<?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 (floehopper)</title>
    <link>https://pinboard.in/u:floehopper/public/</link>
    <description>recent bookmarks from floehopper</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://github.com/bjesus/pipet"/>
	<rdf:li rdf:resource="https://simonwillison.net/series/git-scraping/"/>
	<rdf:li rdf:resource="http://www.chadcf.com/blog/using-capybara-javascript-capable-replacement-mechanize"/>
	<rdf:li rdf:resource="https://chrome.google.com/webstore/detail/mbigbapnjcgaffohmbkdlecaccepngjd"/>
	<rdf:li rdf:resource="https://github.com/techbelly/gouge"/>
	<rdf:li rdf:resource="http://github.com/a2800276/rtemplatemaker"/>
	<rdf:li rdf:resource="http://www.out-law.com//default.aspx?page=10975&amp;utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+out-law-NewsRoundUP+(OUT-LAW+News-RoundUP)"/>
	<rdf:li rdf:resource="http://www.nationalrail.co.uk/contact/tandc/"/>
	<rdf:li rdf:resource="http://alpha.scraperwiki.com/"/>
	<rdf:li rdf:resource="http://anemone.rubyforge.org/"/>
	<rdf:li rdf:resource="http://www.freesteel.co.uk/wpblog/2009/03/replace-your-tired-api-with-a-shiny-codewiki/"/>
	<rdf:li rdf:resource="http://www.selectorgadget.com/"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://github.com/bjesus/pipet">
    <title>bjesus/pipet: Swiss-army tool for scraping and extracting data from online assets, made for hackers</title>
    <dc:date>2025-03-03T07:53:26+00:00</dc:date>
    <link>https://github.com/bjesus/pipet</link>
    <dc:creator>floehopper</dc:creator><dc:subject>web crawler scraping go-lang</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:floehopper/b:b9883d181614/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:crawler"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraping"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:go-lang"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://simonwillison.net/series/git-scraping/">
    <title>Simon Willison: Git scraping</title>
    <dc:date>2022-10-24T06:49:58+00:00</dc:date>
    <link>https://simonwillison.net/series/git-scraping/</link>
    <dc:creator>floehopper</dc:creator><dc:subject>web scraping git</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:floehopper/b:c092815812e0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraping"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:git"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.chadcf.com/blog/using-capybara-javascript-capable-replacement-mechanize">
    <title>Using capybara as a javascript capable replacement for Mechanize | chadcf</title>
    <dc:date>2012-01-28T20:52:31+00:00</dc:date>
    <link>http://www.chadcf.com/blog/using-capybara-javascript-capable-replacement-mechanize</link>
    <dc:creator>floehopper</dc:creator><dc:subject>capybara javascript ruby scraper scraping webkit mechanize</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:floehopper/b:4aba4d676d1b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:capybara"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:javascript"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:ruby"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraper"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraping"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:webkit"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:mechanize"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://chrome.google.com/webstore/detail/mbigbapnjcgaffohmbkdlecaccepngjd">
    <title>Scraper - Chrome Web Store</title>
    <dc:date>2011-02-22T01:03:36+00:00</dc:date>
    <link>https://chrome.google.com/webstore/detail/mbigbapnjcgaffohmbkdlecaccepngjd</link>
    <dc:creator>floehopper</dc:creator><description><![CDATA["Scraper is a simple extension for reading data from web pages into spreadsheets".]]></description>
<dc:subject>chrome extension scraping web table spreadsheet data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:floehopper/b:aa8609fcda98/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:chrome"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:extension"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraping"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:table"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:spreadsheet"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/techbelly/gouge">
    <title>techbelly/gouge</title>
    <dc:date>2011-02-18T12:42:44+00:00</dc:date>
    <link>https://github.com/techbelly/gouge</link>
    <dc:creator>floehopper</dc:creator><description><![CDATA["Heroku-deployable scraping library".]]></description>
<dc:subject>heroku scraping deployment ruby</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:floehopper/b:dde8273596b7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:heroku"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraping"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:deployment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:ruby"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://github.com/a2800276/rtemplatemaker">
    <title>a2800276's rtemplatemaker</title>
    <dc:date>2010-06-07T07:42:30+00:00</dc:date>
    <link>http://github.com/a2800276/rtemplatemaker</link>
    <dc:creator>floehopper</dc:creator><description><![CDATA["Port of Python templatemaker to Ruby. Given a list of text files in a similar format, templatemaker creates a template that can extract data from files in that same format. The underlying longest-common-substring algorithm is implemented in C for performance".
]]></description>
<dc:subject>screen scraping template extract ruby python common substring text</dc:subject>
<dc:identifier>https://pinboard.in/u:floehopper/b:ab9627a65f45/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:screen"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraping"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:template"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:extract"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:ruby"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:common"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:substring"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:text"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.out-law.com//default.aspx?page=10975&amp;utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+out-law-NewsRoundUP+(OUT-LAW+News-RoundUP)">
    <title>Database builder faces web-scraping lawsuit | Pinsent Masons LLP</title>
    <dc:date>2010-04-30T11:48:22+00:00</dc:date>
    <link>http://www.out-law.com//default.aspx?page=10975&amp;utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+out-law-NewsRoundUP+(OUT-LAW+News-RoundUP)</link>
    <dc:creator>floehopper</dc:creator><description><![CDATA[A ruling from the European Court of Justice in 2004 cast doubt on exactly how much protection database law gives to the back end of websites. Bookmaker William Hill successfully argued at the European Court of Justice that the British Horseracing Board (BHB) could not protect its database of races using the database right.

The Court agreed with the gambling company that the database was a by-product of the BHB's main activity, which was organising horse races. Making the database, then, did not demand the kind of effort that required the law's protection, it successfully argued.
]]></description>
<dc:subject>web scraping law copyright database copy eu</dc:subject>
<dc:identifier>https://pinboard.in/u:floehopper/b:b585be484228/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraping"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:law"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:copyright"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:copy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:eu"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.nationalrail.co.uk/contact/tandc/">
    <title>National Rail Enquiries - Terms &amp; conditions</title>
    <dc:date>2010-04-24T08:45:02+00:00</dc:date>
    <link>http://www.nationalrail.co.uk/contact/tandc/</link>
    <dc:creator>floehopper</dc:creator><description><![CDATA["This Web Site is for your personal and non-commercial use. You may not at any time modify, store, copy (including for example screen scraping), extract, reutilise, distribute, transmit, display, perform, reproduce, publish, license, create derivative works from, transfer, or sell, distribute or create any information, products or services obtained from, linked to or using this Web Site and any data therein or that may provide users with the ability to do the same".
]]></description>
<dc:subject>national rail enquiries terms conditions scraping</dc:subject>
<dc:identifier>https://pinboard.in/u:floehopper/b:d33ce29b045a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:national"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:rail"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:enquiries"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:conditions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraping"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://alpha.scraperwiki.com/">
    <title>ScraperWiki alpha</title>
    <dc:date>2010-02-18T15:19:39+00:00</dc:date>
    <link>http://alpha.scraperwiki.com/</link>
    <dc:creator>floehopper</dc:creator><description><![CDATA[It's a shame they only allow Python scripts.
]]></description>
<dc:subject>scraping web html python</dc:subject>
<dc:identifier>https://pinboard.in/u:floehopper/b:43d54c9d9743/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraping"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:html"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:python"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://anemone.rubyforge.org/">
    <title>Anemone - Ruby Web-Spider Framework</title>
    <dc:date>2009-07-09T09:10:27+00:00</dc:date>
    <link>http://anemone.rubyforge.org/</link>
    <dc:creator>floehopper</dc:creator><dc:subject>ruby spider crawler scraping</dc:subject>
<dc:identifier>https://pinboard.in/u:floehopper/b:d8850be54275/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:ruby"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:spider"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:crawler"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraping"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.freesteel.co.uk/wpblog/2009/03/replace-your-tired-api-with-a-shiny-codewiki/">
    <title>Replace your tired API with a shiny codewiki</title>
    <dc:date>2009-03-26T18:43:03+00:00</dc:date>
    <link>http://www.freesteel.co.uk/wpblog/2009/03/replace-your-tired-api-with-a-shiny-codewiki/</link>
    <dc:creator>floehopper</dc:creator><dc:subject>api wiki scraping</dc:subject>
<dc:identifier>https://pinboard.in/u:floehopper/b:73f4268fa92c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:api"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:wiki"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraping"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.selectorgadget.com/">
    <title>Introducing SelectorGadget: point and click CSS selectors</title>
    <dc:date>2009-03-11T15:23:42+00:00</dc:date>
    <link>http://www.selectorgadget.com/</link>
    <dc:creator>floehopper</dc:creator><description><![CDATA["An open source bookmarklet that makes CSS selector generation and discovery on complicated sites a breeze".
]]></description>
<dc:subject>css bookmarklet element selector scraping</dc:subject>
<dc:identifier>https://pinboard.in/u:floehopper/b:94b1ac1a5005/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:css"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:bookmarklet"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:element"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:selector"/>
	<rdf:li rdf:resource="https://pinboard.in/u:floehopper/t:scraping"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>