Update app.py

app.py

@@ -1,54 +1,43 @@
-# app.py  
-import streamlit as st  
-import cv2  
-import numpy as np  
-import pytesseract  
-from PIL import Image  
-import re  
+import streamlit as st
+import cv2
+import pytesseract
+import numpy as np
+from PIL import Image
+import io
+import re
 
-# Set the title of the webpage  
-st.title("OCR Text Extraction Tool")  
+# Function for OCR processing (similar to your existing code)
+def process_image(image_bytes):
+  # Convert bytes to image and process
+  image = Image.open(io.BytesIO(image_bytes))
+  opencv_image = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
+  text = pytesseract.image_to_string(opencv_image)
+  return text
 
-# Uploading an image  
-uploaded_file = st.file_uploader("Upload an Image", type=["jpg", "jpeg", "png"])  
+# Function for search and highlight (similar to your existing code)
+def search_and_highlight(full_text, keyword):
+  # Implement search and highlighting logic here
 
-if uploaded_file is not None:  
-    # Convert the uploaded file content to an image  
-    image = Image.open(uploaded_file)  
-    
-    # Convert PIL Image to OpenCV format  
-    opencv_image = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)  
+# Streamlit app layout
+st.title("Image Text Search App")
+uploaded_file = st.file_uploader("Upload an Image", type="jpg,png")
 
-    # Display the image  
-    st.image(image, caption='Uploaded Image', use_column_width=True)  
-    
-    try:  
-        # Perform OCR  
-        text = pytesseract.image_to_string(opencv_image)  
-        
-        st.subheader("Extracted Text:")  
-        st.write(text)  
+if uploaded_file is not None:
+  image_bytes = uploaded_file.read()
+  st.image(image_bytes)
 
-        # Search functionality  
-        search_keyword = st.text_input("Enter a keyword to search in the extracted text:")  
-        if search_keyword:  
-            pattern = re.compile(re.escape(search_keyword), re.IGNORECASE)  
-            matches = list(pattern.finditer(text))  
-            
-            if matches:  
-                st.markdown("### Keyword Found:")  
-                for match in matches:  
-                    start, end = match.span()  
-                    context_start = max(0, start - 50)  
-                    context_end = min(len(text), end + 50)  
-                    context = text[context_start:context_end]  
-                    highlighted_text = (  
-                        context[:start-context_start] +  
-                        f"<span style='background-color: yellow;'>{context[start-context_start:end-context_start]}</span>" +  
-                        context[end-context_start:]  
-                    )  
-                    st.markdown(f"...{highlighted_text}...")  
-            else:  
-                st.write(f"Keyword '{search_keyword}' not found in the extracted text.")  
-    except Exception as e:  
-        st.error(f"An error occurred while processing the image: {str(e)}")
+  # Perform OCR
+  extracted_text = process_image(image_bytes)
+  st.write("Extracted Text:")
+  st.write(extracted_text)
+
+  # Search functionality
+  search_keyword = st.text_input("Enter a keyword to search:")
+  if search_keyword:
+    results, highlighted_text = search_and_highlight(extracted_text, search_keyword)
+    if results:
+      st.write(f"Keyword '{search_keyword}' found in the extracted text:")
+      for i, result in enumerate(results, 1):
+        st.write(f"{i}. ...{result}...")
+    else:
+      st.write(f"Keyword '{search_keyword}' not found in the extracted text.")