federal_electric.py

import pdfplumber
import pandas as pd
import re

# Function: Extract Text from PDF
def extract_text_from_pdf(pdf_file):
    with pdfplumber.open(pdf_file.name) as pdf:
        text = ""
        for page in pdf.pages:
            text += page.extract_text()
    return text

# Function: Parse PO Items
def parse_po_items_with_filters(text):
    """
    Parses purchase order items from the extracted text using regex with filters.
    Handles split descriptions across lines and filters unwanted text.
    """
    lines = text.splitlines()
    data = []
    current_item = {}
    description_accumulator = []

    for line in lines:
        # Match the start of an item row
        item_match = re.match(r"^(?P<Item>\d+)\s+(?P<Description>.+)", line)
        if item_match:
            # Save the previous item and start a new one
            if current_item:
                current_item["Description"] = " ".join(description_accumulator).strip()
                data.append(current_item)
                description_accumulator = []

            current_item = {
                "Item": item_match.group("Item"),
                "Description": "",
                "Qty": "",
                "Unit": "",
                "Unit Price": "",
                "Total Price": "",
            }
            description_accumulator.append(item_match.group("Description"))
        elif current_item:
            # Handle additional description lines or split descriptions
            description_accumulator.append(line.strip())

        # Match Qty, Unit, Unit Price, and Total Price
        qty_match = re.search(r"(?P<Qty>\d+)\s+(Nos\.|Set)", line)
        if qty_match:
            current_item["Qty"] = qty_match.group("Qty")
            current_item["Unit"] = qty_match.group(2)

        price_match = re.search(r"(?P<UnitPrice>[\d.]+)\s+(?P<TotalPrice>[\d.]+)$", line)
        if price_match:
            current_item["Unit Price"] = price_match.group("UnitPrice")
            current_item["Total Price"] = price_match.group("TotalPrice")

    # Save the last item
    if current_item:
        current_item["Description"] = " ".join(description_accumulator).strip()
        data.append(current_item)

    if not data:
        return None, "No items found. Please check the PDF file format."
    df = pd.DataFrame(data)
    return df, "Data extracted successfully."

# Function: Save to Excel
def save_to_excel(df, output_path="federal_electric_extracted_data.xlsx"):
    df.to_excel(output_path, index=False)
    return output_path

# Main function to process PDF
def process_pdf(file):
    try:
        text = extract_text_from_pdf(file)
        df, status = parse_po_items_with_filters(text)
        if df is not None:
            output_path = save_to_excel(df)
            return output_path, status
        return None, status
    except Exception as e:
        return None, f"Error during processing: {str(e)}"