> ## Documentation Index
> Fetch the complete documentation index at: https://parserport.outerport.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Receipt to JSON

> A example converting a receipt document to JSON.

## Load the Document

```python theme={null}
from parseport.document.pdf_document import PDFDocument
from parseport.layout_parser.simple_layout_parser import SimpleLayoutParser
from parseport.tools.layout_detector.paddle_layout_detector import PaddleLayoutDetector
from parseport.tools.layout_detector.yolo_layout_detector import YoloLayoutDetector
from parseport.tools.vlm_generator.openai_vlm_generator import OpenAIVLMGenerator
from parseport.content_reader.vlm_reader import VLMDocumentReader
from parseport.formatter.vlm_formatter import VLMFormatter
```

Load your PDF receipt with visual elements enabled for better processing.

```python theme={null}
doc = PDFDocument.from_path('receipt.pdf', include_visuals=True)
```

## Detect Layout Components

Identify different sections and elements in the receipt (text blocks, tables, etc.).

```python theme={null}
detector = YoloLayoutDetector()
parser = SimpleLayoutParser(detector)
components = parser.parse_document(doc)
```

## Visualize Results (Optional)

See how the layout detection performed on your document.

```python theme={null}
image = document.render_image_with_component_blocks(0, components) # page 2
display(Image.fromarray(image))
```

<img src="https://mintcdn.com/parseport/KZLF7iZjsiOLCgyQ/images/receipt_detection.png?fit=max&auto=format&n=KZLF7iZjsiOLCgyQ&q=85&s=3ca713d20b4594699c21d6fa09b292b4" alt="Image" width="2550" height="3301" data-path="images/receipt_detection.png" />

## Extract Text

```python theme={null}
vlm_generator = OpenAIVLMGenerator()
reader = VLMDocumentReader(vlm_generator)
components = await reader.extract_texts(doc, components, show_progress=True)
```

Extract text from the detected components.

## Format Specific Data

Structure the extracted text into your desired format (JSON, table, etc.).

```python theme={null}
formatter = VLMFormatter(vlm_generator)
formatted_texts = await formatter.format_text(
    doc, components,
    "Extract the prices of the items in the receipt in a JSON format. Output the JSON only, no other text."
)
```

## Get Results

```python theme={null}
for page_num, text in formatted_texts.items():
    print(text)
    print("\n")
```

```text theme={null}
[
  {
    "description": "CLEARANCE! Fast Dell Desktop Computer PC DUAL CORE WINDOWS 10 4/8/16GB RAM",
    "net_price": 209.00,
    "net_worth": 627.00,
    "gross_worth": 689.70
  },
  {
    "description": "HP T520 Thin Client Computer AMD GX-212JC 1.2GHz 4GB RAM TESTED !!READ BELOW!!",
    "net_price": 37.75,
    "net_worth": 188.75,
    "gross_worth": 207.63
  },
 ...
]
```