EE 1.x to Statamic Conversion

1-ee-template-export.xml

{assign_variable:master_weblog_name="blahg"}
{exp:rss:feed weblog="blahg"} 

<?xml version="1.0" encoding="UTF-8"?>
<!-- This is a WordPress eXtended RSS file generated by ExpressionEngine as an export of your blog. -->
<!-- It contains information about your blog's posts, comments, trackbacks and categories. -->
<!-- You use this file to transfer content from your ExpressionEngine blog to your WordPress blog. -->

<!-- To import this information into a WordPress blog follow these steps. -->
<!-- 1. Log into that blog as an administrator. -->
<!-- 2. Go to Tools: Import in the blog's admin panels (or Manage: Import in older versions of WordPress). -->
<!-- 3. Choose "WordPress" from the list. -->
<!-- 4. Upload this file using the form provided on that page. -->
<!-- 5. You will first be asked to map the authors in this export file to users -->
<!--    on the blog.  For each author, you may choose to map to an -->
<!--    existing user on the blog or to create a new user -->
<!-- 6. WordPress will then import each of the posts, comments, trackbacks and categories -->
<!--    contained in this file into your blog -->

<!-- generator="WordPress/2.8.4" created="2009-09-20 01:49"-->
<rss version="2.0"
    xmlns:excerpt="http://wordpress.org/export/1.0/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/1.0/"
>

<channel>
    <title>{weblog_name}</title>
    <link>http://also-ran.com/blahg</link>
    <description>{weblog_description}</description>
    <pubDate></pubDate>
    <generator>http://wordpress.org/?v=2.8.4</generator>
    <language>{weblog_language}</language>
    <wp:wxr_version>1.0</wp:wxr_version>
    <wp:base_site_url>{trimmed_url}</wp:base_site_url>
    <wp:base_blog_url>{trimmed_url}</wp:base_blog_url>

    {exp:weblog:entries weblog="blahg" limit="999" rdf="off" dynamic_start="on" disable="member_data|trackbacks|pagination"}
    <item>
        <title>{exp:xml_encode}{title}{/exp:xml_encode}</title>
        <link></link>
        <pubDate>{entry_date format="%r"}</pubDate>
        <dc:creator><![CDATA[{author}]]></dc:creator>
        {categories}
                <category><![CDATA[{category_name}]]></category>
                <category domain="category" nicename="{category_name}"><![CDATA[{category_name}]]></category>
        {/categories}

        <guid isPermaLink="false"></guid>
        <description></description>
        <content:encoded><![CDATA[{blahg_copy}]]></content:encoded>
        <wp:post_id></wp:post_id>
        <wp:post_date>{entry_date format="%Y-%m-%d %H:%i:%s"}</wp:post_date>
        <wp:post_date_gmt>{gmt_date format="%Y-%m-%d %H:%i:%s"}</wp:post_date_gmt>
        <wp:comment_status>open</wp:comment_status>
        <wp:ping_status>open</wp:ping_status>
        <wp:post_name>{url_title}</wp:post_name>
        <wp:status>publish</wp:status>
        <wp:post_parent>0</wp:post_parent>
        <wp:menu_order>0</wp:menu_order>
        <wp:post_type>post</wp:post_type>
        <wp:post_password></wp:post_password>
        {embed="export/comments" the_entry_id="{entry_id}"}
    </item>
    {/exp:weblog:entries} 
</channel>
</rss>
{/exp:rss:feed} 

2-convert.php

<?php
// USAGE: php convert.php

// Edit the details below to your needs
$wp_file = 'data/blahg.xml';
$export_folder = '_import/blahg/'; // existing files will be over-written, use with care

if (file_exists($wp_file)) {
  $xml = simplexml_load_file($wp_file);
  $count = 0;
  foreach ($xml->channel->item as $item) {
    $count ++;

    print "Exporting: (".$count.") " . $item->title."\n";
    $title = $item->title;
    $tags = array();
    $categories = array();
    $item_date = strtotime($item->pubDate);
    $file_name = $export_folder.date("Y-m-d", $item_date)."-".slugify($title).".md";

    if ($title == '') {
        $title = 'Untitled post';
    }

    foreach($item->category as $taxonomy) {
        if ($taxonomy['domain'] == 'post_tag') {
            $tags[] = $taxonomy['nicename'];
        }
        if ($taxonomy['domain'] == 'category') {
            $categories[] = $taxonomy['nicename'];
        }
    }

    print "  -- filename: ".$file_name;

    $markdown  = "---\n";
    $markdown .= "title: '" . $title ."'\n";
    if (sizeof($tags)) {
    	$markdown .= "tags:\n  - ".implode("\n  - ", $tags)."\n";
    }
    if (sizeof($categories)) {
      $markdown .= "categories:\n  - ".implode("\n  - ", $categories)."\n";
    }
    $markdown .= "meta_title: " . $title . "\n";
    $markdown .= "meta_description: \n";
    $markdown .= "meta_image: \n";
    $markdown .= "meta_og_title: \n";
    $markdown .= "meta_og_description: \n";
    $markdown .= "meta_og_type: article\n";
    $markdown .= "meta_twitter_title: "  . $title . "\n";
    $markdown .= "meta_twitter_description: \n";
    $markdown .= "meta_twitter_type: summary\n";
    $markdown .= "excerpt: \n";
    $markdown .= "content_builder:\n";
    $markdown .= "  -\n";
    $markdown .= "    type: content_block\n";
    $markdown .= "    content: '" . str_replace(array("\n", "\t", "\r"), '', $item->children('content', true)->encoded) . "'\n";
    $markdown .= "---\n";
    //$markdown .= $item->children('content', true)->encoded;
    $markdown .= "\n";

    file_put_contents($file_name, $markdown);

    print "\n";
  }
}

// Credit: http://sourcecookbook.com/en/recipes/8/function-to-slugify-strings-in-php
function slugify($text)
{
    // replace non letter or digits by -
    $text = preg_replace('~[^\\pL\d]+~u', '-', $text);
 
    // trim
    $text = trim($text, '-');
 
    // transliterate
    if (function_exists('iconv'))
    {
        $text = iconv('utf-8', 'us-ascii//TRANSLIT', $text);
    }
 
    // lowercase
    $text = strtolower($text);
 
    // remove unwanted characters
    $text = preg_replace('~[^-\w]+~', '', $text);
 
    if (empty($text))
    {
        return 'n-a';
    }
 
    return $text;
}