%pip install -q docling

import urllib.request
from pathlib import Path

# Create directory for EPUB data
data_dir = Path("epub_data")
data_dir.mkdir(exist_ok=True)

# Download sample EPUB file from Standard Ebooks
# Note: We use the Docling test data mirror for reliable downloads in notebooks
# Original source: https://standardebooks.org/ebooks/sarah-louisa-forten-purvis/poetry
epub_file = data_dir / "sarah-louisa-forten-purvis_poetry.epub"
if not epub_file.exists():
    print("Downloading sample EPUB file...")
    print("Source: 'Poetry' by Sarah Louisa Forten Purvis from Standard Ebooks")
    # Using Docling test data for reliable notebook execution
    epub_url = "https://raw.githubusercontent.com/docling-project/docling/main/tests/data/epub/epub_purvis_poetry.epub"
    urllib.request.urlretrieve(epub_url, epub_file)
    print(f"Downloaded: {epub_file}")
    print(f"File size: {epub_file.stat().st_size / 1024:.1f} KB")
else:
    print(f"Using existing file: {epub_file}")
    print(f"File size: {epub_file.stat().st_size / 1024:.1f} KB")

from docling.document_converter import DocumentConverter

# Create converter instance
converter = DocumentConverter()

# Convert the EPUB file
print(f"Converting EPUB document: {epub_file}")
result = converter.convert(epub_file)
doc = result.document

print("\nConversion successful!")
print(f"Document name: {doc.name}")
print(f"Number of items: {len(list(doc.iterate_items()))}")

from docling_core.types.doc import DocItemLabel

# Count items by type
item_counts = {}
for item, _ in doc.iterate_items():
    label = item.label
    item_counts[label] = item_counts.get(label, 0) + 1

print("Document structure:")
for label, count in sorted(item_counts.items(), key=lambda x: x[1], reverse=True):
    print(f"  {label.value}: {count}")

# Display first few text items
print("Sample text content:\n")
text_count = 0
for item, _ in doc.iterate_items():
    if item.label == DocItemLabel.TEXT and text_count < 5:
        print(f"- {item.text[:150]}..." if len(item.text) > 150 else f"- {item.text}")
        print()
        text_count += 1

# Export to Markdown without images
markdown_content = doc.export_to_markdown()

# Display first 1500 characters
print("Markdown export (first 1500 characters):\n")
print(markdown_content[:1500])
print("\n...")

# Save to file using save_as_markdown (faster than write_text)
output_md = data_dir / "output_basic.md"
doc.save_as_markdown(output_md)
print(f"\nFull markdown saved to: {output_md}")

from docling.datamodel.backend_options import EpubBackendOptions
from docling.document_converter import DocumentConverter, EpubFormatOption

# Configure EPUB options to extract images
epub_options = EpubBackendOptions(
    fetch_images=True,  # Extract images from EPUB archive
    enable_local_fetch=True,  # Allow reading local image files
    enable_remote_fetch=False,  # Disable fetching remote images
)

# Create converter with EPUB options
converter_with_images = DocumentConverter(
    format_options={"epub": EpubFormatOption(backend_options=epub_options)}
)

# Convert the EPUB with image extraction
print("Converting EPUB with image extraction...")
result_with_images = converter_with_images.convert(epub_file)
doc_with_images = result_with_images.document

print("\nConversion with images successful!")
print(f"Number of items: {len(list(doc_with_images.iterate_items()))}")

# Export with embedded images (base64-encoded)
markdown_with_images = doc_with_images.export_to_markdown(image_mode="embedded")

# Display first 1500 characters
print("Markdown with embedded images (first 1500 characters):\n")
print(markdown_with_images[:1500])
print("\n...")

# Save to file using save_as_markdown
output_md_images = data_dir / "output_with_images.md"
doc_with_images.save_as_markdown(output_md_images, image_mode="embedded")
print(f"\nMarkdown with embedded images saved to: {output_md_images}")

# Check for pictures in the document
from docling_core.types.doc import PictureItem

pictures = [
    item for item, _ in doc_with_images.iterate_items() if isinstance(item, PictureItem)
]

if pictures:
    print(f"Found {len(pictures)} image(s) in the EPUB:")
    for i, pic in enumerate(pictures[:5], 1):  # Show first 5
        print(f"  {i}. Image at position {pic.self_ref}")
        if hasattr(pic, "image") and pic.image:
            print(
                f"     Size: {pic.image.size if hasattr(pic.image, 'size') else 'unknown'}"
            )
else:
    print("No images found in this EPUB.")
    print("Note: This particular EPUB (poetry collection) may not contain images.")

import json

# Export to JSON
output_json = data_dir / "output.json"
doc_with_images.save_as_json(output_json)

print(f"Document exported to JSON: {output_json}")
print(f"File size: {output_json.stat().st_size / 1024:.2f} KB")

# Display a sample of the JSON structure
with open(output_json) as f:
    json_data = json.load(f)
    print("\nJSON structure (top-level keys):")
    for key in json_data.keys():
        print(f"  - {key}")

from pathlib import Path
from docling.document_converter import DocumentConverter

converter = DocumentConverter()

# Convert all EPUB files in a directory
epub_dir = Path("path/to/epub/directory")
for epub_file in epub_dir.glob("*.epub"):
    print(f"Converting {epub_file.name}...")
    result = converter.convert(str(epub_file))

    # Save to markdown with embedded images
    output_path = epub_file.with_suffix(".md")
    result.document.save_as_markdown(output_path, image_mode="embedded")
    print(f"Saved to {output_path}")

docling --to md --from epub path/to/epub/directory

<!-- In the text -->
...five versts [1](#note-1) from Durnovka...

<!-- At the end (footnote section) -->
1. A verst is two-thirds of a mile. [↩︎](#noteref-1)