Create app.py

app.py

@@ -0,0 +1,65 @@
+# app.py
+
+import fitz  # PyMuPDF
+import pandas as pd
+
+# Define function to extract table data from PDF
+def extract_data_from_pdf(pdf_path, start_pos, end_pos):
+    doc = fitz.open(pdf_path)
+    data = []
+
+    for page_num in range(len(doc)):
+        page = doc[page_num]
+        text = page.get_text("text")
+        lines = text.split('\n')
+        
+        for line in lines:
+            # Check if line starts with the required 'Pos.' format
+            if line.startswith("Pos."):
+                parts = line.split()
+                pos = int(parts[1])
+                
+                # Check if position is within the desired range
+                if start_pos <= pos <= end_pos:
+                    item_code = parts[2]
+                    unit = parts[3]
+                    delivery_date = parts[4]
+                    quantity = parts[5]
+                    basic_price = parts[6]
+                    discount = parts[7]
+                    currency = parts[8]
+                    amount = parts[9]
+                    
+                    # Append structured data to list
+                    data.append({
+                        "Sl No": pos,
+                        "Item Code": item_code,
+                        "Unit": unit,
+                        "Delivery Date": delivery_date,
+                        "Quantity": quantity,
+                        "Basic Price": basic_price,
+                        "Discount": discount,
+                        "Currency": currency,
+                        "Amount": amount
+                    })
+    
+    # Convert list to DataFrame
+    df = pd.DataFrame(data)
+    return df
+
+# Main function to run extraction and save to Excel
+def main():
+    pdf_path = "P24101337 - LABELS.pdf"  # Replace with your PDF file path
+    start_pos = 10
+    end_pos = 450
+    
+    # Extract data from PDF
+    df = extract_data_from_pdf(pdf_path, start_pos, end_pos)
+    
+    # Save DataFrame to Excel
+    output_path = "extracted_data.xlsx"
+    df.to_excel(output_path, index=False)
+    print(f"Data has been extracted and saved to {output_path}")
+
+if __name__ == "__main__":
+    main()