CLI script to recreate all urls in articles on a Joomla! website and create redirects for the old urls.

migrate-urls.php

<?php
/**
 * @package    Joomla.Cli
 *
 * @copyright  Copyright (C) 2018 Niels van der Veer. All rights reserved.
 * @license    GNU General Public License version 2 or later; see LICENSE.txt
 */

/**
 * This is a CRON script which should be called from the command-line, not the
 * web. For example something like:
 * /usr/bin/php /path/to/site/cli/update_cron.php
 */

// Set flag that this is a parent file.
const _JEXEC = 1;

error_reporting(E_ALL | E_NOTICE);
ini_set('display_errors', 1);

// Load system defines
if (file_exists(dirname(__DIR__) . '/defines.php'))
{
    require_once dirname(__DIR__) . '/defines.php';
}

if (!defined('_JDEFINES'))
{
    define('JPATH_BASE', dirname(__DIR__));
    require_once JPATH_BASE . '/includes/defines.php';
}

require_once JPATH_LIBRARIES . '/import.legacy.php';
require_once JPATH_LIBRARIES . '/cms.php';

// Load the configuration
require_once JPATH_CONFIGURATION . '/configuration.php';

JLoader::register('ContentHelperRoute', JPATH_ROOT . '/components/com_content/helpers/route.php');

/**
 * This script will fetch the update information for all extensions and store
 * them in the database, speeding up your administrator.
 *
 * @since  2.5
 */
class MigrateUrlsCli extends JApplicationCli
{
    /**
     * Entry point for the script
     *
     * @return  void
     *
     * @since   2.5
     */
    public function doExecute()
    {
        $articles = $this->getAllArticles();

        foreach ($articles as $article) {
            $replacedText = $article->introtext;

            preg_match_all('~<a(.*?)href="([^"]+)"(.*?)>~', $article->introtext, $matches);

            foreach ($matches[2] as $key => $match) {
                $url = $this->recreateUrl($match);
                $html = $matches[0][$key];

                if ($url != null) {
                    $replacedText = str_replace($html, '<a href="' . $url . '">', $replacedText);
                }
            }

            $this->updateArticleText($article->id, $replacedText);

            // Use this method to create a redirect for a old url to a new url. Write some custom logic here to get the correct category and url that fit your needs.
            // $this->addRedirect('/' . $article->alias, '/' . $category . '/' . $article->alias);
        }
    }

    /**
     * Parse a found url in the article
     *
     * @param $url string Url to parse`
     *
     * @since  1.0.0
     * @return boolean
     */
    private function recreateUrl($url)
    {
        if (strpos($url, "index.php") === false)
        {
            return null;
        }

        // Parse url and query
        $parsedUrl = parse_url(str_replace("&amp;", "&", $url));
        parse_str($parsedUrl['query'], $parsedQuery);

        // If the link has no id, print and skip
        if(!array_key_exists("id", $parsedQuery)) {
            $this->out("No id found in: " . $url);
            return null;
        }

        // If the id contains a alias, remove it
        if (strpos($parsedQuery["id"], ":") !== false)
        {
            $parsedQuery["id"] = preg_split("/:/", $parsedQuery["id"])[0];
        }

        // Get the article and create a new url
        $article = $this->getArticle($parsedQuery['id']);

        if ($article == null)
        {
            $this->out("no article found for id: " . $parsedQuery["id"]);
            return null;
        }

        return htmlspecialchars(ContentHelperRoute::getArticleRoute($article->id, $article->catid, '*'));
    }

    /**
     * Get a single article by ID
     *
     * @param $id int id of the article
     * @return stdClass
     */
    private function getArticle($id)
    {
        $db = \Joomla\CMS\Factory::getDbo();
        $q = $db->getQuery(true)
            ->select("*")
            ->from($db->qn("#__content"))
            ->where($db->qn("id") . '=' . (int) $id);

        $db->setQuery($q);

        return $db->loadObject();
    }

    /**
     * Get all articles in the database
     *
     * @return mixed
     */
    private function getAllArticles()
    {
        $db = \Joomla\CMS\Factory::getDbo();
        $q = $db->getQuery(true)
            ->select("*")
            ->from($db->qn("#__content"));

        $db->setQuery($q);

        return $db->loadObjectList();
    }

    /**
     * Update the article text of a article
     *
     * @param $id int Article id
     * @param $text string New article text
     * 
     * @return void
     */
    private function updateArticleText($id, $text)
    {
        $db = \Joomla\CMS\Factory::getDbo();
        $query = $db->getQuery(true);

        // Fields to update.
        $fields = array(
            $db->quoteName('introtext') . ' = ' . $db->quote($text)
        );

        // Conditions for which records should be updated.
        $conditions = array(
            $db->quoteName('id') . ' = ' . (int) $id
        );

        $query->update($db->quoteName('#__content'))->set($fields)->where($conditions);
        $db->setQuery($query);
        $db->execute();
    }

    /**
     * Add a 301 redirect
     * 
     * $oldUrl string The old url to redirect
     * $newUrl string The new url
     */
    private function addRedirect($oldUrl, $newUrl)
    {
        $date = \Joomla\CMS\Factory::getDate();
        $db = \Joomla\CMS\Factory::getDbo();

        // Create a new query object.
        $query = $db->getQuery(true);

        // Insert columns.
        $columns = array('old_url', 'new_url', 'published', 'header', 'created_date', 'modified_date');

        // Insert values.
        $values = array($db->quote($oldUrl), $db->quote($newUrl), 1, 301, $db->quote($date->toSql()), $db->quote($date->toSql()));

        // Prepare the insert query.
        $query
            ->insert($db->quoteName('#__redirect_links'))
            ->columns($db->quoteName($columns))
            ->values(implode(',', $values));

        // Set the query using our newly populated query object and execute it.
        $db->setQuery($query);
        $db->execute();
    }
}

JApplicationCli::getInstance('MigrateUrlsCli')->execute();