ChatGPT_Windows-PDF-Renamer

A basic script to scan all PDFs in a folder and rename them based on GPT suggestion.

PDF File Renamer

This script is a utility for renaming PDF files based on the content of the first page of the document. It makes use of the OpenAI GPT-3.5 turbo model to generate the new file name.

This tool can be very handy for large numbers of PDF files, and it offers the option to search subdirectories recursively.

Requirements

Python 3.7 or newer.
Tesseract-OCR
Python packages: pytesseract, PyPDF2, pdf2image, requests

Installation

Follow these steps to install and use the script:

Install Python if it's not already installed. You can download it from the official site: Python.org
Install Tesseract-OCR. It's an OCR engine that this script uses to extract text from scanned PDFs. Download it from the official GitHub repository: Tesseract-OCR GitHub. Remember the path where you installed Tesseract, you will need it.
Install Popplrt Download the latest poppler package. Move the extracted directory to the desired place on your system Add the bin/ directory to your PATH environmental variable. Test that all went well by opening cmd and making sure that you can call 'pdftoppm -h'
Clone this repository to your local machine or download the Python script file.
Open a Command Prompt and navigate to the directory where you saved the script.
Install the required Python packages by running the following command: pip install pytesseract PyPDF2 pdf2image requests.
Open the script in a text editor.
Update the following line with the path where you installed Tesseract-OCR:

pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'  # adjust the path accordingly

Update the following line with your OpenAI key:

API_KEY = 'sk-YOURKEY'  # replace with your OpenAI key

Usage

Run the script from a Command Prompt with the command: python <script_name.py>

The script will ask for the following input:

Directory with PDF files: Enter the full path to the directory where your PDF files are located.
Directory to save renamed files: Enter the full path to the directory where you want to save the renamed files. You can use the same directory as the input directory.
Include subdirectories: Enter "yes" or "no". If you enter "yes", the script will also rename PDFs found in subdirectories of the input directory.

Note