Extracting Registration Codes from PDF

Have you ever ordered a bunch of Fortinet gear or services and forgot to add FortiDeploy to you order and now you are sitting with sometimes hundreds of PDF files containing the registration numbers you need to add to support.fortinet.com.  How much easier would it be to dump the contents of all the PDF Contract Registration Code Into a CSV file so you can add the codes faster and identify location, device name, serial number, date, etc.

As you can see in the graphic, It says Contract Registration Code however if you look at it using pdfplumber,  it displays ContactRegistrationCode without the spaces.  The idea is to have a folder containing all the PDFs.  Then we run the script and it will create an output csv file named contract_codes.csv (obviously you can modify the script to change it).  It will show the file name and the registration code.  In my example I ran it from my desktop in a folder named lic2 (For reference, I tried to run Optical Character Recognition (OCR) against the file and it did not work.

python3 get.py /Users/fernandezm/Desktop/lic2

#!/usr/bin/env python3

import pdfplumber
import csv
import re
import os
import sys

def extract_contract_code_from_pdf(pdf_path):
    try:
        with pdfplumber.open(pdf_path) as pdf:
            for page in pdf.pages:
                text = page.extract_text()
                if not text:
                    continue
                # No spaces between words in PDF and everything after the :
                match = re.search(r"ContractRegistrationCodes*:s*([A-Z0-9-]+)", text)
                if match:
                    return match.group(1)
    except Exception as e:
        print(f"[ERROR] Failed to process {pdf_path}: {e}")
    return None

def process_folder_and_export_to_csv(folder_path, output_csv):
    results = []

    for filename in os.listdir(folder_path):
        if filename.lower().endswith(".pdf"):
            filepath = os.path.join(folder_path, filename)
            code = extract_contract_code_from_pdf(filepath)
            if code:
                results.append([filename, code])
            else:
                print(f"[!] No contract code found in {filename}")

    # Write to CSV
    try:
        with open(output_csv, "w", newline='', encoding='utf-8') as csvfile:
            writer = csv.writer(csvfile)
            writer.writerow(["Filename", "Contract Registration Code"])
            writer.writerows(results)
        print(f"Exported {len(results)} row(s) to '{output_csv}'")
    except Exception as e:
        print(f"[ERROR] Could not write CSV: {e}")

if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("Usage: python get.py /path/to/pdf/folder")
        sys.exit(1)

    folder_path = sys.argv[1]
    if not os.path.isdir(folder_path):
        print(f"[ERROR] Folder not found: {folder_path}")
        sys.exit(1)
    
    #You can change the output file name and even add a path
    output_csv = "contract_codes.csv"
    process_folder_and_export_to_csv(folder_path, output_csv)