|
import gradio as gr |
|
import pytesseract |
|
from PIL import Image |
|
import io |
|
|
|
def extract_text(file): |
|
if file is None: |
|
return "Please upload an invoice." |
|
|
|
image = Image.open(file.name) |
|
text = pytesseract.image_to_string(image) |
|
print(text) |
|
return text |
|
|
|
with gr.Blocks() as demo: |
|
gr.Markdown("## Invoice OCR Extractor") |
|
|
|
with gr.Row(): |
|
file_input = gr.File(label="Upload Invoice (PDF or Image)") |
|
extract_button = gr.Button("Extract Text") |
|
|
|
text_output = gr.Textbox(label="Extracted Text", lines=10) |
|
|
|
extract_button.click(extract_text, inputs=file_input, outputs=text_output) |
|
|
|
demo.launch() |