| Name | document-data-extractor JSON |
| Version |
1.0.4
JSON |
| download |
| home_page | None |
| Summary | Best open-source document to markdown extractor for LLM training data. Convert PDF, Word, PowerPoint, Excel, images, URLs to clean markdown, JSON, HTML locally. Alternative to Unstructured, Docling, Marker, MarkItDown, MinerU, PaddleOCR, Tesseract |
| upload_time | 2025-07-29 08:25:56 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.8 |
| license | MIT |
| keywords |
llm
document-processing
document-conversion
markdown
pdf
image-processing
intelligent-document-processing
document-understanding
ocr
rag
ai-training-data
unstructured-alternative
docling-alternative
marker-alternative
markitdown-alternative
mineru-alternative
paddleocr-alternative
tesseract-alternative
document-to-markdown
pdf-to-markdown
local-document-processing
offline-document-extractor
structured-data-extraction
table-extraction
layout-detection
llm-ready-data
document-ai
text-extraction
html-to-markdown
excel-to-markdown
powerpoint-to-markdown
word-to-markdown
batch-document-processing
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Document Data Extractor
[](https://badge.fury.io/py/document-data-extractor)
[](https://pypi.org/project/document-data-extractor/)
[](https://github.com/NanoNets/llm-data-converter)
[](https://opensource.org/licenses/MIT)
> **Try Cloud Mode for Free!**
> Extract documents data instantly with our cloud API - no setup required.
> For unlimited processing, [get your free API key](https://app.nanonets.com/#/keys).
Transform any document, image, or URL into LLM-ready formats (Markdown, JSON, CSV, HTML) with intelligent content extraction and advanced OCR.
## Key Features
- **Cloud Processing (Default)**: Instant conversion with Nanonets API - no local setup needed
- **Local Processing**: CPU/GPU options for complete privacy and control
- **Universal Input**: PDFs, Word docs, Excel, PowerPoint, images, URLs, and raw text
- **Smart Output**: Markdown, JSON, CSV, HTML, and plain text formats
- **LLM-Optimized**: Clean, structured output perfect for AI processing
- **Intelligent Extraction**: Extract specific fields or structured data using AI
- **Advanced OCR**: Multiple OCR engines with automatic fallback
- **Table Processing**: Accurate table extraction and formatting
- **Image Handling**: Extract text from images and visual content
- **URL Processing**: Direct conversion from web pages
## Installation
```bash
pip install document-data-extractor
```
## Quick Start
### Basic Usage (Cloud Mode - Default)
```python
from document_extractor import DocumentExtractor
# Default cloud mode - no setup required
extractor = DocumentExtractor()
# Extract data from any document
result = extractor.extract("document.pdf")
# Get different output formats
markdown = result.extract_markdown()
json_data = result.extract_data()
html = result.extract_html()
csv_tables = result.extract_csv()
# Extract specific fields
extracted_fields = result.extract_data(specified_fields=[
"title", "author", "date", "summary", "key_points"
])
# Extract using JSON schema
schema = {
"title": "string",
"author": "string",
"date": "string",
"summary": "string",
"key_points": ["string"],
"metadata": {
"page_count": "number",
"language": "string"
}
}
structured_data = result.extract_data(json_schema=schema)
```
### With API Key (Unlimited Access)
```python
# Get your free API key from https://app.nanonets.com/#/keys
extractor = DocumentExtractor(api_key="your_api_key_here")
result = extractor.extract("document.pdf")
```
### Local Processing
```python
# Force local CPU processing
extractor = DocumentExtractor(cpu=True)
# Force local GPU processing (requires CUDA)
extractor = DocumentExtractor(gpu=True)
```
## Output Formats
- **Markdown**: Clean, LLM-friendly format with preserved structure
- **JSON**: Structured data with metadata and intelligent parsing
- **HTML**: Formatted output with styling and layout
- **CSV**: Extract tables and data in spreadsheet format
- **Text**: Plain text with smart formatting
## Examples
### Convert Multiple File Types
```python
from document_extractor import DocumentExtractor
extractor = DocumentExtractor()
# PDF document
pdf_result = extractor.extract("report.pdf")
print(pdf_result.extract_markdown())
# Word document
docx_result = extractor.extract("document.docx")
print(docx_result.extract_data())
# Excel spreadsheet
excel_result = extractor.extract("data.xlsx")
print(excel_result.extract_csv())
# PowerPoint presentation
pptx_result = extractor.extract("slides.pptx")
print(pptx_result.extract_html())
# Image with text
image_result = extractor.extract("screenshot.png")
print(image_result.to_text())
# Web page
url_result = extractor.extract("https://example.com")
print(url_result.extract_markdown())
```
### Extract Tables to CSV
```python
# Extract all tables from a document
result = extractor.extract("financial_report.pdf")
csv_data = result.extract_csv(include_all_tables=True)
print(csv_data)
```
### Enhanced JSON Conversion
The library now uses intelligent document understanding for JSON conversion:
```python
from document_extractor import DocumentExtractor
extractor = DocumentExtractor()
result = extractor.extract("document.pdf")
# Enhanced JSON with Ollama (when available)
json_data = result.extract_data()
print(json_data["format"]) # "ollama_structured_json" or "structured_json"
# The enhanced conversion provides:
# - Better document structure understanding
# - Intelligent table parsing
# - Automatic metadata extraction
# - Key information identification
# - Proper data type handling
```
**Requirements for enhanced JSON (if using cpu=True):**
- Install: `pip install 'document-data-extractor[local-llm]'`
- [Install Ollama](https://ollama.ai/) and run: `ollama serve`
- Pull a model: `ollama pull llama3.2`
*If Ollama is not available, the library automatically falls back to the standard JSON parser.*
### Extract Specific Fields & Structured Data
```python
# Extract specific fields from any document
result = extractor.extract("invoice.pdf")
# Method 1: Extract specific fields
extracted = result.extract_data(specified_fields=[
"invoice_number",
"total_amount",
"vendor_name",
"due_date"
])
# Method 2: Extract using JSON schema
schema = {
"invoice_number": "string",
"total_amount": "number",
"vendor_name": "string",
"line_items": [{
"description": "string",
"amount": "number"
}]
}
structured = result.extract_data(json_schema=schema)
```
**How it works:**
- Automatically uses cloud API when available
- Falls back to local Ollama for privacy-focused processing
- Same interface works for both cloud and local modes
**Cloud Mode Usage Examples:**
```python
from document_extractor import DocumentExtractor
# Default cloud mode (rate-limited without API key)
extractor = DocumentExtractor()
# With API key for unlimited access
extractor = DocumentExtractor(api_key="your_api_key_here")
# Extract specific fields from invoice
result = extractor.extract("invoice.pdf")
# Extract key invoice information
invoice_fields = result.extract_data(specified_fields=[
"invoice_number",
"total_amount",
"vendor_name",
"due_date",
"items_count"
])
print("Extracted Invoice Fields:")
print(invoice_fields)
# Output: {"extracted_fields": {"invoice_number": "INV-001", ...}, "format": "specified_fields"}
# Extract structured data using schema
invoice_schema = {
"invoice_number": "string",
"total_amount": "number",
"vendor_name": "string",
"billing_address": {
"street": "string",
"city": "string",
"zip_code": "string"
},
"line_items": [{
"description": "string",
"quantity": "number",
"unit_price": "number",
"total": "number"
}],
"taxes": {
"tax_rate": "number",
"tax_amount": "number"
}
}
structured_invoice = result.extract_data(json_schema=invoice_schema)
print("Structured Invoice Data:")
print(structured_invoice)
# Output: {"structured_data": {...}, "schema": {...}, "format": "structured_json"}
# Extract from different document types
receipt = extractor.extract("receipt.jpg")
receipt_data = receipt.extract_data(specified_fields=[
"merchant_name", "total_amount", "date", "payment_method"
])
contract = extractor.extract("contract.pdf")
contract_schema = {
"parties": [{
"name": "string",
"role": "string"
}],
"contract_value": "number",
"start_date": "string",
"end_date": "string",
"key_terms": ["string"]
}
contract_data = contract.extract_data(json_schema=contract_schema)
```
**Local extraction requirements (if using cpu=True):**
- Install ollama package: `pip install 'document-data-extractor[local-llm]'`
- [Install Ollama](https://ollama.ai/) and run: `ollama serve`
- Pull a model: `ollama pull llama3.2`
### Chain with LLM
```python
# Perfect for LLM workflows
document_text = extractor.extract("research_paper.pdf").extract_markdown()
# Use with any LLM
response = your_llm_client.chat(
messages=[{
"role": "user",
"content": f"Summarize this research paper:\n\n{document_text}"
}]
)
```
## Command Line Interface
```bash
# Basic conversion (cloud mode default)
document-data-extractor document.pdf
# With API key for unlimited access
document-data-extractor document.pdf --api-key YOUR_API_KEY
# Local processing modes
document-data-extractor document.pdf --cpu-mode
document-data-extractor document.pdf --gpu-mode
# Different output formats
document-data-extractor document.pdf --output json
document-data-extractor document.pdf --output html
document-data-extractor document.pdf --output csv
# Extract specific fields
document-data-extractor invoice.pdf --output json --extract-fields invoice_number total_amount
# Extract with JSON schema
document-data-extractor document.pdf --output json --json-schema schema.json
# Multiple files
document-data-extractor *.pdf --output markdown
# Save to file
document-data-extractor document.pdf --output-file result.md
# Comprehensive field extraction examples
document-data-extractor invoice.pdf --output json --extract-fields invoice_number vendor_name total_amount due_date line_items
# Extract from different document types with specific fields
document-data-extractor receipt.jpg --output json --extract-fields merchant_name total_amount date payment_method
document-data-extractor contract.pdf --output json --extract-fields parties contract_value start_date end_date
# Using JSON schema files for structured extraction
document-data-extractor invoice.pdf --output json --json-schema invoice_schema.json
document-data-extractor contract.pdf --output json --json-schema contract_schema.json
# Combine with API key for unlimited access
document-data-extractor document.pdf --api-key YOUR_API_KEY --output json --extract-fields title author date summary
# Force local processing with field extraction (requires Ollama)
document-data-extractor document.pdf --cpu-mode --output json --extract-fields key_points conclusions recommendations
```
**Example schema.json file:**
```json
{
"invoice_number": "string",
"total_amount": "number",
"vendor_name": "string",
"billing_address": {
"street": "string",
"city": "string",
"zip_code": "string"
},
"line_items": [{
"description": "string",
"quantity": "number",
"unit_price": "number"
}]
}
```
## API Reference for library
### DocumentExtractor
```python
DocumentExtractor(
preserve_layout: bool = True, # Preserve document structure
include_images: bool = True, # Include image content
ocr_enabled: bool = True, # Enable OCR processing
api_key: str = None, # API key for unlimited cloud access
model: str = None, # Model for cloud processing ("gemini", "openapi")
cpu: bool = False, # Force local CPU processing
gpu: bool = False # Force local GPU processing
)
```
### ConversionResult Methods
```python
result.extract_markdown() -> str # Clean markdown output
result.extract_data( # Structured JSON
specified_fields: List[str] = None, # Extract specific fields
json_schema: Dict = None # Extract with schema
) -> Dict
result.extract_html() -> str # Formatted HTML
result.extract_csv() -> str # CSV format for tables
result.to_text() -> str # Plain text
```
## Advanced Configuration
### Custom OCR Settings
```python
extractor = DocumentExtractor(
cpu=True, # Use local processing
ocr_enabled=True, # Enable OCR
preserve_layout=True, # Maintain structure
include_images=True # Process images
)
```
### Environment Variables
```bash
export NANONETS_API_KEY="your_api_key"
# Now all conversions use your API key automatically
```
## Contributing
We welcome contributions! Please see our [Contributing Guidelines](CONTRIBUTING.md) for details.
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## Support
- **Email**: support@nanonets.com
- **Issues**: [GitHub Issues](https://github.com/NanoNets/llm-data-converter/issues)
- **Discussions**: [GitHub Discussions](https://github.com/NanoNets/llm-data-converter/discussions)
---
**Star this repo** if you find it helpful! Your support helps us improve the library.
Raw data
{
"_id": null,
"home_page": null,
"name": "document-data-extractor",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "llm, document-processing, document-conversion, markdown, pdf, image-processing, intelligent-document-processing, document-understanding, ocr, rag, ai-training-data, unstructured-alternative, docling-alternative, marker-alternative, markitdown-alternative, mineru-alternative, paddleocr-alternative, tesseract-alternative, document-to-markdown, pdf-to-markdown, local-document-processing, offline-document-extractor, structured-data-extraction, table-extraction, layout-detection, llm-ready-data, document-ai, text-extraction, html-to-markdown, excel-to-markdown, powerpoint-to-markdown, word-to-markdown, batch-document-processing",
"author": null,
"author_email": "Nanonets <team@nanonets.com>",
"download_url": "https://files.pythonhosted.org/packages/7c/3c/af3604e88a00abf3397abeacc3a3045fbb680e9973ffcbb1cce997acbccd/document_data_extractor-1.0.4.tar.gz",
"platform": null,
"description": "# Document Data Extractor\n\n[](https://badge.fury.io/py/document-data-extractor)\n[](https://pypi.org/project/document-data-extractor/)\n[](https://github.com/NanoNets/llm-data-converter)\n[](https://opensource.org/licenses/MIT)\n\n> **Try Cloud Mode for Free!** \n> Extract documents data instantly with our cloud API - no setup required. \n> For unlimited processing, [get your free API key](https://app.nanonets.com/#/keys).\n\nTransform any document, image, or URL into LLM-ready formats (Markdown, JSON, CSV, HTML) with intelligent content extraction and advanced OCR.\n\n## Key Features\n\n- **Cloud Processing (Default)**: Instant conversion with Nanonets API - no local setup needed\n- **Local Processing**: CPU/GPU options for complete privacy and control\n- **Universal Input**: PDFs, Word docs, Excel, PowerPoint, images, URLs, and raw text\n- **Smart Output**: Markdown, JSON, CSV, HTML, and plain text formats\n- **LLM-Optimized**: Clean, structured output perfect for AI processing\n- **Intelligent Extraction**: Extract specific fields or structured data using AI\n- **Advanced OCR**: Multiple OCR engines with automatic fallback\n- **Table Processing**: Accurate table extraction and formatting\n- **Image Handling**: Extract text from images and visual content\n- **URL Processing**: Direct conversion from web pages\n\n## Installation\n\n```bash\npip install document-data-extractor\n```\n\n## Quick Start\n\n### Basic Usage (Cloud Mode - Default)\n\n```python\nfrom document_extractor import DocumentExtractor\n\n# Default cloud mode - no setup required\nextractor = DocumentExtractor()\n\n# Extract data from any document\nresult = extractor.extract(\"document.pdf\")\n\n# Get different output formats\nmarkdown = result.extract_markdown()\njson_data = result.extract_data()\nhtml = result.extract_html()\ncsv_tables = result.extract_csv()\n\n# Extract specific fields\nextracted_fields = result.extract_data(specified_fields=[\n \"title\", \"author\", \"date\", \"summary\", \"key_points\"\n])\n\n# Extract using JSON schema\nschema = {\n \"title\": \"string\",\n \"author\": \"string\", \n \"date\": \"string\",\n \"summary\": \"string\",\n \"key_points\": [\"string\"],\n \"metadata\": {\n \"page_count\": \"number\",\n \"language\": \"string\"\n }\n}\nstructured_data = result.extract_data(json_schema=schema)\n```\n\n### With API Key (Unlimited Access)\n\n```python\n# Get your free API key from https://app.nanonets.com/#/keys\nextractor = DocumentExtractor(api_key=\"your_api_key_here\")\nresult = extractor.extract(\"document.pdf\")\n```\n\n### Local Processing\n\n```python\n# Force local CPU processing\nextractor = DocumentExtractor(cpu=True)\n\n# Force local GPU processing (requires CUDA)\nextractor = DocumentExtractor(gpu=True)\n```\n\n## Output Formats\n\n- **Markdown**: Clean, LLM-friendly format with preserved structure\n- **JSON**: Structured data with metadata and intelligent parsing\n- **HTML**: Formatted output with styling and layout\n- **CSV**: Extract tables and data in spreadsheet format\n- **Text**: Plain text with smart formatting\n\n## Examples\n\n### Convert Multiple File Types\n\n```python\nfrom document_extractor import DocumentExtractor\n\nextractor = DocumentExtractor()\n\n# PDF document\npdf_result = extractor.extract(\"report.pdf\")\nprint(pdf_result.extract_markdown())\n\n# Word document \ndocx_result = extractor.extract(\"document.docx\")\nprint(docx_result.extract_data())\n\n# Excel spreadsheet\nexcel_result = extractor.extract(\"data.xlsx\")\nprint(excel_result.extract_csv())\n\n# PowerPoint presentation\npptx_result = extractor.extract(\"slides.pptx\")\nprint(pptx_result.extract_html())\n\n# Image with text\nimage_result = extractor.extract(\"screenshot.png\")\nprint(image_result.to_text())\n\n# Web page\nurl_result = extractor.extract(\"https://example.com\")\nprint(url_result.extract_markdown())\n```\n\n### Extract Tables to CSV\n\n```python\n# Extract all tables from a document\nresult = extractor.extract(\"financial_report.pdf\")\ncsv_data = result.extract_csv(include_all_tables=True)\nprint(csv_data)\n```\n\n### Enhanced JSON Conversion\n\nThe library now uses intelligent document understanding for JSON conversion:\n\n```python\nfrom document_extractor import DocumentExtractor\n\nextractor = DocumentExtractor()\nresult = extractor.extract(\"document.pdf\")\n\n# Enhanced JSON with Ollama (when available)\njson_data = result.extract_data()\nprint(json_data[\"format\"]) # \"ollama_structured_json\" or \"structured_json\"\n\n# The enhanced conversion provides:\n# - Better document structure understanding\n# - Intelligent table parsing\n# - Automatic metadata extraction \n# - Key information identification\n# - Proper data type handling\n```\n\n**Requirements for enhanced JSON (if using cpu=True):**\n- Install: `pip install 'document-data-extractor[local-llm]'`\n- [Install Ollama](https://ollama.ai/) and run: `ollama serve`\n- Pull a model: `ollama pull llama3.2`\n\n*If Ollama is not available, the library automatically falls back to the standard JSON parser.*\n\n### Extract Specific Fields & Structured Data\n\n```python\n# Extract specific fields from any document\nresult = extractor.extract(\"invoice.pdf\")\n\n# Method 1: Extract specific fields\nextracted = result.extract_data(specified_fields=[\n \"invoice_number\", \n \"total_amount\", \n \"vendor_name\",\n \"due_date\"\n])\n\n# Method 2: Extract using JSON schema\nschema = {\n \"invoice_number\": \"string\",\n \"total_amount\": \"number\", \n \"vendor_name\": \"string\",\n \"line_items\": [{\n \"description\": \"string\",\n \"amount\": \"number\"\n }]\n}\n\nstructured = result.extract_data(json_schema=schema)\n```\n\n**How it works:**\n- Automatically uses cloud API when available\n- Falls back to local Ollama for privacy-focused processing\n- Same interface works for both cloud and local modes\n\n**Cloud Mode Usage Examples:**\n\n```python\nfrom document_extractor import DocumentExtractor\n\n# Default cloud mode (rate-limited without API key)\nextractor = DocumentExtractor()\n\n# With API key for unlimited access\nextractor = DocumentExtractor(api_key=\"your_api_key_here\")\n\n# Extract specific fields from invoice\nresult = extractor.extract(\"invoice.pdf\")\n\n# Extract key invoice information\ninvoice_fields = result.extract_data(specified_fields=[\n \"invoice_number\",\n \"total_amount\", \n \"vendor_name\",\n \"due_date\",\n \"items_count\"\n])\n\nprint(\"Extracted Invoice Fields:\")\nprint(invoice_fields)\n# Output: {\"extracted_fields\": {\"invoice_number\": \"INV-001\", ...}, \"format\": \"specified_fields\"}\n\n# Extract structured data using schema\ninvoice_schema = {\n \"invoice_number\": \"string\",\n \"total_amount\": \"number\",\n \"vendor_name\": \"string\",\n \"billing_address\": {\n \"street\": \"string\",\n \"city\": \"string\", \n \"zip_code\": \"string\"\n },\n \"line_items\": [{\n \"description\": \"string\",\n \"quantity\": \"number\",\n \"unit_price\": \"number\",\n \"total\": \"number\"\n }],\n \"taxes\": {\n \"tax_rate\": \"number\",\n \"tax_amount\": \"number\"\n }\n}\n\nstructured_invoice = result.extract_data(json_schema=invoice_schema)\nprint(\"Structured Invoice Data:\")\nprint(structured_invoice)\n# Output: {\"structured_data\": {...}, \"schema\": {...}, \"format\": \"structured_json\"}\n\n# Extract from different document types\nreceipt = extractor.extract(\"receipt.jpg\")\nreceipt_data = receipt.extract_data(specified_fields=[\n \"merchant_name\", \"total_amount\", \"date\", \"payment_method\"\n])\n\ncontract = extractor.extract(\"contract.pdf\") \ncontract_schema = {\n \"parties\": [{\n \"name\": \"string\",\n \"role\": \"string\"\n }],\n \"contract_value\": \"number\",\n \"start_date\": \"string\",\n \"end_date\": \"string\",\n \"key_terms\": [\"string\"]\n}\ncontract_data = contract.extract_data(json_schema=contract_schema)\n```\n\n**Local extraction requirements (if using cpu=True):**\n- Install ollama package: `pip install 'document-data-extractor[local-llm]'`\n- [Install Ollama](https://ollama.ai/) and run: `ollama serve`\n- Pull a model: `ollama pull llama3.2`\n\n### Chain with LLM\n\n```python\n# Perfect for LLM workflows\ndocument_text = extractor.extract(\"research_paper.pdf\").extract_markdown()\n\n# Use with any LLM\nresponse = your_llm_client.chat(\n messages=[{\n \"role\": \"user\", \n \"content\": f\"Summarize this research paper:\\n\\n{document_text}\"\n }]\n)\n```\n\n## Command Line Interface\n\n```bash\n# Basic conversion (cloud mode default)\ndocument-data-extractor document.pdf\n\n# With API key for unlimited access\ndocument-data-extractor document.pdf --api-key YOUR_API_KEY\n\n# Local processing modes\ndocument-data-extractor document.pdf --cpu-mode\ndocument-data-extractor document.pdf --gpu-mode\n\n# Different output formats\ndocument-data-extractor document.pdf --output json\ndocument-data-extractor document.pdf --output html\ndocument-data-extractor document.pdf --output csv\n\n# Extract specific fields\ndocument-data-extractor invoice.pdf --output json --extract-fields invoice_number total_amount\n\n# Extract with JSON schema\ndocument-data-extractor document.pdf --output json --json-schema schema.json\n\n# Multiple files\ndocument-data-extractor *.pdf --output markdown\n\n# Save to file\ndocument-data-extractor document.pdf --output-file result.md\n\n# Comprehensive field extraction examples\ndocument-data-extractor invoice.pdf --output json --extract-fields invoice_number vendor_name total_amount due_date line_items\n\n# Extract from different document types with specific fields\ndocument-data-extractor receipt.jpg --output json --extract-fields merchant_name total_amount date payment_method\n\ndocument-data-extractor contract.pdf --output json --extract-fields parties contract_value start_date end_date\n\n# Using JSON schema files for structured extraction\ndocument-data-extractor invoice.pdf --output json --json-schema invoice_schema.json\ndocument-data-extractor contract.pdf --output json --json-schema contract_schema.json\n\n# Combine with API key for unlimited access\ndocument-data-extractor document.pdf --api-key YOUR_API_KEY --output json --extract-fields title author date summary\n\n# Force local processing with field extraction (requires Ollama)\ndocument-data-extractor document.pdf --cpu-mode --output json --extract-fields key_points conclusions recommendations\n```\n\n**Example schema.json file:**\n```json\n{\n \"invoice_number\": \"string\",\n \"total_amount\": \"number\",\n \"vendor_name\": \"string\",\n \"billing_address\": {\n \"street\": \"string\",\n \"city\": \"string\",\n \"zip_code\": \"string\"\n },\n \"line_items\": [{\n \"description\": \"string\",\n \"quantity\": \"number\",\n \"unit_price\": \"number\"\n }]\n}\n```\n\n## API Reference for library\n\n### DocumentExtractor\n\n```python\nDocumentExtractor(\n preserve_layout: bool = True, # Preserve document structure\n include_images: bool = True, # Include image content\n ocr_enabled: bool = True, # Enable OCR processing\n api_key: str = None, # API key for unlimited cloud access\n model: str = None, # Model for cloud processing (\"gemini\", \"openapi\")\n cpu: bool = False, # Force local CPU processing\n gpu: bool = False # Force local GPU processing\n)\n```\n\n### ConversionResult Methods\n\n```python\nresult.extract_markdown() -> str # Clean markdown output\nresult.extract_data( # Structured JSON\n specified_fields: List[str] = None, # Extract specific fields\n json_schema: Dict = None # Extract with schema\n) -> Dict\nresult.extract_html() -> str # Formatted HTML\nresult.extract_csv() -> str # CSV format for tables\nresult.to_text() -> str # Plain text\n```\n\n## Advanced Configuration\n\n### Custom OCR Settings\n\n```python\nextractor = DocumentExtractor(\n cpu=True, # Use local processing\n ocr_enabled=True, # Enable OCR\n preserve_layout=True, # Maintain structure\n include_images=True # Process images\n)\n```\n\n### Environment Variables\n\n```bash\nexport NANONETS_API_KEY=\"your_api_key\"\n# Now all conversions use your API key automatically\n```\n\n## Contributing\n\nWe welcome contributions! Please see our [Contributing Guidelines](CONTRIBUTING.md) for details.\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Support\n\n- **Email**: support@nanonets.com \n- **Issues**: [GitHub Issues](https://github.com/NanoNets/llm-data-converter/issues)\n- **Discussions**: [GitHub Discussions](https://github.com/NanoNets/llm-data-converter/discussions)\n\n---\n\n**Star this repo** if you find it helpful! Your support helps us improve the library. \n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Best open-source document to markdown extractor for LLM training data. Convert PDF, Word, PowerPoint, Excel, images, URLs to clean markdown, JSON, HTML locally. Alternative to Unstructured, Docling, Marker, MarkItDown, MinerU, PaddleOCR, Tesseract",
"version": "1.0.4",
"project_urls": {
"Documentation": "https://github.com/nanonets/llm-data-converter#readme",
"Homepage": "https://github.com/nanonets/llm-data-converter",
"Issues": "https://github.com/nanonets/llm-data-converter/issues",
"Repository": "https://github.com/nanonets/llm-data-converter"
},
"split_keywords": [
"llm",
" document-processing",
" document-conversion",
" markdown",
" pdf",
" image-processing",
" intelligent-document-processing",
" document-understanding",
" ocr",
" rag",
" ai-training-data",
" unstructured-alternative",
" docling-alternative",
" marker-alternative",
" markitdown-alternative",
" mineru-alternative",
" paddleocr-alternative",
" tesseract-alternative",
" document-to-markdown",
" pdf-to-markdown",
" local-document-processing",
" offline-document-extractor",
" structured-data-extraction",
" table-extraction",
" layout-detection",
" llm-ready-data",
" document-ai",
" text-extraction",
" html-to-markdown",
" excel-to-markdown",
" powerpoint-to-markdown",
" word-to-markdown",
" batch-document-processing"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "345a4353667ef06c1c34f234a27b3d2b513506943bd3cc6ba2560aad5363dbbc",
"md5": "eef88f292f80d9210c30ba6c87c3e3a1",
"sha256": "d021bd3ba5d34ef241b9b66dbbf5b0884d829e725f06e8c8b1b7ffac1433690f"
},
"downloads": -1,
"filename": "document_data_extractor-1.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "eef88f292f80d9210c30ba6c87c3e3a1",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 230204,
"upload_time": "2025-07-29T08:25:54",
"upload_time_iso_8601": "2025-07-29T08:25:54.401894Z",
"url": "https://files.pythonhosted.org/packages/34/5a/4353667ef06c1c34f234a27b3d2b513506943bd3cc6ba2560aad5363dbbc/document_data_extractor-1.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "7c3caf3604e88a00abf3397abeacc3a3045fbb680e9973ffcbb1cce997acbccd",
"md5": "fda9d87781d65411290680182988dac5",
"sha256": "9c8b4c4d05745210e4aba9b1037c612cd63a256b456fe0d77da8c5f0a9458f63"
},
"downloads": -1,
"filename": "document_data_extractor-1.0.4.tar.gz",
"has_sig": false,
"md5_digest": "fda9d87781d65411290680182988dac5",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 164143,
"upload_time": "2025-07-29T08:25:56",
"upload_time_iso_8601": "2025-07-29T08:25:56.100103Z",
"url": "https://files.pythonhosted.org/packages/7c/3c/af3604e88a00abf3397abeacc3a3045fbb680e9973ffcbb1cce997acbccd/document_data_extractor-1.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-29 08:25:56",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "nanonets",
"github_project": "llm-data-converter#readme",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "document-data-extractor"
}
