share-lt/app/Console/Commands/ImportBlogs.php

<?php

namespace App\Console\Commands;

use Illuminate\Console\Command;
use Illuminate\Support\Facades\DB;
use Illuminate\Support\Facades\Storage;
use App\Models\Entry;

class ImportBlogs extends Command
{
    /**
     * The name and signature of the console command.
     *
     * @var string
     */
    protected $signature = 'app:import-blogs';

    /**
     * The console command description.
     *
     * @var string
     */
    protected $description = 'Command description';

    /**
     * Execute the console command.
     */
    public function handle()
    {

        /*

            {
                "id": 7,
                "title": "Low/No Code FlowiseAI",
                "slug": "lowno-code-flowiseai",
                "content": "<p><img alt=\"\" src=\"http://127.0.0.1:8000/storage/99/ZsTHWAQRbdvgRUEwGmCIsm4TyChIjBwiY71VmnnR.webp\"/></p>\n<p>In <a href=\"https://flowiseai.com/\">FlowiseAI</a>, applications based on the JavaScript fork of LangChain are modeled in a 'no/low-code' environment. If you are coming from a closed source world, yet trying to implement devops principles this may fill you with fear, dread and uncertainty. FlowiseAI offers the advantage of using plain-text JSON files to represent each workflow. These files are easy to understand, open, and readily backup-able, unlike opaque proprietary binary formats\nThe data used at runtime and other component prerequisites like credentials are stored in the FlowiseAI data volume, which looks like this</p>\n<p><code>bash\nMode                 LastWriteTime      .....    8ZS1C0ZBB.webp",
                "created_at": "2024-12-17 11:24:59",
                "updated_at": "2024-12-17 12:53:54",
                "category_id": 1,
                "blog_date": "2024-02-26 00:00",
                "is_featured": 0,
                "published": 1
            },

        */

        $filePath = '/home/user/projects/laravel/12/media_library/boring-astro-static/imported_database/blogs.json';

        if (!file_exists($filePath)) {
            $this->error("File not found: $filePath");
            return 1;
        }

        $jsonContent = file_get_contents($filePath);
        $blogs = json_decode($jsonContent, true);

        if (!$blogs) {
            $this->error("Could not parse JSON file: $filePath");
            return 1;
        }

        foreach ($blogs as $blog) {
            // Only process the blog with ID 51
            if (($blog['id'] ?? null) !== 51) {
                continue;
            }

            $slug = $blog['slug'] ?? null;
            $this->info("Processing blog ID: {$blog['id']} with slug: {$slug}");
            // Check if the entry already exists
            $existingEntry = Entry::where('slug', $slug)->first();

            if ($existingEntry) {
                // Update existing entry with cleaned content
                $existingEntry->update([
                    'content' => $this->cleanHtmlForFilament($blog['content'] ?? ''),
                    'description' => $this->extractPlainTextFromHtml($blog['content'] ?? ''),
                ]);
                $this->info("Updated content for: {$existingEntry->title}");
            } else {
                // Create new entry
                Entry::create([
                    'title' => $blog['title'] ?? null,
                    'slug' => $slug,
                    'description' => $this->extractPlainTextFromHtml($blog['content'] ?? ''),
                    'is_published' => $blog['published'] ?? false,
                    'is_featured' => $blog['is_featured'] ?? false,
                    'published_at' => $blog['blog_date'] ?? null,
                    'content' => $this->cleanHtmlForFilament($blog['content'] ?? ''),
                    'category_id' => 1, // Default category
                ]);
                $this->info("Created new entry: " . ($blog['title'] ?? 'Untitled'));
            }
        }

        $this->info('Blogs imported successfully.');
    }

    /**
     * Extract plain text from HTML for description field
     */
    private function extractPlainTextFromHtml(string $html): string
    {
        if (empty($html)) {
            return '';
        }

        // Decode HTML entities and strip tags
        $text = html_entity_decode(strip_tags($html));

        // Clean up whitespace
        $text = preg_replace('/\s+/', ' ', $text);

        // Limit to reasonable length for description
        return trim(substr($text, 0, 500));
    }

    /**
     * Clean HTML content for Filament rich editor
     */
    private function cleanHtmlForFilament(string $html): string
    {
        if (empty($html)) {
            return '';
        }

        // Convert escaped newlines to actual newlines
        $html = str_replace(['\\n', '\\r\\n', '\\r'], "\n", $html);

        // Decode HTML entities
        $html = html_entity_decode($html, ENT_QUOTES | ENT_HTML5, 'UTF-8');

        // Clean up excessive whitespace but preserve paragraph structure
        $html = preg_replace('/\s*\n\s*/', ' ', $html);
        $html = preg_replace('/[ \t]+/', ' ', $html);

        // Ensure paragraphs have proper spacing
        $html = str_replace('</p><p>', '</p>' . "\n" . '<p>', $html);

        return trim($html);
    }
}