This commit is contained in:
18
docs/snippets/python/ocr/ocr_elements.md
Normal file
18
docs/snippets/python/ocr/ocr_elements.md
Normal file
@@ -0,0 +1,18 @@
|
||||
```python title="Python"
|
||||
from kreuzberg import extract_file_sync, ExtractionConfig, OcrConfig
|
||||
|
||||
config: ExtractionConfig = ExtractionConfig(
|
||||
ocr=OcrConfig(backend="paddleocr", language="en")
|
||||
)
|
||||
|
||||
result = extract_file_sync("scanned.pdf", config=config)
|
||||
|
||||
if result.ocr_elements:
|
||||
for element in result.ocr_elements:
|
||||
print(f"Text: {element.text}")
|
||||
print(f"Confidence: {element.confidence.recognition:.2f}")
|
||||
print(f"Geometry: {element.geometry}")
|
||||
if element.rotation:
|
||||
print(f"Rotation: {element.rotation.angle}°")
|
||||
print()
|
||||
```
|
||||
Reference in New Issue
Block a user