Create bhel.py

bhel.py

@@ -0,0 +1,76 @@
+import pdfplumber
+
+import pandas as pd
+
+import gradio as gr
+
+# Define function to extract data
+
+def extract_data(pdf_file):
+
+    data = []
+
+    columns = ["SI No", "Material Description", "Unit", "Quantity", "Dely Qty", "Dely Date", "Unit Rate", "Value"] 
+
+    start_si, end_si = 10, 1150
+
+    with pdfplumber.open(pdf_file) as pdf:
+
+        for page in pdf.pages:
+
+            text = page.extract_text().splitlines()
+
+            for line in text:
+
+                parts = line.split()
+
+                try:
+
+                    si_no = int(parts[0])
+
+                    if start_si <= si_no <= end_si:
+
+                        material_desc = " ".join(parts[1:3])
+
+                        unit = parts[3]
+
+                        quantity = int(parts[4])
+
+                        dely_qty = int(parts[5])
+
+                        dely_date = parts[6]
+
+                        unit_rate = float(parts[7])
+
+                        value = float(parts[8])
+
+                        data.append([si_no, material_desc, unit, quantity, dely_qty, dely_date, unit_rate, value])
+
+                except (ValueError, IndexError):
+
+                    continue
+
+    df = pd.DataFrame(data, columns=columns)
+
+    excel_path = "/tmp/Extracted_Purchase_Order_Data.xlsx"
+
+    df.to_excel(excel_path, index=False)
+
+    return excel_path
+    
+# Set up Gradio interface
+
+iface = gr.Interface(
+
+    fn=extract_data,
+
+    inputs=gr.File(label="Upload PDF"),
+
+    outputs=gr.File(label="Download Excel"),
+
+    title="PDF Data Extractor"
+
+)
+# Launch the app
+
+iface.launch()