Python script to retrieve the title of ChatGPT conversations

get_gpt_conversations_title.py

#!/usr/local/bin/python

import sys
import requests
from bs4 import BeautifulSoup
import json

def get_data_object(url) -> dict | None:
    try:
        # Fetch HTML content from the URL
        response = requests.get(url)
        response.raise_for_status()  # Raise an exception for bad responses

        # Parse HTML content using BeautifulSoup
        soup = BeautifulSoup(response.text, 'html.parser')

        # Find the script tag with id="__NEXT_DATA__"
        script_tag = soup.find('script', id='__NEXT_DATA__')

        if script_tag:
            # Extract the inner content of the script tag
            inner_content = script_tag.contents[0] if script_tag.contents else None
            if inner_content == None:
                return inner_content
            return json.loads(inner_content)
        else:
            return None

    except requests.RequestException as e:
        print(f"ERROR fetching content: {e}")
        return None
    
def get_page_title(data: dict | None) -> str | None:
    if data == None:
        return None

    return data.get('props', {}).get('pageProps', {}).get('serverResponse', {}).get('data', {}).get('title')

if __name__ == "__main__":
    # Check if at least one URL is provided as a command-line argument
    if len(sys.argv) < 2:
        print(f"Usage: {sys.argv[0]} <URL1> <URL2> ...")
        sys.exit(1)

    # Get the list of URLs from the command-line arguments
    urls = sys.argv[1:]
    results = {}

    for url in urls:
        print(f"Processing {url}...")

        data_object = get_data_object(url)
        page_title = get_page_title(data_object)

        if page_title:
            results[url] = page_title
            print("OK!")

    print(json.dumps(results))

requirements.txt

beautifulsoup4==4.12.2
requests==2.31.0