<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Datengraben</title>
    <link>https://datengraben.com/en/</link>
    <description>Recent content on Datengraben</description>
    <generator>Hugoo -- gohugo.io</generator>
    <language>en</language>
    <lastBuildDate>Thu, 22 Feb 2024 20:45:15 +0100</lastBuildDate><atom:link href="https://datengraben.com/en/rss.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Using git-history to build a web scraper in less than a minute</title>
      <link>https://datengraben.com/en/posts/2021-12-12-git-history-ffm-parking/</link>
      <pubDate>Thu, 22 Feb 2024 20:45:15 +0100</pubDate>
      
      
      <guid>https://datengraben.com/en/posts/2021-12-12-git-history-ffm-parking/</guid>
      <description>&lt;p&gt;Simon Willison describes in &lt;a href=&#34;https://simonwillison.net/2021/Dec/7/git-history/&#34;&gt;his blog post git-history&lt;/a&gt;,
a python tool which leverages a pattern, previously described &lt;a href=&#34;https://simonwillison.net/2020/Oct/9/git-scraping/&#34;&gt;by Simon&lt;/a&gt;
to scrape web content via &lt;a href=&#34;https://github.com/features/actions&#34;&gt;Github actions&lt;/a&gt;. Basically the pattern
scrapes a web resource and commits differences into a git repository.&lt;/p&gt;
&lt;p&gt;I wanted to try this pattern on a to this date static source of open data, to supply the future with a
time series of this former static source. So I did with the &lt;a href=&#34;https://offenedaten.frankfurt.de/dataset/912fe0ab-8976-4837-b591-57dbf163d6e5/resource/48378186-5732-41f3-9823-9d1938f2695e/download/parkdaten_dyn.xml&#34;&gt;parking data of Frankfurt&lt;/a&gt;
and you can inspect the data in &lt;a href=&#34;https://github.com/cpwnd/ffm-parking-history&#34;&gt;this repository&lt;/a&gt;.&lt;/p&gt;</description>
    </item>
    
  </channel>
</rss>
