story_downloader/example_usage.py

"""
Project Gutenberg Downloader - Example Usage

This script demonstrates how to use the GutenbergDownloader to download
and process free e-books from Project Gutenberg.

Project Gutenberg URLs:
- https://www.gutenberg.org/ebooks/11 - Alice's Adventures in Wonderland
- https://www.gutenberg.org/ebooks/1342 - Pride and Prejudice
- https://www.gutenberg.org/ebooks/98 - A Tale of Two Cities
- https://www.gutenberg.org/ebooks/219 - Heart of Darkness
- https://www.gutenberg.org/ebooks/514 - Little Women
- https://www.gutenberg.org/ebooks/4300 - Ulysses
- https://www.gutenberg.org/ebooks/1661 - Sherlock Holmes - A Study in Scarlet
"""

import json
from pathlib import Path
from gutenberg_downloader import GutenbergDownloader


def example_1_single_book():
    """Example 1: Download and process a single book."""
    print("\n" + "=" * 70)
    print("Example 1: Download and Process a Single Book")
    print("=" * 70)

    downloader = GutenbergDownloader(cache_dir="./gutenberg_cache")

    # Download Alice in Wonderland
    book_url = "https://www.gutenberg.org/ebooks/11"
    print(f"\nDownloading from: {book_url}")

    content = downloader.download_book(book_url, format_type="text")

    if content:
        print(f"Downloaded {len(content)} characters")

        # Parse the book
        book_data = downloader.parse_text_book(content)

        print(f"\nBook Title: {book_data['title']}")
        print(f"Chapters found: {len(book_data['chapters'])}")
        print(f"Main text length: {len(book_data['main_text'])} characters")

        # Display first chapter
        if book_data['chapters']:
            print(f"\nFirst chapter: {book_data['chapters'][0]}")

        # Display first 500 characters of main text
        print(f"\nFirst 500 characters of main text:")
        print(book_data['main_text'][:500])

        # Save to file
        output_file = Path("./processed_books/alice.json")
        output_file.parent.mkdir(parents=True, exist_ok=True)
        with open(output_file, 'w', encoding='utf-8') as f:
            json.dump(book_data, f, indent=2, ensure_ascii=False)
        print(f"\nSaved to: {output_file}")
    else:
        print("Failed to download book")


def example_2_multiple_books():
    """Example 2: Download and process multiple books."""
    print("\n" + "=" * 70)
    print("Example 2: Batch Download Multiple Books")
    print("=" * 70)

    downloader = GutenbergDownloader(cache_dir="./gutenberg_cache")

    # List of books to download
    books = [
        ("https://www.gutenberg.org/ebooks/11", "Alice in Wonderland"),
        ("https://www.gutenberg.org/ebooks/1342", "Pride and Prejudice"),
        ("https://www.gutenberg.org/ebooks/98", "A Tale of Two Cities"),
    ]

    results = downloader.process_books(
        [book_url for book_url, _ in books],
        format_type="text",
        output_dir="./processed_books"
    )

    print(f"\nProcessed {len(results)} books:\n")
    for i, result in enumerate(results, 1):
        if result['status'] == 'success':
            print(f"{i}. {result['title']}")
            print(f"   File: {result['file']}")

            # Load and display stats
            with open(result['file'], 'r', encoding='utf-8') as f:
                data = json.load(f)
                print(f"   Chapters: {len(data['chapters'])}")
                print(f"   Text length: {len(data['main_text'])} characters")
        else:
            print(f"{i}. FAILED: {result['url']}")
        print()


def example_3_process_and_extract():
    """Example 3: Process a book and extract specific information."""
    print("\n" + "=" * 70)
    print("Example 3: Process and Extract Specific Information")
    print("=" * 70)

    downloader = GutenbergDownloader(cache_dir="./gutenberg_cache")

    # Download Pride and Prejudice
    book_url = "https://www.gutenberg.org/ebooks/1342"
    print(f"\nDownloading: {book_url}")

    content = downloader.download_book(book_url, format_type="text")

    if content:
        book_data = downloader.parse_text_book(content)

        print(f"\nTitle: {book_data['title']}")
        print(f"Format: {book_data['format']}")
        print(f"Source: {book_data['source']}")

        # Extract and display chapters
        print(f"\n--- Chapter Titles ({len(book_data['chapters'])} found) ---")
        for i, chapter in enumerate(book_data['chapters'][:10], 1):
            print(f"{i}. {chapter[:60]}")  # Truncate for display

        # Extract and display statistics
        print(f"\n--- Content Statistics ---")
        print(f"Total characters: {len(book_data['main_text']):,}")
        print(f"Total words (approx): {len(book_data['main_text'].split()):,}")
        print(f"Average chapter length: {len(book_data['main_text']) / len(book_data['chapters']):.0f} characters")

        # Display text sample
        print(f"\n--- Text Sample (first 800 characters) ---")
        print(book_data['main_text'][:800])
        print("...")


def example_4_save_as_text():
    """Example 4: Save extracted book as plain text file."""
    print("\n" + "=" * 70)
    print("Example 4: Save Book as Plain Text File")
    print("=" * 70)

    downloader = GutenbergDownloader(cache_dir="./gutenberg_cache")

    # Download Little Women
    book_url = "https://www.gutenberg.org/ebooks/514"
    print(f"\nDownloading: {book_url}")

    content = downloader.download_book(book_url, format_type="text")

    if content:
        book_data = downloader.parse_text_book(content)

        # Create output file
        output_file = Path("./processed_books/little_women.txt")
        output_file.parent.mkdir(parents=True, exist_ok=True)

        with open(output_file, 'w', encoding='utf-8') as f:
            # Write title
            f.write(f"{'='*70}\n")
            f.write(f"{book_data['title']}\n")
            f.write(f"{'='*70}\n\n")

            # Write chapter list
            if book_data['chapters']:
                f.write("CHAPTERS:\n")
                for chapter in book_data['chapters']:
                    f.write(f"  - {chapter}\n")
                f.write("\n" + "="*70 + "\n\n")

            # Write main text
            f.write(book_data['main_text'])

        print(f"Saved to: {output_file}")
        print(f"File size: {output_file.stat().st_size:,} bytes")


def example_5_extract_first_chapter():
    """Example 5: Extract and save only the first chapter."""
    print("\n" + "=" * 70)
    print("Example 5: Extract and Save First Chapter")
    print("=" * 70)

    downloader = GutenbergDownloader(cache_dir="./gutenberg_cache")

    # Download A Tale of Two Cities
    book_url = "https://www.gutenberg.org/ebooks/98"
    print(f"\nDownloading: {book_url}")

    content = downloader.download_book(book_url, format_type="text")

    if content:
        book_data = downloader.parse_text_book(content)

        print(f"\nTitle: {book_data['title']}")
        print(f"Chapters: {len(book_data['chapters'])}")

        # Find first chapter marker in text
        if book_data['chapters']:
            first_chapter = book_data['chapters'][0]
            print(f"\nFirst chapter: {first_chapter}")

            # Save first chapter metadata
            chapter_data = {
                'book_title': book_data['title'],
                'chapter_title': first_chapter,
                'chapter_number': 1,
                'text_preview': book_data['main_text'][:1000]
            }

            output_file = Path("./processed_books/chapter_extract.json")
            output_file.parent.mkdir(parents=True, exist_ok=True)
            with open(output_file, 'w', encoding='utf-8') as f:
                json.dump(chapter_data, f, indent=2, ensure_ascii=False)

            print(f"\nSaved chapter data to: {output_file}")


def example_6_api_usage():
    """Example 6: Using the downloader as a Python API."""
    print("\n" + "=" * 70)
    print("Example 6: Python API Usage")
    print("=" * 70)

    # Initialize downloader
    downloader = GutenbergDownloader(cache_dir="./gutenberg_cache")

    # Download a book
    print("\nDownloading book...")
    content = downloader.download_book(
        "https://www.gutenberg.org/ebooks/11",
        format_type="text"
    )

    # Parse the book
    print("Parsing book...")
    book_data = downloader.parse_text_book(content)

    # Access data programmatically
    print(f"\nBook Title: {book_data['title']}")
    print(f"Format: {book_data['format']}")
    print(f"Source: {book_data['source']}")
    print(f"Chapters: {len(book_data['chapters'])}")

    # Use the data in your application
    book_json = json.dumps(book_data, ensure_ascii=False)
    print(f"\nJSON representation size: {len(book_json):,} bytes")


def main():
    """Run all examples."""
    print("\n")
    print("#" * 70)
    print("# Project Gutenberg Downloader - Usage Examples")
    print("#" * 70)

    # Run examples
    try:
        example_1_single_book()
    except Exception as e:
        print(f"Example 1 error: {e}")

    try:
        example_2_multiple_books()
    except Exception as e:
        print(f"Example 2 error: {e}")

    try:
        example_3_process_and_extract()
    except Exception as e:
        print(f"Example 3 error: {e}")

    try:
        example_4_save_as_text()
    except Exception as e:
        print(f"Example 4 error: {e}")

    try:
        example_5_extract_first_chapter()
    except Exception as e:
        print(f"Example 5 error: {e}")

    try:
        example_6_api_usage()
    except Exception as e:
        print(f"Example 6 error: {e}")

    print("\n" + "=" * 70)
    print("All examples completed!")
    print("=" * 70 + "\n")


if __name__ == "__main__":
    main()