rss-xml-url-sub-input.xml

<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0"
  xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>RStudio Blog</title>
    <link>https://blog.rstudio.com/</link>
    <description>Recent content on RStudio Blog</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <managingEditor>info@rstudio.com (RStudio, Inc.)</managingEditor>
    <webMaster>info@rstudio.com (RStudio, Inc.)</webMaster>
    <lastBuildDate>Wed, 23 Dec 2020 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://blog.rstudio.com/" rel="self" type="application/rss+xml" />
    <item>
      <title>Exploring US COVID-19 Cases and Deaths</title>
      <link>https://blog.rstudio.com/2020/12/23/exploring-us-covid-19-cases/</link>
      <pubDate>Wed, 23 Dec 2020 00:00:00 +0000</pubDate>
      <author>Art Steinmetz</author>
      <guid>https://blog.rstudio.com/2020/12/23/exploring-us-covid-19-cases/</guid>
      <description>
        &lt;img src="pic12.png" /&gt;
        &lt;a src="anchor12.png" /&gt;
        &lt;script src="script12.js" /&gt;
      </description>
    </item>
    <item>
      <title>Winners of the 2020 RStudio Table Contest</title>
      <link>https://blog.rstudio.com/2020/12/23/winners-of-the-2020-rstudio-table-contest/</link>
      <pubDate>Wed, 23 Dec 2020 00:00:00 +0000</pubDate>
      <author>Rich Iannone and Curtis Kephart</author>
      <guid>https://blog.rstudio.com/2020/12/23/winners-of-the-2020-rstudio-table-contest/</guid>
      <description>
        &lt;img src="pic22.png" /&gt;
        &lt;a src="anchor22.png" /&gt;
        &lt;script src="script22.js" /&gt;
      </description>
    </item>
  </channel>
</rss>

rss-xml-url-sub-output.xml

<?xml version='1.0' encoding='utf-8'?>
<rss xmlns:ns0="http://www.w3.org/2005/Atom" version="2.0">
  <channel>
    <title>RStudio Blog</title>
    <link>https://blog.rstudio.com/</link>
    <description>Recent content on RStudio Blog</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <managingEditor>info@rstudio.com (RStudio, Inc.)</managingEditor>
    <webMaster>info@rstudio.com (RStudio, Inc.)</webMaster>
    <lastBuildDate>Wed, 23 Dec 2020 00:00:00 +0000</lastBuildDate>
    <ns0:link href="https://blog.rstudio.com/" rel="self" type="application/rss+xml" />
    <item>
      <title>Exploring US COVID-19 Cases and Deaths</title>
      <link>https://blog.rstudio.com/2020/12/23/exploring-us-covid-19-cases/</link>
      <pubDate>Wed, 23 Dec 2020 00:00:00 +0000</pubDate>
      <author>Art Steinmetz</author>
      <guid>https://blog.rstudio.com/2020/12/23/exploring-us-covid-19-cases/</guid>
      <description>
        &lt;img src="https://blog.rstudio.com/2020/12/23/exploring-us-covid-19-cases/pic12.png" /&gt;
        &lt;a src="https://blog.rstudio.com/2020/12/23/exploring-us-covid-19-cases/anchor12.png" /&gt;
        &lt;script src="script12.js" /&gt;
      </description>
    </item>
    <item>
      <title>Winners of the 2020 RStudio Table Contest</title>
      <link>https://blog.rstudio.com/2020/12/23/winners-of-the-2020-rstudio-table-contest/</link>
      <pubDate>Wed, 23 Dec 2020 00:00:00 +0000</pubDate>
      <author>Rich Iannone and Curtis Kephart</author>
      <guid>https://blog.rstudio.com/2020/12/23/winners-of-the-2020-rstudio-table-contest/</guid>
      <description>
        &lt;img src="https://blog.rstudio.com/2020/12/23/winners-of-the-2020-rstudio-table-contest/pic22.png" /&gt;
        &lt;a src="https://blog.rstudio.com/2020/12/23/winners-of-the-2020-rstudio-table-contest/anchor22.png" /&gt;
        &lt;script src="script22.js" /&gt;
      </description>
    </item>
  </channel>
</rss>

rss-xml-url-sub.py

# Platform :  Darwin-20.2.0-x86_64-i386-64bit
# Version  :  3.7.4
import platform
import subprocess
import re
import defusedxml.cElementTree as ET


def main():
    input_file = "rss-xml-url-sub-input.xml"
    output_file = "rss-xml-url-sub-output.xml"

    print("Before   :", subprocess.check_output(
        'grep -m 1 "img" ' + input_file, shell=True))

    tree = ET.parse("rss-xml-url-sub-input.xml")
    root = tree.getroot()
    for item in root.iter("item"):
        link_url = item.find("link").text
        description = item.find("description")
        description.text = re.sub(
            # refer: https://regexr.com/3e9bv
            r'(<(?:img|a)[^>]+(?:src|href)=[\"|\'])(?!https?:\/\/)([^\/].+?)([\"|\'])',
            r'\1' + link_url + r'\2\3',
            description.text
        )

    tree.write(output_file, encoding="utf-8", xml_declaration=True)

    print("After    :", subprocess.check_output(
        'grep -m 1 "img" ' + output_file, shell=True))


if __name__ == "__main__":
    print("Platform : ", platform.platform())
    print("Version  : ", platform.python_version())
    main()