Update question_extractor.py

question_extractor.py

@@ -300,6 +300,12 @@ def extract_questions_with_layout(image_path):
     for idx, line in enumerate(lines):
         if line["top"] < header_cutoff:
             continue
+        text_lower = line["text"].lower()
+        # Skip obvious table header rows for VIT-style papers
+        if "q. no" in text_lower or "q no" in text_lower:
+            continue
+        if "description" in text_lower and "marks" in text_lower:
+            continue
         # Consider only the first alphanumeric token on the line to avoid
         # picking up numbers that appear in the middle of sentences.
         first_tok = None
@@ -312,10 +318,11 @@ def extract_questions_with_layout(image_path):
             first_tok = tok
             break
 
+        # Require a pure integer token in a reasonable range, in the
+        # left-most part of the page (Q.No column in VIT tables).
         if first_tok and first_tok["text"].isdigit():
             n = int(first_tok["text"])
-            # Number near left margin and in a reasonable range
-            if first_tok["left"] < width * 0.25 and 1 <= n <= 50:
+            if 1 <= n <= 50 and first_tok["left"] < width * 0.2:
                 raw_q_indices.append(idx)
                 raw_q_numbers.append(n)