Ebook Extractor

ebooklib
beautifulsoup4
PyMuPDF

#!/usr/bin/env python3
"""Extract text from EPUB files."""

import sys
from pathlib import Path

try:
    import ebooklib
    from ebooklib import epub
    from bs4 import BeautifulSoup
except ImportError as e:
    print(f"Missing dependency: {e}", file=sys.stderr)
    print("Install with: pip install ebooklib beautifulsoup4", file=sys.stderr)
    sys.exit(1)


def extract_text_from_epub(epub_path: str) -> str:
    """Extract all text content from an EPUB file."""
    book = epub.read_epub(epub_path)

    text_parts = []

    for item in book.get_items():
        if item.get_type() == ebooklib.ITEM_DOCUMENT:
            content = item.get_content().decode('utf-8', errors='ignore')
            soup = BeautifulSoup(content, 'html.parser')

            # Remove script and style elements
            for element in soup(['script', 'style', 'nav']):
                element.decompose()

            # Get text with reasonable whitespace handling
            text = soup.get_text(separator='\n', strip=True)

            if text.strip():
                text_parts.append(text)

    return '\n\n'.join(text_parts)


def main():
    if len(sys.argv) < 2:
        print("Usage: extract_epub.py <epub_file> [-o output_file]", file=sys.stderr)
        sys.exit(1)

    epub_path = sys.argv[1]
    output_path = None

    if '-o' in sys.argv:
        idx = sys.argv.index('-o')
        if idx + 1 < len(sys.argv):
            output_path = sys.argv[idx + 1]

    if not Path(epub_path).exists():
        print(f"File not found: {epub_path}", file=sys.stderr)
        sys.exit(1)

    text = extract_text_from_epub(epub_path)

    if output_path:
        Path(output_path).write_text(text, encoding='utf-8')
        print(f"Extracted to: {output_path}", file=sys.stderr)
    else:
        print(text)


if __name__ == '__main__':
    main()

#!/usr/bin/env python3
"""Extract text from MOBI files using Calibre conversion."""

import subprocess
import sys
import tempfile
from pathlib import Path

# Import the EPUB extractor
script_dir = Path(__file__).parent
sys.path.insert(0, str(script_dir))
from extract_epub import extract_text_from_epub


def check_calibre():
    """Check if Calibre's ebook-convert is available."""
    try:
        subprocess.run(
            ['ebook-convert', '--version'],
            capture_output=True,
            check=True
        )
        return True
    except (subprocess.CalledProcessError, FileNotFoundError):
        return False


def extract_text_from_mobi(mobi_path: str) -> str:
    """Extract text from MOBI by converting to EPUB first."""
    if not check_calibre():
        print("Error: Calibre not found. Install with: brew install calibre", file=sys.stderr)
        sys.exit(1)

    # Convert MOBI to temporary EPUB
    with tempfile.NamedTemporaryFile(suffix='.epub', delete=False) as tmp:
        tmp_epub = tmp.name

    try:
        result = subprocess.run(
            ['ebook-convert', mobi_path, tmp_epub],
            capture_output=True,
            text=True
        )

        if result.returncode != 0:
            print(f"Conversion failed: {result.stderr}", file=sys.stderr)
            sys.exit(1)

        # Extract text from the converted EPUB
        return extract_text_from_epub(tmp_epub)

    finally:
        # Clean up temp file
        Path(tmp_epub).unlink(missing_ok=True)


def main():
    if len(sys.argv) < 2:
        print("Usage: extract_mobi.py <mobi_file> [-o output_file]", file=sys.stderr)
        sys.exit(1)

    mobi_path = sys.argv[1]
    output_path = None

    if '-o' in sys.argv:
        idx = sys.argv.index('-o')
        if idx + 1 < len(sys.argv):
            output_path = sys.argv[idx + 1]

    if not Path(mobi_path).exists():
        print(f"File not found: {mobi_path}", file=sys.stderr)
        sys.exit(1)

    text = extract_text_from_mobi(mobi_path)

    if output_path:
        Path(output_path).write_text(text, encoding='utf-8')
        print(f"Extracted to: {output_path}", file=sys.stderr)
    else:
        print(text)


if __name__ == '__main__':
    main()

#!/usr/bin/env python3
"""Extract text from PDF files using PyMuPDF."""

import sys
from pathlib import Path

try:
    import fitz  # PyMuPDF
except ImportError:
    print("Missing dependency: PyMuPDF", file=sys.stderr)
    print("Install with: pip install PyMuPDF", file=sys.stderr)
    sys.exit(1)


def extract_text_from_pdf(pdf_path: str) -> str:
    """Extract all text content from a PDF file."""
    doc = fitz.open(pdf_path)

    text_parts = []

    for page_num in range(len(doc)):
        page = doc[page_num]
        text = page.get_text()

        if text.strip():
            text_parts.append(text)

    doc.close()

    return '\n\n'.join(text_parts)


def main():
    if len(sys.argv) < 2:
        print("Usage: extract_pdf.py <pdf_file> [-o output_file]", file=sys.stderr)
        sys.exit(1)

    pdf_path = sys.argv[1]
    output_path = None

    if '-o' in sys.argv:
        idx = sys.argv.index('-o')
        if idx + 1 < len(sys.argv):
            output_path = sys.argv[idx + 1]

    if not Path(pdf_path).exists():
        print(f"File not found: {pdf_path}", file=sys.stderr)
        sys.exit(1)

    text = extract_text_from_pdf(pdf_path)

    if output_path:
        Path(output_path).write_text(text, encoding='utf-8')
        print(f"Extracted to: {output_path}", file=sys.stderr)
    else:
        print(text)


if __name__ == '__main__':
    main()

#!/usr/bin/env python3
"""
Unified ebook text extractor.
Auto-detects format and extracts text from EPUB, MOBI, and PDF files.
"""

import sys
from pathlib import Path

# Add script directory to path for imports
script_dir = Path(__file__).parent
sys.path.insert(0, str(script_dir))


def detect_format(file_path: str) -> str:
    """Detect ebook format from file extension."""
    ext = Path(file_path).suffix.lower()

    format_map = {
        '.epub': 'epub',
        '.mobi': 'mobi',
        '.azw': 'mobi',
        '.azw3': 'mobi',
        '.pdf': 'pdf',
    }

    return format_map.get(ext, 'unknown')


def extract_text(file_path: str) -> str:
    """Extract text from any supported ebook format."""
    fmt = detect_format(file_path)

    if fmt == 'epub':
        from extract_epub import extract_text_from_epub
        return extract_text_from_epub(file_path)

    elif fmt == 'mobi':
        from extract_mobi import extract_text_from_mobi
        return extract_text_from_mobi(file_path)

    elif fmt == 'pdf':
        from extract_pdf import extract_text_from_pdf
        return extract_text_from_pdf(file_path)

    else:
        print(f"Unsupported format: {Path(file_path).suffix}", file=sys.stderr)
        print("Supported formats: .epub, .mobi, .azw, .azw3, .pdf", file=sys.stderr)
        sys.exit(1)


def main():
    if len(sys.argv) < 2:
        print("Usage: extract.py <ebook_file> [-o output_file]", file=sys.stderr)
        print("", file=sys.stderr)
        print("Supported formats: EPUB, MOBI, AZW, AZW3, PDF", file=sys.stderr)
        sys.exit(1)

    file_path = sys.argv[1]
    output_path = None

    if '-o' in sys.argv:
        idx = sys.argv.index('-o')
        if idx + 1 < len(sys.argv):
            output_path = sys.argv[idx + 1]

    if not Path(file_path).exists():
        print(f"File not found: {file_path}", file=sys.stderr)
        sys.exit(1)

    fmt = detect_format(file_path)
    print(f"Detected format: {fmt.upper()}", file=sys.stderr)

    text = extract_text(file_path)

    if output_path:
        Path(output_path).write_text(text, encoding='utf-8')
        print(f"Extracted to: {output_path}", file=sys.stderr)
    else:
        print(text)


if __name__ == '__main__':
    main()

#!/bin/bash
# Setup script for ebook-extractor skill

set -e

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"

echo "=== Ebook Extractor Setup ==="
echo

# Check Python
if ! command -v python3 &> /dev/null; then
    echo "ERROR: Python 3 not found. Please install Python 3 first."
    exit 1
fi
echo "✓ Python 3 found: $(python3 --version)"

# Install Python packages
echo
echo "Installing Python packages..."
pip3 install -q -r "$SCRIPT_DIR/requirements.txt"
echo "✓ Python packages installed"

# Check for Calibre (optional, for MOBI support)
echo
if command -v ebook-convert &> /dev/null; then
    echo "✓ Calibre found (MOBI support enabled)"
else
    echo "⚠ Calibre not found (MOBI support disabled)"
    echo "  To enable MOBI support, install Calibre:"
    echo "    macOS:  brew install calibre"
    echo "    Linux:  sudo apt install calibre"
fi

echo
echo "=== Setup complete ==="
echo
echo "Usage:"
echo "  python3 $SCRIPT_DIR/scripts/extract.py <ebook_file>"