================================================================================
PRACTICAL PYTHON SCRIPTING - CHALLENGE 1 SOLUTION
Chapter 6: Building Your Own Utilities
Challenge: Create a Blog Post Importer
================================================================================

PROBLEM:
Build a utility that:
1. Finds all blog-*.md files
2. Parses title and date from front matter
3. Inserts into database
4. Reports count

SOLUTION:
================================================================================

import sys
from pathlib import Path
import re
from datetime import datetime

# Import database utilities
sys.path.insert(0, str(Path(__file__).parent))
from db_utils import DatabaseConnection, get_or_create_subtopic, insert_chapter_with_content

SCRIPT_DIR = Path(__file__).resolve().parent
POSTS_DIR = SCRIPT_DIR / "blog"

def find_posts():
    """Find all blog-*.md files."""
    if not POSTS_DIR.exists():
        print(f"❌ Blog directory not found: {POSTS_DIR}")
        return []

    md_files = sorted(POSTS_DIR.glob("blog-*.md"))
    if not md_files:
        print(f"⚠️ No blog files found in {POSTS_DIR}")
        return []

    print(f"✅ Found {len(md_files)} blog posts\n")
    return md_files


def parse_front_matter(content):
    """Extract YAML front matter from markdown."""
    # Match YAML front matter between --- delimiters
    match = re.match(r'^---\n(.*?)\n---', content, re.DOTALL)
    if not match:
        return None

    front_matter = match.group(1)
    data = {}

    # Parse YAML-like format
    for line in front_matter.split('\n'):
        if ':' in line:
            key, value = line.split(':', 1)
            data[key.strip()] = value.strip().strip('"\'')

    return data


def parse_post(md_file):
    """Extract post data from markdown file."""
    try:
        content = md_file.read_text(encoding='utf-8')

        # Parse front matter
        front_matter = parse_front_matter(content)
        if not front_matter:
            return None

        # Extract body (after front matter)
        body_match = re.match(r'^---\n.*?\n---(.*)', content, re.DOTALL)
        body = body_match.group(1).strip() if body_match else ""

        return {
            'title': front_matter.get('title', 'Untitled'),
            'date': front_matter.get('date', ''),
            'body': body,
            'filename': md_file.name
        }

    except Exception as e:
        print(f"❌ Error parsing {md_file.name}: {e}")
        return None


def main():
    """Main blog import workflow."""
    print("=" * 60)
    print("🚀 Blog Post Importer")
    print("=" * 60 + "\n")

    # Step 1: Find posts
    print("📚 Step 1: Finding blog posts...")
    md_files = find_posts()
    if not md_files:
        print("❌ No posts found.")
        return False

    # Step 2: Connect to database
    print("📚 Step 2: Connecting to database...")
    db = DatabaseConnection()
    if not db.connect():
        print("❌ Database connection failed")
        return False

    try:
        # Step 3: Create or get blog subtopic
        print(f"\n📚 Step 3: Creating 'Blog' section...\n")
        subtopic_id = get_or_create_subtopic(
            db,
            subject_id=1,  # News/Blog
            subtopic_name="Blog Posts",
            description="Published blog articles"
        )

        if subtopic_id is None:
            print("❌ Failed to create blog section")
            return False

        # Step 4: Import posts
        print(f"\n📚 Step 4: Importing {len(md_files)} posts...\n")

        posts_imported = 0
        for md_file in md_files:
            post = parse_post(md_file)
            if not post:
                continue

            # Insert post
            page_id = insert_chapter_with_content(
                db,
                subtopic_id=subtopic_id,
                chapter_title=post['title'],
                html_content=post['body'],
                sort_order=posts_imported * 10
            )

            if page_id:
                posts_imported += 1
                print(f"✅ Imported: {post['title']}")

        # Step 5: Report results
        print("\n" + "=" * 60)
        print("✅ IMPORT COMPLETE!")
        print("=" * 60)
        print(f"\n📊 Results:")
        print(f"   Posts Imported: {posts_imported}")
        print(f"   Total Found: {len(md_files)}")

        return True

    finally:
        db.disconnect()


if __name__ == "__main__":
    success = main()
    sys.exit(0 if success else 1)

================================================================================

HOW IT WORKS:
================================================================================

1. FIND POSTS
   - Use glob("blog-*.md") to find markdown files
   - Same pattern as chapter discovery in Chapter 5

2. PARSE FRONT MATTER
   - Extract YAML between --- delimiters
   - Parse key: value pairs
   - This is how Jekyll and other blogs store metadata

3. PARSE BODY
   - Extract content after front matter
   - This becomes the page content

4. INSERT INTO DATABASE
   - Reuse db_utils functions
   - Different domain (blog posts), same database patterns

================================================================================

EXAMPLE BLOG FILE:
================================================================================

blog-1.md:

---
title: Getting Started with Python
date: 2026-06-29
author: Philip
---

# Getting Started with Python

Python is an amazing language...

## Section 1

More content here.

================================================================================

KEY PATTERNS APPLIED:
================================================================================

✅ File Discovery (Chapter 1) → glob("blog-*.md")
✅ Configuration (Chapter 2) → Load from .env
✅ Database (Chapter 3) → DatabaseConnection
✅ DB Utilities (Chapter 4) → get_or_create_subtopic()
✅ Automation (Chapter 5) → Complete workflow
✅ Best Practices (Chapter 6) → Error handling, type hints

Same patterns, different domain!

================================================================================