Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import pytesseract | |
| import pandas as pd | |
| from io import BytesIO | |
| import fitz # PyMuPDF | |
| import re | |
| from PIL import Image | |
| import tempfile | |
| # Explicitly set the Tesseract path | |
| pytesseract.pytesseract.tesseract_cmd = "/usr/bin/tesseract" | |
| def extract_data_from_pdf(pdf_file): | |
| # Open the PDF file using the path provided by gr.File | |
| doc = fitz.open(pdf_file.name) | |
| text_data = [] | |
| # Process each page in the PDF using Tesseract OCR | |
| for page_num in range(doc.page_count): | |
| page = doc[page_num] | |
| pix = page.get_pixmap() # Render page to a Pixmap image | |
| # Convert Pixmap to PIL Image | |
| image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples) | |
| # Use Tesseract to extract text from the image | |
| text = pytesseract.image_to_string(image) | |
| text_data.append(text) | |
| # Initialize list for parsed data | |
| data = [] | |
| # Define regular expressions for parsing rows | |
| row_pattern = re.compile( | |
| r'(?P<pos>\d+)\s+(?P<item_code>\d+)\s+(?P<description>.+?)\s+(?P<unit>\S+)\s+(?P<date>\d{4}-\d{2}-\d{2})\s+(?P<quantity>\d+\.\d+)\s+(?P<price>\d+\.\d+)\s+(?P<discount>\d+\.\d+)\s+(?P<currency>\S+)\s+(?P<amount>\d+\.\d+)' | |
| ) | |
| # Process and structure extracted text | |
| for text in text_data: | |
| for line in text.split('\n'): | |
| # Apply row pattern to each line | |
| match = row_pattern.search(line) | |
| if match: | |
| row = match.groupdict() | |
| row["description"] = row["description"].strip() # Clean description | |
| row["quantity"] = float(row["quantity"]) | |
| row["price"] = float(row["price"]) | |
| row["discount"] = float(row["discount"]) | |
| row["amount"] = float(row["amount"]) | |
| # Calculate Sub Total with assumed tax rate | |
| central_gst = row["amount"] * 0.09 # Central GST 9% | |
| state_gst = row["amount"] * 0.09 # State GST 9% | |
| row["Central GST"] = round(central_gst, 2) | |
| row["State GST"] = round(state_gst, 2) | |
| row["Sub Total"] = round(row["amount"] + central_gst + state_gst - row["discount"], 2) | |
| data.append(row) | |
| # Create DataFrame if data was extracted | |
| if data: | |
| df = pd.DataFrame(data) | |
| df.columns = [ | |
| "Pos", "Item Code", "Description", "Unit", "Delivery Date", "Quantity", "Basic Price", | |
| "Discount", "Currency", "Amount", "Central GST", "State GST", "Sub Total" | |
| ] | |
| # Save the DataFrame to a temporary Excel file | |
| temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".xlsx") | |
| with pd.ExcelWriter(temp_file.name, engine="xlsxwriter") as writer: | |
| df.to_excel(writer, index=False, sheet_name="Extracted Data") | |
| return temp_file.name | |
| else: | |
| # If no data was found, create a blank Excel file | |
| temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".xlsx") | |
| with pd.ExcelWriter(temp_file.name, engine="xlsxwriter") as writer: | |
| pd.DataFrame([["No structured data found. Please check the PDF structure."]], columns=["Error"]).to_excel(writer, index=False, sheet_name="Error") | |
| return temp_file.name | |
| # Define Gradio Interface with updated components | |
| iface = gr.Interface( | |
| fn=extract_data_from_pdf, | |
| inputs=gr.File(label="Upload PDF"), | |
| outputs=gr.File(label="Download Excel"), | |
| title="Advanced Document Data Extractor", | |
| description=( | |
| "Upload a PDF file to extract structured purchase order data and download it as an Excel file. " | |
| "The app will parse rows with fields like Position, Item Code, Description, Quantity, Price, etc. " | |
| "Calculated fields (like Central GST, State GST, and Sub Total) are automatically included." | |
| ), | |
| ) | |
| iface.launch() | |