Create toshiba.py

toshiba.py

@@ -0,0 +1,87 @@
+import gradio as gr
+
+import pdfplumber
+
+import pandas as pd
+
+import re
+
+def extract_data(pdf_file):
+
+    data = []
+
+    purchase_order, order_date = None, None
+
+    with pdfplumber.open(pdf_file) as pdf:
+
+        for page in pdf.pages:
+
+            text = page.extract_text().splitlines()
+
+
+
+
+            if not purchase_order or not order_date:
+
+                for line in text:
+
+                    po_match = re.search(r'Purchase Order\s*:\s*(P\d+)', line)
+
+                    date_match = re.search(r'Order Date\s*:\s*([\d-]+)', line)
+
+                    if po_match:
+
+                        purchase_order = po_match.group(1)
+
+                    if date_match:
+
+                        order_date = date_match.group(1)
+
+
+
+
+            for line in text:
+
+                parts = line.split()
+
+                try:
+
+                    pos = int(parts[0])
+
+                    if 10 <= pos <= 450:
+
+                        item_code = parts[1]
+
+                        quantity = float(parts[4])
+
+                        basic_price = float(parts[5])
+
+                        sub_total = float(parts[-1])
+
+                        data.append([purchase_order, order_date, pos, item_code, quantity, basic_price, sub_total])
+
+                except (ValueError, IndexError):
+
+                    continue
+
+    df = pd.DataFrame(data, columns=["Purchase Order", "Order Date", "Pos", "Item Code", "Quantity", "Basic Price", "Sub Total"])
+
+    excel_path = "/tmp/Extracted_Purchase_Order_Data.xlsx"
+
+    df.to_excel(excel_path, index=False)
+
+    return excel_path
+
+iface = gr.Interface(
+
+    fn=extract_data,
+
+    inputs=gr.File(label="Upload PDF"),
+
+    outputs=gr.File(label="Download Excel"),
+
+    title="PDF Data Extractor"
+
+)
+
+iface.launch()