Update app.py

app.py

@@ -2,24 +2,32 @@ from typing import List
 
 import pytesseract
 from PIL import Image
-
 import gradio as gr
 
-def tesseract_ocr(filepath: str, languages: List[str]):
+def tesseract_ocr(filepath: str, keyword: str):
+    # Load the image and perform OCR
     image = Image.open(filepath)
-    return pytesseract.image_to_string(image=image, lang=', '.join(languages))
+    extracted_text = pytesseract.image_to_string(image=image)
+    
+    # Highlight the keyword in the extracted text
+    if keyword:
+        highlighted_text = extracted_text.replace(keyword, f"<mark>{keyword}</mark>")
+    else:
+        highlighted_text = extracted_text
     
+    return highlighted_text
+
 title = "Tesseract OCR"
-description = "Gradio demo for Tesseract. Tesseract is an open source text recognition (OCR) Engine."
+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()
+
 
 demo = gr.Interface(
     fn=tesseract_ocr, 
     inputs=[
-        gr.Image(type="filepath", label="Input"), 
-        gr.CheckboxGroup(language_choices, type="value", value=['eng'], label='language')
+        gr.Image(type="filepath", label="Upload Image for OCR"), 
+        gr.Textbox(label="Keyword to Highlight", placeholder="Enter a keyword...")  # Keyword input
         ],
     outputs='html',
     title=title,
@@ -29,4 +37,4 @@ demo = gr.Interface(
 
 if __name__ == '__main__':
     demo.launch()
-    print("Finished running")
+    print("Finished running")