Introduce medium importer

docs/_data/importer_dependencies.yml

@@ -50,6 +50,8 @@ jrnl:
 - safe_yaml
 marley:
 - safe_yaml
+medium:
+- safe_yaml
 mephisto:
 - mysql2
 - sequel

docs/_importers/medium.md

@@ -0,0 +1,27 @@
+---
+layout: docs
+title: Medium
+prev_section: marley
+link_source: medium
+next_section: mephisto
+permalink: /docs/medium/
+---
+
+To import your posts from [Medium](https://medium.com/), run:
+
+{% highlight bash %}
+$ ruby -r rubygems -e 'require "jekyll-import";
+    JekyllImport::Importers::Medium.run({
+        "username"       => "name",
+        "render_audio"   => false,
+        "canonical_link" => false,
+    })'
+{% endhighlight %}
+
+The `username` refers to the medium username, and it's a mandatory field.
+
+Other optional fields are as follows:
+* `canonical_link` – copy original link as `canonical_url` to post. (default: `false`)
+* `render_audio` – render `<audio>` element in posts for the enclosure URLs. (default: `false`)
+
+_Note:_ This importer will also import the existing tags/labels from Medium post and include the tags to [Front Matter](https://jekyllrb.com/docs/front-matter/).

lib/jekyll-import/importers/medium.rb

@@ -0,0 +1,36 @@
+# frozen_string_literal: true
+
+module JekyllImport
+  module Importers
+    class Medium < Importer
+      def self.specify_options(c)
+        c.option "username",       "--username NAME",  "Medium username"
+        c.option "canonical_link", "--canonical_link", "Copy original link as canonical_url to post (default: false)"
+        c.option "render_audio",   "--render_audio",   "Render <audio> element in posts for the enclosure URLs (default: false)"
+      end
+
+      def self.validate(options)
+        abort "Missing mandatory option --username." if options["username"].nil?
+      end
+
+      def self.require_deps
+        Importers::RSS.require_deps
+      end
+
+      # Medium posts and associated metadata are exported as an RSS Feed. Hence invoke our RSS Importer to create the
+      # Jekyll source directory.
+      #
+      # "Tags" attached to a Medium post are exported under the markup `<item><category>...</category></item>` in the
+      # export feed. Therefore, configure the RSS Importer to always look for tags in the `<category></category>` field
+      # of an RSS item.
+      def self.process(options)
+        Importers::RSS.process({
+          "source"         => "https://medium.com/feed/@#{options.fetch("username")}",
+          "render_audio"   => options.fetch("render_audio", false),
+          "canonical_link" => options.fetch("canonical_link", false),
+          "extract_tags"   => "category",
+        })
+      end
+    end
+  end
+end

test/mocks/medium_feed.xml

@@ -0,0 +1,50 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/"
+     xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"
+     xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
+  <channel>
+    <title><![CDATA[Stories by John Doe on Medium]]></title>
+    <description><![CDATA[Stories by John Doe on Medium]]></description>
+    <link>https://medium.com/@John.Doe?source=rss-621a1d970ada------2</link>
+    <image>
+      <url>https://cdn-images-1.medium.com/fit/c/150/150/1*dmbNkD5D-u45r44go_cf0g.png</url>
+      <title>Stories by John Doe on Medium</title>
+      <link>https://medium.com/@John.Doe?source=rss-621a1d970ada------2</link>
+    </image>
+    <generator>Medium</generator>
+    <lastBuildDate>Tue, 06 Dec 2022 06:52:04 GMT</lastBuildDate>
+    <atom:link href="https://medium.com/@John.Doe/feed" rel="self" type="application/rss+xml"/>
+    <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
+    <atom:link href="http://medium.superfeedr.com" rel="hub"/>
+    <item>
+      <title><![CDATA[This is a Dummy Post]]></title>
+      <link>https://example.com/blog/this-is-a-dummy-post-50703370aea7?source=rss-621a1d970ada------2</link>
+      <guid isPermaLink="false">https://medium.com/p/50703370aea7</guid>
+      <category><![CDATA[java]]></category>
+      <category><![CDATA[custom-jre]]></category>
+      <category><![CDATA[image-size-reduce]]></category>
+      <category><![CDATA[jvm]]></category>
+      <category><![CDATA[docker]]></category>
+      <dc:creator><![CDATA[John Doe]]></dc:creator>
+      <pubDate>Tue, 22 Nov 2022 08:01:46 GMT</pubDate>
+      <atom:updated>2022-11-23T14:51:57.412Z</atom:updated>
+      <content:encoded><<![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*v5nynoXfnHHGCpd0V0p8uw.png"
+        /></figure><p>The quick brown fox jumps over the lazy dog</p>]]></content:encoded>
+    </item>
+    <item>
+      <title><![CDATA[How I cross post Medium articles to GitHub Pages]]></title>
+      <link>https://example.com/blog/how-i-cross-post-medium-articles-to-github-pages-1cdf174bc674?source=rss-621a1d970ada------2</link>
+      <guid isPermaLink="false">https://medium.com/p/1cdf174bc674</guid>
+      <category><![CDATA[import]]></category>
+      <category><![CDATA[jekyll]]></category>
+      <category><![CDATA[github-pages]]></category>
+      <category><![CDATA[medium]]></category>
+      <category><![CDATA[personal-website]]></category>
+      <dc:creator><![CDATA[John Doe]]></dc:creator>
+      <pubDate>Thu, 10 Nov 2022 21:39:51 GMT</pubDate>
+      <atom:updated>2022-11-11T09:33:39.955Z</atom:updated>
+      <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*cR9eGZr50HArf_j9-rnjjQ.png"
+        /></figure><p>The quick brown fox jumps over the lazy dog</p>]]></content:encoded>
+    </item>
+  </channel>
+</rss>