app.py

from typing import List

import pytesseract
from PIL import Image

import gradio as gr

def tesseract_ocr(filepath: str, languages: List[str]):
    image = Image.open(filepath)
    return pytesseract.image_to_string(image=image, lang=', '.join(languages))

title = "Tesseract OCR"
description = "Gradio demo for Tesseract. Tesseract is an open source text recognition (OCR) Engine."
article = "<p style='text-align: center'><a href='https://tesseract-ocr.github.io/' target='_blank'>Tesseract documentation</a> | <a href='https://github.com/tesseract-ocr/tesseract' target='_blank'>Github Repo</a></p>"

language_choices = pytesseract.get_languages()

def search_and_highlight(text, keyword):
    highlighted_text = re.sub(f"({keyword})", r"<mark>\1</mark>", text, flags=re.IGNORECASE)
    return highlighted_text

def ocr_and_search(image, keyword, language_choices):
    if image is None:
        return "Please upload an image."

    extracted_text = tesseract_ocr(image)

    if keyword:
        highlighted_text = search_and_highlight(extracted_text, keyword)
        return highlighted_text
    else:
        return extracted_text

iface = gr.Interface(
    fn=ocr_and_search,
    inputs=[
        gr.Image(type="pil", label="Upload Image"),
        gr.Textbox(label="Enter keyword to search (optional)"),
    ],
    outputs=gr.HTML(label="Extracted and Highlighted Text"),
    title="OCR and Keyword Search",
    description="Upload an image to extract text using OCR and optionally search for keywords in the extracted text."
)

iface.launch()