Makes a tab-delimited file from a WordPress post export

posts_by_language.xsl

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet version="2.0"
        xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
        xmlns:excerpt="http://wordpress.org/export/1.2/excerpt/"
        xmlns:content="http://purl.org/rss/1.0/modules/content/"
        xmlns:wfw="http://wellformedweb.org/CommentAPI/"
        xmlns:dc="http://purl.org/dc/elements/1.1/"
        xmlns:wp="http://wordpress.org/export/1.2/">

<xsl:output encoding="UTF-8" indent="yes" cdata-section-elements="content:encoded wp:meta_value category" method="text" standalone="yes" />

<xsl:variable name="language">en</xsl:variable>
<xsl:variable name="domain">language</xsl:variable>

<xsl:template match="/">
  <xsl:text>post_id&#x9;</xsl:text>
  <xsl:text>pubDate&#x9;</xsl:text>
  <xsl:text>status&#x9;</xsl:text>
  <xsl:text>title&#x9;</xsl:text>
  <xsl:text>link&#x9;</xsl:text>
  <xsl:text>categories</xsl:text>
  <xsl:text>&#xd;</xsl:text>
  <xsl:apply-templates select="rss/channel/item" />
</xsl:template>

<xsl:template match="item" priority="3">
  <xsl:choose>
    <xsl:when test="wp:post_type[contains(., 'post')]">
      <xsl:if test="category[@domain = $domain] and category[@nicename = $language]">
        <xsl:call-template name="item" />
      </xsl:if>
    </xsl:when>
  </xsl:choose>
</xsl:template>

<xsl:template name="item">
  <item>
    <xsl:variable name="title" select="title" />
    <xsl:value-of select="wp:post_id" />
    <xsl:text>&#x9;</xsl:text>
    <xsl:value-of select="pubDate" />
    <xsl:text>&#x9;</xsl:text>
    <xsl:value-of select="wp:status" />
    <xsl:text>&#x9;</xsl:text>
    <xsl:value-of select="replace($title, '&#x9;', '')" />
    <xsl:text>&#x9;</xsl:text>
    <!-- leave the last &#x9; as a placeholder cell for category -->
    <xsl:value-of select="link" /><xsl:text>?flag=us</xsl:text>
    <xsl:text>&#xd;</xsl:text>
  </item>
</xsl:template>

</xsl:stylesheet>

results.txt

post_id	pubDate	status	title	link	categories
602	Mon, 14 Apr 2014 19:19:22 +0000	publish	Example post	http://127.0.0.1/sample-post/?flag=us

sample_input.xml

<?xml version="1.0" encoding="UTF-8" ?>
<!-- This is a WordPress eXtended RSS file generated by WordPress as an export of your site. -->
<!-- It contains information about your site's posts, pages, comments, categories, and other content. -->
<!-- You may use this file to transfer that content from one site to another. -->
<!-- This file is not intended to serve as a complete backup of your site. -->

<!-- To import this information into a WordPress site follow these steps: -->
<!-- 1. Log in to that site as an administrator. -->
<!-- 2. Go to Tools: Import in the WordPress admin panel. -->
<!-- 3. Install the "WordPress" importer from the list. -->
<!-- 4. Activate & Run Importer. -->
<!-- 5. Upload this file using the form provided on that page. -->
<!-- 6. You will first be asked to map the authors in this export file to users -->
<!--    on the site. For each author, you may choose to map to an -->
<!--    existing user on the site or to create a new user. -->
<!-- 7. WordPress will then import each of the posts, pages, comments, categories, etc. -->
<!--    contained in this file into your site. -->

<!-- generator="WordPress/4.6.1" created="2016-09-15 18:45" -->
<rss version="2.0"
  xmlns:excerpt="http://wordpress.org/export/1.2/excerpt/"
  xmlns:content="http://purl.org/rss/1.0/modules/content/"
  xmlns:wfw="http://wellformedweb.org/CommentAPI/"
  xmlns:dc="http://purl.org/dc/elements/1.1/"
  xmlns:wp="http://wordpress.org/export/1.2/"
>

<channel>
  <title>Sitename</title>
  <link>http://127.0.0.1</link>
  <description>another wp website</description>
  <pubDate>Thu, 15 Sep 2016 18:45:29 +0000</pubDate>
  <language>en-US</language>
  <wp:wxr_version>1.2</wp:wxr_version>
  <wp:base_site_url>http://127.0.0.1</wp:base_site_url>
  <wp:base_blog_url>http://127.0.0.1</wp:base_blog_url>

  <wp:author><wp:author_id>3</wp:author_id><wp:author_login><![CDATA[admin]]></wp:author_login><wp:author_email><![CDATA[[email protected]]]></wp:author_email><wp:author_display_name><![CDATA[admin]]></wp:author_display_name><wp:author_first_name><![CDATA[]]></wp:author_first_name><wp:author_last_name><![CDATA[]]></wp:author_last_name></wp:author>


  <generator>https://wordpress.org/?v=4.6.1</generator>

  <item>
    <title>Example post</title>
    <link>http://127.0.0.1/sample-post/</link>
    <pubDate>Mon, 14 Apr 2014 19:19:22 +0000</pubDate>
    <dc:creator><![CDATA[admin]]></dc:creator>
    <guid isPermaLink="false">http://127.0.0.1/?p=602</guid>
    <description></description>
    <content:encoded><![CDATA[<a href="/wp-content/uploads/2014/05/file">Sample post</a>]]></content:encoded>
    <excerpt:encoded><![CDATA[]]></excerpt:encoded>
    <wp:post_id>602</wp:post_id>
    <wp:post_date><![CDATA[2014-04-14 14:19:22]]></wp:post_date>
    <wp:post_date_gmt><![CDATA[2014-04-14 19:19:22]]></wp:post_date_gmt>
    <wp:comment_status><![CDATA[closed]]></wp:comment_status>
    <wp:ping_status><![CDATA[closed]]></wp:ping_status>
    <wp:post_name><![CDATA[sample-post]]></wp:post_name>
    <wp:status><![CDATA[publish]]></wp:status>
    <wp:post_parent>0</wp:post_parent>
    <wp:menu_order>0</wp:menu_order>
    <wp:post_type><![CDATA[post]]></wp:post_type>
    <wp:post_password><![CDATA[]]></wp:post_password>
    <wp:is_sticky>0</wp:is_sticky>
    <category domain="language" nicename="en"><![CDATA[English]]></category>
    <category domain="category" nicename="newsroom"><![CDATA[Newsroom]]></category>
    <category domain="post_translations" nicename="pll_54454839cbd7f"><![CDATA[pll_54454839cbd7f]]></category>
    <wp:postmeta>
      <wp:meta_key><![CDATA[_edit_last]]></wp:meta_key>
      <wp:meta_value><![CDATA[6]]></wp:meta_value>
    </wp:postmeta>
    <wp:postmeta>
      <wp:meta_key><![CDATA[slide_template]]></wp:meta_key>
      <wp:meta_value><![CDATA[default]]></wp:meta_value>
    </wp:postmeta>
    <wp:postmeta>
      <wp:meta_key><![CDATA[newsroom-pdf]]></wp:meta_key>
      <wp:meta_value><![CDATA[761]]></wp:meta_value>
    </wp:postmeta>
    <wp:postmeta>
      <wp:meta_key><![CDATA[_newsroom-pdf]]></wp:meta_key>
      <wp:meta_value><![CDATA[field_53921515bf5a9]]></wp:meta_value>
    </wp:postmeta>
  </item>
  </channel>
  </rss>

wordpress_posts_by_language.sh

java -jar c:\tools\saxon\saxon9he.jar -s:sample_input.xml -xsl:posts_by_language.xsl -o:results.txt