<?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 (mt3_666)</title>
    <link>https://pinboard.in/u:mt3_666/public/</link>
    <description>recent bookmarks from mt3_666</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://github.com/kschluns-16/mtg-deck-data"/>
	<rdf:li rdf:resource="https://magicmargins.ca/news"/>
	<rdf:li rdf:resource="https://pcpartpicker.com/?__cf_chl_captcha_tk__=3vAQgFGZuKvU3JG8GlsqdYdqiBY6zHw6nolMUSuhW_0-1636812530-0-gaNycGzNB6U"/>
	<rdf:li rdf:resource="https://camelcamelcamel.com/"/>
	<rdf:li rdf:resource="http://zetcode.com/python/beautifulsoup/"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=gCLzNUhH9bI"/>
	<rdf:li rdf:resource="http://enterprise.import.io/getting-data-from-the-web/"/>
	<rdf:li rdf:resource="https://import.io/"/>
	<rdf:li rdf:resource="http://commoncrawl.org/navigating-the-warc-file-format/"/>
	<rdf:li rdf:resource="http://www.gregreda.com/2014/07/27/scraping-craigslist-for-tickets/"/>
	<rdf:li rdf:resource="https://github.com/OpenRefine/OpenRefine/wiki/StrippingHTML"/>
	<rdf:li rdf:resource="http://blog.algorithmia.com/post/86295023534/algorithmic-tagging-of-hackernews-or-any-other-site"/>
	<rdf:li rdf:resource="http://lemurproject.org/clueweb12/FACC1/"/>
	<rdf:li rdf:resource="http://lemurproject.org/clueweb09/FACC1/"/>
	<rdf:li rdf:resource="http://www.tensionsoftware.com/osx/urlextractor/"/>
	<rdf:li rdf:resource="http://www.michael-noll.com/dmoz100k06/"/>
	<rdf:li rdf:resource="http://wwwranking.webdatacommons.org/"/>
	<rdf:li rdf:resource="http://www.elasticsearch.org/case-study/stumbleupon/"/>
	<rdf:li rdf:resource="http://software.charliemonroe.net/downie.php"/>
	<rdf:li rdf:resource="http://news.rapgenius.com/Rap-genius-founders-rap-genius-is-back-on-google-lyrics"/>
	<rdf:li rdf:resource="http://www.kaggle.com/c/yandex-personalized-web-search-challenge/data"/>
	<rdf:li rdf:resource="http://www.macdrifter.com/2013/11/devonagent-for-web-searching-sponsor.html"/>
	<rdf:li rdf:resource="http://bootcat.sslmit.unibo.it/"/>
	<rdf:li rdf:resource="http://love-python.blogspot.ca/2008/03/use-proxy-in-your-spider.html"/>
	<rdf:li rdf:resource="http://love-python.blogspot.ca/2013/09/free-proxy-list-for-crawlers.html"/>
	<rdf:li rdf:resource="https://github.com/ianmilligan1/Exploring-Wide-Scrape"/>
	<rdf:li rdf:resource="http://www.blindfiveyearold.com/crawl-optimization"/>
	<rdf:li rdf:resource="http://fruchterco.com/post/53164489086/python-headless-web-browser-scraping-on-amazon-linux"/>
	<rdf:li rdf:resource="http://davidwalsh.name/python-scrape"/>
	<rdf:li rdf:resource="http://www.gregreda.com/2013/04/29/more-web-scraping-with-python/"/>
	<rdf:li rdf:resource="http://www.gregreda.com/2013/03/03/web-scraping-101-with-python/"/>
	<rdf:li rdf:resource="https://github.com/Max00355/PySpider"/>
	<rdf:li rdf:resource="http://webscraping.com/blog/Generate-website-screenshot-history/"/>
	<rdf:li rdf:resource="http://webscraping.com/blog/Web-Scraping-Interface/"/>
	<rdf:li rdf:resource="http://lemurproject.org/clueweb12.php/"/>
	<rdf:li rdf:resource="https://github.com/zaiste/cu"/>
	<rdf:li rdf:resource="https://github.com/oscardelben/rawler"/>
	<rdf:li rdf:resource="http://cnets.indiana.edu/groups/nan/webtraffic/click-dataset"/>
	<rdf:li rdf:resource="http://www.codeproject.com/Articles/526872/Crawlingpluswithplusthreads"/>
	<rdf:li rdf:resource="https://github.com/socketubs/4chandownloader"/>
	<rdf:li rdf:resource="http://searchco.de/blog/view/code-for-a-search-engine-in-php-part-1"/>
	<rdf:li rdf:resource="https://code.google.com/p/ldspider/"/>
	<rdf:li rdf:resource="https://github.com/drdrang/radio2"/>
	<rdf:li rdf:resource="https://github.com/Miserlou/AngelGraph"/>
	<rdf:li rdf:resource="https://github.com/scrapy/slybot"/>
	<rdf:li rdf:resource="https://github.com/svetlyak40wt/scrapy-useragents"/>
	<rdf:li rdf:resource="https://github.com/darthbear/scrapy-mongodb-pipeline"/>
	<rdf:li rdf:resource="https://github.com/darthbear/scrapy-simple-http-queue"/>
	<rdf:li rdf:resource="https://github.com/darthbear/scrapy-proxynova"/>
	<rdf:li rdf:resource="http://www.atlantbh.com/apache-nutch-overview/"/>
	<rdf:li rdf:resource="http://mathoverflow.net/questions/686/handling-arxiv-feeds-to-avoid-duplicates"/>
	<rdf:li rdf:resource="http://devblog.seomoz.org/2012/07/solutions-for-crawler-problems/"/>
	<rdf:li rdf:resource="http://devblog.seomoz.org/2012/06/how-does-seomoz-crawl-the-web/"/>
	<rdf:li rdf:resource="https://github.com/seomoz/g-crawl-py"/>
	<rdf:li rdf:resource="https://github.com/seomoz/url-py"/>
	<rdf:li rdf:resource="http://macwright.org/2012/11/14/indexing-searching-big-static-data.html"/>
	<rdf:li rdf:resource="https://github.com/joehand/Rampage-Killers-Data"/>
	<rdf:li rdf:resource="https://news.ycombinator.com/item?id=4207439"/>
	<rdf:li rdf:resource="http://www.searchenabler.com/blog/build-your-own-data-center/"/>
	<rdf:li rdf:resource="https://github.com/matpalm/common-crawl"/>
	<rdf:li rdf:resource="http://rjpower.org/wordpress/running-a-pdf-crawler-with-heritrix/"/>
	<rdf:li rdf:resource="https://github.com/bbrodriges/pholcidae"/>
	<rdf:li rdf:resource="https://github.com/noplay/scrapy-mongodb"/>
	<rdf:li rdf:resource="https://github.com/noplay/scrapy-couchdb"/>
	<rdf:li rdf:resource="https://github.com/noplay/scrapy-dot"/>
	<rdf:li rdf:resource="https://github.com/noplay/scrapy-graphite"/>
	<rdf:li rdf:resource="https://github.com/bcoe/routers-news"/>
	<rdf:li rdf:resource="https://github.com/wallunit/cocktail-search"/>
	<rdf:li rdf:resource="http://blog.luckyoyster.com/post/33592990831/data-mining-the-web-100-worth-of-priceless"/>
	<rdf:li rdf:resource="http://zyxt.com/post/26851542949/study-of-1-3-billion-urls-22-of-web-pages-reference"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://github.com/kschluns-16/mtg-deck-data">
    <title>kschluns-16/mtg-deck-data</title>
    <dc:date>2023-02-06T07:17:55+00:00</dc:date>
    <link>https://github.com/kschluns-16/mtg-deck-data</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>magic rpg data webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:bcdb9ba8f226/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:magic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:rpg"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://magicmargins.ca/news">
    <title>Magic Margins</title>
    <dc:date>2022-08-10T07:38:15+00:00</dc:date>
    <link>https://magicmargins.ca/news</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>magic search canada rpg games vancity evaluation webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:67b9ee52cac9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:magic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:canada"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:rpg"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:games"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:vancity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:evaluation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://pcpartpicker.com/?__cf_chl_captcha_tk__=3vAQgFGZuKvU3JG8GlsqdYdqiBY6zHw6nolMUSuhW_0-1636812530-0-gaNycGzNB6U">
    <title>Pick parts. Build your PC. Compare and share. - PCPartPicker</title>
    <dc:date>2021-11-13T14:09:41+00:00</dc:date>
    <link>https://pcpartpicker.com/?__cf_chl_captcha_tk__=3vAQgFGZuKvU3JG8GlsqdYdqiBY6zHw6nolMUSuhW_0-1636812530-0-gaNycGzNB6U</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>evaluation kompooter webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:ff0ef2a210d4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:evaluation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:kompooter"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://camelcamelcamel.com/">
    <title>Amazon price tracker, Amazon price history charts, price watches, and price drop alerts. | camelcamelcamel.com</title>
    <dc:date>2021-11-13T14:08:19+00:00</dc:date>
    <link>https://camelcamelcamel.com/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>amazon webspider evaluation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:d3e3d4a8f511/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:amazon"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:evaluation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://zetcode.com/python/beautifulsoup/">
    <title>BeautifulSoup tutorial - parse HTML, XML documents in Python</title>
    <dc:date>2019-05-28T19:02:05+00:00</dc:date>
    <link>http://zetcode.com/python/beautifulsoup/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python html parser xml webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:65712af82499/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:parser"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:xml"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=gCLzNUhH9bI">
    <title>How to use XPaths and Regular Expressions in Import.io - YouTube</title>
    <dc:date>2016-02-26T13:30:20+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=gCLzNUhH9bI</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider html xpaths regex api</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:53126965f274/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:xpaths"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:regex"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:api"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://enterprise.import.io/getting-data-from-the-web/">
    <title>10 Ways to Get Data From the Web: Code, Tools, &amp; Data Sets | Import.io Enterprise</title>
    <dc:date>2015-05-06T20:58:23+00:00</dc:date>
    <link>http://enterprise.import.io/getting-data-from-the-web/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>datamining webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:6edb041e50fe/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://import.io/">
    <title>import.io | Web Data Platform &amp; Free Web Scraping Tool</title>
    <dc:date>2014-11-20T11:56:43+00:00</dc:date>
    <link>https://import.io/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>api datamining excel webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:e317b4255311/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:api"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:excel"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://commoncrawl.org/navigating-the-warc-file-format/">
    <title>Navigating the WARC file format | CommonCrawl</title>
    <dc:date>2014-09-26T04:29:45+00:00</dc:date>
    <link>http://commoncrawl.org/navigating-the-warc-file-format/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>html webspider http nlp corpora java python</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:543b3b28db50/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:http"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.gregreda.com/2014/07/27/scraping-craigslist-for-tickets/">
    <title>Scraping Craigslist for sold out concert tickets</title>
    <dc:date>2014-08-11T06:44:23+00:00</dc:date>
    <link>http://www.gregreda.com/2014/07/27/scraping-craigslist-for-tickets/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python webspider ecommerce search</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:88bfd3caf139/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:ecommerce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/OpenRefine/OpenRefine/wiki/StrippingHTML">
    <title>Extracting &amp; Converting HTML markup with OpenRefine</title>
    <dc:date>2014-07-29T22:32:29+00:00</dc:date>
    <link>https://github.com/OpenRefine/OpenRefine/wiki/StrippingHTML</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider html parser openrefine python beautifulsoup</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:63d1d3911277/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:parser"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:openrefine"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:beautifulsoup"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.algorithmia.com/post/86295023534/algorithmic-tagging-of-hackernews-or-any-other-site">
    <title>• Algorithmic Tagging of HackerNews (or any other site)</title>
    <dc:date>2014-06-01T04:49:48+00:00</dc:date>
    <link>http://blog.algorithmia.com/post/86295023534/algorithmic-tagging-of-hackernews-or-any-other-site</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>news nlp tag machinelearning lda stats corpora webspider html</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:2fbb6b5b4384/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:news"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:tag"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:machinelearning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:lda"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:stats"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://lemurproject.org/clueweb12/FACC1/">
    <title>ClueWeb12 Related Data: FACC1</title>
    <dc:date>2014-04-02T03:33:01+00:00</dc:date>
    <link>http://lemurproject.org/clueweb12/FACC1/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>database corpora annotation webspider html</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:f2e40caf139f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:annotation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://lemurproject.org/clueweb09/FACC1/">
    <title>ClueWeb09 Related Data: FACC1</title>
    <dc:date>2014-04-02T03:32:31+00:00</dc:date>
    <link>http://lemurproject.org/clueweb09/FACC1/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>corpora webspider html</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:c5bc29133764/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.tensionsoftware.com/osx/urlextractor/">
    <title>URL Extractor 4</title>
    <dc:date>2014-03-23T14:03:32+00:00</dc:date>
    <link>http://www.tensionsoftware.com/osx/urlextractor/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>url webspider search mac</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:178fb013d548/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:url"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:mac"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.michael-noll.com/dmoz100k06/">
    <title>DMOZ100k06 - Michael G. Noll</title>
    <dc:date>2014-02-19T11:35:18+00:00</dc:date>
    <link>http://www.michael-noll.com/dmoz100k06/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>corpora bookmark html webspider nlp search</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:a6c023f15cbf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:bookmark"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://wwwranking.webdatacommons.org/">
    <title>The Common Crawl WWW Ranking</title>
    <dc:date>2014-02-15T05:39:49+00:00</dc:date>
    <link>http://wwwranking.webdatacommons.org/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>html ranking webspider search corpora</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:0c7fbf61b788/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:ranking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.elasticsearch.org/case-study/stumbleupon/">
    <title>StumbleUpon | Case Study | Elasticsearch</title>
    <dc:date>2014-01-22T13:38:43+00:00</dc:date>
    <link>http://www.elasticsearch.org/case-study/stumbleupon/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>search elasticsearch rss webspider html nlp text</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:9edfd9b31d46/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:elasticsearch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:rss"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:text"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://software.charliemonroe.net/downie.php">
    <title>Downie - Charlie Monroe Software</title>
    <dc:date>2014-01-07T00:27:07+00:00</dc:date>
    <link>http://software.charliemonroe.net/downie.php</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider video mac</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:270e6541126b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:mac"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://news.rapgenius.com/Rap-genius-founders-rap-genius-is-back-on-google-lyrics">
    <title>Rap Genius Founders – Rap Genius is Back on Google | News Genius</title>
    <dc:date>2014-01-05T14:12:42+00:00</dc:date>
    <link>http://news.rapgenius.com/Rap-genius-founders-rap-genius-is-back-on-google-lyrics</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>google webspider url search</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:d287802ed663/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:url"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.kaggle.com/c/yandex-personalized-web-search-challenge/data">
    <title>Data - Personalized Web Search Challenge | Kaggle</title>
    <dc:date>2013-12-04T02:55:47+00:00</dc:date>
    <link>http://www.kaggle.com/c/yandex-personalized-web-search-challenge/data</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>corpora webspider search</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:698857273ac7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.macdrifter.com/2013/11/devonagent-for-web-searching-sponsor.html">
    <title>DEVONagent for Web Searching [Sponsor]</title>
    <dc:date>2013-11-17T13:23:45+00:00</dc:date>
    <link>http://www.macdrifter.com/2013/11/devonagent-for-web-searching-sponsor.html</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>devonthink search browser webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:0231e483d3d9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:devonthink"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:browser"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://bootcat.sslmit.unibo.it/">
    <title>BootCaT</title>
    <dc:date>2013-09-13T05:01:45+00:00</dc:date>
    <link>http://bootcat.sslmit.unibo.it/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>corpora nlp perl webspider datamining</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:3d2e97384a41/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:perl"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:datamining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://love-python.blogspot.ca/2008/03/use-proxy-in-your-spider.html">
    <title>life is short - you need Python!: Use Proxy in your Spider</title>
    <dc:date>2013-09-07T22:03:39+00:00</dc:date>
    <link>http://love-python.blogspot.ca/2008/03/use-proxy-in-your-spider.html</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python proxy webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:bafb313a1a3e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:proxy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://love-python.blogspot.ca/2013/09/free-proxy-list-for-crawlers.html">
    <title>life is short - you need Python!: free proxy list for crawlers</title>
    <dc:date>2013-09-07T22:02:00+00:00</dc:date>
    <link>http://love-python.blogspot.ca/2013/09/free-proxy-list-for-crawlers.html</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>proxy webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:79367d4cf8bf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:proxy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/ianmilligan1/Exploring-Wide-Scrape">
    <title>ianmilligan1/Exploring-Wide-Scrape</title>
    <dc:date>2013-08-20T06:06:55+00:00</dc:date>
    <link>https://github.com/ianmilligan1/Exploring-Wide-Scrape</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>wget webspider html corpora</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:74e434f3d279/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:wget"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.blindfiveyearold.com/crawl-optimization">
    <title>Crawl Optimization: You Are What Googlebot Eats</title>
    <dc:date>2013-08-04T06:20:26+00:00</dc:date>
    <link>http://www.blindfiveyearold.com/crawl-optimization</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>search webspider evaluation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:e62e0ecb7f14/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:evaluation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://fruchterco.com/post/53164489086/python-headless-web-browser-scraping-on-amazon-linux">
    <title>Fruchter &amp; Co. — Python Headless Web Browser Scraping on Amazon Linux</title>
    <dc:date>2013-06-17T15:24:55+00:00</dc:date>
    <link>http://fruchterco.com/post/53164489086/python-headless-web-browser-scraping-on-amazon-linux</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python webspider ec2 s3</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:aad7f8bd2997/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:ec2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:s3"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://davidwalsh.name/python-scrape">
    <title>Scraping iTunes Charts Using Scrapy Python</title>
    <dc:date>2013-06-12T23:10:12+00:00</dc:date>
    <link>http://davidwalsh.name/python-scrape</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>itunes python webspider scrapy</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:9cdaeda9d249/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:itunes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:scrapy"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.gregreda.com/2013/04/29/more-web-scraping-with-python/">
    <title>Greg Reda | More web scraping with Python (and a map)</title>
    <dc:date>2013-05-04T12:50:52+00:00</dc:date>
    <link>http://www.gregreda.com/2013/04/29/more-web-scraping-with-python/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider python</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:3e10cc638b46/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.gregreda.com/2013/03/03/web-scraping-101-with-python/">
    <title>Greg Reda | Web Scraping 101 with Python</title>
    <dc:date>2013-03-11T10:21:55+00:00</dc:date>
    <link>http://www.gregreda.com/2013/03/03/web-scraping-101-with-python/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:433c3b43e51f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/Max00355/PySpider">
    <title>Max00355/PySpider · GitHub</title>
    <dc:date>2013-03-02T07:54:18+00:00</dc:date>
    <link>https://github.com/Max00355/PySpider</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:b0734ea320ec/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://webscraping.com/blog/Generate-website-screenshot-history/">
    <title>Generating a website screenshot history | WebScraping.com</title>
    <dc:date>2013-02-18T12:59:33+00:00</dc:date>
    <link>http://webscraping.com/blog/Generate-website-screenshot-history/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider screenshot html</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:3ceb8e4073a8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:screenshot"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://webscraping.com/blog/Web-Scraping-Interface/">
    <title>Web Scraping User Interface | WebScraping.com</title>
    <dc:date>2013-02-18T12:59:17+00:00</dc:date>
    <link>http://webscraping.com/blog/Web-Scraping-Interface/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider gui</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:a73828c1f7a2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:gui"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://lemurproject.org/clueweb12.php/">
    <title>The ClueWeb12 Dataset</title>
    <dc:date>2013-02-14T13:37:41+00:00</dc:date>
    <link>http://lemurproject.org/clueweb12.php/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>corpora webspider nlp url</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:f23525fca20b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:url"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/zaiste/cu">
    <title>zaiste/cu · GitHub</title>
    <dc:date>2013-01-26T09:22:43+00:00</dc:date>
    <link>https://github.com/zaiste/cu</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>curl url webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:c9fda7a6b544/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:curl"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:url"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/oscardelben/rawler">
    <title>oscardelben/rawler · GitHub</title>
    <dc:date>2013-01-26T04:35:40+00:00</dc:date>
    <link>https://github.com/oscardelben/rawler</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>url ruby webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:de544df11d5e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:url"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:ruby"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://cnets.indiana.edu/groups/nan/webtraffic/click-dataset">
    <title>Click Dataset | Center for Complex Networks and Systems Research</title>
    <dc:date>2013-01-20T07:13:11+00:00</dc:date>
    <link>http://cnets.indiana.edu/groups/nan/webtraffic/click-dataset</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider url corpora</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:485e8f533f52/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:url"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.codeproject.com/Articles/526872/Crawlingpluswithplusthreads">
    <title>Crawling with threads - CodeProject</title>
    <dc:date>2013-01-14T01:51:49+00:00</dc:date>
    <link>http://www.codeproject.com/Articles/526872/Crawlingpluswithplusthreads</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python webspider distributed evaluation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:c006b9694cc5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:evaluation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/socketubs/4chandownloader">
    <title>socketubs/4chandownloader · GitHub</title>
    <dc:date>2013-01-12T11:37:27+00:00</dc:date>
    <link>https://github.com/socketubs/4chandownloader</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python 4chan webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:2c207ca18fe1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:4chan"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://searchco.de/blog/view/code-for-a-search-engine-in-php-part-1">
    <title>Code a Search Engine in PHP Part 1 | searchcode</title>
    <dc:date>2013-01-11T07:34:51+00:00</dc:date>
    <link>http://searchco.de/blog/view/code-for-a-search-engine-in-php-part-1</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>search php webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:33026b97fdaf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:php"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://code.google.com/p/ldspider/">
    <title>ldspider - Java implementation of a Linked Data web crawler - Google Project Hosting</title>
    <dc:date>2013-01-10T22:13:03+00:00</dc:date>
    <link>https://code.google.com/p/ldspider/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>java datamining semanticweb webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:c703a41236c9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:semanticweb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/drdrang/radio2">
    <title>drdrang/radio2 · GitHub</title>
    <dc:date>2013-01-10T19:24:38+00:00</dc:date>
    <link>https://github.com/drdrang/radio2</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>applescript music internet webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:73e4c3deed21/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:applescript"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:music"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:internet"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/Miserlou/AngelGraph">
    <title>Miserlou/AngelGraph · GitHub</title>
    <dc:date>2013-01-09T07:45:54+00:00</dc:date>
    <link>https://github.com/Miserlou/AngelGraph</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python visualization webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:9ed266bac2dd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/scrapy/slybot">
    <title>scrapy/slybot · GitHub</title>
    <dc:date>2013-01-09T01:48:31+00:00</dc:date>
    <link>https://github.com/scrapy/slybot</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python scrapy webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:6a0b5b89db68/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:scrapy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/svetlyak40wt/scrapy-useragents">
    <title>svetlyak40wt/scrapy-useragents · GitHub</title>
    <dc:date>2013-01-09T01:24:45+00:00</dc:date>
    <link>https://github.com/svetlyak40wt/scrapy-useragents</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python scrapy webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:7a313eac155b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:scrapy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/darthbear/scrapy-mongodb-pipeline">
    <title>darthbear/scrapy-mongodb-pipeline · GitHub</title>
    <dc:date>2013-01-09T01:22:09+00:00</dc:date>
    <link>https://github.com/darthbear/scrapy-mongodb-pipeline</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>scrapy python mongodb webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:e5eb1961b8e7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:scrapy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:mongodb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/darthbear/scrapy-simple-http-queue">
    <title>darthbear/scrapy-simple-http-queue · GitHub</title>
    <dc:date>2013-01-09T01:21:47+00:00</dc:date>
    <link>https://github.com/darthbear/scrapy-simple-http-queue</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>scrapy python webspider distributed queue url</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:6863e50c50d7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:scrapy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:queue"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:url"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/darthbear/scrapy-proxynova">
    <title>darthbear/scrapy-proxynova · GitHub</title>
    <dc:date>2013-01-09T01:18:40+00:00</dc:date>
    <link>https://github.com/darthbear/scrapy-proxynova</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider scrapy python proxy</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:a77f43ea8b50/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:scrapy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:proxy"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.atlantbh.com/apache-nutch-overview/">
    <title>Apache Nutch Overview « Atlantbh :: Software Development, Hadoop, Big Data, Cloud, Outsourcing</title>
    <dc:date>2013-01-08T11:20:27+00:00</dc:date>
    <link>http://www.atlantbh.com/apache-nutch-overview/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>nutch webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:382e33271cfb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:nutch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://mathoverflow.net/questions/686/handling-arxiv-feeds-to-avoid-duplicates">
    <title>Handling arXiv feeds to avoid duplicates - MathOverflow</title>
    <dc:date>2013-01-08T09:45:14+00:00</dc:date>
    <link>http://mathoverflow.net/questions/686/handling-arxiv-feeds-to-avoid-duplicates</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>arxiv rss webspider deduplication</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:9bfe0e78f683/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:arxiv"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:rss"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:deduplication"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://devblog.seomoz.org/2012/07/solutions-for-crawler-problems/">
    <title>Solutions for Crawler Problems | SEOmoz Developer Blog</title>
    <dc:date>2013-01-07T12:42:27+00:00</dc:date>
    <link>http://devblog.seomoz.org/2012/07/solutions-for-crawler-problems/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:8f0afeec451c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://devblog.seomoz.org/2012/06/how-does-seomoz-crawl-the-web/">
    <title>How does SEOmoz Crawl the Web? | SEOmoz Developer Blog</title>
    <dc:date>2013-01-07T12:42:18+00:00</dc:date>
    <link>http://devblog.seomoz.org/2012/06/how-does-seomoz-crawl-the-web/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:ebf55f92257f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/seomoz/g-crawl-py">
    <title>seomoz/g-crawl-py · GitHub</title>
    <dc:date>2013-01-07T12:40:13+00:00</dc:date>
    <link>https://github.com/seomoz/g-crawl-py</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider python</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:d47259c6857d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/seomoz/url-py">
    <title>seomoz/url-py · GitHub</title>
    <dc:date>2013-01-07T12:39:57+00:00</dc:date>
    <link>https://github.com/seomoz/url-py</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python url webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:625c46db9830/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:url"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://macwright.org/2012/11/14/indexing-searching-big-static-data.html">
    <title>Indexing and Searching Big Static Data - macwright.org</title>
    <dc:date>2013-01-03T04:50:20+00:00</dc:date>
    <link>http://macwright.org/2012/11/14/indexing-searching-big-static-data.html</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>search javascript indexing webspider algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:46a8bff9b749/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:javascript"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:indexing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/joehand/Rampage-Killers-Data">
    <title>joehand/Rampage-Killers-Data · GitHub</title>
    <dc:date>2013-01-03T04:48:47+00:00</dc:date>
    <link>https://github.com/joehand/Rampage-Killers-Data</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python corpora datamining webspider wikipedia</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:a6d527897cc9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:wikipedia"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://news.ycombinator.com/item?id=4207439">
    <title>How We Built A Data Center With Commodity Hardware And FOSS | Hacker News</title>
    <dc:date>2013-01-02T10:26:39+00:00</dc:date>
    <link>https://news.ycombinator.com/item?id=4207439</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webserver webspider evaluation ec2 RAM kompooter</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:3641cf1a89af/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webserver"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:evaluation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:ec2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:RAM"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:kompooter"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.searchenabler.com/blog/build-your-own-data-center/">
    <title>How We Built A Data Center With Commodity Hardware And FOSS | SearchEnabler</title>
    <dc:date>2013-01-02T10:19:05+00:00</dc:date>
    <link>http://www.searchenabler.com/blog/build-your-own-data-center/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>sysadmin webspider webserver RAM kompooter evaluation storage</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:4ec13aad4134/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:sysadmin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webserver"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:RAM"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:kompooter"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:evaluation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:storage"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/matpalm/common-crawl">
    <title>matpalm/common-crawl · GitHub</title>
    <dc:date>2012-12-27T14:22:38+00:00</dc:date>
    <link>https://github.com/matpalm/common-crawl</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>corpora datamining webspider html wikipedia nlp machinelearning python java pig hadoop</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:de25beec0bda/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:html"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:wikipedia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:machinelearning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:pig"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:hadoop"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://rjpower.org/wordpress/running-a-pdf-crawler-with-heritrix/">
    <title>running a pdf crawler with heritrix » idle thoughts</title>
    <dc:date>2012-12-26T23:28:43+00:00</dc:date>
    <link>http://rjpower.org/wordpress/running-a-pdf-crawler-with-heritrix/</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>pdf webspider heritrix indexing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:bcb383f0fa37/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:pdf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:heritrix"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:indexing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/bbrodriges/pholcidae">
    <title>bbrodriges/pholcidae · GitHub</title>
    <dc:date>2012-12-26T20:56:53+00:00</dc:date>
    <link>https://github.com/bbrodriges/pholcidae</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python webspider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:784c2d77d59e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/noplay/scrapy-mongodb">
    <title>noplay/scrapy-mongodb · GitHub</title>
    <dc:date>2012-12-26T17:11:21+00:00</dc:date>
    <link>https://github.com/noplay/scrapy-mongodb</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python webspider scrapy mongodb</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:8da8f915df89/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:scrapy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:mongodb"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/noplay/scrapy-couchdb">
    <title>noplay/scrapy-couchdb · GitHub</title>
    <dc:date>2012-12-26T17:10:45+00:00</dc:date>
    <link>https://github.com/noplay/scrapy-couchdb</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python webspider couchdb</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:96d12567cbe2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:couchdb"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/noplay/scrapy-dot">
    <title>noplay/scrapy-dot · GitHub</title>
    <dc:date>2012-12-26T17:10:29+00:00</dc:date>
    <link>https://github.com/noplay/scrapy-dot</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python webspider visualization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:27900cac0eb2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:visualization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/noplay/scrapy-graphite">
    <title>noplay/scrapy-graphite · GitHub</title>
    <dc:date>2012-12-26T17:09:59+00:00</dc:date>
    <link>https://github.com/noplay/scrapy-graphite</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>python webspider graph visualization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:44e699b2d38d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:graph"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:visualization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/bcoe/routers-news">
    <title>bcoe/routers-news · GitHub</title>
    <dc:date>2012-12-26T11:28:42+00:00</dc:date>
    <link>https://github.com/bcoe/routers-news</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider news terminal node javascript</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:d38094d168db/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:news"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:terminal"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:node"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:javascript"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/wallunit/cocktail-search">
    <title>wallunit/cocktail-search · GitHub</title>
    <dc:date>2012-12-23T00:04:53+00:00</dc:date>
    <link>https://github.com/wallunit/cocktail-search</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>search scrapy sphinx python webspider cook</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:a9a420f85dc0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:scrapy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:sphinx"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:cook"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.luckyoyster.com/post/33592990831/data-mining-the-web-100-worth-of-priceless">
    <title>Lucky Oyster - Thought Pearls — Data Mining the Web: $100 Worth of Priceless</title>
    <dc:date>2012-12-19T01:05:55+00:00</dc:date>
    <link>http://blog.luckyoyster.com/post/33592990831/data-mining-the-web-100-worth-of-priceless</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider corpora s3 datamining informationretrieval</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:dcaf6486f549/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:s3"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:informationretrieval"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://zyxt.com/post/26851542949/study-of-1-3-billion-urls-22-of-web-pages-reference">
    <title>Zyxt Labs, Inc., Study of ~1.3 Billion URLs: ~22% of Web Pages Reference Facebook</title>
    <dc:date>2012-12-19T01:04:22+00:00</dc:date>
    <link>http://zyxt.com/post/26851542949/study-of-1-3-billion-urls-22-of-web-pages-reference</link>
    <dc:creator>mt3_666</dc:creator><dc:subject>webspider datamining corpora url</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:mt3_666/b:1b204e271ada/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:webspider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:mt3_666/t:url"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>