pip install docling

# For page range processing (optional but recommended)
pip install pymupdf

# For Tesseract OCR (optional):
# macOS: brew install tesseract
# Ubuntu: apt-get install tesseract-ocr

# Basic conversion (output to directory)
docling document.pdf --to markdown

# With OCR for scanned documents
docling scanned.pdf --ocr --ocr-engine easyocr --to markdown

# Batch conversion
docling file1.pdf file2.docx --output ./converted

from docling.document_converter import DocumentConverter

converter = DocumentConverter()
result = converter.convert("document.pdf")
print(result.document.export_to_markdown())

# Basic PDF to Markdown with image extraction
python scripts/convert_document.py document.pdf -o ./output

# All formats (Markdown, JSON, HTML) with images
python scripts/convert_document.py document.pdf -o ./output -f all

# With OCR (Japanese + English)
python scripts/convert_document.py scanned.pdf -o ./output --ocr --languages ja en

# High accuracy table extraction
python scripts/convert_document.py document.pdf -o ./output --table-mode accurate

# Process specific page range
python scripts/convert_document.py large.pdf -o ./output --pages 1-20

# Generate batch script for large files (50+ pages)
python scripts/convert_document.py large.pdf -o ./output --generate-script

output/
├── document.md       # Markdown with embedded image links
├── document.json     # Structured JSON data
├── document.html     # HTML output (optional)
└── images/
    ├── figure_001.png   # Diagrams, charts as PNG
    ├── figure_002.png
    ├── photo_001.jpg    # Photos as JPEG
    └── photo_002.jpg

# Process pages 1-20
python scripts/convert_document.py large.pdf -o ./output --pages 1-20

# Then process pages 21-40
python scripts/convert_document.py large.pdf -o ./output2 --pages 21-40

# Generate a batch processing script
python scripts/convert_document.py large.pdf -o ./output --generate-script --batch-size 20

# Run the generated script
python ./output/batch_process.py

from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions, EasyOcrOptions

pipeline = PdfPipelineOptions()
pipeline.do_ocr = True
pipeline.ocr_options = EasyOcrOptions(
    lang=["ja", "en"],  # Languages for OCR
    confidence_threshold=0.5
)

converter = DocumentConverter(
    format_options={InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline)}
)

from docling.datamodel.pipeline_options import TableFormerMode

pipeline.do_table_structure = True
pipeline.table_structure_options.mode = TableFormerMode.ACCURATE  # or FAST
pipeline.table_structure_options.do_cell_matching = True

from pathlib import Path
from docling.document_converter import DocumentConverter
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.datamodel.base_models import InputFormat
from docling.document_converter import PdfFormatOption

# Enable image generation
pipeline = PdfPipelineOptions()
pipeline.generate_picture_images = True

converter = DocumentConverter(
    format_options={InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline)}
)
result = converter.convert("document.pdf")

# Save images
images_dir = Path("./output/images")
images_dir.mkdir(parents=True, exist_ok=True)

for idx, picture in enumerate(result.document.pictures):
    if picture.image and picture.image.pil_image:
        pil_img = picture.image.pil_image
        pil_img.save(images_dir / f"image_{idx:03d}.png", "PNG")

# Markdown
markdown = doc.export_to_markdown()

# JSON (dict)
data = doc.export_to_dict()

# HTML
html = doc.export_to_html()

# Save with different image modes
from docling_core.types.doc import ImageRefMode
doc.save_as_markdown("output.md", image_mode=ImageRefMode.REFERENCED)

from pathlib import Path

converter = DocumentConverter()
for pdf in Path("docs").glob("*.pdf"):
    result = converter.convert(str(pdf))
    output = pdf.with_suffix(".md")
    output.write_text(result.document.export_to_markdown())

from docling.chunking import HierarchicalChunker

chunker = HierarchicalChunker()
chunks = list(chunker.chunk(result.document))
for chunk in chunks:
    print(chunk.text)

for idx, table in enumerate(result.document.tables):
    df = table.export_to_dataframe()
    df.to_csv(f"table_{idx}.csv", index=False)
    print(df.to_markdown())  # Print as Markdown