# List semua posts dan pages
# Gunakan plugin: Export to Markdown atau manual export

# Check:
- Total posts
- Total pages
- Custom post types
- Categories dan tags
- Media files
- Comments
- Users

WordPress URL: /2024/02/03/hello-world/
Hugo URL:     /blog/hello-world/

Decision:
- Keep same: /:year/:month/:day/:slug/
- New structure: /:slug/
- Redirect old URLs ke new

# Install WP-CLI jika belum
curl -O https://raw.githubusercontent.com/wp-cli/builds/gh-pages/phar/wp-cli.phar
chmod +x wp-cli.phar
sudo mv wp-cli.phar /usr/local/bin/wp

# Export posts ke Markdown
wp post list --format=ids | xargs -I {} wp post get {} --field=content --format=json > posts.json

# Atau gunakan plugin untuk bulk export

-- Export posts
SELECT post_title, post_content, post_date, post_name 
FROM wp_posts 
WHERE post_type = 'post' AND post_status = 'publish';

# Install Hugo jika belum
# (lihat artikel install Hugo)

# Buat site baru
hugo new site my-wordpress-migration
cd my-wordpress-migration

# Initialize Git
git init

# Install theme
# Pilih theme yang mirip dengan WordPress theme Anda
git submodule add https://github.com/theNewDynamic/gohugo-theme-ananke.git themes/ananke

baseURL = 'https://yourdomain.com'
languageCode = 'en-us'
title = 'Your Site Title'
theme = 'ananke'

# Match WordPress permalink structure
[permalinks]
  posts = '/:year/:month/:day/:slug/'

# Preserve WordPress categories dan tags
[taxonomies]
  category = 'categories'
  tag = 'tags'

[params]
  author = 'Your Name'
  description = 'Site description'

# Clone tool
git clone https://github.com/SchumacherFM/wordpress-to-hugo-exporter.git
cd wordpress-to-hugo-exporter

# Install dependencies
composer install

# Export WordPress content
php hugo-export.php

#!/usr/bin/env python3
import re
import os
from datetime import datetime

def convert_wordpress_to_hugo(wp_file, output_dir):
    with open(wp_file, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # Extract title
    title_match = re.search(r'title: (.*)', content)
    title = title_match.group(1) if title_match else 'Untitled'
    
    # Extract date
    date_match = re.search(r'date: (\d{4}-\d{2}-\d{2})', content)
    date_str = date_match.group(1) if date_match else datetime.now().strftime('%Y-%m-%d')
    
    # Create frontmatter
    frontmatter = f"""---
title: "{title}"
date: {date_str}T00:00:00+00:00
draft: false
---

"""
    
    # Clean WordPress content
    body = re.sub(r'---.*?---', '', content, flags=re.DOTALL)
    body = clean_wordpress_content(body)
    
    # Write to file
    slug = re.sub(r'[^\w\s-]', '', title).strip().lower()
    slug = re.sub(r'[-\s]+', '-', slug)
    
    output_file = os.path.join(output_dir, f"{date_str}-{slug}.md")
    with open(output_file, 'w', encoding='utf-8') as f:
        f.write(frontmatter + body)
    
    print(f"Created: {output_file}")

def clean_wordpress_content(content):
    # Remove WordPress-specific tags
    content = re.sub(r'\[.*?\]', '', content)  # Shortcodes
    content = re.sub(r'<!--.*?-->', '', content, flags=re.DOTALL)  # Comments
    
    # Convert HTML ke Markdown jika perlu
    # atau keep HTML yang valid
    
    return content.strip()

# Usage
convert_wordpress_to_hugo('wordpress-post.txt', 'content/posts/')

# Copy converted files
cp -r wordpress-export/content/* my-hugo-site/content/

# Organize structure
mkdir -p content/posts content/pages
mv content/20* content/posts/  # Move dated posts
mv content/page-* content/pages/  # Move pages

#!/bin/bash
# fix-frontmatter.sh

for file in content/posts/*.md; do
  # Add description jika tidak ada
  if ! grep -q "^description:" "$file"; then
    sed -i 's/^---$/---\ndescription: ""/g' "$file"
  fi
  
  # Add categories jika tidak ada
  if ! grep -q "^categories:" "$file"; then
    sed -i 's/^---$/---\ncategories: []/g' "$file"
  fi
done

# Download all media files
# Option 1: Gunakan plugin "Export Media Library"

# Option 2: Manual download
wget --mirror --convert-links --adjust-extension \
     --page-requisites --no-parent \
     https://yourwordpresssite.com/wp-content/uploads/

# Move ke Hugo static folder
mkdir -p static/images/wp-content
mv wordpress-uploads/* static/images/wp-content/

# Optimize images (opsional)
# Gunakan Hugo image processing atau tools seperti ImageMagick

#!/usr/bin/env python3
import re
import os

def update_image_urls(directory):
    for root, dirs, files in os.walk(directory):
        for file in files:
            if file.endswith('.md'):
                filepath = os.path.join(root, file)
                
                with open(filepath, 'r', encoding='utf-8') as f:
                    content = f.read()
                
                # Replace WordPress URLs dengan Hugo URLs
                content = re.sub(
                    r'https?://[^\s\"]+/wp-content/uploads/(\d{4})/(\d{2})/([^\s\"]+)',
                    r'/images/wp-content/\1/\2/\3',
                    content
                )
                
                with open(filepath, 'w', encoding='utf-8') as f:
                    f.write(content)
                
                print(f"Updated: {filepath}")

update_image_urls('content/')

# Redirect old WordPress URLs ke Hugo URLs
/blog/:year/:month/:day/:slug/  /posts/:slug/  301
/category/:name/                 /categories/:name/  301
/tag/:name/                     /tags/:name/  301
/author/:name/                  /authors/:name/  301
/feed/                          /index.xml  301
/wp-content/uploads/*           /images/wp-content/:splat  301

RewriteEngine On

# Redirect WordPress posts
RewriteRule ^([0-9]{4})/([0-9]{2})/([0-9]{2})/([^/]+)/?$ /posts/$4/ [R=301,L]

# Redirect categories
RewriteRule ^category/([^/]+)/?$ /categories/$1/ [R=301,L]

# Redirect tags
RewriteRule ^tag/([^/]+)/?$ /tags/$1/ [R=301,L]

#!/usr/bin/env python3
import re

def generate_redirects(wp_export_file):
    redirects = []
    
    # Read WordPress export
    with open(wp_export_file, 'r') as f:
        content = f.read()
    
    # Extract post URLs
    post_urls = re.findall(r'https?://[^\s\"]+/\d{4}/\d{2}/\d{2}/([^/\s\"]+)', content)
    
    for slug in post_urls:
        old_url = f"/20*/20*/20*/{slug}/"
        new_url = f"/posts/{slug}/"
        redirects.append(f"{old_url} {new_url} 301")
    
    # Write to file
    with open('static/_redirects', 'w') as f:
        f.write('\n'.join(redirects))
    
    print(f"Generated {len(redirects)} redirects")

generate_redirects('wordpress-export.xml')

# Export comments dari WordPress
# Gunakan plugin "Export Comments to JSON"

# Convert ke static HTML atau YAML

<!-- layouts/partials/comments.html -->
{{ if .Site.Params.disqus }}
<div id="disqus_thread"></div>
<script>
  var disqus_config = function () {
    this.page.url = "{{ .Permalink }}";
    this.page.identifier = "{{ .RelPermalink }}";
  };
  (function() {
    var d = document, s = d.createElement('script');
    s.src = 'https://{{ .Site.Params.disqus }}.disqus.com/embed.js';
    s.setAttribute('data-timestamp', +new Date());
    (d.head || d.body).appendChild(s);
  })();
</script>
{{ end }}

<script src="https://utteranc.es/client.js"
        repo="username/repo"
        issue-term="pathname"
        theme="github-light"
        crossorigin="anonymous"
        async>
</script>

# Development mode
hugo server -D

# Production build
hugo --gc --minify

# Content tests
- [ ] Semua posts muncul
- [ ] Semua pages muncul
- [ ] Categories dan tags work
- [ ] Images load correctly
- [ ] Internal links work

# Functionality tests
- [ ] Search works
- [ ] Navigation works
- [ ] Pagination works
- [ ] RSS feed valid
- [ ] Sitemap valid

# SEO tests
- [ ] Meta titles correct
- [ ] Meta descriptions present
- [ ] Open Graph tags work
- [ ] Twitter Cards work
- [ ] Canonical URLs correct
- [ ] Redirects work

# Performance tests
- [ ] Lighthouse score > 90
- [ ] Page size < 1MB
- [ ] Loading time < 3s

# WordPress metrics (before)
Page size: 2.5MB
Load time: 4.2s
Lighthouse: 65/100

# Hugo metrics (after)
Page size: 0.4MB
Load time: 0.8s
Lighthouse: 95/100

# .github/workflows/deploy.yml
name: Deploy Hugo
on:
  push:
    branches: [main]
jobs:
  deploy:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - uses: peaceiris/actions-hugo@v2
        with:
          hugo-version: 'latest'
          extended: true
      - run: hugo --gc --minify
      - uses: peaceiris/actions-gh-pages@v3
        with:
          github_token: ${{ secrets.GITHUB_TOKEN }}
          publish_dir: ./public

# Check DNS
dig yourdomain.com
nslookup yourdomain.com

# Test dari berbagai lokasi
# Gunakan tools: whatsmydns.net

# Submit sitemap baru ke Google Search Console
# Check for crawl errors
# Monitor 404 errors
# Update robots.txt jika perlu

# Check analytics untuk drop traffic
# Monitor 404 errors di console
# Fix broken links

# Backup WordPress files
# Export database untuk archive
# Cancel WordPress hosting
# Update bookmarks/documentation

# Check image paths
grep -r "wp-content/uploads" content/

# Fix dengan sed
sed -i 's|/wp-content/uploads/|/images/wp-content/|g' content/**/*.md

# Find broken links
grep -r "http://olddomain.com" content/

# Replace dengan new domain
sed -i 's|http://olddomain.com|https://newdomain.com|g' content/**/*.md