<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (martinkenny)</title>
    <link>https://pinboard.in/u:martinkenny/public/</link>
    <description>recent bookmarks from martinkenny</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="http://www.documentsnap.com/pdfpen-ocr-applescript-to-automatically-make-pdfs-searchable/"/>
	<rdf:li rdf:resource="https://github.com/ogrisel/paper2ebook"/>
	<rdf:li rdf:resource="http://documentcloud.github.com/docsplit/"/>
	<rdf:li rdf:resource="http://simonwillison.net/2010/Jun/17/pdfjs/"/>
	<rdf:li rdf:resource="http://simonwillison.net/2009/Nov/17/nodepdf/"/>
	<rdf:li rdf:resource="http://prawn.majesticseacreature.com/"/>
	<rdf:li rdf:resource="http://blogs.adobe.com/insidepdf/2008/07/text_content_in_pdf_files.html"/>
	<rdf:li rdf:resource="http://www.unixuser.org/~euske/python/pdfminer/index.html"/>
	<rdf:li rdf:resource="http://skim-app.sourceforge.net/index.html"/>
	<rdf:li rdf:resource="http://www.ironicsoftware.com/yep/index.html"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="http://www.documentsnap.com/pdfpen-ocr-applescript-to-automatically-make-pdfs-searchable/">
    <title>PDFPen OCR Applescript To Automatically Make PDFs Searchable | Tips To Learn How To Go Paperless | DocumentSnap Paperless Blog</title>
    <dc:date>2011-10-24T22:37:08+00:00</dc:date>
    <link>http://www.documentsnap.com/pdfpen-ocr-applescript-to-automatically-make-pdfs-searchable/</link>
    <dc:creator>martinkenny</dc:creator><dc:subject>pdfpen scansnap ocr pdf os-x applescript</dc:subject>
<dc:identifier>https://pinboard.in/u:martinkenny/b:cd02cc3150bf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:pdfpen"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:scansnap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:ocr"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:os-x"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:applescript"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/ogrisel/paper2ebook">
    <title>ogrisel's paper2ebook at master - GitHub</title>
    <dc:date>2010-11-15T12:25:05+00:00</dc:date>
    <link>https://github.com/ogrisel/paper2ebook</link>
    <dc:creator>martinkenny</dc:creator><description><![CDATA["Utility to re-structure research papers published in US Letter or A4 format PDF files to typically remove the 2 columns layout."
]]></description>
<dc:subject>pdf converter papers ebooks kindle</dc:subject>
<dc:identifier>https://pinboard.in/u:martinkenny/b:dd69e4550331/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:converter"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:papers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:ebooks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:kindle"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://documentcloud.github.com/docsplit/">
    <title>Doc⚡split</title>
    <dc:date>2010-08-10T09:16:42+00:00</dc:date>
    <link>http://documentcloud.github.com/docsplit/</link>
    <dc:creator>martinkenny</dc:creator><description><![CDATA["Docsplit is a command-line utility and Ruby library for splitting apart documents into their component parts: searchable UTF-8 plain text via OCR if necessary, page images or thumbnails in any format, PDFs, single pages, and document metadata (title, author, number of pages...)"
]]></description>
<dc:subject>pdf text documents text-extraction</dc:subject>
<dc:identifier>https://pinboard.in/u:martinkenny/b:df027e2a29a2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:text"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:documents"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:text-extraction"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://simonwillison.net/2010/Jun/17/pdfjs/">
    <title>pdf.js</title>
    <dc:date>2010-06-17T19:39:48+00:00</dc:date>
    <link>http://simonwillison.net/2010/Jun/17/pdfjs/</link>
    <dc:creator>martinkenny</dc:creator><description><![CDATA[pdf.js. A JavaScript library for creating simple PDF files. Works (flakily) in your browser using a data:URI hack, but is also compatible with server-side JavaScript implementations such as Node.js.

]]></description>
<dc:subject>datauri javascript node nodejs pdf</dc:subject>
<dc:identifier>https://pinboard.in/u:martinkenny/b:117b42c591b0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:datauri"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:javascript"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:node"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:nodejs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:pdf"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://simonwillison.net/2009/Nov/17/nodepdf/">
    <title>node.js at JSConf.eu (PDF)</title>
    <dc:date>2009-11-17T18:07:37+00:00</dc:date>
    <link>http://simonwillison.net/2009/Nov/17/nodepdf/</link>
    <dc:creator>martinkenny</dc:creator><description><![CDATA[node.js at JSConf.eu (PDF). node.js creator Ryan Dahl’s presentation at this year’s JSConf.eu. The principle philosophy is that I/O in web applications should be asynchronous—for everything. No blocking for database calls, no blocking for filesystem access. JavaScript is a mainstream programming language with a culture of callback APIs (thanks to the DOM) and is hence ideally suited to building asynchronous frameworks.

]]></description>
<dc:subject>asynchronous eventio javascript node pdf ryandahl</dc:subject>
<dc:identifier>https://pinboard.in/u:martinkenny/b:1e517a696462/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:asynchronous"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:eventio"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:javascript"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:node"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:ryandahl"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://prawn.majesticseacreature.com/">
    <title>http://prawn.majesticseacreature.com/</title>
    <dc:date>2009-01-17T12:11:09+00:00</dc:date>
    <link>http://prawn.majesticseacreature.com/</link>
    <dc:creator>martinkenny</dc:creator><description><![CDATA["Building printable documents doesn't have to be hard

If you've ever needed to produce PDF documents before, in Ruby or another language, you probably know how much it can suck. Prawn takes the pain out of generating beautiful printable documents, while still remaining fast, tiny and nimble. It is also named after a majestic sea creature, and that has to count for something."
]]></description>
<dc:subject>pdf ruby library programming</dc:subject>
<dc:identifier>https://pinboard.in/u:martinkenny/b:303fb37761d4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:ruby"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:programming"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blogs.adobe.com/insidepdf/2008/07/text_content_in_pdf_files.html">
    <title>Inside PDF: Text Content in PDF Files</title>
    <dc:date>2008-10-26T12:13:26+00:00</dc:date>
    <link>http://blogs.adobe.com/insidepdf/2008/07/text_content_in_pdf_files.html</link>
    <dc:creator>martinkenny</dc:creator><description><![CDATA[To extract text from PDF documents is a rather difficult and a highly technical task and I hope to explain, here, why that is the case.
]]></description>
<dc:subject>pdf adobe informationretrieval indexing text</dc:subject>
<dc:identifier>https://pinboard.in/u:martinkenny/b:cfa0fda51801/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:adobe"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:informationretrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:indexing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:text"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.unixuser.org/~euske/python/pdfminer/index.html">
    <title>PDFMiner</title>
    <dc:date>2008-08-08T15:10:21+00:00</dc:date>
    <link>http://www.unixuser.org/~euske/python/pdfminer/index.html</link>
    <dc:creator>martinkenny</dc:creator><description><![CDATA[PDFMiner is a suite of programs that aims to help analyzing text data from PDF documents. It includes a PDF parser, a PDF renderer (though only rendering text is supported for now), and a couple of nice tools to extract texts. Unlike other PDF-related tools, it allows to obtain the exact location of texts in a page, as well as other layout information such as font size or font name, which could be useful for analyzing the document. It also infers text running within a page by using clustering technique.
]]></description>
<dc:subject>pdf python library open-source parser</dc:subject>
<dc:identifier>https://pinboard.in/u:martinkenny/b:265283d035d5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:parser"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://skim-app.sourceforge.net/index.html">
    <title>Skim | Home (PDF reader for OS X)</title>
    <dc:date>2008-03-18T06:26:41+00:00</dc:date>
    <link>http://skim-app.sourceforge.net/index.html</link>
    <dc:creator>martinkenny</dc:creator><dc:subject>pdf os-x software tools</dc:subject>
<dc:identifier>https://pinboard.in/u:martinkenny/b:f46ecc484d3e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:os-x"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:tools"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.ironicsoftware.com/yep/index.html">
    <title>Yep</title>
    <dc:date>2007-12-23T13:21:23+00:00</dc:date>
    <link>http://www.ironicsoftware.com/yep/index.html</link>
    <dc:creator>martinkenny</dc:creator><dc:subject>mac os-x tools pdf organization</dc:subject>
<dc:identifier>https://pinboard.in/u:martinkenny/b:429d53a90809/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:mac"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:os-x"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:tools"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:martinkenny/t:organization"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>