Untitled

import pdfplumber
import pandas as pd
import re
from pathlib import Path

def extract_chargen_nr(lines):
    for i, line in enumerate(lines):
        if "Chargen Nr." in line:
            return lines[i+1].split(" ")[3]
    return None

def extract_kd_wst_bez(lines):
    for line in lines:
        pattern = r"Kd Wst Bez\s+(.*?)\s+Werkstoff"
        match = re.search(pattern, line)
        if match:
            return match.group(1)
    return None

def extract_abmessung(lines):
    for line in lines:
        if line.startswith('Abmessung'):
            pattern = r'\d{1,3}(?:\.\d{3})*(?:,\d+)?'
            matches = re.findall(pattern, line)
            if matches:
                return [float(num.replace('.', '').replace(',', '.')) for num in matches]
    return None

def extract_reduction_ratio(lines):
    for line in lines:
        if line.startswith("Verformungsgrad"):
            pattern = r'(\d+,\d+)(?=:1)'
            match = re.search(pattern, line)
            if match:
                return match.group(1)
    return None

def extract_karbid(lines):
    results = {
        'Karbidnetzwerk': [],
        'Karbidzeiligkeit': []
    }

    for i, line in enumerate(lines):
        if line.startswith("Glühgefüge"):
            extracted_lines = lines[i+2:i+6]
            for item in extracted_lines:
                if not ('Karbidnetzwerk' in item or 'Karbidzeiligkeit' in item):
                    continue

                if 'Karbidnetzwerk' in item:
                    values = item.split('Karbidnetzwerk')[-1].strip().split('-')
                    results['Karbidnetzwerk'].extend([float(val.strip()) for val in values])

                if 'Karbidzeiligkeit' in item:
                    values = item.split('Karbidzeiligkeit')[-1].strip().split('-')
                    results['Karbidzeiligkeit'].extend([float(val.strip()) for val in values])

    return results

def process_pdf(pdf_path):
    """Process a single PDF and return its extracted data as a dictionary."""
    with pdfplumber.open(pdf_path) as pdf:
        text = ""
        for page in pdf.pages:
            text += page.extract_text()

        lines = text.split("\n")
        lines = [line.strip() for line in lines if line.strip()]

        karbid_results = extract_karbid(lines)
        abmessung_results = extract_abmessung(lines)

        data = {
            'filename': pdf_path.name,
            'chargen_nr': extract_chargen_nr(lines),
            'kd_wst_bez': extract_kd_wst_bez(lines),
            'reduction_ratio': extract_reduction_ratio(lines),
            'Karbidnetzwerk': karbid_results['Karbidnetzwerk'],
            'Karbidzeiligkeit': karbid_results['Karbidzeiligkeit'],
            'Abmessung' : abmessung_results
        }
        return data

def process_multiple_pdfs(pdf_folder):
    """Process all PDFs in a folder and return a DataFrame."""
    pdf_folder = Path(pdf_folder)
    all_data = []

    for pdf_path in pdf_folder.glob('*.pdf'):
        try:
            pdf_data = process_pdf(pdf_path)
            all_data.append(pdf_data)
        except Exception as e:
            print(f"Error processing {pdf_path}: {str(e)}")

    # Convert to DataFrame
    df = pd.DataFrame(all_data)

    # Convert Karbid lists to strings with values joined by '-'
    if 'Karbidnetzwerk' in df.columns:
        df['Karbidnetzwerk'] = df['Karbidnetzwerk'].apply(lambda x: ','.join(map(str, x)) if isinstance(x, list) else x)

    if 'Karbidzeiligkeit' in df.columns:
        df['Karbidzeiligkeit'] = df['Karbidzeiligkeit'].apply(lambda x: ','.join(map(str, x)) if isinstance(x, list) else x)

    return df

# Example usage:
if __name__ == "__main__":
    # Replace with your PDF folder path
    pdf_folder = r"D:\Programming\Python\shaeffler_task\pdf"

    # Process all PDFs and create DataFrame
    df = process_multiple_pdfs(pdf_folder)

    # Save to CSV
    df.to_csv("extracted_data.csv", index=False)

    print("Data extraction completed!")
    print(f"Processed {len(df)} PDF files")
    print("\nFirst few rows of the DataFrame:")
    print(df.head())