Building rebuild_typescript_course.py

🔄 Building rebuild_typescript_course.py

📋 Overview: What This Script Does

The script automates the complete workflow:

📁 Directory Structure

The script expects this layout:

Copymyapp/
├── .env                          ← Configuration (loaded by script)
├── rebuild_typescript_course.py  ← This script
└── courses/
    └── Programming/
        └── TypeScript/
            └── html/
                ├── ts1-1.html    ← Chapter files
                ├── ts1-2.html
                ├── ts1-3.html
                ...
                └── ts1-12.html

🔧 Main Components

Imports & Constants

Copyfrom pathlib import Path
import sys
import re

from db_utils import DatabaseConnection, get_or_create_subtopic, insert_chapter_with_content

# Constants
SUBJECT_ID = 3  # Programming subject
SUBJECT_NAME = "Programming"
SUBTOPIC_NAME = "TypeScript Fundamentals"

# Calculate path to chapters directory
SCRIPT_DIR = Path(__file__).resolve().parent
CHAPTERS_DIR = SCRIPT_DIR / "courses" / "Programming" / "TypeScript" / "html"

Finding Chapter Files

Copydef find_chapters() -> list:
    """Find all chapter HTML files."""
    if not CHAPTERS_DIR.exists():
        print(f"❌ Chapters directory not found: {CHAPTERS_DIR}")
        return []

    # Find all ts1-*.html files and sort them
    html_files = sorted(CHAPTERS_DIR.glob("ts1-*.html"))

    if not html_files:
        print(f"⚠️ No chapter files found in {CHAPTERS_DIR}")
        return []

    print(f"✅ Found {len(html_files)} chapter files")
    return html_files

Parsing Chapter Data

Copydef parse_chapter(html_file: Path) -> dict:
    """Extract chapter data from HTML file."""
    try:
        # Read HTML content
        html_content = html_file.read_text(encoding='utf-8')

        # Extract chapter number from filename (ts1-1.html → 1)
        match = re.match(r"ts1-(\d+)", html_file.stem)
        if not match:
            return None

        chapter_num = int(match.group(1))

        # Extract title from <h2> tag
        title_match = re.search(r'<h2>(.*?)</h2>', html_content)
        chapter_title = title_match.group(1) if title_match else f"Chapter {chapter_num}"

        return {
            'number': chapter_num,
            'title': chapter_title,
            'html': html_content,
            'sort_order': chapter_num * 10
        }

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

Main Workflow

Copydef main():
    """Main rebuild workflow."""
    print("=" * 60)
    print("🚀 TypeScript Course Rebuild")
    print("=" * 60 + "\n")

    # Step 1: Find chapters
    html_files = find_chapters()
    if not html_files:
        exit(1)

    # Step 2: Connect to database
    print("\n🔌 Connecting to database...")
    db = DatabaseConnection()
    if not db.connect():
        exit(1)

    try:
        # Step 3: Create or get subtopic
        print("\n📚 Creating course...")
        subtopic_id = get_or_create_subtopic(
            db,
            subject_id=SUBJECT_ID,
            subtopic_name=SUBTOPIC_NAME,
            description="Master TypeScript from fundamentals to advanced patterns"
        )

        if subtopic_id is None:
            print("❌ Failed to create subtopic")
            exit(1)

        # Step 4: Insert chapters
        print(f"\n📝 Inserting {len(html_files)} chapters...")

        inserted_count = 0
        for html_file in html_files:
            chapter = parse_chapter(html_file)
            if not chapter:
                continue

            page_id = insert_chapter_with_content(
                db,
                subtopic_id=subtopic_id,
                chapter_title=chapter['title'],
                html_content=chapter['html'],
                sort_order=chapter['sort_order']
            )

            if page_id:
                inserted_count += 1

        # Step 5: Report results
        print("\n" + "=" * 60)
        print(f"✅ REBUILD COMPLETE!")
        print("=" * 60)
        print(f"Course: {SUBTOPIC_NAME}")
        print(f"Chapters inserted: {inserted_count}")

    finally:
        db.disconnect()


if __name__ == "__main__":
    main()

📌 Key Patterns Used

Pattern	From Chapter	Purpose
Path(__file__).parent	Chapter 1	Find script's directory
glob("ts1-*.html")	Chapter 1	Find all chapter files
load_dotenv()	Chapter 2	Load database credentials
DatabaseConnection	Chapter 3	Connect to database
get_or_create_subtopic()	Chapter 4	Create course
insert_chapter_with_content()	Chapter 4	Insert chapters

🚀 Running the Script

Copy# From the myapp directory:
python rebuild_typescript_course.py

# Output:
============================================================
🚀 TypeScript Course Rebuild
============================================================

✅ Found 12 chapter files

🔌 Connecting to database...
✅ Database connection established

📚 Creating course...
✅ Created subtopic 'TypeScript Fundamentals' with ID 8

📝 Inserting 12 chapters...
✅ Created chapter with ID: 101
✅ Created chapter with ID: 102
✅ Created chapter with ID: 103
...

============================================================
✅ REBUILD COMPLETE!
============================================================
Course: TypeScript Fundamentals
Chapters inserted: 12

💻 Coding Challenges

🎯 What's Next

Chapter 6, the final chapter, covers Building Your Own Utilities — how to take the patterns you've learned and create your own reusable scripts for any project. You'll also learn best practices for organizing, documenting, and testing your utilities.