<?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 Re: PDF extraction  in Alfresco Archive</title>
    <link>https://connect.hyland.com/t5/alfresco-archive/pdf-extraction/m-p/289370#M242500</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;SPAN&gt;Hello,&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;author is one example of metadata that should already be extracted automatically when you upload a PDF via Share. You can also trigger metadata extraction by starting the action "extract-metadata" (ContentMetadataExtracter) via a script / rule. "Modified By" (cm:modified) isn't a property that should be extracted - this should only be maintained / managed by the system. You could of course define a custom property and map the extracted value of any "Modified By" document header via the PdfBoxMetadataExtracter.properties mapping configuration.&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Please also have a look at the &amp;lt;a href="&lt;/SPAN&gt;&lt;A href="http://wiki.alfresco.com/wiki/Metadata_Extraction" rel="nofollow noopener noreferrer"&gt;http://wiki.alfresco.com/wiki/Metadata_Extraction&lt;/A&gt;&lt;SPAN&gt;"&amp;gt;wiki article about metadata extraction&amp;lt;/a&amp;gt;.&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;Regards&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Axel&lt;/SPAN&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Thu, 14 Mar 2013 14:36:13 GMT</pubDate>
    <dc:creator>afaust</dc:creator>
    <dc:date>2013-03-14T14:36:13Z</dc:date>
    <item>
      <title>PDF extraction</title>
      <link>https://connect.hyland.com/t5/alfresco-archive/pdf-extraction/m-p/289367#M242497</link>
      <description>Hi,Is there any add-ons available for extraction pdf to other format(metadata extraction) ? Your help would be greatly appreciated…</description>
      <pubDate>Thu, 14 Mar 2013 06:48:15 GMT</pubDate>
      <guid>https://connect.hyland.com/t5/alfresco-archive/pdf-extraction/m-p/289367#M242497</guid>
      <dc:creator>rinuthomas90</dc:creator>
      <dc:date>2013-03-14T06:48:15Z</dc:date>
    </item>
    <item>
      <title>Re: PDF extraction</title>
      <link>https://connect.hyland.com/t5/alfresco-archive/pdf-extraction/m-p/289368#M242498</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;SPAN&gt;Hello,&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;metadata extraction from PDF is already contained as part of the standard platform. Usually, there are no add-ons required for this unless you have a very specific requirement. What are you trying to do? Where do you think the default functionality of Alfresco provides too little support?&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;Regards&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Axel&lt;/SPAN&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Thu, 14 Mar 2013 09:47:35 GMT</pubDate>
      <guid>https://connect.hyland.com/t5/alfresco-archive/pdf-extraction/m-p/289368#M242498</guid>
      <dc:creator>afaust</dc:creator>
      <dc:date>2013-03-14T09:47:35Z</dc:date>
    </item>
    <item>
      <title>Re: PDF extraction</title>
      <link>https://connect.hyland.com/t5/alfresco-archive/pdf-extraction/m-p/289369#M242499</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;SPAN&gt;I want to extract the information's like: author, modified by,..etc. Can you help me in getting these details? &lt;/SPAN&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Thu, 14 Mar 2013 14:03:26 GMT</pubDate>
      <guid>https://connect.hyland.com/t5/alfresco-archive/pdf-extraction/m-p/289369#M242499</guid>
      <dc:creator>rinuthomas90</dc:creator>
      <dc:date>2013-03-14T14:03:26Z</dc:date>
    </item>
    <item>
      <title>Re: PDF extraction</title>
      <link>https://connect.hyland.com/t5/alfresco-archive/pdf-extraction/m-p/289370#M242500</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;SPAN&gt;Hello,&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;author is one example of metadata that should already be extracted automatically when you upload a PDF via Share. You can also trigger metadata extraction by starting the action "extract-metadata" (ContentMetadataExtracter) via a script / rule. "Modified By" (cm:modified) isn't a property that should be extracted - this should only be maintained / managed by the system. You could of course define a custom property and map the extracted value of any "Modified By" document header via the PdfBoxMetadataExtracter.properties mapping configuration.&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Please also have a look at the &amp;lt;a href="&lt;/SPAN&gt;&lt;A href="http://wiki.alfresco.com/wiki/Metadata_Extraction" rel="nofollow noopener noreferrer"&gt;http://wiki.alfresco.com/wiki/Metadata_Extraction&lt;/A&gt;&lt;SPAN&gt;"&amp;gt;wiki article about metadata extraction&amp;lt;/a&amp;gt;.&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;Regards&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Axel&lt;/SPAN&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Thu, 14 Mar 2013 14:36:13 GMT</pubDate>
      <guid>https://connect.hyland.com/t5/alfresco-archive/pdf-extraction/m-p/289370#M242500</guid>
      <dc:creator>afaust</dc:creator>
      <dc:date>2013-03-14T14:36:13Z</dc:date>
    </item>
    <item>
      <title>Re: PDF extraction</title>
      <link>https://connect.hyland.com/t5/alfresco-archive/pdf-extraction/m-p/289371#M242501</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;SPAN&gt;Hi,&lt;/SPAN&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;please can you share some of the screen shots of the solution.&lt;/SPAN&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Mon, 18 Mar 2013 14:01:31 GMT</pubDate>
      <guid>https://connect.hyland.com/t5/alfresco-archive/pdf-extraction/m-p/289371#M242501</guid>
      <dc:creator>ashwini_g_krish</dc:creator>
      <dc:date>2013-03-18T14:01:31Z</dc:date>
    </item>
  </channel>
</rss>

