Spaces:
Runtime error
Runtime error
| import re | |
| from typing import Dict, List, Union | |
| import gradio as gr | |
| import fitz # PyMuPDF | |
| import pandas as pd | |
| from io import BytesIO | |
| import tempfile | |
| import os | |
| def parse_federal_transformers(file_text: str) -> Dict[str, Union[str, List[Dict[str, Union[str, int, float]]]]]: | |
| parsed_data = { | |
| "Purchase Order No": "", | |
| "Date": "", | |
| "Supplier": "Federal Transformers Co. LLC", | |
| "Invoice Address": "", | |
| "Delivery Address": "", | |
| "Currency": "", | |
| "Payment Terms": "", | |
| "Items": [] | |
| } | |
| try: | |
| # Extract Purchase Order No and Date | |
| parsed_data["Purchase Order No"] = re.search(r"Purchase Order No\.\s(\d+)", file_text).group(1) | |
| parsed_data["Date"] = re.search(r"Date:\s+(\d{2}-\w{3}-\d{2})", file_text).group(1) | |
| # Extract Invoice Address and Delivery Address | |
| parsed_data["Invoice Address"] = re.search(r"Invoice Address\s*:\s*(.*?)(?=\sDelivery Address)", file_text, re.DOTALL).group(1).strip() | |
| parsed_data["Delivery Address"] = re.search(r"Delivery Address\s*:\s*(.*?)(?=\sNote)", file_text, re.DOTALL).group(1).strip() | |
| # Define pattern for extracting item details | |
| item_pattern = re.compile(r"(\d+)\s+([\w\s]+)\s+(\d+)\s+([\d.]+)\s+([\d.]+)") | |
| for match in item_pattern.finditer(file_text): | |
| parsed_data["Items"].append({ | |
| "Item No": match.group(1), | |
| "Description": match.group(2).strip(), | |
| "Quantity": int(match.group(3)), | |
| "Unit Price": float(match.group(4)), | |
| "Total Price": float(match.group(5)), | |
| }) | |
| except Exception as e: | |
| print(f"Error parsing Federal Transformers PO: {e}") | |
| return parsed_data | |
| def read_pdf(file_path): | |
| """Reads the text content from a PDF file.""" | |
| text = "" | |
| with fitz.open(file_path) as pdf: | |
| for page_num in range(len(pdf)): | |
| text += pdf[page_num].get_text() | |
| return text | |
| def process_pdf(file): | |
| """Handles PDF file input, extracts text, parses it, and returns an Excel file path.""" | |
| file_text = read_pdf(file.name) # Read text from PDF | |
| parsed_data = parse_federal_transformers(file_text) # Parse extracted text | |
| # Convert parsed data to DataFrame and create an Excel file | |
| with tempfile.NamedTemporaryFile(delete=False, suffix=".xlsx") as temp_file: | |
| with pd.ExcelWriter(temp_file.name, engine='openpyxl') as writer: | |
| # Write main PO details to the first sheet | |
| main_info = { | |
| "Field": ["Purchase Order No", "Date", "Supplier", "Invoice Address", "Delivery Address", "Currency", "Payment Terms"], | |
| "Value": [ | |
| parsed_data["Purchase Order No"], | |
| parsed_data["Date"], | |
| parsed_data["Supplier"], | |
| parsed_data["Invoice Address"], | |
| parsed_data["Delivery Address"], | |
| parsed_data["Currency"], | |
| parsed_data["Payment Terms"] | |
| ] | |
| } | |
| main_df = pd.DataFrame(main_info) | |
| main_df.to_excel(writer, index=False, sheet_name="Purchase Order Details") | |
| # Write item details to a second sheet | |
| items_df = pd.DataFrame(parsed_data["Items"]) | |
| items_df.to_excel(writer, index=False, sheet_name="Items") | |
| # Return the temporary file path for download | |
| return temp_file.name | |
| # Create Gradio interface | |
| iface = gr.Interface( | |
| fn=process_pdf, | |
| inputs=gr.File(label="Upload PDF"), | |
| outputs=gr.File(label="Download Excel"), | |
| title="Federal Transformers PO Parser", | |
| description="Upload a PDF of a Federal Transformers purchase order to extract details and download as an Excel file." | |
| ) | |
| if __name__ == "__main__": | |
| iface.launch() | |