Blog reset

maandag 7 december 2020 - 476 woorden, 3 min read

Na meer dan 8 jaar heb ik een grote reset uitgevoerd voor mijn blog.

Mijn laatste blog is meer dan 8 jaar oud en dateert van 6 november 2012. Deze content stond al jaren niet meer online. Zonde, het zijn toch meer dan 150 berichten die ik tussen 2007 en 2012 heb geschreven op twee verschillende blogs. Één werk gerelateerde blog en één studie blog. De berichten van beide blogs heb ik nu samengevoegd op deze nieuwe blog.

Voor het overzetten van alle berichten uit Wordpress (uit 2 database tabellen) naar Markdown, heb ik het volgende PHP scriptje in elkaar gezet:

<?php

error_reporting(E_ALL);

require 'vendor/autoload.php';

use League\HTMLToMarkdown\HtmlConverter;

try {
  // Connect to database
  $db = mysqli_connect('sebastix_db', 'root', 'root', 'sebastix_blog', 3306);
  if ($db->connect_error) {
    throw new Exception($db->connect_error);
  }
  //
  // Select data from wp_posts table (io.sebastix.nl)
  //
  $query = 'SELECT * FROM `wp_posts` WHERE post_status = "publish"';
  $stmt = $db->prepare($query);
  $stmt->execute();
  $result = $stmt->get_result();
  $data = $result->fetch_all(MYSQLI_ASSOC);
  foreach($data as $i => $row) {
    $markdown_post_string = format_post($data[$i]);
    // create directory in development/content/blog with name $data[$i]['post_name']
    $targetDir = 'development/content/blog/io/' . $data[$i]['post_name'];
    if (!mkdir($concurrentDirectory = $targetDir) && !is_dir($concurrentDirectory)) {
      throw new \RuntimeException(sprintf('Directory "%s" was not created', $concurrentDirectory));
    }
    // write file index.md with $markdown_post_string
    file_put_contents($targetDir.'/index.md', $markdown_post_string);
  }

  //
  // Select data from ioblog_posts table (interactieontwerpen.sebastix.nl)
  //
  $query = 'SELECT * FROM `ioblog_posts` WHERE post_status = "publish"';
  $stmt = $db->prepare($query);
  $stmt->execute();
  $result = $stmt->get_result();
  $data = $result->fetch_all(MYSQLI_ASSOC);
  foreach($data as $i => $row) {
    $markdown_post_string = format_post($data[$i]);
    // create directory in development/content/blog with name $data[$i]['post_name']
    $targetDir = 'development/content/blog/interactieontwerpen/' . $data[$i]['post_name'];
    if (!mkdir($concurrentDirectory = $targetDir) && !is_dir($concurrentDirectory)) {
      throw new \RuntimeException(sprintf('Directory "%s" was not created', $concurrentDirectory));
    }
    // write file index.md with $markdown_post_string
    file_put_contents($targetDir.'/index.md', $markdown_post_string);
  }
} catch (Exception $e) {
  echo $e->getMessage();
}

/**
 * @param $data
 * @return string|string[]
 * @throws Exception
 */
function format_post($data){
  $markdown_template =
'---
title: "%post_title"
date: "%post_date"
description: "%description"
categories: [internet]
comments: true
---

%post_content
';
  // Format date from 2011-09-21 18:28:29 to 2011-09-21T18:28:29.000Z
  $post_date = new DateTime($data['post_date']);
  $post_date = $post_date->format('Y-m-d\TH:i:s.000\Z');
  /*
   * Post_content rewrites from HTML to Markdown
   * https://github.com/thephpleague/html-to-markdown gebruiken
   * Links
   * Images
   * remove: <!--more--> strings
   */
  // Replace newlines with <br />
  $data['post_content'] = nl2br($data['post_content']);
  $converter = new HtmlConverter();
  // Will strip all HTML tags which have no Markdown tag, such as <span> of <div> tags
  // $converter->getConfig()->setOption('strip_tags', true);
  $markdown_content = $converter->convert($data['post_content']);
  // Replace <img> url starting with http://www.sebastix.nl/blog/wp-content/uploads/ to ../../../images/
  // Replace <img> url starting with http://interactieontwerpen.sebastix.nl/uploads/ to ../../../images/
  // Replace <img> url starting with /uploads/ to ../../../images/
  $markdown_content = str_replace(array('http://www.sebastix.nl/blog/wp-content/uploads/', 'http://interactieontwerpen.sebastix.nl/uploads/', '/uploads/'), '../../../images/', $markdown_content);
  // TODO replace internal links starting with http://www.sebastix.nl or http://interactieontwerpen.sebastix.nl
  // TODO replace tags [flash http://youtube.com/id] with embedded iFrames
  // TODO replace html flash objects like <object height="344" width="425"><param name="movie" value="http://www.youtube.com/v/pcLaB0_eWmM&hl=nl&fs=1"></param><param name="allowFullScreen" value="true"></param><param name="allowscriptaccess" value="always"></param><embed allowfullscreen="true" allowscriptaccess="always" height="344" src="http://www.youtube.com/v/pcLaB0_eWmM&hl=nl&fs=1" type="application/x-shockwave-flash" width="425"></embed></object>

  $args = [
    '%post_title' => str_replace('"', '',$data['post_title']),
    '%post_date' => $post_date,
    '%description' => substr(strip_tags($data['post_content']), 0, 120) . '...',
    '%post_content' => $markdown_content
  ];
  return str_replace(array_keys($args), array_values($args), $markdown_template);
}