Update app.py

app.py

@@ -50,8 +50,14 @@ def extract_student_name(text):
 
 # Function to extract questions from the text
 def extract_questions_from_text(text):
-    questions = re.findall(r'([^.]*\?)', text)  # Extract sentences ending with '?'
+    # Improved logic: extract sentences ending with '?' or "Question: [text]"
+    questions = re.findall(r'(Question\s*[:|-]?\s*[\w\s\?]+)', text)  # Extract questions starting with "Question:"
+    questions += re.findall(r'([^.]*\?)', text)  # Also extract any sentence ending with "?"
+    
+    # Remove duplicates and metadata like 'Name', 'Roll No', etc.
+    questions = list(set(questions))  # Remove duplicates
     questions = [q for q in questions if not any(keyword in q.lower() for keyword in ['name', 'roll no', 'school'])]
+    
     return questions
 
 # Streamlit Interface
@@ -71,6 +77,10 @@ if uploaded_file is not None:
     if not text:  # If no text extracted, try OCR
         text = extract_text_from_image_pdf("uploaded_file.pdf")
 
+    # Print the extracted text to manually check what was extracted (optional)
+    st.subheader("Extracted Text:")
+    st.text(text)
+
     # Preprocess text
     preprocessed_text = preprocess_text(text)
 
@@ -93,4 +103,3 @@ if uploaded_file is not None:
         st.write(f"**Score**: {result['score']:.2f}")
         st.write(f"**Feedback**: {result['feedback']}")
         st.write("---")
-