<?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 (rtlechow)</title>
    <link>https://pinboard.in/u:rtlechow/public/</link>
    <description>recent bookmarks from rtlechow</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://www.gnu.org/software/parallel/man.html#example__breadth_first_parallel_web_crawler_mirrorer"/>
	<rdf:li rdf:resource="http://www.csstrashman.com/"/>
	<rdf:li rdf:resource="http://www.michaelnielsen.org/ddi/how-to-crawl-a-quarter-billion-webpages-in-40-hours/"/>
	<rdf:li rdf:resource="http://commoncrawl.org/"/>
	<rdf:li rdf:resource="http://blog.marc-seeger.de/2010/12/09/my-thesis-building-blocks-of-a-scalable-webcrawler"/>
	<rdf:li rdf:resource="http://www.dotnetdotcom.org/"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://www.gnu.org/software/parallel/man.html#example__breadth_first_parallel_web_crawler_mirrorer">
    <title>GNU Parallel</title>
    <dc:date>2016-09-02T17:33:58+00:00</dc:date>
    <link>https://www.gnu.org/software/parallel/man.html#example__breadth_first_parallel_web_crawler_mirrorer</link>
    <dc:creator>rtlechow</dc:creator><dc:subject>gnu parallel wget crawler</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:rtlechow/b:0d82e32e21ee/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:gnu"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:parallel"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:wget"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:crawler"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.csstrashman.com/">
    <title>CSS Trashman</title>
    <dc:date>2013-01-26T23:30:51+00:00</dc:date>
    <link>http://www.csstrashman.com/</link>
    <dc:creator>rtlechow</dc:creator><dc:subject>css crawler optimization html</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:rtlechow/b:ceb4bff33dc3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:css"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:crawler"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:html"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.michaelnielsen.org/ddi/how-to-crawl-a-quarter-billion-webpages-in-40-hours/">
    <title>How to crawl a quarter billion webpages in 40 hours | DDI</title>
    <dc:date>2012-10-31T18:32:05+00:00</dc:date>
    <link>http://www.michaelnielsen.org/ddi/how-to-crawl-a-quarter-billion-webpages-in-40-hours/</link>
    <dc:creator>rtlechow</dc:creator><dc:subject>architecture crawler datamining web crawling</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:rtlechow/b:43a691c62342/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:architecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:crawler"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:crawling"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://commoncrawl.org/">
    <title>CommonCrawl | | CommonCrawl</title>
    <dc:date>2012-02-15T23:34:16+00:00</dc:date>
    <link>http://commoncrawl.org/</link>
    <dc:creator>rtlechow</dc:creator><dc:subject>crawler opensource research web</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:rtlechow/b:d57e01932212/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:crawler"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:opensource"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:web"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.marc-seeger.de/2010/12/09/my-thesis-building-blocks-of-a-scalable-webcrawler">
    <title>My thesis - building blocks of a scalable webcrawler - Marc's Blog</title>
    <dc:date>2011-01-05T05:02:29+00:00</dc:date>
    <link>http://blog.marc-seeger.de/2010/12/09/my-thesis-building-blocks-of-a-scalable-webcrawler</link>
    <dc:creator>rtlechow</dc:creator><dc:subject>crawler crawling ruby scalability web</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:rtlechow/b:811b1d4ced29/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:crawler"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:crawling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:ruby"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:web"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.dotnetdotcom.org/">
    <title>dotbot | DotNetDotCom.org</title>
    <dc:date>2009-02-04T16:38:31+00:00</dc:date>
    <link>http://www.dotnetdotcom.org/</link>
    <dc:creator>rtlechow</dc:creator><dc:subject>crawler index dotbot crawl opendata spider graph web internet search statistics</dc:subject>
<dc:identifier>https://pinboard.in/u:rtlechow/b:1985d19b36f0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:crawler"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:index"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:dotbot"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:crawl"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:opendata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:spider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:graph"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:internet"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:rtlechow/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>