;/P&gt;</description>
    <pubDate>Tue, 15 Oct 2019 10:08:53 GMT</pubDate>
    <dc:creator>Anonymous</dc:creator>
    <dc:date>2019-10-15T10:08:53Z</dc:date>
    <item>
      <title>split a pdf into single pages</title>
      <link>https://community.qlik.com/t5/Talend-Studio/split-a-pdf-into-single-pages/m-p/2201705#M3692</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;I need a way to split PDFs into their single Pages within a Talend job to further process them.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Does anybody has a good solution for this?&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Thanks&lt;/P&gt;</description>
      <pubDate>Tue, 15 Oct 2019 10:08:53 GMT</pubDate>
      <guid>https://community.qlik.com/t5/Talend-Studio/split-a-pdf-into-single-pages/m-p/2201705#M3692</guid>
      <dc:creator>Anonymous</dc:creator>
      <dc:date>2019-10-15T10:08:53Z</dc:date>
    </item>
    <item>
      <title>Re: split a pdf into single pages</title>
      <link>https://community.qlik.com/t5/Talend-Studio/split-a-pdf-into-single-pages/m-p/2201706#M3693</link>
      <description>&lt;P&gt;Meanwhile Ive found the solution, so i thought i post it here, if someone needs it.&lt;/P&gt; 
&lt;P&gt;Ive written a small routine:&lt;/P&gt; 
&lt;P&gt;&amp;nbsp;&lt;/P&gt; 
&lt;PRE&gt;package routines;
import java.io.File;
import java.io.IOException;
import java.util.List; 
import java.util.Iterator;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.multipdf.Splitter; 


public static void splitPdf(String arg, String directory) throws IOException
    {
    	PDDocument document = PDDocument.load(new File(arg));
    	Splitter splitter = new Splitter();
    	List&amp;lt;PDDocument&amp;gt; Pages = splitter.split(document);
    	Iterator&amp;lt;PDDocument&amp;gt; iterator = Pages.listIterator();
    		
    	int i = 1;
    	while (iterator.hasNext()) {
    		PDDocument pd = iterator.next();
    		pd.save(directory+ i + ".pdf");
    		i++;
    	}
    	document.close();
    }&lt;/PRE&gt; 
&lt;P&gt;It takes the PDF given and extracts every single page to a directory.&lt;/P&gt;</description>
      <pubDate>Tue, 15 Oct 2019 11:13:09 GMT</pubDate>
      <guid>https://community.qlik.com/t5/Talend-Studio/split-a-pdf-into-single-pages/m-p/2201706#M3693</guid>
      <dc:creator>Anonymous</dc:creator>
      <dc:date>2019-10-15T11:13:09Z</dc:date>
    </item>
  </channel>
</rss>

