eudaimon_screenshots

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

'''
################################################################################
#                                                                              #
# eudaimon_screenshots                                                         #
#                                                                              #
################################################################################
#                                                                              #
# LICENCE INFORMATION                                                          #
#                                                                              #
# This program uploads a screenshot every few seconds with a standard prompt   #
# for OpenAI analysis and returns a text response for each screenshot.         #
#                                                                              #
# copyright (C) 2024 William Breaden Madden                                    #
#                                                                              #
# This software is released under the terms of the GNU General Public License  #
# version 3 (GPLv3).                                                           #
#                                                                              #
# This program is free software: you can redistribute it and/or modify it      #
# under the terms of the GNU General Public License as published by the Free   #
# Software Foundation, either version 3 of the License, or (at your option)    #
# any later version.                                                           #
#                                                                              #
# This program is distributed in the hope that it will be useful, but WITHOUT  #
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or        #
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for     #
# more details.                                                                #
#                                                                              #
# For a copy of the GNU General Public License, see                            #
# <http://www.gnu.org/licenses>.                                               #
#                                                                              #
################################################################################

usage:
    program [options]

options:
    -h, --help           display help message
    --prompt=TEXT        prompt [default: Without describing the GUI or including any passcodes or secure information, what's the content in focus in this screenshot?]
    --interval=seconds   time between screenshots in seconds [default: 45]
'''

from datetime import datetime
import docopt
import base64
import os
import requests
import sys
import time

from openai import OpenAI
import pyautogui

__version__ = '2024-06-10T2255Z'

def take_screenshot():
	try:
	    filename = datetime.utcnow().strftime("%Y-%m-%dT%H%M%S%fZ") + '.png'
	    screenshot = pyautogui.screenshot()
	    screenshot.save(filename)
	    return filename
	except:
		return None

def encode_image(image_path):
    try:
        with open(image_path, "rb") as image_file:
            return base64.b64encode(image_file.read()).decode('utf-8')
    except FileNotFoundError:
        print(f"error: file {image_path} not found")
        return None
    except Exception as e:
        print(f"error encoding image: {str(e)}")
        return None

def analyse_image(image_path="image.png", text_prompt="What's in this image?"):
    api_key = os.getenv('OPENAI_API_KEY')
    if not api_key:
        print('error: OPENAI_API_KEY environment variable not set')
        return None

    base64_image = encode_image(image_path)
    if not base64_image:
        return None

    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {api_key}"
    }
    payload = {
        "model": "gpt-4o",
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": text_prompt
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/jpeg;base64,{base64_image}"
                        }
                    }
                ]
            }
        ],
        "max_tokens": 300
    }

    try:
        response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
        response.raise_for_status() # Raise error for HTTP codes 4xx/5xx
        content = response.json()['choices'][0]['message']['content']
        return content
    except requests.exceptions.HTTPError as http_err:
        print(f"HTTP error occurred: {http_err}")
    except requests.exceptions.RequestException as req_err:
        print(f"request error occurred: {req_err}")
    except KeyError:
        print("unexpected response format")
        return response.json()
    except Exception as e:
        print(f"error: {str(e)}")

    return None

def main(options=docopt.docopt(__doc__)):
    interval = int(options['--interval'])
    prompt = options['--prompt']

    api_key = os.getenv('OPENAI_API_KEY')
    client = OpenAI()

    print(f"starting in {interval} seconds")
    time.sleep(interval)

    while True:
        image_path = take_screenshot()
        print('\n' + image_path)
        result = analyse_image(image_path, prompt)
        print(result)
        time.sleep(interval)

if __name__ == '__main__':
    main()